Existing Annotations Review

GO Term	Evidence	Action	Reason
GO:0004540 RNA nuclease activity	IBA GO_REF:0000033	ACCEPT	Summary: Phylogenetic RNase transfer matches direct mouse biochemical evidence. Reason: Mouse Ang2 has direct RNA/tRNA cleavage evidence. Supporting Evidence: PMID:8633065 Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang. PMID:23170778 mAng-2 is almost 80% active compared to the human form of the protein file:mouse/Ang2/Ang2-deep-research-falcon.md Ang2/Angrp is enzymatically active as a ribonuclease. Recombinant mAngrp cleaves tRNA test substrates in vitro.
GO:0005615 extracellular space	IBA GO_REF:0000033	KEEP AS NON CORE	Summary: Secreted extracellular localization is plausible, but it is a localization note rather than a core function. Reason: Signal peptide and secreted RNase family context support extracellular localization. Supporting Evidence: file:mouse/Ang2/Ang2-deep-research-falcon.md Angiogenins are secreted vertebrate-specific ribonucleases within the pancreatic RNase A superfamily.
GO:0019731 antibacterial humoral response	IBA GO_REF:0000033	REMOVE	Summary: Family-level antibacterial transfer is not supported for mouse Ang2. Reason: Likely conflates canonical angiogenin or antimicrobial paralogs with Ang2. Supporting Evidence: file:mouse/Ang2/Ang2-deep-research-falcon.md Direct evidence for Ang2-specific tiRNA production in mouse cells is lacking file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md Immune/antimicrobial ISO terms are particularly weak because their current human ANG source is itself inferred rather than experimental.
GO:0045087 innate immune response	IBA GO_REF:0000033	REMOVE	Summary: Family-level innate-immune transfer is not supported for mouse Ang2. Reason: Likely conflates canonical angiogenin or antimicrobial paralogs with Ang2. Supporting Evidence: file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md Immune/antimicrobial ISO terms are particularly weak because their current human ANG source is itself inferred rather than experimental.
GO:0050830 defense response to Gram-positive bacterium	IBA GO_REF:0000033	REMOVE	Summary: Family-level antibacterial transfer is not supported for mouse Ang2. Reason: Likely conflates canonical angiogenin or antimicrobial paralogs with Ang2. Supporting Evidence: file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md Immune/antimicrobial ISO terms are particularly weak because their current human ANG source is itself inferred rather than experimental.
GO:0061844 antimicrobial humoral immune response mediated by antimicrobial peptide	IBA GO_REF:0000033	REMOVE	Summary: Family-level antimicrobial transfer is not supported for mouse Ang2. Reason: Likely conflates canonical angiogenin or antimicrobial paralogs with Ang2. Supporting Evidence: file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md Immune/antimicrobial ISO terms are particularly weak because their current human ANG source is itself inferred rather than experimental.
GO:0001525 angiogenesis	IBA GO_REF:0000033	REMOVE	Summary: Angiogenesis is contradicted by direct mouse Ang2 literature. Reason: PMID:8633065 shows Angrp is not angiogenic. Supporting Evidence: PMID:8633065 mouse Ang is potently angiogenic, but Angrp is not, even when assayed at relatively high doses. file:mouse/Ang2/Ang2-deep-research-falcon.md A defining functional divergence of Ang2/Angrp is that it is non-angiogenic (or far less angiogenic than canonical angiogenin) in standard assays.
GO:0003676 nucleic acid binding	IEA GO_REF:0000002	MARK AS OVER ANNOTATED	Summary: Generic nucleic acid binding is less informative than the specific RNase activity. Reason: Prefer RNA nuclease activity.
GO:0003677 DNA binding	IEA GO_REF:0000043	REMOVE	Summary: DNA binding is inferred from canonical angiogenin biology, not demonstrated for mouse Ang2. Reason: No direct mouse evidence supports DNA binding for Ang2. Supporting Evidence: file:mouse/Ang2/Ang2-deep-research-falcon.md nuclear/nucleolar roles and tiRNA-mediated translation regulation should be treated as family-based hypotheses unless demonstrated directly for mAng2/Angrp.
GO:0004518 nuclease activity	IEA GO_REF:0000043	MODIFY	Summary: Generic nuclease parent term; RNA nuclease activity is the informative term. Reason: Specific RNA nuclease terms better capture the supported mouse Ang2/Angrp activity. Proposed replacements: RNA nuclease activity tRNA-specific ribonuclease activity
GO:0004519 endonuclease activity	IEA GO_REF:0000043	MODIFY	Summary: Generic endonuclease activity is broader than the supported RNase activity. Reason: Specific RNA nuclease terms better capture the supported mouse Ang2/Angrp activity. Proposed replacements: RNA nuclease activity tRNA-specific ribonuclease activity
GO:0004540 RNA nuclease activity	IEA GO_REF:0000117	ACCEPT	Summary: Electronic RNase prediction matches direct mouse biochemical evidence. Reason: Consistent with direct mouse RNase assays. Supporting Evidence: PMID:8633065 Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang. PMID:23170778 mAng-2 is almost 80% active compared to the human form of the protein file:mouse/Ang2/Ang2-deep-research-falcon.md Ang2/Angrp is enzymatically active as a ribonuclease. Recombinant mAngrp cleaves tRNA test substrates in vitro.
GO:0005576 extracellular region	IEA GO_REF:0000044	ACCEPT	Summary: Extracellular localization is plausible for a secreted Ang2 protein and is used as the core-function location. Reason: Secreted extracellular-region localization is consistent with the core RNase function. Supporting Evidence: file:mouse/Ang2/Ang2-deep-research-falcon.md Angiogenins are secreted vertebrate-specific ribonucleases within the pancreatic RNase A superfamily.
GO:0005730 nucleolus	IEA GO_REF:0000044	REMOVE	Summary: Nucleolar localization is imported from canonical angiogenin biology and is not shown for mouse Ang2. Reason: No direct mouse evidence. Supporting Evidence: file:mouse/Ang2/Ang2-deep-research-falcon.md Direct Ang2/Angrp-specific localization evidence was not retrieved in this run.
GO:0016787 hydrolase activity	IEA GO_REF:0000043	MODIFY	Summary: Generic hydrolase parent term; RNA nuclease activity is the informative term. Reason: Specific RNA nuclease terms better capture the supported mouse Ang2/Angrp activity. Proposed replacements: RNA nuclease activity tRNA-specific ribonuclease activity
GO:0031410 cytoplasmic vesicle	IEA GO_REF:0000120	REMOVE	Summary: Cytoplasmic-vesicle localization is a speculative automated transfer, not demonstrated for mouse Ang2. Reason: No direct mouse evidence. Supporting Evidence: file:mouse/Ang2/Ang2-deep-research-falcon.md Direct Ang2/Angrp-specific localization evidence was not retrieved in this run.
GO:0046872 metal ion binding	IEA GO_REF:0000043	KEEP AS NON CORE	Summary: Metal binding is supported by the mouse structural study, but it is secondary to the core RNase activity. Reason: Mouse Ang2 binds Zn2+ and shows metal-sensitive RNase activity. Supporting Evidence: PMID:23170778 first crystal structures of an Ang with a zinc ion bound at the active site
GO:0005615 extracellular space	ISO GO_REF:0000119	KEEP AS NON CORE	Summary: Transferred from human ANG via GO_REF:0000119, but the stronger is_active_in qualifier is not demonstrated for mouse Ang2 and is redundant with broader secretion annotations. Reason: Extracellular localization is plausible, but the qualifier is stronger than the direct mouse evidence.
GO:0001525 angiogenesis	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but mouse Ang2/Angrp is explicitly non-angiogenic. Reason: PMID:8633065 contradicts the transfer. Supporting Evidence: PMID:8633065 mouse Ang is potently angiogenic, but Angrp is not, even when assayed at relatively high doses. file:mouse/Ang2/Ang2-deep-research-falcon.md A defining functional divergence of Ang2/Angrp is that it is non-angiogenic (or far less angiogenic than canonical angiogenin) in standard assays.
GO:0001666 response to hypoxia	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG hypoxia biology, not shown for mouse Ang2. Reason: Divergent paralog with no direct mouse evidence for this process.
GO:0001878 response to yeast	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term. Reason: Stale ISO transfer.
GO:0001938 positive regulation of endothelial cell proliferation	ISO GO_REF:0000119	REMOVE	Summary: Transferred endothelial-proliferation biology from human ANG, but mouse Ang2 is non-angiogenic. Reason: PMID:8633065 shows Angrp does not share canonical angiogenic biology.
GO:0002181 cytoplasmic translation	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term. Reason: Stale ISO transfer.
GO:0003779 actin binding	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG actin-binding studies, but mouse Ang2 receptor/interface biology diverges from canonical angiogenin. Reason: No direct mouse evidence and paralog divergence makes transfer unsafe.
GO:0004540 RNA nuclease activity	ISO GO_REF:0000119	ACCEPT	Summary: Transferred from human ANG via GO_REF:0000119 and independently supported by mouse Ang2 biochemical assays. Reason: Direct mouse RNase evidence exists. Supporting Evidence: PMID:8633065 Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang. PMID:23170778 mAng-2 is almost 80% active compared to the human form of the protein file:mouse/Ang2/Ang2-deep-research-falcon.md Ang2/Angrp is enzymatically active as a ribonuclease. Recombinant mAngrp cleaves tRNA test substrates in vitro.
GO:0004549 tRNA-specific ribonuclease activity	ISO GO_REF:0000119	ACCEPT	Summary: Transferred from human ANG via GO_REF:0000119 and directly supported by mouse Ang2 tRNA cleavage assays. Reason: Direct mouse tRNA cleavage evidence exists. Supporting Evidence: PMID:8633065 Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang. PMID:23170778 mAng-2 is almost 80% active compared to the human form of the protein file:mouse/Ang2/Ang2-deep-research-falcon.md Ang2/Angrp is enzymatically active as a ribonuclease. Recombinant mAngrp cleaves tRNA test substrates in vitro.
GO:0005102 signaling receptor binding	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG receptor-binding studies, but mouse Ang2 lacks canonical receptor-mediated angiogenic biology. Reason: PMID:8633065 implicates deficient receptor binding in Angrp.
GO:0005507 copper ion binding	ISO GO_REF:0000119	MODIFY	Summary: Human ANG source supports copper binding, but mouse Ang2 data support only broader divalent-metal binding. Reason: Mouse structural data support metal ion binding, not copper specificity. Proposed replacements: metal ion binding Supporting Evidence: PMID:23170778 These constitute the first crystal structures of an Ang with a zinc ion bound at the active site
GO:0005604 basement membrane	ISO GO_REF:0000119	REMOVE	Summary: Transferred basement-membrane association from human ANG angiogenic biology, not shown for mouse Ang2. Reason: Non-angiogenic paralog; no direct mouse evidence.
GO:0005615 extracellular space	ISO GO_REF:0000119	KEEP AS NON CORE	Summary: Transferred extracellular-space location from human ANG; plausible but redundant with retained non-ISO secretion annotations. Reason: Extracellular localization is plausible, but it remains non-core and redundant.
GO:0005634 nucleus	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG nuclear-activity studies, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0005634 nucleus	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG nuclear-localization studies, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0005694 chromosome	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term. Reason: Stale ISO transfer.
GO:0005730 nucleolus	ISO GO_REF:0000119	REMOVE	Summary: Transferred nucleolar localization from human ANG, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0005737 cytoplasm	ISO GO_REF:0000119	REMOVE	Summary: Transferred cytoplasmic activity from human ANG intracellular stress studies, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0006898 receptor-mediated endocytosis	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term. Reason: Stale ISO transfer.
GO:0007165 signal transduction	ISO GO_REF:0000119	REMOVE	Summary: Transferred signal transduction from human ANG, but mouse Ang2 lacks canonical angiogenic signaling evidence. Reason: Non-angiogenic paralog with no direct mouse support.
GO:0008201 heparin binding	ISO GO_REF:0000119	REMOVE	Summary: Transferred heparin binding from human ANG, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0009303 rRNA transcription	ISO GO_REF:0000119	REMOVE	Summary: Transferred rRNA-transcription biology from human ANG, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0009725 response to hormone	ISO GO_REF:0000119	REMOVE	Summary: Transferred hormone-response biology from human ANG, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0010494 cytoplasmic stress granule	ISO GO_REF:0000119	REMOVE	Summary: Transferred stress-granule localization from human ANG stress-response studies, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0015629 actin cytoskeleton	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term. Reason: Stale ISO transfer.
GO:0016477 cell migration	ISO GO_REF:0000119	REMOVE	Summary: Transferred cell-migration biology from human ANG angiogenic studies, but mouse Ang2 is non-angiogenic. Reason: No direct mouse evidence and canonical angiogenic transfer is unsafe.
GO:0019731 antibacterial humoral response	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source is itself inferred-only (IBA). Reason: Do not stack inference on inference.
GO:0019732 antifungal humoral response	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term. Reason: Stale ISO transfer.
GO:0023052 signaling	ISO GO_REF:0000119	REMOVE	Summary: Transferred generic signaling from human ANG, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0030139 endocytic vesicle	ISO GO_REF:0000119	REMOVE	Summary: Transferred endocytic-vesicle localization from human ANG internalization studies, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0032055 negative regulation of translation in response to stress	ISO GO_REF:0000119	REMOVE	Summary: Transferred translational stress-response biology from human ANG, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0032311 angiogenin-PRI complex	ISO GO_REF:0000119	REMOVE	Summary: Transferred angiogenin-PRI complex membership from human ANG, not demonstrated for mouse Ang2. Reason: No direct mouse evidence.
GO:0033554 cellular response to stress	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term. Reason: Stale ISO transfer.
GO:0034063 stress granule assembly	ISO GO_REF:0000119	REMOVE	Summary: Transferred stress-granule assembly from human ANG, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0036416 tRNA stabilization	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term. Reason: Stale ISO transfer.
GO:0042277 peptide binding	ISO GO_REF:0000119	REMOVE	Summary: Transferred peptide-binding annotation from human ANG receptor/actin studies, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0042327 positive regulation of phosphorylation	ISO GO_REF:0000119	REMOVE	Summary: Transferred positive regulation of phosphorylation from human ANG signaling studies, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0042803 protein homodimerization activity	ISO GO_REF:0000119	REMOVE	Summary: Transferred protein homodimerization from human ANG, but mouse Ang2 dimerization is not established as a physiological activity. Reason: Structural observations are insufficient for this GO claim.
GO:0043022 ribosome binding	ISO GO_REF:0000119	REMOVE	Summary: Transferred ribosome binding from human ANG stress-response studies, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0045087 innate immune response	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source is itself inferred-only (IBA). Reason: Do not stack inference on inference.
GO:0048018 receptor ligand activity	ISO GO_REF:0000119	REMOVE	Summary: Transferred receptor-ligand activity from human ANG, but mouse Ang2 lacks canonical receptor-mediated angiogenic signaling evidence. Reason: Non-angiogenic paralog with no direct mouse evidence.
GO:0048662 negative regulation of smooth muscle cell proliferation	ISO GO_REF:0000119	REMOVE	Summary: Transferred smooth-muscle proliferation phenotype from human ANG, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0050714 positive regulation of protein secretion	ISO GO_REF:0000119	REMOVE	Summary: Transferred positive regulation of protein secretion from human ANG, but mouse Ang2 lacks direct evidence for this process. Reason: Source support is not sufficient to justify propagation to Ang2.
GO:0050830 defense response to Gram-positive bacterium	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source is itself inferred-only (IBA). Reason: Do not stack inference on inference.
GO:0061844 antimicrobial humoral immune response mediated by antimicrobial peptide	ISO GO_REF:0000119	REMOVE	Summary: Transferred from human ANG via GO_REF:0000119, but the current human source is itself inferred-only (IBA). Reason: Do not stack inference on inference.
GO:0071425 hematopoietic stem cell proliferation	ISO GO_REF:0000119	REMOVE	Summary: Transferred hematopoietic stem-cell proliferation from human ANG, not shown for mouse Ang2. Reason: No direct mouse evidence.
GO:0006468 protein phosphorylation	IMP PMID:25313067 Angiotensin II signaling via protein kinase C phosphorylates...	REMOVE	Summary: Misannotation from AngII signaling, not Ang2/angiogenin-related protein. Reason: The paper studies angiotensin II signaling through KLHL3 and WNK4. Supporting Evidence: PMID:25313067 Angiotensin II signaling via protein kinase C phosphorylates Kelch-like 3, preventing WNK4 degradation.
GO:0006468 protein phosphorylation	IDA PMID:28096417 Phosphorylation by PKC and PKA regulate the kinase activity ...	REMOVE	Summary: Misannotation from AngII signaling, not Ang2/angiogenin-related protein. Reason: The paper studies WNK4 phosphorylation downstream of AngII and vasopressin. Supporting Evidence: PMID:28096417 Phosphorylation by PKC and PKA regulate the kinase activity and downstream signaling of WNK4.
GO:0010467 gene expression	IDA PMID:25313067 Angiotensin II signaling via protein kinase C phosphorylates...	REMOVE	Summary: Misannotation from AngII signaling, not Ang2/angiogenin-related protein. Reason: The paper is about angiotensin II regulation of KLHL3 and WNK4, not the Ang2 gene product.
GO:0010467 gene expression	IDA PMID:28096417 Phosphorylation by PKC and PKA regulate the kinase activity ...	REMOVE	Summary: Misannotation from AngII signaling, not Ang2/angiogenin-related protein. Reason: The paper is about WNK4 phosphorylation downstream of AngII and vasopressin, not Ang2.
GO:0038166 angiotensin-activated signaling pathway	IDA PMID:25313067 Angiotensin II signaling via protein kinase C phosphorylates...	REMOVE	Summary: Misannotation from AngII signaling, not Ang2/angiogenin-related protein. Reason: The paper concerns angiotensin II as a hormone stimulus, not the Ang2 gene product.
GO:0070293 renal absorption	IDA PMID:25313067 Angiotensin II signaling via protein kinase C phosphorylates...	REMOVE	Summary: Misannotation from AngII/WNK4 physiology, not Ang2/angiogenin-related protein. Reason: This physiology belongs to the angiotensin II pathway, not the Ang2 gene.
GO:0001934 positive regulation of protein phosphorylation	IDA PMID:29065170 Zinc-finger protein 418 overexpression protects against card...	REMOVE	Summary: Misannotation from a ZNF418 cardiac-hypertrophy study that uses Ang II as a stimulus. Reason: The paper is about ZNF418, not Ang2/angiogenin-related protein. Supporting Evidence: PMID:29065170 This study aimed to investigated the effect and mechanism of zinc-finger protein 418 (ZNF418) on cardiac hypertrophy caused by aortic banding (AB), phenylephrine (PE) or angiotensin II (Ang II) in vivo and in vitro.
GO:0003300 cardiac muscle hypertrophy	IDA PMID:29065170 Zinc-finger protein 418 overexpression protects against card...	REMOVE	Summary: Misannotation from a ZNF418 cardiac-hypertrophy study that uses Ang II as a stimulus. Reason: The paper is about ZNF418, not Ang2/angiogenin-related protein.
GO:0061049 cell growth involved in cardiac muscle cell development	IDA PMID:29065170 Zinc-finger protein 418 overexpression protects against card...	REMOVE	Summary: Misannotation from a ZNF418 cardiac-hypertrophy study that uses Ang II as a stimulus. Reason: The paper is about ZNF418, not Ang2/angiogenin-related protein.
GO:0004540 RNA nuclease activity	IDA PMID:23170778 Crystal structures of murine angiogenin-2 and -3-probing 'st...	ACCEPT	Summary: Direct biochemical evidence for mouse Ang2 RNase activity. Reason: On-target mouse structural and enzymatic study. Supporting Evidence: PMID:23170778 mAng-2 is almost 80% active compared to the human form of the protein
GO:0071333 cellular response to glucose stimulus	IDA PMID:17670746 High glucose increases angiopoietin-2 transcription in micro...	REMOVE	Summary: Misannotation from an angiopoietin-2 paper, not Ang2/angiogenin-related protein. Reason: The paper studies angiopoietin-2 (Ang-2), not mouse Ang2/Angrp. Supporting Evidence: PMID:17670746 High glucose increases angiopoietin-2 transcription in microvascular endothelial cells through methylglyoxal modification of mSin3A.

Core Functions

Secreted angiogenin-related RNase with direct biochemical tRNA cleavage activity. Mouse Ang2 retains RNase chemistry but does not share the broad angiogenic/signaling program transferred from canonical human ANG.

Molecular Function:

tRNA-specific ribonuclease activity

Cellular Locations:

extracellular region

Supporting Evidence:

PMID:8633065
Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang.
PMID:23170778
mAng-2 is almost 80% active compared to the human form of the protein
file:mouse/Ang2/Ang2-deep-research-falcon.md
Best-supported annotation for Q64438 is: **secreted RNase A-family paralog with strong in vitro RNase/tRNA-cleaving activity but little or no angiogenic activity**
file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md
`GO:0004540` and `GO:0004549` are the main ISO terms that remain biologically plausible for Ang2

References

GO_REF:0000002

Gene Ontology annotation through association of InterPro records with GO terms

GO_REF:0000033

Annotation inferences using phylogenetic trees

GO_REF:0000043

Gene Ontology annotation based on UniProtKB/Swiss-Prot keyword mapping

GO_REF:0000044

Gene Ontology annotation based on UniProtKB/Swiss-Prot Subcellular Location vocabulary mapping, accompanied by conservative changes to GO terms applied by UniProt

GO_REF:0000117

Electronic Gene Ontology annotations created by ARBA machine learning models

GO_REF:0000119

Automated transfer of experimentally-verified manual GO annotation data to mouse-human orthologs

GO_REF:0000120

Combined Automated Annotation using Multiple IEA Methods

PMID:8633065

Characterization of mouse angiogenin-related protein: implications for functional studies on angiogenin.

Mouse Ang2/Angrp is not angiogenic in assays where mouse angiogenin is active.

"mouse Ang is potently angiogenic, but Angrp is not"
Mouse Ang2/Angrp retains ribonucleolytic activity toward tRNA and dinucleotide substrates.

"Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang"
Loss of angiogenic activity is attributed to defective cellular receptor binding rather than loss of RNase catalytic capacity.

"an inability to bind cellular receptors is implicated since Angrp does not inhibit Ang-induced angiogenesis"

PMID:16045902

Expression and regulation of murine macrophage angiopoietin-2.

This UniProt tissue-specificity citation is about angiopoietin-2, not angiogenin-2/Angrp.

"Expression and regulation of murine macrophage angiopoietin-2."

PMID:17670746

High glucose increases angiopoietin-2 transcription in microvascular endothelial cells through methylglyoxal modification of mSin3A.

This publication studies angiopoietin-2/Ang-2 expression, not mouse angiogenin-2/Angrp.

"High glucose increases angiopoietin-2 transcription in microvascular endothelial cells"

PMID:23170778

Crystal structures of murine angiogenin-2 and -3-probing 'structure--function' relationships amongst angiogenin homologues.

mAng-2 has substantial tRNA-cleavage activity in comparative RNase assays.

"mAng-2 is almost 80% active compared to the human form of the protein"
The mAng-2 crystal structure captured zinc bound at the active site.

"first crystal structures of an Ang with a zinc ion bound at the active site"
The structural study reinforces that mAng-2 is not angiogenic despite RNase activity.

"whereas mAng-2 is not angiogenic"

PMID:25313067

Angiotensin II signaling via protein kinase C phosphorylates Kelch-like 3, preventing WNK4 degradation.

This publication concerns angiotensin II regulation of KLHL3/WNK4, not the Ang2 gene product.

"Angiotensin II signaling via protein kinase C phosphorylates Kelch-like 3, preventing WNK4 degradation"

PMID:28096417

Phosphorylation by PKC and PKA regulate the kinase activity and downstream signaling of WNK4.

This publication concerns WNK4 phosphorylation downstream of AngII/vasopressin signaling, not the Ang2 gene product.

"With-no-lysine kinase 4 (WNK4) regulates electrolyte homeostasis and blood pressure"

PMID:29065170

Zinc-finger protein 418 overexpression protects against cardiac hypertrophy and fibrosis.

This publication concerns ZNF418 and uses angiotensin II as a stimulus; it is not an Ang2/Angrp study.

"effect and mechanism of zinc-finger protein 418 (ZNF418) on cardiac hypertrophy caused by aortic banding"

file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md

Ang2 ISO source trace results

All 46 ISO annotations in the local Ang2 GOA were transferred from human ANG through GO_REF:0000119.

"Every one of those 46 ISO rows is transferred through `GO_REF:0000119` from the same source entity, `UniProtKB:P03950` (human angiogenin/ANG)."
Mouse Ang2 is a divergent paralog, so human ANG angiogenic, receptor/signaling, nuclear/stress, and immune annotations should not be propagated automatically.

"even ISO terms with real experimental support on human ANG are unsafe to accept automatically for mouse Ang2 when they concern angiogenesis, receptor binding, signaling, stress-granule biology, nuclear trafficking, or immune effector roles."
The experimental GOA block contains homonym errors from angiopoietin-2, angiotensin II, and ZNF418 papers.

"The non-ISO experimental block in the local GOA file also contains clear homonym errors"

file:mouse/Ang2/Ang2-deep-research-falcon.md

Falcon deep research report for mouse Ang2

Falcon verified that mouse Ang2 is angiogenin-2/Angrp rather than angiopoietin-2.

"The UniProt target provided (Q64438) is instead a **murine angiogenin paralog**, commonly referred to as **mouse angiogenin-2 (mAng2)** or **angiogenin-related protein (Angrp)**"
Falcon identified the best-supported direct function as secreted RNase activity with tRNA/dinucleotide substrates and little or no angiogenic activity.

"Best-supported annotation for Q64438 is: **secreted RNase A-family paralog with strong in vitro RNase/tRNA-cleaving activity but little or no angiogenic activity**"
Falcon found no recent primary studies centered directly on mouse Ang2/Angrp.

"**Key limitation:** no 2023–2024 primary studies explicitly centered on **mouse Ang2/Angrp** were retrieved here."

Suggested Experiments

Experiment: Compare recombinant mouse Ang2, canonical mouse angiogenin, and additional murine angiogenin paralogs in endothelial proliferation, receptor-binding, RNase-inhibitor binding, and cell-uptake assays.

Hypothesis: Mouse Ang2 retains RNase activity but lacks the receptor-binding and angiogenic outputs of canonical angiogenin.

Type: Comparative biochemical and cell-based functional assays

Experiment: Use endogenous tagging or targeted perturbation in tissues that express Ang2 to identify where the protein localizes and which RNAs are cleaved in vivo.

Hypothesis: The physiological role of Ang2 is RNase-centered and more restricted than the transferred human ANG stress and signaling annotations.

Type: Endogenous tagging plus RNA substrate profiling

📚 Additional Documentation

Deep Research Falcon

(Ang2-deep-research-falcon.md)

provider: falcon
model: Edison Scientific Literature
cached: false
start_time: '2026-03-21T17:01:34.816269'
end_time: '2026-03-21T17:14:30.034766'
duration_seconds: 775.22
template_file: templates/gene_research_go_focused.md
template_variables:
organism: mouse
gene_id: Ang2
gene_symbol: Ang2
uniprot_accession: Q64438
protein_description: 'RecName: Full=Angiogenin-2; EC=3.1.27.- {ECO:0000269|PubMed:8633065};
AltName: Full=Angiogenin-related protein; Flags: Precursor;'
gene_info: Name=Ang2; Synonyms=Angrp;
organism_full: Mus musculus (Mouse).
protein_family: Belongs to the pancreatic ribonuclease family.
protein_domains: RNaseA. (IPR001427); RNaseA-like_dom_sf. (IPR036816); RNaseA_AS.
(IPR023411); RNaseA_domain. (IPR023412); RnaseA (PF00074)
provider_config:
timeout: 600
max_retries: 3
parameters:
allowed_domains: []
temperature: 0.1
citation_count: 27

Question

Gene Research for Functional Annotation

⚠️ CRITICAL: Gene/Protein Identification Context

BEFORE YOU BEGIN RESEARCH: You MUST verify you are researching the CORRECT gene/protein. Gene symbols can be ambiguous, especially for less well-characterized genes from non-model organisms.

Target Gene/Protein Identity (from UniProt):

UniProt Accession: Q64438
Protein Description: RecName: Full=Angiogenin-2; EC=3.1.27.- {ECO:0000269|PubMed:8633065}; AltName: Full=Angiogenin-related protein; Flags: Precursor;
Gene Information: Name=Ang2; Synonyms=Angrp;
Organism (full): Mus musculus (Mouse).
Protein Family: Belongs to the pancreatic ribonuclease family.
Key Domains: RNaseA. (IPR001427); RNaseA-like_dom_sf. (IPR036816); RNaseA_AS. (IPR023411); RNaseA_domain. (IPR023412); RnaseA (PF00074)

MANDATORY VERIFICATION STEPS:

Check if the gene symbol "Ang2" matches the protein description above
Verify the organism is correct: Mus musculus (Mouse).
Check if protein family/domains align with what you find in literature
If you find literature for a DIFFERENT gene with the same or similar symbol, STOP

If Gene Symbol is Ambiguous or You Cannot Find Relevant Literature:

DO NOT PROCEED WITH RESEARCH ON A DIFFERENT GENE. Instead:
- State clearly: "The gene symbol 'Ang2' is ambiguous or literature is limited for this specific protein"
- Explain what you found (e.g., "Found extensive literature on a different gene with the same symbol in a different organism")
- Describe the protein based ONLY on the UniProt information provided above
- Suggest that the protein function can be inferred from domain/family information

Research Target:

Please provide a comprehensive research report on the gene Ang2 (gene ID: Ang2, UniProt: Q64438) in mouse.

The research report should be a detailed narrative explaining the function, biological processes, and localization of the gene product. Citations should be given for all claims.

You should prioritize authoritative reviews and primary scientific literature when conducting research. You can supplement
this with annotations you find in gene/protein databases, but these can be outdated or inaccurate.

We are specifically interested in the primary function of the gene - for enzymes, what reaction is catalyzed, and what is the substrate specificity? For transporters, what is the substrate? For structural proteins or adapters, what is the broader structural role? For signaling molecules, what is the role in the pathway.

We are interested in where in or outside the cell the gene product carries out its function.

We are also interested in the signaling or biochemical pathways in which the gene functions. We are less interested in broad pleiotropic effects, except where these elucidate the precise role.

Include evidence where possible. We are interested in both experimental evidence as well as inference from structure, evolution, or bioinformatic analysis. Precise studies should be prioritized over high-throughput, where available.

Output

Question: You are an expert researcher providing comprehensive, well-cited information.

Provide detailed information focusing on:
1. Key concepts and definitions with current understanding
2. Recent developments and latest research (prioritize 2023-2024 sources)
3. Current applications and real-world implementations
4. Expert opinions and analysis from authoritative sources
5. Relevant statistics and data from recent studies

Format as a comprehensive research report with proper citations. Include URLs and publication dates where available.
Always prioritize recent, authoritative sources and provide specific citations for all major claims.

Gene Research for Functional Annotation

⚠️ CRITICAL: Gene/Protein Identification Context

BEFORE YOU BEGIN RESEARCH: You MUST verify you are researching the CORRECT gene/protein. Gene symbols can be ambiguous, especially for less well-characterized genes from non-model organisms.

Target Gene/Protein Identity (from UniProt):

UniProt Accession: Q64438
Protein Description: RecName: Full=Angiogenin-2; EC=3.1.27.- {ECO:0000269|PubMed:8633065}; AltName: Full=Angiogenin-related protein; Flags: Precursor;
Gene Information: Name=Ang2; Synonyms=Angrp;
Organism (full): Mus musculus (Mouse).
Protein Family: Belongs to the pancreatic ribonuclease family.
Key Domains: RNaseA. (IPR001427); RNaseA-like_dom_sf. (IPR036816); RNaseA_AS. (IPR023411); RNaseA_domain. (IPR023412); RnaseA (PF00074)

MANDATORY VERIFICATION STEPS:

Check if the gene symbol "Ang2" matches the protein description above
Verify the organism is correct: Mus musculus (Mouse).
Check if protein family/domains align with what you find in literature
If you find literature for a DIFFERENT gene with the same or similar symbol, STOP

If Gene Symbol is Ambiguous or You Cannot Find Relevant Literature:

Research Target:

Please provide a comprehensive research report on the gene Ang2 (gene ID: Ang2, UniProt: Q64438) in mouse.

The research report should be a detailed narrative explaining the function, biological processes, and localization of the gene product. Citations should be given for all claims.

We are interested in where in or outside the cell the gene product carries out its function.

We are also interested in the signaling or biochemical pathways in which the gene functions. We are less interested in broad pleiotropic effects, except where these elucidate the precise role.

1) Target verification (critical disambiguation)

Ang2 is an ambiguous symbol in the literature because “Ang-2” frequently denotes angiopoietin-2 (ANGPT2) in vascular biology. The UniProt target provided (Q64438) is instead a murine angiogenin paralog, commonly referred to as mouse angiogenin-2 (mAng2) or angiogenin-related protein (Angrp), and is part of the pancreatic RNase A superfamily (angiogenin branch). Mouse angiogenins comprise a multi-gene paralog set (variously summarized as 5–6 genes across reviews, often on chromosome 14), explicitly including mAng2/Angrp. (sultana2022humanandmouse pages 5-6, sultana2022humanandmouse pages 1-2, sheng2016threedecadesof pages 1-2, adams2004theangiogeninsan pages 6-8, holloway2001highlevelexpressionof pages 1-2)

2) Key concepts and definitions (current understanding)

2.1 Angiogenins as RNase A superfamily members

Angiogenins are secreted vertebrate-specific ribonucleases within the pancreatic RNase A superfamily. They are typically synthesized as preproteins with an N-terminal signal peptide, then processed to a mature ~120 aa, disulfide-rich RNase-fold protein. (lyons2017rnabiologyof pages 1-3, holloway2001highlevelexpressionof pages 1-2)

Angiogenin-family RNases are unusual in that their “classic” RNase activity on small substrates is low, yet they have potent biological effects, including RNA cleavage events (notably tRNA cleavage) and cell signaling activities in some contexts. (garnett2021emergingbiologicalfunctions pages 6-8, lyons2017rnabiologyof pages 4-6)

2.2 Catalyzed reaction and substrate specificity

For angiogenins generally, the enzymatic function is endoribonucleolytic cleavage of RNA, with reported preference for cleavage on the 3′ side of pyrimidines (yielding cyclic phosphate intermediates), and activity against tRNA (and in some studies rRNA). (adams2004theangiogeninsan pages 2-3)

For mouse Ang2/Angrp (Q64438) specifically, multiple sources support that it is an active RNase, with notable activity toward tRNA and dinucleotide substrates (e.g., CpA, CpG). (holloway2001highlevelexpressionof pages 1-2, fu1999mangiogenin3atarget pages 5-7)

3) Gene-/protein-specific functional evidence for Ang2/Angrp (mAng2)

3.1 Biochemical activity (direct evidence)

Ang2/Angrp is enzymatically active as a ribonuclease. Recombinant mAngrp cleaves tRNA test substrates in vitro. (holloway2001highlevelexpressionof pages 1-2)

A comparative enzymology table (values attributed to Nobile et al., 1996, as reported in Fu et al., 1999) gives relative activities for mAngrp: tRNA activity 90.0 (with hANG set to 100), and dinucleotide cleavage values 48.5 (CpA) and 12.3 (CpG). These data support robust catalytic activity (at least relative to other angiogenin-family members) on these substrates. (fu1999mangiogenin3atarget pages 5-7)

Across reviews, Ang2/Angrp is described as having greater RNase activity toward tRNA and dinucleotide substrates than mouse angiogenin (mAng1), despite being weak/non-angiogenic. (adams2004theangiogeninsan pages 6-8, sultana2022humanandmouse pages 5-6)

3.2 Angiogenic activity (direct evidence: negative)

A defining functional divergence of Ang2/Angrp is that it is non-angiogenic (or far less angiogenic than canonical angiogenin) in standard assays.

In a chick chorioallantoic membrane (CAM) assay, mAngrp showed no angiogenic activity even at 100 ng, whereas other angiogenins (hANG, mAng1, mAng-3) were angiogenic at substantially lower doses (down to ~1–2 ng for hANG and mAng1). (holloway2001highlevelexpressionof pages 1-2)
Reviews likewise summarize CAM evidence that mAng2/Angrp is non-angiogenic, with a proposed explanation that substitutions at key cell-binding residues impair receptor/cell interaction. (sultana2022humanandmouse pages 5-6)

Mechanistically, Fu et al. summarize residue differences enriched in non-angiogenic Angrp and report mutational tests (e.g., combined mutations including Lys60→Asn and Arg66→Glu) that did not restore angiogenic activity, consistent with impaired cell binding and/or additional determinants beyond those substitutions. (fu1999mangiogenin3atarget pages 11-12)

3.3 Localization and cellular compartment of action (direct vs inferred)

Direct Ang2/Angrp-specific localization evidence was not retrieved in this run. However, as an angiogenin-family member, Ang2/Angrp is expected to be secreted (signal peptide) and potentially internalized by cells.

For angiogenin-family proteins in general:

ANG is secreted and can be taken up by cells via receptor-mediated endocytosis or other routes (the receptor identity can vary by context; syndecan-4 and other proteins have been proposed). (sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3, lyons2017rnabiologyof pages 1-3)
ANG can localize to the nucleus/nucleolus, where it promotes rRNA transcription and growth-associated ribosome biogenesis programs, in part through RNA cleavage events (e.g., pRNA cleavage) and rDNA promoter regulation. (sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3, garnett2021emergingbiologicalfunctions pages 8-9, lyons2017rnabiologyof pages 4-6)
Under stress, angiogenin can accumulate in the cytosol and cleave tRNAs to generate tRNA-derived stress-induced fragments (tiRNAs), which can inhibit translation initiation and promote stress granule formation (e.g., 5′-tiRNAs with oligo-G motifs interacting with YB-1). (sheng2016threedecadesof pages 4-5, lyons2017rnabiologyof pages 4-6)

For Ang2/Angrp, tRNA cleavage is direct evidence, but nuclear/nucleolar roles and tiRNA-mediated translation regulation should be treated as family-based hypotheses unless demonstrated directly for mAng2/Angrp. (holloway2001highlevelexpressionof pages 1-2, lyons2017rnabiologyof pages 4-6)

3.4 Regulation and pathway context (RNH1/RI system)

No Ang2-specific RNH1-binding constant was retrieved. For angiogenin-family proteins broadly, the cytosolic ribonuclease inhibitor (RI/RNH1) binds angiogenin with extremely high affinity (reported Kd ~1 fM) and suppresses RNase activity. (sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3, garnett2021emergingbiologicalfunctions pages 6-8)

This ANG–RNH1 system is positioned as a regulator of translation and ribosome biogenesis: ANG can promote rRNA transcription in the nucleus under homeostasis and generate tRNA fragments under stress; RNH1 inhibits ANG RNase activity and is essential in mouse development (RNH1 knockout embryonic lethal). (sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3)

Given Ang2/Angrp’s strong RNase activity toward tRNA, its physiological impact may depend strongly on RI/RNH1 availability and compartmentalization, but this remains to be tested directly for Q64438. (sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3)

4) Expression and biological roles

4.1 Genomic and evolutionary context (mouse-specific paralog expansion)

Mouse differs from humans in having multiple angiogenin paralogs rather than a single ANG gene. This paralog expansion complicates phenotype interpretation because paralogs can partially compensate for one another. (kulka2009humanmastcells pages 1-2, lyons2017rnabiologyof pages 1-3, sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3)

Ang2/Angrp shares ~78% sequence identity with mAng1 but appears functionally diverged—especially in angiogenic capacity—likely reflecting evolutionary subfunctionalization/neofunctionalization among murine paralogs. (sultana2022humanandmouse pages 5-6, fu1999mangiogenin3atarget pages 1-2)

4.2 Tissue/cell-type expression

This run did not retrieve a modern Ang2/Angrp-specific expression atlas or single-cell dataset. Older and review literature indicates different paralogs have distinct tissue roles (e.g., intestinal Ang4 from Paneth/goblet cells), but Ang2/Angrp expression patterns remain insufficiently evidenced here. (sultana2022humanandmouse pages 5-6)

5) Recent developments (prioritize 2023–2024) and how they relate to Ang2

Key limitation: no 2023–2024 primary studies explicitly centered on mouse Ang2/Angrp were retrieved here.

Nevertheless, recent murine angiogenin-paralog work provides updated context for angiogenin-family functions in vivo:

Hu et al., Mar 2023 (PLOS ONE) used an AOM-DSS colitis-associated cancer model comparing WT vs Ang1 knockout mice, showing Ang1 deletion worsened colitis but reduced tumor formation. Quantitatively, WT developed 134 tumors (4.6 tumors/mouse) vs Ang1-KO 46 tumors (1.5 tumors/mouse), and Ang1-KO tumor-bearing mice showed a 34-fold decrease in Ang4 relative to WT (with Ang1 absent). The study also reported durable microbiome differences between genotypes (FDR < 0.2 for some taxa associations). These results reinforce the concept that murine angiogenins can couple mucosal inflammation, antimicrobial activity, microbiome composition, and cancer risk, but they do not directly address Ang2/Angrp. (hu2023ang1andang4 pages 1-2, hu2023ang1andang4 pages 8-10)

A recent synthesis review (Nov 2022) remains a key authoritative consolidation for Ang2/Angrp, emphasizing (i) its non-angiogenic phenotype and (ii) its comparatively high RNase activity. (sultana2022humanandmouse pages 5-6)

6) Current applications and real-world implementations

6.1 Applications (largely for ANG/RNase5 rather than Ang2/Angrp)

Most translational applications in the retrieved literature focus on human angiogenin (ANG/RNase5) rather than mouse Ang2/Angrp.

Cancer biomarker / therapy stratification: A high-impact study reports ANG as an EGFR ligand and a serum biomarker for erlotinib sensitivity in pancreatic ductal adenocarcinoma, suggesting clinical stratification and therapeutic targeting of the ANG–EGFR axis. (Wang et al., Apr 2018, URL: https://doi.org/10.1016/j.ccell.2018.02.012) (wang2018angiogeninribonuclease5is pages 1-4, wang2018angiogeninribonuclease5is pages 8-9)
Disease-associated serum factor: Reviews describe that serum ANG levels change across multiple inflammatory/vascular diseases and may have biomarker utility, though such statements are typically broader and context dependent. (sheng2016threedecadesof pages 8-8, adams2004theangiogeninsan pages 6-8)

6.2 Implications for Ang2/Angrp applications

Ang2/Angrp is non-angiogenic in CAM assays and is described as undetectable in human serum in a review, arguing against direct translation of pro-angiogenic/blood biomarker roles from ANG to Ang2/Angrp. (holloway2001highlevelexpressionof pages 1-2, adams2004theangiogeninsan pages 6-8)

Given its strong RNase activity (tRNA/dinucleotide substrates) but poor angiogenic activity, Ang2/Angrp’s more plausible application space is as a model RNase paralog for studying how angiogenin-family proteins can decouple RNA catalysis from angiogenesis/cell-binding determinants, and potentially for probing host-defense RNase biology in mouse systems. (holloway2001highlevelexpressionof pages 1-2, fu1999mangiogenin3atarget pages 5-7, fu1999mangiogenin3atarget pages 11-12)

7) Expert synthesis and interpretive analysis (authoritative perspectives)

Authoritative reviews converge on a working model where angiogenins integrate extracellular secretion and uptake with intracellular RNA biology.

Under growth conditions, angiogenin-family proteins can accumulate in the nucleolus and promote rRNA transcription, thereby supporting proliferative capacity. (sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3, lyons2017rnabiologyof pages 4-6)
Under stress, angiogenin can shift to the cytosol and generate tiRNAs that suppress global translation and promote stress granules. (sheng2016threedecadesof pages 4-5, lyons2017rnabiologyof pages 4-6)
RI/RNH1 is a central brake on angiogenin RNase activity and therefore a plausible determinant of when/where enzymatic activity is permitted. (sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3, garnett2021emergingbiologicalfunctions pages 6-8)

Within this framework, mouse Ang2/Angrp stands out as a paralog with preserved or enhanced RNase activity but lost angiogenic potential, likely due to alterations in cell-binding/internalization determinants (e.g., residues around positions ~60–70 implicated as receptor/cell-binding in angiogenin-family proteins). (sultana2022humanandmouse pages 5-6, fu1999mangiogenin3atarget pages 11-12)

8) Key statistics and data points (from primary studies and reviews)

Ang2/Angrp vs mAng1 sequence identity: ~78%. (sultana2022humanandmouse pages 5-6, fu1999mangiogenin3atarget pages 1-2)
Ang2/Angrp angiogenesis (CAM): no activity even at 100 ng dose (contrasting with other angiogenins active at 10 ng or lower). (holloway2001highlevelexpressionof pages 1-2)
Ang2/Angrp RNase activities (reported in Fu 1999 table; attributed to Nobile 1996): tRNA activity 90.0 (hANG=100), CpA 48.5, CpG 12.3. (fu1999mangiogenin3atarget pages 5-7)
Recombinant mAngrp yield: 7.6 mg/L culture (protein expression/purification study). (holloway2001highlevelexpressionof pages 1-2)
ANG family binding to RI/RNH1: Kd ~1 fM (reported for ANG–RNH1 system). (sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3)
ANG catalytic activity vs RNase 1 (family context): ~10^4-fold lower on simple substrates, yet effective tRNA cleavage. (garnett2021emergingbiologicalfunctions pages 6-8)
Human circulating ANG concentration (family context): ~400 ng/mL. (garnett2021emergingbiologicalfunctions pages 6-8)
Recent in vivo murine angiogenin-paralog disease model (2023): AOM-DSS: WT 134 tumors (4.6/mouse) vs Ang1-KO 46 tumors (1.5/mouse); Ang1-KO tumor-bearing mice showed 34-fold decrease in Ang4 relative to WT. (hu2023ang1andang4 pages 1-2)

9) Summary: best-supported functional annotation for UniProt Q64438 (mouse Ang2/Angrp)

Most defensible primary function (supported by direct evidence):

Secreted angiogenin-family endoribonuclease with robust activity toward tRNA and dinucleotide RNA substrates. (holloway2001highlevelexpressionof pages 1-2, fu1999mangiogenin3atarget pages 5-7)

Key functional distinction (supported by direct evidence):

Non-angiogenic in CAM assays despite RNase activity (no activity up to 100 ng), likely due to loss/alteration of cell-binding determinants. (holloway2001highlevelexpressionof pages 1-2, sultana2022humanandmouse pages 5-6, fu1999mangiogenin3atarget pages 11-12)

Likely but not directly proven for Ang2/Angrp (family-based inference):

Secretion followed by potential cell uptake; possible nuclear/nucleolar trafficking and/or stress-responsive cytosolic tRNA cleavage roles, modulated by RNH1/RI. These mechanisms are well supported for angiogenin-family proteins generally but require Ang2-specific validation. (sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3, sheng2016threedecadesof pages 4-5, garnett2021emergingbiologicalfunctions pages 6-8, lyons2017rnabiologyof pages 4-6)

Structured summary table

Annotation topic	Summary for Mus musculus Ang2 / Angrp (UniProt Q64438)	Key quantitative data	Citations
Identity / nomenclature	Target identity is mouse angiogenin-2, also called angiogenin-related protein (Angrp, mAng2), a member of the murine angiogenin/RNase 5 paralog set and distinct from angiopoietin-2 (Angpt2). Reviews of murine angiogenins explicitly list mAng2/Angrp among the expanded mouse paralogs.	mAng2/Angrp shares ~78% sequence identity with mAng1; mice have 5–6 angiogenin paralogs reported across reviews, plus pseudogenes in some annotations.	(sultana2022humanandmouse pages 5-6, sultana2022humanandmouse pages 1-2, sheng2016threedecadesof pages 1-2, adams2004theangiogeninsan pages 6-8, holloway2001highlevelexpressionof pages 1-2)
Protein family / domains	Ang2/Angrp belongs to the pancreatic RNase A superfamily (angiogenin branch), consistent with UniProt Q64438 annotation and family reviews describing mouse angiogenins as small secreted RNases with conserved catalytic machinery and disulfide-rich RNase A-like fold.	Mature angiogenin-family proteins are typically ~120–123 aa and contain 3 disulfide bonds.	(holloway2001highlevelexpressionof pages 1-2, lyons2017rnabiologyof pages 1-3, adams2004theangiogeninsan pages 6-8)
Biochemical activity / substrate preference	Ang2/Angrp is an endoribonuclease with conserved RNase active-site residues. Family evidence indicates angiogenins preferentially cleave RNA on the 3' side of pyrimidines and can act on tRNA and some rRNA substrates. For Ang2/Angrp specifically, primary/review data indicate strong activity toward tRNA and dinucleotide substrates, higher than some other mouse angiogenins. Direct evidence that Ang2 itself generates stress tiRNAs is limited; this is inferred from its tRNA-cleaving capacity and broader angiogenin-family biology.	Ang2/Angrp reported to have greater RNase activity toward tRNA and dinucleotide substrates than mouse angiogenin/mAng1 in comparative studies.	(adams2004theangiogeninsan pages 6-8, sultana2022humanandmouse pages 5-6, holloway2001highlevelexpressionof pages 1-2, adams2004theangiogeninsan pages 2-3)
Angiogenic activity	Unlike canonical angiogenin, mouse Ang2/Angrp is non-angiogenic or very weakly angiogenic in standard assays. The leading explanation is altered cell/receptor-binding residues despite preserved RNase activity.	In CAM assays, hANG, mAng1, and mAng3 were active at 10 ng; hANG and mAng1 remained active at 1–2 ng; mAngrp/Ang2 showed no angiogenic activity even at 100 ng. Proposed loss-of-function residues include Asn61 and Arg66 substitutions affecting cell binding.	(sultana2022humanandmouse pages 5-6, holloway2001highlevelexpressionof pages 1-2)
Localization / trafficking	Ang2/Angrp is expected to be a secreted preprotein like other angiogenins. Direct Ang2-specific localization data are sparse, but angiogenin-family evidence shows secretion, cellular uptake, and likely capacity for nuclear/nucleolar localization because many family members retain candidate NLS-like basic motifs. For angiogenins generally, growth conditions favor nucleolar accumulation linked to rRNA transcription, whereas stress shifts activity toward the cytosol for tRNA cleavage.	ANG family proteins include an N-terminal signal peptide; general ANG circulation reported at ~400 ng/mL in humans. Family NLS includes Arg31-Arg32-Arg33 in human ANG.	(sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3, sheng2016threedecadesof pages 4-5, lyons2017rnabiologyof pages 1-3, garnett2021emergingbiologicalfunctions pages 8-9, garnett2021emergingbiologicalfunctions pages 6-8, adams2004theangiogeninsan pages 6-8)
Stress biology / tiRNA context	Direct evidence for Ang2-specific tiRNA production in mouse cells is lacking, but angiogenin-family work shows ANG cleaves tRNAs in the anticodon loop to generate tiRNAs under stress, and only 5'-tiRNAs are potent translation inhibitors/stress-granule promoters. Thus, Ang2/Angrp is plausibly capable of similar reactions because it robustly cleaves tRNA, but this remains an inference rather than a demonstrated Ang2-specific pathway.	ANG catalytic activity toward simple substrates is ~10^4-fold lower than RNase 1, yet ANG efficiently cleaves tRNAs; recombinant wild-type ANG, but not catalytically dead ANG, promotes stress granules.	(garnett2021emergingbiologicalfunctions pages 6-8, sheng2016threedecadesof pages 4-5, garnett2021emergingbiologicalfunctions pages 8-9, lyons2017rnabiologyof pages 4-6)
Regulation by RNH1 / RI	No Ang2-specific binding study was identified, but angiogenins broadly are regulated by ribonuclease inhibitor (RI/RNH1), which binds ANG-family proteins with extremely high affinity and suppresses RNase activity until release/disruption. This likely applies to Ang2/Angrp by family membership, though direct quantitative validation for Q64438 was not found.	ANG-RNH1 affinity reported at Kd ~1 fM; RNH1 is essential in mice, whereas ANG knockout mice survive, suggesting buffering/compensation in the angiogenin system.	(sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3, garnett2021emergingbiologicalfunctions pages 6-8)
Expression / evolutionary context	Mouse has an expanded angiogenin locus on chromosome 14 with multiple paralogs; this complicates knockout interpretation and suggests subfunctionalization. Ang2/Angrp is one such paralog. Specific robust modern tissue-expression data for Ang2 itself were not retrieved here. Reviews note expression diversity among paralogs and identify Ang2/Angrp as functionally diverged from angiogenic mAng1.	Mouse reported to carry 4, 5, or 6 angiogenin-family genes depending on annotation framework and date; pseudogenes are also described.	(sultana2022humanandmouse pages 1-2, sheng2016threedecadesof pages 1-2, strydom1998theangiogenins pages 1-2, kulka2009humanmastcells pages 1-2, sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3)
Practical functional annotation	Best-supported annotation for Q64438 is: secreted RNase A-family paralog with strong in vitro RNase/tRNA-cleaving activity but little or no angiogenic activity, likely functioning in extracellular or internalized RNA-related biology rather than classic pro-angiogenic signaling. Nuclear/stress functions are reasonable family-based hypotheses, but should be labeled inferred unless shown directly for Ang2/Angrp.	Strongest gene-specific numbers: 78% identity to mAng1, ~120–123 aa, no CAM activity up to 100 ng, recombinant yield 7.6 mg/L in E. coli purification study.	(adams2004theangiogeninsan pages 6-8, sultana2022humanandmouse pages 5-6, holloway2001highlevelexpressionof pages 1-2)

Table: This table summarizes the strongest gene-specific and family-supported functional annotation points for Mus musculus Ang2/Angrp (UniProt Q64438). It distinguishes direct evidence for Ang2 from broader angiogenin-family inferences, which is important because the symbol Ang2 is ambiguous and mouse angiogenins are a paralog-expanded RNase family.

References

(sultana2022humanandmouse pages 5-6): Mst. Farzana Sultana, Hirohito Abo, and Hiroto Kawashima. Human and mouse angiogenins: emerging insights and potential opportunities. Frontiers in Microbiology, Nov 2022. URL: https://doi.org/10.3389/fmicb.2022.1022945, doi:10.3389/fmicb.2022.1022945. This article has 17 citations and is from a peer-reviewed journal.
(sultana2022humanandmouse pages 1-2): Mst. Farzana Sultana, Hirohito Abo, and Hiroto Kawashima. Human and mouse angiogenins: emerging insights and potential opportunities. Frontiers in Microbiology, Nov 2022. URL: https://doi.org/10.3389/fmicb.2022.1022945, doi:10.3389/fmicb.2022.1022945. This article has 17 citations and is from a peer-reviewed journal.
(sheng2016threedecadesof pages 1-2): Jinghao Sheng and Zhengping Xu. Three decades of research on angiogenin: a review and perspective. Acta biochimica et biophysica Sinica, 48 5:399-410, May 2016. URL: https://doi.org/10.1093/abbs/gmv131, doi:10.1093/abbs/gmv131. This article has 267 citations and is from a peer-reviewed journal.
(adams2004theangiogeninsan pages 6-8): Susan A. Adams and Vasanta Subramanian. The angiogenins: an emerging family of ribonuclease related proteins with diverse cellular functions. Angiogenesis, 3:189-199, Jan 2004. URL: https://doi.org/10.1023/a:1009015512200, doi:10.1023/a:1009015512200. This article has 85 citations and is from a domain leading peer-reviewed journal.
(holloway2001highlevelexpressionof pages 1-2): Daniel E. Holloway, Michelle C. Hares, Robert Shapiro, Vasanta Subramanian, and K.Ravi Acharya. High-level expression of three members of the murine angiogenin family in escherichia coli and purification of the recombinant proteins. Protein expression and purification, 22 2:307-17, Jul 2001. URL: https://doi.org/10.1006/prep.2001.1434, doi:10.1006/prep.2001.1434. This article has 58 citations and is from a peer-reviewed journal.
(lyons2017rnabiologyof pages 1-3): Shawn M. Lyons, Marta M. Fay, Yasutoshi Akiyama, Paul J. Anderson, and Pavel Ivanov. Rna biology of angiogenin: current state and perspectives. RNA Biology, 14:171-178, Feb 2017. URL: https://doi.org/10.1080/15476286.2016.1272746, doi:10.1080/15476286.2016.1272746. This article has 147 citations and is from a peer-reviewed journal.
(garnett2021emergingbiologicalfunctions pages 6-8): Emily R. Garnett and Ronald T. Raines. Emerging biological functions of ribonuclease 1 and angiogenin. Critical Reviews in Biochemistry and Molecular Biology, 57(3):244-260, Dec 2021. URL: https://doi.org/10.1080/10409238.2021.2004577, doi:10.1080/10409238.2021.2004577. This article has 29 citations and is from a peer-reviewed journal.
(lyons2017rnabiologyof pages 4-6): Shawn M. Lyons, Marta M. Fay, Yasutoshi Akiyama, Paul J. Anderson, and Pavel Ivanov. Rna biology of angiogenin: current state and perspectives. RNA Biology, 14:171-178, Feb 2017. URL: https://doi.org/10.1080/15476286.2016.1272746, doi:10.1080/15476286.2016.1272746. This article has 147 citations and is from a peer-reviewed journal.
(adams2004theangiogeninsan pages 2-3): Susan A. Adams and Vasanta Subramanian. The angiogenins: an emerging family of ribonuclease related proteins with diverse cellular functions. Angiogenesis, 3:189-199, Jan 2004. URL: https://doi.org/10.1023/a:1009015512200, doi:10.1023/a:1009015512200. This article has 85 citations and is from a domain leading peer-reviewed journal.
(fu1999mangiogenin3atarget pages 5-7): Xinyu Fu, W. Gregory Roberts, Valentina Nobile, Robert Shapiro, and Mark P. Kamps. Mangiogenin-3, a target gene of oncoprotein e2a-pbx1, encodes a new angiogenic member of the angiogenin family. Growth factors, 17 2:125-37, Jan 1999. URL: https://doi.org/10.3109/08977199909103521, doi:10.3109/08977199909103521. This article has 42 citations and is from a peer-reviewed journal.
(fu1999mangiogenin3atarget pages 11-12): Xinyu Fu, W. Gregory Roberts, Valentina Nobile, Robert Shapiro, and Mark P. Kamps. Mangiogenin-3, a target gene of oncoprotein e2a-pbx1, encodes a new angiogenic member of the angiogenin family. Growth factors, 17 2:125-37, Jan 1999. URL: https://doi.org/10.3109/08977199909103521, doi:10.3109/08977199909103521. This article has 42 citations and is from a peer-reviewed journal.
(sarangdhar2021angiogenin(ang)—ribonucleaseinhibitor pages 2-3): Mayuresh Anant Sarangdhar and Ramanjaneyulu Allam. Angiogenin (ang)—ribonuclease inhibitor (rnh1) system in protein synthesis and disease. International Journal of Molecular Sciences, 22:1287, Jan 2021. URL: https://doi.org/10.3390/ijms22031287, doi:10.3390/ijms22031287. This article has 47 citations.
(garnett2021emergingbiologicalfunctions pages 8-9): Emily R. Garnett and Ronald T. Raines. Emerging biological functions of ribonuclease 1 and angiogenin. Critical Reviews in Biochemistry and Molecular Biology, 57(3):244-260, Dec 2021. URL: https://doi.org/10.1080/10409238.2021.2004577, doi:10.1080/10409238.2021.2004577. This article has 29 citations and is from a peer-reviewed journal.
(sheng2016threedecadesof pages 4-5): Jinghao Sheng and Zhengping Xu. Three decades of research on angiogenin: a review and perspective. Acta biochimica et biophysica Sinica, 48 5:399-410, May 2016. URL: https://doi.org/10.1093/abbs/gmv131, doi:10.1093/abbs/gmv131. This article has 267 citations and is from a peer-reviewed journal.
(kulka2009humanmastcells pages 1-2): Marianna Kulka, Nobuyuki Fukuishi, and Dean D Metcalfe. Human mast cells synthesize and release angiogenin, a member of the ribonuclease a (rnase a) superfamily. Journal of Leukocyte Biology, 86:1217-1226, Nov 2009. URL: https://doi.org/10.1189/jlb.0908517, doi:10.1189/jlb.0908517. This article has 59 citations and is from a peer-reviewed journal.
(fu1999mangiogenin3atarget pages 1-2): Xinyu Fu, W. Gregory Roberts, Valentina Nobile, Robert Shapiro, and Mark P. Kamps. Mangiogenin-3, a target gene of oncoprotein e2a-pbx1, encodes a new angiogenic member of the angiogenin family. Growth factors, 17 2:125-37, Jan 1999. URL: https://doi.org/10.3109/08977199909103521, doi:10.3109/08977199909103521. This article has 42 citations and is from a peer-reviewed journal.
(hu2023ang1andang4 pages 1-2): Alexander Hu, Cullen Roberts, Andrei Moscalu, Mark Redston, and James Yoo. Ang1 and ang4 differentially affect colitis and carcinogenesis in an aom-dss mouse model. PLOS ONE, 18:e0281529, Mar 2023. URL: https://doi.org/10.1371/journal.pone.0281529, doi:10.1371/journal.pone.0281529. This article has 3 citations and is from a peer-reviewed journal.
(hu2023ang1andang4 pages 8-10): Alexander Hu, Cullen Roberts, Andrei Moscalu, Mark Redston, and James Yoo. Ang1 and ang4 differentially affect colitis and carcinogenesis in an aom-dss mouse model. PLOS ONE, 18:e0281529, Mar 2023. URL: https://doi.org/10.1371/journal.pone.0281529, doi:10.1371/journal.pone.0281529. This article has 3 citations and is from a peer-reviewed journal.
(wang2018angiogeninribonuclease5is pages 1-4): Ying-Nai Wang, Heng-Huan Lee, Chao-Kai Chou, Wen-Hao Yang, Yongkun Wei, Chun-Te Chen, Jun Yao, Jennifer L. Hsu, Cihui Zhu, Haoqiang Ying, Yuanqing Ye, Wei-Jan Wang, Seung-Oe Lim, Weiya Xia, How-Wen Ko, Xiuping Liu, Chang-Gong Liu, Xifeng Wu, Huamin Wang, Donghui Li, Laura R. Prakash, Matthew H. Katz, Yaan Kang, Michael Kim, Jason B. Fleming, David Fogelman, Milind Javle, Anirban Maitra, and Mien-Chie Hung. Angiogenin/ribonuclease 5 is an egfr ligand and a serum biomarker for erlotinib sensitivity in pancreatic cancer. Cancer cell, 33 4:752-769.e8, Apr 2018. URL: https://doi.org/10.1016/j.ccell.2018.02.012, doi:10.1016/j.ccell.2018.02.012. This article has 99 citations and is from a highest quality peer-reviewed journal.
(wang2018angiogeninribonuclease5is pages 8-9): Ying-Nai Wang, Heng-Huan Lee, Chao-Kai Chou, Wen-Hao Yang, Yongkun Wei, Chun-Te Chen, Jun Yao, Jennifer L. Hsu, Cihui Zhu, Haoqiang Ying, Yuanqing Ye, Wei-Jan Wang, Seung-Oe Lim, Weiya Xia, How-Wen Ko, Xiuping Liu, Chang-Gong Liu, Xifeng Wu, Huamin Wang, Donghui Li, Laura R. Prakash, Matthew H. Katz, Yaan Kang, Michael Kim, Jason B. Fleming, David Fogelman, Milind Javle, Anirban Maitra, and Mien-Chie Hung. Angiogenin/ribonuclease 5 is an egfr ligand and a serum biomarker for erlotinib sensitivity in pancreatic cancer. Cancer cell, 33 4:752-769.e8, Apr 2018. URL: https://doi.org/10.1016/j.ccell.2018.02.012, doi:10.1016/j.ccell.2018.02.012. This article has 99 citations and is from a highest quality peer-reviewed journal.
(sheng2016threedecadesof pages 8-8): Jinghao Sheng and Zhengping Xu. Three decades of research on angiogenin: a review and perspective. Acta biochimica et biophysica Sinica, 48 5:399-410, May 2016. URL: https://doi.org/10.1093/abbs/gmv131, doi:10.1093/abbs/gmv131. This article has 267 citations and is from a peer-reviewed journal.
(strydom1998theangiogenins pages 1-2): D. J. Strydom. The angiogenins. Cellular and Molecular Life Sciences CMLS, 54:811-824, Aug 1998. URL: https://doi.org/10.1007/s000180050210, doi:10.1007/s000180050210. This article has 239 citations.

Citations

adams2004theangiogeninsan pages 2-3
holloway2001highlevelexpressionof pages 1-2
sultana2022humanandmouse pages 5-6
garnett2021emergingbiologicalfunctions pages 6-8
sultana2022humanandmouse pages 1-2
sheng2016threedecadesof pages 1-2
adams2004theangiogeninsan pages 6-8
lyons2017rnabiologyof pages 1-3
lyons2017rnabiologyof pages 4-6
garnett2021emergingbiologicalfunctions pages 8-9
sheng2016threedecadesof pages 4-5
kulka2009humanmastcells pages 1-2
sheng2016threedecadesof pages 8-8
strydom1998theangiogenins pages 1-2
https://doi.org/10.1016/j.ccell.2018.02.012
https://doi.org/10.3389/fmicb.2022.1022945,
https://doi.org/10.1093/abbs/gmv131,
https://doi.org/10.1023/a:1009015512200,
https://doi.org/10.1006/prep.2001.1434,
https://doi.org/10.1080/15476286.2016.1272746,
https://doi.org/10.1080/10409238.2021.2004577,
https://doi.org/10.3109/08977199909103521,
https://doi.org/10.3390/ijms22031287,
https://doi.org/10.1189/jlb.0908517,
https://doi.org/10.1371/journal.pone.0281529,
https://doi.org/10.1016/j.ccell.2018.02.012,
https://doi.org/10.1007/s000180050210,

Bioinformatics Results

(RESULTS.md)

Ang2 ISO Source Trace Results

Command used:

python3 genes/mouse/Ang2/Ang2-bioinformatics/trace_iso_sources.py

Summary

The local Ang2-goa.tsv file contains 46 ISO annotations for mouse Ang2.
Every one of those 46 ISO rows is transferred through GO_REF:0000119 from the same source entity, UniProtKB:P03950 (human angiogenin/ANG).
The current QuickGO trace divides those source terms into three buckets:
34 with current direct experimental support on human ANG.
4 with only inferred support on human ANG (GO:0019731, GO:0045087, GO:0050830, GO:0061844).
8 with no current matching human ANG source term (GO:0001878, GO:0002181, GO:0006898, GO:0005694, GO:0015629, GO:0019732, GO:0033554, GO:0036416).
9 ISO terms overlap a non-ISO mouse Ang2 annotation for the same GO term in the local GOA export, so those transfers are redundant even before biological review.

Biological Interpretation

Mouse Ang2 is Angrp / angiogenin-related protein, a paralog of canonical mouse/human angiogenin rather than a simple one-to-one functional equivalent. The original biochemical characterization found that mouse Ang is angiogenic but Angrp is not, while Angrp still has appreciable ribonucleolytic activity toward tRNA and related substrates PMID:8633065.
The later structural study reinforced paralog divergence and showed that mAng-2 is almost 80% active compared to the human form in comparative tRNA cleavage assays, while also noting that mAng-2 is not angiogenic among the murine paralogues [PMID:23170778 "mAng-2 is almost 80% active compared to the human form" ; "Experiments have shown that mAng, mAng-3 and mAng-4 have angiogenic activities comparable to that of hAng, whereas mAng-2 is not angiogenic"].
Because of that divergence, even ISO terms with real experimental support on human ANG are unsafe to accept automatically for mouse Ang2 when they concern angiogenesis, receptor binding, signaling, stress-granule biology, nuclear trafficking, or immune effector roles.

Review Implications

GO:0004540 and GO:0004549 are the main ISO terms that remain biologically plausible for Ang2, because mouse Ang2 has direct biochemical evidence for RNase/tRNA cleavage activity PMID:8633065 PMID:23170778.
Immune/antimicrobial ISO terms are particularly weak because their current human ANG source is itself inferred rather than experimental.
ISO terms with no current human source term are best treated as stale transfers.
The non-ISO experimental block in the local GOA file also contains clear homonym errors:
PMID:17670746 is about angiopoietin-2, not angiogenin-2 PMID:17670746.
PMID:25313067 and PMID:28096417 are about angiotensin II (AngII) signaling and WNK4, not Ang2/angiogenin-related protein PMID:25313067 PMID:28096417.
PMID:29065170 is a ZNF418 cardiac hypertrophy paper that uses Ang II as a stimulus, not an Ang2 gene study PMID:29065170.

📄 View Raw YAML

id: Q64438
gene_symbol: Ang2
product_type: PROTEIN
status: COMPLETE
taxon:
  id: NCBITaxon:10090
  label: Mus musculus
description: >-
  Ang2 encodes mouse angiogenin-related protein (Angrp), a secreted RNase A
  family paralog of canonical mouse/human angiogenin. The directly supported
  function is RNA/tRNA cleavage activity. In contrast, a systematic trace of the
  local ISO block shows that all 46 ISO annotations were transferred from human
  ANG (UniProtKB:P03950) via GO_REF:0000119, and most of the transferred
  angiogenic, signaling, stress-response, and immune terms overstate the biology
  of the divergent non-angiogenic mouse paralog. Several non-ISO experimental
  GOA rows also appear to be homonym errors from angiopoietin-2 or angiotensin
  II papers rather than annotations to angiogenin-2/Angrp.
references:
  - id: GO_REF:0000002
    title: Gene Ontology annotation through association of InterPro records with GO terms
    findings: []
  - id: GO_REF:0000033
    title: Annotation inferences using phylogenetic trees
    findings: []
  - id: GO_REF:0000043
    title: Gene Ontology annotation based on UniProtKB/Swiss-Prot keyword mapping
    findings: []
  - id: GO_REF:0000044
    title: Gene Ontology annotation based on UniProtKB/Swiss-Prot Subcellular Location vocabulary mapping, accompanied by conservative changes to GO terms applied by UniProt
    findings: []
  - id: GO_REF:0000117
    title: Electronic Gene Ontology annotations created by ARBA machine learning models
    findings: []
  - id: GO_REF:0000119
    title: Automated transfer of experimentally-verified manual GO annotation data to mouse-human orthologs
    findings: []
  - id: GO_REF:0000120
    title: Combined Automated Annotation using Multiple IEA Methods
    findings: []
  - id: PMID:8633065
    title: "Characterization of mouse angiogenin-related protein: implications for functional studies on angiogenin."
    findings:
      - statement: Mouse Ang2/Angrp is not angiogenic in assays where mouse angiogenin is active.
        supporting_text: mouse Ang is potently angiogenic, but Angrp is not
        reference_section_type: ABSTRACT
      - statement: Mouse Ang2/Angrp retains ribonucleolytic activity toward tRNA and dinucleotide substrates.
        supporting_text: Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang
        reference_section_type: ABSTRACT
      - statement: Loss of angiogenic activity is attributed to defective cellular receptor binding rather than loss of RNase catalytic capacity.
        supporting_text: an inability to bind cellular receptors is implicated since Angrp does not inhibit Ang-induced angiogenesis
        reference_section_type: ABSTRACT
  - id: PMID:16045902
    title: Expression and regulation of murine macrophage angiopoietin-2.
    is_invalid: true
    findings:
      - statement: This UniProt tissue-specificity citation is about angiopoietin-2, not angiogenin-2/Angrp.
        supporting_text: Expression and regulation of murine macrophage angiopoietin-2.
        reference_section_type: TITLE
  - id: PMID:17670746
    title: High glucose increases angiopoietin-2 transcription in microvascular endothelial cells through methylglyoxal modification of mSin3A.
    is_invalid: true
    findings:
      - statement: This publication studies angiopoietin-2/Ang-2 expression, not mouse angiogenin-2/Angrp.
        supporting_text: High glucose increases angiopoietin-2 transcription in microvascular endothelial cells
        reference_section_type: TITLE
  - id: PMID:23170778
    title: "Crystal structures of murine angiogenin-2 and -3-probing 'structure--function' relationships amongst angiogenin homologues."
    findings:
      - statement: mAng-2 has substantial tRNA-cleavage activity in comparative RNase assays.
        supporting_text: mAng-2 is almost 80% active compared to the human form of the protein
        reference_section_type: RESULTS
      - statement: The mAng-2 crystal structure captured zinc bound at the active site.
        supporting_text: first crystal structures of an Ang with a zinc ion bound at the active site
        reference_section_type: ABSTRACT
      - statement: The structural study reinforces that mAng-2 is not angiogenic despite RNase activity.
        supporting_text: whereas mAng-2 is not angiogenic
        reference_section_type: INTRODUCTION
  - id: PMID:25313067
    title: Angiotensin II signaling via protein kinase C phosphorylates Kelch-like 3, preventing WNK4 degradation.
    is_invalid: true
    findings:
      - statement: This publication concerns angiotensin II regulation of KLHL3/WNK4, not the Ang2 gene product.
        supporting_text: Angiotensin II signaling via protein kinase C phosphorylates Kelch-like 3, preventing WNK4 degradation
        reference_section_type: TITLE
  - id: PMID:28096417
    title: Phosphorylation by PKC and PKA regulate the kinase activity and downstream signaling of WNK4.
    is_invalid: true
    findings:
      - statement: This publication concerns WNK4 phosphorylation downstream of AngII/vasopressin signaling, not the Ang2 gene product.
        supporting_text: With-no-lysine kinase 4 (WNK4) regulates electrolyte homeostasis and blood pressure
        reference_section_type: ABSTRACT
  - id: PMID:29065170
    title: Zinc-finger protein 418 overexpression protects against cardiac hypertrophy and fibrosis.
    is_invalid: true
    findings:
      - statement: This publication concerns ZNF418 and uses angiotensin II as a stimulus; it is not an Ang2/Angrp study.
        supporting_text: effect and mechanism of zinc-finger protein 418 (ZNF418) on cardiac hypertrophy caused by aortic banding
        reference_section_type: ABSTRACT
  - id: file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md
    title: Ang2 ISO source trace results
    findings:
      - statement: All 46 ISO annotations in the local Ang2 GOA were transferred from human ANG through GO_REF:0000119.
        supporting_text: Every one of those 46 ISO rows is transferred through `GO_REF:0000119` from the same source entity, `UniProtKB:P03950` (human angiogenin/ANG).
      - statement: Mouse Ang2 is a divergent paralog, so human ANG angiogenic, receptor/signaling, nuclear/stress, and immune annotations should not be propagated automatically.
        supporting_text: even ISO terms with real experimental support on human ANG are unsafe to accept automatically for mouse Ang2 when they concern angiogenesis, receptor binding, signaling, stress-granule biology, nuclear trafficking, or immune effector roles.
      - statement: The experimental GOA block contains homonym errors from angiopoietin-2, angiotensin II, and ZNF418 papers.
        supporting_text: The non-ISO experimental block in the local GOA file also contains clear homonym errors
  - id: file:mouse/Ang2/Ang2-deep-research-falcon.md
    title: Falcon deep research report for mouse Ang2
    findings:
      - statement: Falcon verified that mouse Ang2 is angiogenin-2/Angrp rather than angiopoietin-2.
        supporting_text: The UniProt target provided (Q64438) is instead a **murine angiogenin paralog**, commonly referred to as **mouse angiogenin-2 (mAng2)** or **angiogenin-related protein (Angrp)**
      - statement: Falcon identified the best-supported direct function as secreted RNase activity with tRNA/dinucleotide substrates and little or no angiogenic activity.
        supporting_text: "Best-supported annotation for Q64438 is: **secreted RNase A-family paralog with strong in vitro RNase/tRNA-cleaving activity but little or no angiogenic activity**"
      - statement: Falcon found no recent primary studies centered directly on mouse Ang2/Angrp.
        supporting_text: "**Key limitation:** no 2023–2024 primary studies explicitly centered on **mouse Ang2/Angrp** were retrieved here."
existing_annotations:
  - term:
      id: GO:0004540
      label: RNA nuclease activity
    qualifier: enables
    evidence_type: IBA
    original_reference_id: GO_REF:0000033
    review:
      summary: Phylogenetic RNase transfer matches direct mouse biochemical evidence.
      action: ACCEPT
      reason: Mouse Ang2 has direct RNA/tRNA cleavage evidence.
      supported_by:
        - reference_id: PMID:8633065
          supporting_text: Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang.
        - reference_id: PMID:23170778
          supporting_text: mAng-2 is almost 80% active compared to the human form of the protein
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: Ang2/Angrp is enzymatically active as a ribonuclease. Recombinant mAngrp cleaves **tRNA test substrates** in vitro.
  - term:
      id: GO:0005615
      label: extracellular space
    qualifier: is_active_in
    evidence_type: IBA
    original_reference_id: GO_REF:0000033
    review:
      summary: Secreted extracellular localization is plausible, but it is a localization note rather than a core function.
      action: KEEP_AS_NON_CORE
      reason: Signal peptide and secreted RNase family context support extracellular localization.
      supported_by:
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: Angiogenins are **secreted vertebrate-specific ribonucleases** within the pancreatic RNase A superfamily.
  - term:
      id: GO:0019731
      label: antibacterial humoral response
    qualifier: involved_in
    evidence_type: IBA
    original_reference_id: GO_REF:0000033
    review:
      summary: Family-level antibacterial transfer is not supported for mouse Ang2.
      action: REMOVE
      reason: Likely conflates canonical angiogenin or antimicrobial paralogs with Ang2.
      supported_by:
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: Direct evidence for **Ang2-specific tiRNA production in mouse cells** is lacking
        - reference_id: file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md
          supporting_text: Immune/antimicrobial ISO terms are particularly weak because their current human ANG source is itself inferred rather than experimental.
  - term:
      id: GO:0045087
      label: innate immune response
    qualifier: involved_in
    evidence_type: IBA
    original_reference_id: GO_REF:0000033
    review:
      summary: Family-level innate-immune transfer is not supported for mouse Ang2.
      action: REMOVE
      reason: Likely conflates canonical angiogenin or antimicrobial paralogs with Ang2.
      supported_by:
        - reference_id: file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md
          supporting_text: Immune/antimicrobial ISO terms are particularly weak because their current human ANG source is itself inferred rather than experimental.
  - term:
      id: GO:0050830
      label: defense response to Gram-positive bacterium
    qualifier: involved_in
    evidence_type: IBA
    original_reference_id: GO_REF:0000033
    review:
      summary: Family-level antibacterial transfer is not supported for mouse Ang2.
      action: REMOVE
      reason: Likely conflates canonical angiogenin or antimicrobial paralogs with Ang2.
      supported_by:
        - reference_id: file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md
          supporting_text: Immune/antimicrobial ISO terms are particularly weak because their current human ANG source is itself inferred rather than experimental.
  - term:
      id: GO:0061844
      label: antimicrobial humoral immune response mediated by antimicrobial peptide
    qualifier: involved_in
    evidence_type: IBA
    original_reference_id: GO_REF:0000033
    review:
      summary: Family-level antimicrobial transfer is not supported for mouse Ang2.
      action: REMOVE
      reason: Likely conflates canonical angiogenin or antimicrobial paralogs with Ang2.
      supported_by:
        - reference_id: file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md
          supporting_text: Immune/antimicrobial ISO terms are particularly weak because their current human ANG source is itself inferred rather than experimental.
  - term:
      id: GO:0001525
      label: angiogenesis
    qualifier: involved_in
    evidence_type: IBA
    original_reference_id: GO_REF:0000033
    review:
      summary: Angiogenesis is contradicted by direct mouse Ang2 literature.
      action: REMOVE
      reason: PMID:8633065 shows Angrp is not angiogenic.
      supported_by:
        - reference_id: PMID:8633065
          supporting_text: mouse Ang is potently angiogenic, but Angrp is not, even when assayed at relatively high doses.
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: A defining functional divergence of Ang2/Angrp is that it is **non-angiogenic** (or far less angiogenic than canonical angiogenin) in standard assays.
  - term:
      id: GO:0003676
      label: nucleic acid binding
    qualifier: enables
    evidence_type: IEA
    original_reference_id: GO_REF:0000002
    review:
      summary: Generic nucleic acid binding is less informative than the specific RNase activity.
      action: MARK_AS_OVER_ANNOTATED
      reason: Prefer RNA nuclease activity.
  - term:
      id: GO:0003677
      label: DNA binding
    qualifier: enables
    evidence_type: IEA
    original_reference_id: GO_REF:0000043
    review:
      summary: DNA binding is inferred from canonical angiogenin biology, not demonstrated for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence supports DNA binding for Ang2.
      supported_by:
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: nuclear/nucleolar roles and tiRNA-mediated translation regulation should be treated as **family-based hypotheses** unless demonstrated directly for mAng2/Angrp.
  - term:
      id: GO:0004518
      label: nuclease activity
    qualifier: enables
    evidence_type: IEA
    original_reference_id: GO_REF:0000043
    review:
      summary: Generic nuclease parent term; RNA nuclease activity is the informative term.
      action: MODIFY
      reason: Specific RNA nuclease terms better capture the supported mouse Ang2/Angrp activity.
      proposed_replacement_terms:
        - id: GO:0004540
          label: RNA nuclease activity
        - id: GO:0004549
          label: tRNA-specific ribonuclease activity
  - term:
      id: GO:0004519
      label: endonuclease activity
    qualifier: enables
    evidence_type: IEA
    original_reference_id: GO_REF:0000043
    review:
      summary: Generic endonuclease activity is broader than the supported RNase activity.
      action: MODIFY
      reason: Specific RNA nuclease terms better capture the supported mouse Ang2/Angrp activity.
      proposed_replacement_terms:
        - id: GO:0004540
          label: RNA nuclease activity
        - id: GO:0004549
          label: tRNA-specific ribonuclease activity
  - term:
      id: GO:0004540
      label: RNA nuclease activity
    qualifier: enables
    evidence_type: IEA
    original_reference_id: GO_REF:0000117
    review:
      summary: Electronic RNase prediction matches direct mouse biochemical evidence.
      action: ACCEPT
      reason: Consistent with direct mouse RNase assays.
      supported_by:
        - reference_id: PMID:8633065
          supporting_text: Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang.
        - reference_id: PMID:23170778
          supporting_text: mAng-2 is almost 80% active compared to the human form of the protein
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: Ang2/Angrp is enzymatically active as a ribonuclease. Recombinant mAngrp cleaves **tRNA test substrates** in vitro.
  - term:
      id: GO:0005576
      label: extracellular region
    qualifier: located_in
    evidence_type: IEA
    original_reference_id: GO_REF:0000044
    review:
      summary: Extracellular localization is plausible for a secreted Ang2 protein and is used as the core-function location.
      action: ACCEPT
      reason: Secreted extracellular-region localization is consistent with the core RNase function.
      supported_by:
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: Angiogenins are **secreted vertebrate-specific ribonucleases** within the pancreatic RNase A superfamily.
  - term:
      id: GO:0005730
      label: nucleolus
    qualifier: located_in
    evidence_type: IEA
    original_reference_id: GO_REF:0000044
    review:
      summary: Nucleolar localization is imported from canonical angiogenin biology and is not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
      supported_by:
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: "**Direct Ang2/Angrp-specific localization evidence** was not retrieved in this run."
  - term:
      id: GO:0016787
      label: hydrolase activity
    qualifier: enables
    evidence_type: IEA
    original_reference_id: GO_REF:0000043
    review:
      summary: Generic hydrolase parent term; RNA nuclease activity is the informative term.
      action: MODIFY
      reason: Specific RNA nuclease terms better capture the supported mouse Ang2/Angrp activity.
      proposed_replacement_terms:
        - id: GO:0004540
          label: RNA nuclease activity
        - id: GO:0004549
          label: tRNA-specific ribonuclease activity
  - term:
      id: GO:0031410
      label: cytoplasmic vesicle
    qualifier: located_in
    evidence_type: IEA
    original_reference_id: GO_REF:0000120
    review:
      summary: Cytoplasmic-vesicle localization is a speculative automated transfer, not demonstrated for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
      supported_by:
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: "**Direct Ang2/Angrp-specific localization evidence** was not retrieved in this run."
  - term:
      id: GO:0046872
      label: metal ion binding
    qualifier: enables
    evidence_type: IEA
    original_reference_id: GO_REF:0000043
    review:
      summary: Metal binding is supported by the mouse structural study, but it is secondary to the core RNase activity.
      action: KEEP_AS_NON_CORE
      reason: Mouse Ang2 binds Zn2+ and shows metal-sensitive RNase activity.
      supported_by:
        - reference_id: PMID:23170778
          supporting_text: first crystal structures of an Ang with a zinc ion bound at the active site
  - term:
      id: GO:0005615
      label: extracellular space
    qualifier: is_active_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the stronger is_active_in qualifier is not demonstrated for mouse Ang2 and is redundant with broader secretion annotations.
      action: KEEP_AS_NON_CORE
      reason: Extracellular localization is plausible, but the qualifier is stronger than the direct mouse evidence.
  - term:
      id: GO:0001525
      label: angiogenesis
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but mouse Ang2/Angrp is explicitly non-angiogenic.
      action: REMOVE
      reason: PMID:8633065 contradicts the transfer.
      supported_by:
        - reference_id: PMID:8633065
          supporting_text: mouse Ang is potently angiogenic, but Angrp is not, even when assayed at relatively high doses.
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: A defining functional divergence of Ang2/Angrp is that it is **non-angiogenic** (or far less angiogenic than canonical angiogenin) in standard assays.
  - term:
      id: GO:0001666
      label: response to hypoxia
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG hypoxia biology, not shown for mouse Ang2.
      action: REMOVE
      reason: Divergent paralog with no direct mouse evidence for this process.
  - term:
      id: GO:0001878
      label: response to yeast
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term.
      action: REMOVE
      reason: Stale ISO transfer.
  - term:
      id: GO:0001938
      label: positive regulation of endothelial cell proliferation
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred endothelial-proliferation biology from human ANG, but mouse Ang2 is non-angiogenic.
      action: REMOVE
      reason: PMID:8633065 shows Angrp does not share canonical angiogenic biology.
  - term:
      id: GO:0002181
      label: cytoplasmic translation
    qualifier: acts_upstream_of_or_within
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term.
      action: REMOVE
      reason: Stale ISO transfer.
  - term:
      id: GO:0003779
      label: actin binding
    qualifier: enables
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG actin-binding studies, but mouse Ang2 receptor/interface biology diverges from canonical angiogenin.
      action: REMOVE
      reason: No direct mouse evidence and paralog divergence makes transfer unsafe.
  - term:
      id: GO:0004540
      label: RNA nuclease activity
    qualifier: enables
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119 and independently supported by mouse Ang2 biochemical assays.
      action: ACCEPT
      reason: Direct mouse RNase evidence exists.
      supported_by:
        - reference_id: PMID:8633065
          supporting_text: Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang.
        - reference_id: PMID:23170778
          supporting_text: mAng-2 is almost 80% active compared to the human form of the protein
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: Ang2/Angrp is enzymatically active as a ribonuclease. Recombinant mAngrp cleaves **tRNA test substrates** in vitro.
  - term:
      id: GO:0004549
      label: tRNA-specific ribonuclease activity
    qualifier: enables
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119 and directly supported by mouse Ang2 tRNA cleavage assays.
      action: ACCEPT
      reason: Direct mouse tRNA cleavage evidence exists.
      supported_by:
        - reference_id: PMID:8633065
          supporting_text: Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang.
        - reference_id: PMID:23170778
          supporting_text: mAng-2 is almost 80% active compared to the human form of the protein
        - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
          supporting_text: Ang2/Angrp is enzymatically active as a ribonuclease. Recombinant mAngrp cleaves **tRNA test substrates** in vitro.
  - term:
      id: GO:0005102
      label: signaling receptor binding
    qualifier: enables
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG receptor-binding studies, but mouse Ang2 lacks canonical receptor-mediated angiogenic biology.
      action: REMOVE
      reason: PMID:8633065 implicates deficient receptor binding in Angrp.
  - term:
      id: GO:0005507
      label: copper ion binding
    qualifier: enables
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Human ANG source supports copper binding, but mouse Ang2 data support only broader divalent-metal binding.
      action: MODIFY
      reason: Mouse structural data support metal ion binding, not copper specificity.
      proposed_replacement_terms:
        - id: GO:0046872
          label: metal ion binding
      supported_by:
        - reference_id: PMID:23170778
          supporting_text: These constitute the first crystal structures of an Ang with a zinc ion bound at the active site
  - term:
      id: GO:0005604
      label: basement membrane
    qualifier: located_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred basement-membrane association from human ANG angiogenic biology, not shown for mouse Ang2.
      action: REMOVE
      reason: Non-angiogenic paralog; no direct mouse evidence.
  - term:
      id: GO:0005615
      label: extracellular space
    qualifier: located_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred extracellular-space location from human ANG; plausible but redundant with retained non-ISO secretion annotations.
      action: KEEP_AS_NON_CORE
      reason: Extracellular localization is plausible, but it remains non-core and redundant.
  - term:
      id: GO:0005634
      label: nucleus
    qualifier: is_active_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG nuclear-activity studies, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0005634
      label: nucleus
    qualifier: located_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG nuclear-localization studies, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0005694
      label: chromosome
    qualifier: located_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term.
      action: REMOVE
      reason: Stale ISO transfer.
  - term:
      id: GO:0005730
      label: nucleolus
    qualifier: located_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred nucleolar localization from human ANG, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0005737
      label: cytoplasm
    qualifier: is_active_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred cytoplasmic activity from human ANG intracellular stress studies, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0006898
      label: receptor-mediated endocytosis
    qualifier: acts_upstream_of_or_within
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term.
      action: REMOVE
      reason: Stale ISO transfer.
  - term:
      id: GO:0007165
      label: signal transduction
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred signal transduction from human ANG, but mouse Ang2 lacks canonical angiogenic signaling evidence.
      action: REMOVE
      reason: Non-angiogenic paralog with no direct mouse support.
  - term:
      id: GO:0008201
      label: heparin binding
    qualifier: enables
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred heparin binding from human ANG, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0009303
      label: rRNA transcription
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred rRNA-transcription biology from human ANG, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0009725
      label: response to hormone
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred hormone-response biology from human ANG, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0010494
      label: cytoplasmic stress granule
    qualifier: located_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred stress-granule localization from human ANG stress-response studies, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0015629
      label: actin cytoskeleton
    qualifier: located_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term.
      action: REMOVE
      reason: Stale ISO transfer.
  - term:
      id: GO:0016477
      label: cell migration
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred cell-migration biology from human ANG angiogenic studies, but mouse Ang2 is non-angiogenic.
      action: REMOVE
      reason: No direct mouse evidence and canonical angiogenic transfer is unsafe.
  - term:
      id: GO:0019731
      label: antibacterial humoral response
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source is itself inferred-only (IBA).
      action: REMOVE
      reason: Do not stack inference on inference.
  - term:
      id: GO:0019732
      label: antifungal humoral response
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term.
      action: REMOVE
      reason: Stale ISO transfer.
  - term:
      id: GO:0023052
      label: signaling
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred generic signaling from human ANG, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0030139
      label: endocytic vesicle
    qualifier: located_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred endocytic-vesicle localization from human ANG internalization studies, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0032055
      label: negative regulation of translation in response to stress
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred translational stress-response biology from human ANG, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0032311
      label: angiogenin-PRI complex
    qualifier: part_of
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred angiogenin-PRI complex membership from human ANG, not demonstrated for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0033554
      label: cellular response to stress
    qualifier: acts_upstream_of_or_within
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term.
      action: REMOVE
      reason: Stale ISO transfer.
  - term:
      id: GO:0034063
      label: stress granule assembly
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred stress-granule assembly from human ANG, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0036416
      label: tRNA stabilization
    qualifier: acts_upstream_of_or_within
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source no longer carries this term.
      action: REMOVE
      reason: Stale ISO transfer.
  - term:
      id: GO:0042277
      label: peptide binding
    qualifier: enables
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred peptide-binding annotation from human ANG receptor/actin studies, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0042327
      label: positive regulation of phosphorylation
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred positive regulation of phosphorylation from human ANG signaling studies, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0042803
      label: protein homodimerization activity
    qualifier: enables
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred protein homodimerization from human ANG, but mouse Ang2 dimerization is not established as a physiological activity.
      action: REMOVE
      reason: Structural observations are insufficient for this GO claim.
  - term:
      id: GO:0043022
      label: ribosome binding
    qualifier: enables
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred ribosome binding from human ANG stress-response studies, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0045087
      label: innate immune response
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source is itself inferred-only (IBA).
      action: REMOVE
      reason: Do not stack inference on inference.
  - term:
      id: GO:0048018
      label: receptor ligand activity
    qualifier: enables
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred receptor-ligand activity from human ANG, but mouse Ang2 lacks canonical receptor-mediated angiogenic signaling evidence.
      action: REMOVE
      reason: Non-angiogenic paralog with no direct mouse evidence.
  - term:
      id: GO:0048662
      label: negative regulation of smooth muscle cell proliferation
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred smooth-muscle proliferation phenotype from human ANG, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0050714
      label: positive regulation of protein secretion
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred positive regulation of protein secretion from human ANG, but mouse Ang2 lacks direct evidence for this process.
      action: REMOVE
      reason: Source support is not sufficient to justify propagation to Ang2.
  - term:
      id: GO:0050830
      label: defense response to Gram-positive bacterium
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source is itself inferred-only (IBA).
      action: REMOVE
      reason: Do not stack inference on inference.
  - term:
      id: GO:0061844
      label: antimicrobial humoral immune response mediated by antimicrobial peptide
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred from human ANG via GO_REF:0000119, but the current human source is itself inferred-only (IBA).
      action: REMOVE
      reason: Do not stack inference on inference.
  - term:
      id: GO:0071425
      label: hematopoietic stem cell proliferation
    qualifier: involved_in
    evidence_type: ISO
    original_reference_id: GO_REF:0000119
    supporting_entities:
      - UniProtKB:P03950
    review:
      summary: Transferred hematopoietic stem-cell proliferation from human ANG, not shown for mouse Ang2.
      action: REMOVE
      reason: No direct mouse evidence.
  - term:
      id: GO:0006468
      label: protein phosphorylation
    qualifier: involved_in
    evidence_type: IMP
    original_reference_id: PMID:25313067
    review:
      summary: Misannotation from AngII signaling, not Ang2/angiogenin-related protein.
      action: REMOVE
      reason: The paper studies angiotensin II signaling through KLHL3 and WNK4.
      supported_by:
        - reference_id: PMID:25313067
          supporting_text: Angiotensin II signaling via protein kinase C phosphorylates Kelch-like 3, preventing WNK4 degradation.
  - term:
      id: GO:0006468
      label: protein phosphorylation
    qualifier: involved_in
    evidence_type: IDA
    original_reference_id: PMID:28096417
    review:
      summary: Misannotation from AngII signaling, not Ang2/angiogenin-related protein.
      action: REMOVE
      reason: The paper studies WNK4 phosphorylation downstream of AngII and vasopressin.
      supported_by:
        - reference_id: PMID:28096417
          supporting_text: Phosphorylation by PKC and PKA regulate the kinase activity and downstream signaling of WNK4.
  - term:
      id: GO:0010467
      label: gene expression
    qualifier: involved_in
    evidence_type: IDA
    original_reference_id: PMID:25313067
    review:
      summary: Misannotation from AngII signaling, not Ang2/angiogenin-related protein.
      action: REMOVE
      reason: The paper is about angiotensin II regulation of KLHL3 and WNK4, not the Ang2 gene product.
  - term:
      id: GO:0010467
      label: gene expression
    qualifier: involved_in
    evidence_type: IDA
    original_reference_id: PMID:28096417
    review:
      summary: Misannotation from AngII signaling, not Ang2/angiogenin-related protein.
      action: REMOVE
      reason: The paper is about WNK4 phosphorylation downstream of AngII and vasopressin, not Ang2.
  - term:
      id: GO:0038166
      label: angiotensin-activated signaling pathway
    qualifier: involved_in
    evidence_type: IDA
    original_reference_id: PMID:25313067
    review:
      summary: Misannotation from AngII signaling, not Ang2/angiogenin-related protein.
      action: REMOVE
      reason: The paper concerns angiotensin II as a hormone stimulus, not the Ang2 gene product.
  - term:
      id: GO:0070293
      label: renal absorption
    qualifier: involved_in
    evidence_type: IDA
    original_reference_id: PMID:25313067
    review:
      summary: Misannotation from AngII/WNK4 physiology, not Ang2/angiogenin-related protein.
      action: REMOVE
      reason: This physiology belongs to the angiotensin II pathway, not the Ang2 gene.
  - term:
      id: GO:0001934
      label: positive regulation of protein phosphorylation
    qualifier: acts_upstream_of_or_within
    evidence_type: IDA
    original_reference_id: PMID:29065170
    review:
      summary: Misannotation from a ZNF418 cardiac-hypertrophy study that uses Ang II as a stimulus.
      action: REMOVE
      reason: The paper is about ZNF418, not Ang2/angiogenin-related protein.
      supported_by:
        - reference_id: PMID:29065170
          supporting_text: This study aimed to investigated the effect and mechanism of zinc-finger protein 418 (ZNF418) on cardiac hypertrophy caused by aortic banding (AB), phenylephrine (PE) or angiotensin II (Ang II) in vivo and in vitro.
  - term:
      id: GO:0003300
      label: cardiac muscle hypertrophy
    qualifier: acts_upstream_of_or_within
    evidence_type: IDA
    original_reference_id: PMID:29065170
    review:
      summary: Misannotation from a ZNF418 cardiac-hypertrophy study that uses Ang II as a stimulus.
      action: REMOVE
      reason: The paper is about ZNF418, not Ang2/angiogenin-related protein.
  - term:
      id: GO:0061049
      label: cell growth involved in cardiac muscle cell development
    qualifier: acts_upstream_of_or_within
    evidence_type: IDA
    original_reference_id: PMID:29065170
    review:
      summary: Misannotation from a ZNF418 cardiac-hypertrophy study that uses Ang II as a stimulus.
      action: REMOVE
      reason: The paper is about ZNF418, not Ang2/angiogenin-related protein.
  - term:
      id: GO:0004540
      label: RNA nuclease activity
    qualifier: enables
    evidence_type: IDA
    original_reference_id: PMID:23170778
    review:
      summary: Direct biochemical evidence for mouse Ang2 RNase activity.
      action: ACCEPT
      reason: On-target mouse structural and enzymatic study.
      supported_by:
        - reference_id: PMID:23170778
          supporting_text: mAng-2 is almost 80% active compared to the human form of the protein
  - term:
      id: GO:0071333
      label: cellular response to glucose stimulus
    qualifier: acts_upstream_of_or_within
    evidence_type: IDA
    original_reference_id: PMID:17670746
    review:
      summary: Misannotation from an angiopoietin-2 paper, not Ang2/angiogenin-related protein.
      action: REMOVE
      reason: The paper studies angiopoietin-2 (Ang-2), not mouse Ang2/Angrp.
      supported_by:
        - reference_id: PMID:17670746
          supporting_text: High glucose increases angiopoietin-2 transcription in microvascular endothelial cells through methylglyoxal modification of mSin3A.
core_functions:
  - molecular_function:
      id: GO:0004549
      label: tRNA-specific ribonuclease activity
    description: >-
      Secreted angiogenin-related RNase with direct biochemical tRNA cleavage
      activity. Mouse Ang2 retains RNase chemistry but does not share the broad
      angiogenic/signaling program transferred from canonical human ANG.
    locations:
      - id: GO:0005576
        label: extracellular region
    supported_by:
      - reference_id: PMID:8633065
        supporting_text: Angrp has somewhat greater ribonucleolytic activity toward tRNA and dinucleotide substrates than does Ang.
      - reference_id: PMID:23170778
        supporting_text: mAng-2 is almost 80% active compared to the human form of the protein
      - reference_id: file:mouse/Ang2/Ang2-deep-research-falcon.md
        supporting_text: "Best-supported annotation for Q64438 is: **secreted RNase A-family paralog with strong in vitro RNase/tRNA-cleaving activity but little or no angiogenic activity**"
      - reference_id: file:mouse/Ang2/Ang2-bioinformatics/RESULTS.md
        supporting_text: "`GO:0004540` and `GO:0004549` are the main ISO terms that remain biologically plausible for Ang2"
suggested_questions:
  - question: What endogenous RNA substrates and tissue contexts define the in vivo function of mouse Ang2 beyond the in vitro tRNA-cleavage assays?
  - question: Which human ANG functions truly map to mouse Ang2 versus other murine angiogenin paralogs, and can ISO transfer rules be constrained for this expanded paralog family?
suggested_experiments:
  - description: Compare recombinant mouse Ang2, canonical mouse angiogenin, and additional murine angiogenin paralogs in endothelial proliferation, receptor-binding, RNase-inhibitor binding, and cell-uptake assays.
    hypothesis: Mouse Ang2 retains RNase activity but lacks the receptor-binding and angiogenic outputs of canonical angiogenin.
    experiment_type: Comparative biochemical and cell-based functional assays
  - description: Use endogenous tagging or targeted perturbation in tissues that express Ang2 to identify where the protein localizes and which RNAs are cleaved in vivo.
    hypothesis: The physiological role of Ang2 is RNase-centered and more restricted than the transferred human ANG stress and signaling annotations.
    experiment_type: Endogenous tagging plus RNA substrate profiling

Ang2

Gene Description

Existing Annotations Review

Core Functions

Secreted angiogenin-related RNase with direct biochemical tRNA cleavage activity. Mouse Ang2 retains RNase chemistry but does not share the broad angiogenic/signaling program transferred from canonical human ANG.

References

Suggested Questions for Experts

Suggested Experiments

📚 Additional Documentation

Deep Research Falcon

Question

Gene Research for Functional Annotation

⚠️ CRITICAL: Gene/Protein Identification Context

Target Gene/Protein Identity (from UniProt):

MANDATORY VERIFICATION STEPS:

If Gene Symbol is Ambiguous or You Cannot Find Relevant Literature:

Research Target:

Output

Gene Research for Functional Annotation

⚠️ CRITICAL: Gene/Protein Identification Context

Target Gene/Protein Identity (from UniProt):

MANDATORY VERIFICATION STEPS:

If Gene Symbol is Ambiguous or You Cannot Find Relevant Literature:

Research Target:

Research Report: Functional Annotation of mouse Ang2 / Angrp (UniProt Q64438) — angiogenin-2 (angiogenin-related protein)

1) Target verification (critical disambiguation)

2) Key concepts and definitions (current understanding)

2.1 Angiogenins as RNase A superfamily members

2.2 Catalyzed reaction and substrate specificity

3) Gene-/protein-specific functional evidence for Ang2/Angrp (mAng2)

3.1 Biochemical activity (direct evidence)

3.2 Angiogenic activity (direct evidence: negative)

3.3 Localization and cellular compartment of action (direct vs inferred)

3.4 Regulation and pathway context (RNH1/RI system)

4) Expression and biological roles

4.1 Genomic and evolutionary context (mouse-specific paralog expansion)

4.2 Tissue/cell-type expression

5) Recent developments (prioritize 2023–2024) and how they relate to Ang2

6) Current applications and real-world implementations

6.1 Applications (largely for ANG/RNase5 rather than Ang2/Angrp)

6.2 Implications for Ang2/Angrp applications

7) Expert synthesis and interpretive analysis (authoritative perspectives)

8) Key statistics and data points (from primary studies and reviews)

9) Summary: best-supported functional annotation for UniProt Q64438 (mouse Ang2/Angrp)

Structured summary table

Citations

Bioinformatics Results

Ang2 ISO Source Trace Results

Summary

Biological Interpretation

Review Implications

📄 View Raw YAML