Provide a comprehensive cross-database identifier and functional mapping reference for human STAT3. This should serve as a definitive lookup resource for researchers. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 1: GENE IDENTIFIERS ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Provide ALL gene-level database identifiers: - HGNC ID and approved symbol - Ensembl gene ID (ENSG) - NCBI Entrez Gene ID - OMIM gene/locus ID - Genomic location: chromosome, start position, end position, strand ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 2: TRANSCRIPT IDENTIFIERS ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ List ALL transcript-level identifiers: - Ensembl transcripts: ALL ENST IDs with biotype (protein_coding, etc.) How many total transcripts? - RefSeq transcripts: ALL NM_ mRNA accessions Mark which is MANE Select (canonical clinical standard) - CCDS IDs: ALL consensus coding sequence identifiers For the CANONICAL/MANE SELECT transcript: - List ALL exon IDs (ENSE) with genomic coordinates - Total exon count ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 3: PROTEIN IDENTIFIERS ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ List ALL protein-level identifiers: - UniProt accessions: ALL entries (reviewed and unreviewed) Mark the canonical reviewed entry - RefSeq protein: ALL NP_ accessions Protein domains and families: - List ALL annotated domains/families with identifiers - Include: domain name, type (domain/family/superfamily), and ID ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 4: STRUCTURE IDENTIFIERS ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Experimental structures: - List ALL PDB structure IDs - For each: experimental method (X-ray, NMR, Cryo-EM) and resolution - Total PDB structure count Predicted structures: - AlphaFold model ID and confidence metrics (pLDDT) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 5: CROSS-SPECIES ORTHOLOGS ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ List orthologous genes in key model organisms (where available): - Mouse (Mus musculus): gene ID, symbol - Rat (Rattus norvegicus): gene ID, symbol - Zebrafish (Danio rerio): gene ID, symbol - Fruit fly (Drosophila melanogaster): gene ID, symbol - Worm (C. elegans): gene ID, symbol - Yeast (S. cerevisiae): gene ID, symbol ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 6: CLINICAL VARIANTS & AI PREDICTIONS ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Clinical variant annotations: - Total variant count in clinical databases - Breakdown by classification: Pathogenic, Likely Pathogenic, Uncertain Significance (VUS), Likely Benign, Benign - List TOP 50 pathogenic/likely pathogenic variants with: variant ID, HGVS notation, associated condition AI-based variant effect predictions: - Splice effect predictions: Total count List TOP 50 predicted splice-altering variants with delta scores - Missense pathogenicity predictions: Total count List TOP 50 predicted pathogenic missense variants with scores ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 7: BIOLOGICAL PATHWAYS & GENE ONTOLOGY ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Pathway membership: - List ALL biological pathways this gene participates in - Include pathway IDs and names - Total pathway count Gene Ontology annotations: - Biological Process: count and TOP 20 terms with IDs - Molecular Function: count and TOP 20 terms with IDs - Cellular Component: count and TOP 20 terms with IDs ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 8: PROTEIN INTERACTIONS & MOLECULAR NETWORKS ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Protein-protein interactions: - Total interaction count - List TOP 50 highest-confidence interacting proteins with scores Protein similarity (evolutionary and structural): - Structural/embedding similarity: How many similar proteins? List TOP 20 with similarity scores - Sequence homology: How many homologous proteins? List TOP 20 with identity/similarity scores ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 9: TRANSCRIPTION FACTOR REGULATORY DATA ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ If this gene encodes a transcription factor: Downstream targets (genes regulated BY this TF): - Total target gene count - List TOP 50 target genes with regulation type (activates/represses) DNA binding profiles: - List ALL known binding motif IDs - Motif family classification Upstream regulators (TFs that regulate THIS gene): - List known transcriptional regulators with evidence type ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 10: DRUG & PHARMACOLOGY DATA ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ If this gene/protein is a drug target: Targeting molecules: - How many drug/compound molecules target this protein? - List TOP 30 molecules by development phase - Include: molecule ID, name, mechanism, highest development phase Clinical trials: - How many clinical trials involve drugs targeting this gene? - List TOP 20 trials with: trial ID, phase, status, intervention Pharmacogenomics: - Known drug-gene interactions affecting drug response - Dosing guidelines if any exist ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 11: EXPRESSION PROFILES ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Tissue expression: - Which tissues express this gene most highly? - List TOP 30 tissues with expression scores/levels - Note any tissue-specific or tissue-enriched patterns Cell type expression: - Which cell types show highest expression? - List TOP 30 cell types with expression scores - Note any cell type-specific patterns Single-cell expression data (if available): - Which single-cell datasets/experiments include this gene? - Notable cell population patterns ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SECTION 12: DISEASE ASSOCIATIONS ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ Mendelian/monogenic disease links: - What diseases are caused by mutations in this gene? - List ALL associated diseases with: disease name, disease ID, inheritance pattern, evidence level Phenotype associations: - What clinical phenotypes are associated with this gene? - List TOP 50 phenotype terms with IDs Complex trait associations (GWAS): - What traits/diseases are linked via genome-wide association studies? - List TOP 30 GWAS associations with: trait, study ID, p-value, effect size if available ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FORMATTING REQUIREMENTS ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ - Present each section with clear headers - Use tables for listing multiple items - Always include COUNTS for every category - For lists with 50 items: show total count + TOP 50 - For lists with

Question

Provide a comprehensive cross-database identifier and functional mapping
reference for human STAT3. This should serve as a definitive
lookup resource for researchers.

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 1: GENE IDENTIFIERS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Provide ALL gene-level database identifiers:
- HGNC ID and approved symbol
- Ensembl gene ID (ENSG)
- NCBI Entrez Gene ID
- OMIM gene/locus ID
- Genomic location: chromosome, start position, end position, strand

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 2: TRANSCRIPT IDENTIFIERS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
List ALL transcript-level identifiers:
- Ensembl transcripts: ALL ENST IDs with biotype (protein_coding, etc.)
  How many total transcripts?
- RefSeq transcripts: ALL NM_ mRNA accessions
  Mark which is MANE Select (canonical clinical standard)
- CCDS IDs: ALL consensus coding sequence identifiers

For the CANONICAL/MANE SELECT transcript:
- List ALL exon IDs (ENSE) with genomic coordinates
- Total exon count

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 3: PROTEIN IDENTIFIERS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
List ALL protein-level identifiers:
- UniProt accessions: ALL entries (reviewed and unreviewed)
  Mark the canonical reviewed entry
- RefSeq protein: ALL NP_ accessions

Protein domains and families:
- List ALL annotated domains/families with identifiers
- Include: domain name, type (domain/family/superfamily), and ID

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 4: STRUCTURE IDENTIFIERS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Experimental structures:
- List ALL PDB structure IDs
- For each: experimental method (X-ray, NMR, Cryo-EM) and resolution
- Total PDB structure count

Predicted structures:
- AlphaFold model ID and confidence metrics (pLDDT)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 5: CROSS-SPECIES ORTHOLOGS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
List orthologous genes in key model organisms (where available):
- Mouse (Mus musculus): gene ID, symbol
- Rat (Rattus norvegicus): gene ID, symbol
- Zebrafish (Danio rerio): gene ID, symbol
- Fruit fly (Drosophila melanogaster): gene ID, symbol
- Worm (C. elegans): gene ID, symbol
- Yeast (S. cerevisiae): gene ID, symbol

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 6: CLINICAL VARIANTS & AI PREDICTIONS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Clinical variant annotations:
- Total variant count in clinical databases
- Breakdown by classification: Pathogenic, Likely Pathogenic,
  Uncertain Significance (VUS), Likely Benign, Benign
- List TOP 50 pathogenic/likely pathogenic variants with:
  variant ID, HGVS notation, associated condition

AI-based variant effect predictions:
- Splice effect predictions: Total count
  List TOP 50 predicted splice-altering variants with delta scores
- Missense pathogenicity predictions: Total count
  List TOP 50 predicted pathogenic missense variants with scores

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 7: BIOLOGICAL PATHWAYS & GENE ONTOLOGY
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Pathway membership:
- List ALL biological pathways this gene participates in
- Include pathway IDs and names
- Total pathway count

Gene Ontology annotations:
- Biological Process: count and TOP 20 terms with IDs
- Molecular Function: count and TOP 20 terms with IDs
- Cellular Component: count and TOP 20 terms with IDs

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 8: PROTEIN INTERACTIONS & MOLECULAR NETWORKS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Protein-protein interactions:
- Total interaction count
- List TOP 50 highest-confidence interacting proteins with scores

Protein similarity (evolutionary and structural):
- Structural/embedding similarity: How many similar proteins?
  List TOP 20 with similarity scores
- Sequence homology: How many homologous proteins?
  List TOP 20 with identity/similarity scores

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 9: TRANSCRIPTION FACTOR REGULATORY DATA
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
If this gene encodes a transcription factor:

Downstream targets (genes regulated BY this TF):
- Total target gene count
- List TOP 50 target genes with regulation type (activates/represses)

DNA binding profiles:
- List ALL known binding motif IDs
- Motif family classification

Upstream regulators (TFs that regulate THIS gene):
- List known transcriptional regulators with evidence type

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 10: DRUG & PHARMACOLOGY DATA
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
If this gene/protein is a drug target:

Targeting molecules:
- How many drug/compound molecules target this protein?
- List TOP 30 molecules by development phase
- Include: molecule ID, name, mechanism, highest development phase

Clinical trials:
- How many clinical trials involve drugs targeting this gene?
- List TOP 20 trials with: trial ID, phase, status, intervention

Pharmacogenomics:
- Known drug-gene interactions affecting drug response
- Dosing guidelines if any exist

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 11: EXPRESSION PROFILES
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Tissue expression:
- Which tissues express this gene most highly?
- List TOP 30 tissues with expression scores/levels
- Note any tissue-specific or tissue-enriched patterns

Cell type expression:
- Which cell types show highest expression?
- List TOP 30 cell types with expression scores
- Note any cell type-specific patterns

Single-cell expression data (if available):
- Which single-cell datasets/experiments include this gene?
- Notable cell population patterns

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SECTION 12: DISEASE ASSOCIATIONS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Mendelian/monogenic disease links:
- What diseases are caused by mutations in this gene?
- List ALL associated diseases with: disease name, disease ID,
  inheritance pattern, evidence level

Phenotype associations:
- What clinical phenotypes are associated with this gene?
- List TOP 50 phenotype terms with IDs

Complex trait associations (GWAS):
- What traits/diseases are linked via genome-wide association studies?
- List TOP 30 GWAS associations with: trait, study ID, p-value,
  effect size if available

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
FORMATTING REQUIREMENTS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
- Present each section with clear headers
- Use tables for listing multiple items
- Always include COUNTS for every category
- For lists with >50 items: show total count + TOP 50
- For lists with <50 items: show ALL items
- Always include database identifiers (IDs), not just names
- Mark canonical/primary/reviewed entries where applicable
- If a section has no data available, state "No data available"
  rather than omitting the section

Accepted Answer

I now have all the data needed to compile the comprehensive STAT3 reference. Let me format it.
STAT3 - Comprehensive Cross-Database Identifier and Functional Mapping Reference Signal Transducer and Activator of Transcription 3
Section 1: Gene Identifiers Primary Gene Identifiers
DatabaseIdentifierDescription HGNCHGNC:11364Approved symbol: STAT3 EnsemblENSG00000168610Ensembl gene ID NCBI Entrez6774Entrez Gene ID OMIM102582Gene/Locus MIM number Gene Information AttributeValue Approved NameSignal …

Attribute	Value
Approved Name	Signal transducer and activator of transcription 3
Previous Name	Signal transducer and activator of transcription 3 (acute-phase response factor)
Aliases	APRF, ADMIO, ADMIO1, HIES
Locus Type	Protein-coding gene
Gene Group	SH2 domain containing
Status	Approved

Attribute	Value
Chromosome	17
Cytogenetic Band	17q21.2
Start Position	42,313,324
End Position	42,388,568
Strand	Minus (-)
Genomic Accession	NC_000017.11

Category	Count
Total Ensembl Transcripts	94
Protein-coding	72
Nonsense-mediated decay	5
Retained intron	11
Other	6
RefSeq Transcripts (human)	20 (mRNA)
CCDS IDs	11

Attribute	Value
RefSeq MANE Select	NM_139276 ★
RefSeq Protein	NP_644805 ★
Ensembl Canonical	ENST00000264657

Transcript ID	Biotype	Start	End
ENST00000264657	protein_coding	42313324	42388442
ENST00000389272	protein_coding	42315468	42388431
ENST00000404395	protein_coding	42315559	42388414
ENST00000585517	protein_coding	42314854	42388439
ENST00000588969	protein_coding	42315491	42388482
ENST00000677002	protein_coding	42314848	42348516
ENST00000677030	protein_coding	42313446	42388505
ENST00000677152	protein_coding	42314848	42388477
ENST00000677421	protein_coding	42313421	42388433
ENST00000677442	protein_coding	42313421	42388474
ENST00000677479	protein_coding	42313471	42388474
ENST00000677603	protein_coding	42314848	42388477
ENST00000677723	protein_coding	42313421	42388474
ENST00000678043	protein_coding	42313421	42388476
ENST00000678044	protein_coding	42313412	42388540
ENST00000678048	protein_coding	42313421	42388442
ENST00000678535	protein_coding	42314903	42388484
ENST00000678572	protein_coding	42313471	42388442
ENST00000678674	protein_coding	42313421	42388442
ENST00000678792	protein_coding	42313421	42388467
ENST00000678827	protein_coding	42313471	42388540
ENST00000678905	protein_coding	42313471	42388474
ENST00000678906	protein_coding	42313412	42388454
ENST00000678913	protein_coding	42313421	42388442
ENST00000678960	protein_coding	42313412	42388373
ENST00000679014	protein_coding	42313421	42388511
ENST00000679166	protein_coding	42313421	42388472
ENST00000679185	protein_coding	42313471	42388503
ENST00000715205	protein_coding	42313412	42388568
ENST00000858552	protein_coding	42314848	42388503

STAT3 Gene Complete Identifier and Functional Mapping Reference

Structured Data Sources

Database	Identifier	Description
HGNC	HGNC:11364	Approved symbol: STAT3
Ensembl	ENSG00000168610	Ensembl gene ID
NCBI Entrez	6774	Entrez Gene ID
OMIM	102582	Gene/Locus MIM number

RefSeq ID	Symbol	Status	MANE Select
NM_139276	STAT3	REVIEWED	★ YES
NM_003150	STAT3	REVIEWED	No
NM_213662	STAT3	REVIEWED	No
NM_001369512	STAT3	REVIEWED	No
NM_001369513	STAT3	REVIEWED	No
NM_001369514	STAT3	REVIEWED	No
NM_001369516	STAT3	REVIEWED	No
NM_001369517	STAT3	REVIEWED	No
NM_001369518	STAT3	REVIEWED	No
NM_001369519	STAT3	REVIEWED	No
NM_001369520	STAT3	REVIEWED	No
NM_001384984	STAT3	REVIEWED	No
NM_001384985	STAT3	REVIEWED	No
NM_001384986	STAT3	REVIEWED	No
NM_001384987	STAT3	REVIEWED	No
NM_001384988	STAT3	REVIEWED	No
NM_001384989	STAT3	REVIEWED	No
NM_001384990	STAT3	REVIEWED	No
NM_001384991	STAT3	REVIEWED	No
NM_001384992	STAT3	REVIEWED	No

Exon ID	Start	End	Strand	Length
ENSE00002972150	42388279	42388442	-	164
ENSE00003551986	42346569	42346713	-	145
ENSE00003631188	42345559	42345657	-	99
ENSE00001302308	42348389	42348539	-	151
ENSE00000725380	42339314	42339409	-	96
ENSE00001505325	42338731	42338812	-	82
ENSE00001505324	42337763	42337857	-	95
ENSE00001228140	42337435	42337586	-	152
ENSE00001228134	42333891	42334049	-	159
ENSE00001228128	42333673	42333765	-	93
ENSE00001228122	42331472	42331531	-	60
ENSE00001228116	42329747	42329776	-	30
ENSE00001228108	42329554	42329647	-	94
ENSE00000950719	42329410	42329457	-	48
ENSE00000950720	42326116	42326199	-	84
ENSE00003534325	42324711	42324846	-	136
ENSE00003503687	42324963	42325061	-	99
ENSE00003504262	42323573	42323625	-	53
ENSE00003463278	42323260	42323354	-	95
ENSE00000950725	42323004	42323143	-	140
ENSE00001179541	42322282	42322494	-	213
ENSE00002832033	42317182	42317224	-	43
ENSE00003466416	42316789	42316901	-	113
ENSE00001835049	42313324	42315800	-	2477

UniProt ID	Status	Name
P40763	★ Reviewed (Swiss-Prot)	Signal transducer and activator of transcription 3
G8JLH9	Unreviewed (TrEMBL)	STAT3 isoform
A0A7I2V2G1	Unreviewed	STAT3 variant
A0A7I2V2T1	Unreviewed	STAT3 variant
A0A7I2V395	Unreviewed	STAT3 variant
A0A7I2V3V0	Unreviewed	STAT3 variant
A0A7I2V444	Unreviewed	STAT3 variant
A0A7I2V4C8	Unreviewed	STAT3 variant
A0A7I2V4F6	Unreviewed	STAT3 variant
A0A7I2V4R2	Unreviewed	STAT3 variant
A0A7I2V4R3	Unreviewed	STAT3 variant
A0A7I2V552	Unreviewed	STAT3 variant
A0A7I2V5N9	Unreviewed	STAT3 variant
A0A7I2YQD2	Unreviewed	STAT3 variant
A0A7I2YQI1	Unreviewed	STAT3 variant
A0A7I2YQR5	Unreviewed	STAT3 variant

Property	Value
Length	770 amino acids
Molecular Mass	88,068 Da
Alternative Name	Acute-phase response factor (APRF)

RefSeq Protein	Symbol	Status	MANE
NP_644805	STAT3	REVIEWED	★ YES
NP_003141	STAT3	REVIEWED	No
NP_998827	STAT3	REVIEWED	No
NP_001356441	STAT3	REVIEWED	No
NP_001356442	STAT3	REVIEWED	No
NP_001356443	STAT3	REVIEWED	No
NP_001356445	STAT3	REVIEWED	No
NP_001356446	STAT3	REVIEWED	No
NP_001356447	STAT3	REVIEWED	No
NP_001356448	STAT3	REVIEWED	No
NP_001356449	STAT3	REVIEWED	No
NP_001371913	STAT3	REVIEWED	No
NP_001371914	STAT3	REVIEWED	No
NP_001371915	STAT3	REVIEWED	No
NP_001371916	STAT3	REVIEWED	No
NP_001371917	STAT3	REVIEWED	No
NP_001371918	STAT3	REVIEWED	No
NP_001371919	STAT3	REVIEWED	No
NP_001371920	STAT3	REVIEWED	No
NP_001371921	STAT3	REVIEWED	No

InterPro ID	Name	Type
IPR001217	STAT	Family
IPR000980	SH2	Domain
IPR035855	STAT3_SH2	Domain
IPR013799	STAT_TF_prot_interaction	Domain
IPR013800	STAT_TF_alpha	Domain
IPR013801	STAT_TF_DNA-bd	Domain
IPR048988	STAT_linker	Domain
IPR008967	p53-like_TF_DNA-bd_sf	Homologous_superfamily
IPR012345	STAT_TF_DNA-bd_N	Homologous_superfamily
IPR015988	STAT_TF_CC	Homologous_superfamily
IPR036535	STAT_N_sf	Homologous_superfamily
IPR036860	SH2_dom_sf	Homologous_superfamily

PDB ID	Method	Resolution (Å)	Title
6NJS	X-ray Diffraction	2.70	Stat3 Core in complex with compound SD36
6QHD	X-ray Diffraction	2.85	Lysine acetylated and tyrosine phosphorylated STAT3 in complex with DNA
6TLC	X-ray Diffraction	2.90	Unphosphorylated human STAT3 in complex with MS3-6 monobody
5AX3	X-ray Diffraction	2.98	Crystal structure of ERK2 complexed with allosteric inhibitors
6NUQ	X-ray Diffraction	3.15	Stat3 Core in complex with compound SI109
5U5S	Solution NMR	-	Brd2 second bromodomain in complex with STAT3 peptide

Species	Ensembl Gene ID	Symbol	RefSeq
Mouse (Mus musculus)	ENSMUSG00000004040	Stat3	NM_011486
Rat (Rattus norvegicus)	ENSRNOG00000019742	Stat3	NM_012747
Zebrafish (Danio rerio)	ENSDARG00000022712	stat3	NM_131479
Worm (C. elegans)	WBGENE00010251	-	-
Worm (C. elegans)	WBGENE00013111	-	-
Fruit fly (D. melanogaster)	No direct ortholog	-	-
Yeast (S. cerevisiae)	No ortholog	-	-

Classification	Count
Pathogenic	43
Likely Pathogenic	~5
Uncertain Significance (VUS)	~50
Likely Benign	~200
Benign	~100
Conflicting	~10

CCDS ID
CCDS32656
CCDS32657
CCDS59288
CCDS92309
CCDS92310
CCDS92311
CCDS92312
CCDS92313
CCDS92314
CCDS92315
CCDS92316

ClinVar ID	HGVS Notation	Protein Change	Review Status
18304	c.1144C>T	p.Arg382Trp	Multiple submitters
18305	c.1145G>A	p.Arg382Gln	Multiple submitters
18306	c.1268G>A	p.Arg423Gln	Multiple submitters
18308	c.1909G>A	p.Val637Met	Multiple submitters
18303	c.1384GTG[1]	p.Val463del	Multiple submitters
224846	c.454C>T	p.Arg152Trp	Multiple submitters
224848	c.2147C>T	p.Thr716Met	Multiple submitters
636714	c.1139+1G>T	Splice site	Multiple submitters
418505	c.1397A>G	p.Asn466Ser	Multiple submitters
224843	c.1032G>C	p.Gln344His	Single submitter
224847	c.1057G>T	p.Val353Phe	Single submitter
224849	c.1260T>G	p.Asn420Lys	Single submitter
224850	c.2107G>A	p.Ala703Thr	Single submitter
476197	c.986T>A	p.Met329Lys	Single submitter
664121	c.1311C>A	p.His437Gln	Single submitter
850251	c.833G>A	p.Arg278His	Single submitter
1005984	c.2141C>T	p.Thr714Ile	Single submitter
1039785	c.1228C>T	p.His410Tyr	Single submitter
1068485	c.1859C>G	p.Thr620Ser	Single submitter
1398166	c.1110-2A>G	Splice site	Single submitter
1429110	c.2116C>A	p.Leu706Met	Single submitter
1429145	c.1915C>G	p.Pro639Ala	Single submitter
1800571	c.988C>T	p.Pro330Ser	Single submitter
2099076	c.1145G>C	p.Arg382Pro	Single submitter
2138013	c.1915C>A	p.Pro639Thr	Single submitter
2138015	c.1907C>A	p.Ser636Tyr	Single submitter
2138016	c.1865C>T	p.Thr622Ile	Single submitter
2169593	c.1934T>A	p.Leu645Gln	Single submitter
2308162	c.995A>T	p.His332Leu	Single submitter
2925614	c.1907C>T	p.Ser636Phe	Single submitter
2925616	c.1181T>C	p.Met394Thr	Single submitter
2940006	c.2137G>T	p.Val713Leu	Single submitter
3391073	c.1309C>T	p.His437Tyr	Single submitter
3759433	c.2137G>C	p.Val713Leu	Single submitter
144030	c.1175A>G	p.Lys392Arg	No criteria
144031	c.1938C>G	p.Asn646Lys	No criteria
144032	c.1974G>C	p.Lys658Asn	No criteria
1705748	c.1910T>C	p.Val637Ala	No criteria
1804642	c.985A>G	p.Met329Val	No criteria
1804643	c.1858A>G	p.Thr620Ala	No criteria

Variant ID	Protein Change	Pathogenicity Score
17:42317197:A:G	F710S	0.997
17:42317188:A:T	V713E	0.996
17:42317194:A:T	I711N	0.995
17:42317213:A:G	Y705H	0.994
17:42317194:A:G	I711T	0.993
17:42317213:A:C	Y705D	0.993
17:42317188:A:G	V713A	0.991
17:42317194:A:C	I711S	0.991
17:42317188:A:C	V713G	0.988
17:42317203:G:A	T708I	0.988
17:42317196:A:C	F710L	0.987
17:42317209:A:G	L706P	0.987
17:42322327:A:C	Y686D	0.972
17:42317197:A:C	F710C	0.974
17:42317189:C:T	V713M	0.974
17:42317213:A:T	Y705N	0.979
17:42317212:T:C	Y705C	0.978
17:42317212:T:G	Y705S	0.968
17:42317189:C:A	V713L	0.967
17:42317190:A:C	C712W	0.962
17:42322326:T:G	Y686S	0.954
17:42317185:G:A	T714I	0.952
17:42317192:A:G	C712R	0.943
17:42317185:G:T	T714K	0.937
17:42317185:G:C	T714R	0.935
17:42317198:A:C	F710V	0.932
17:42317191:C:T	C712Y	0.929
17:42317198:A:T	F710I	0.907
17:42316866:G:A	S727F	0.905
17:42317182:G:A	P715L	0.895
17:42317199:C:A	K709N	0.882
17:42317209:A:T	L706Q	0.876
17:42316866:G:T	S727Y	0.874
17:42317195:T:A	I711F	0.859
17:42322326:T:C	Y686C	0.855
17:42316863:G:T	P728H	0.864
17:42316863:G:A	P728L	0.849
17:42317209:A:C	L706R	0.846
17:42317200:T:A	K709M	0.838
17:42316863:G:C	P728R	0.835

Variant ID	Effect	Delta Score
17:42315796:GGACT:G	acceptor_gain	1.00
17:42315797:GACT:G	acceptor_gain	1.00
17:42315799:CT:C	acceptor_gain	1.00
17:42315801:C:CC	acceptor_gain	1.00
17:42315801:C:CG	acceptor_loss	1.00
17:42316788:CCAAA:C	donor_gain	1.00
17:42316780:AATAC:A	donor_loss	0.99
17:42316781:ATACT:A	donor_loss	0.99
17:42316782:TACT:T	donor_loss	0.99
17:42316783:AC:A	donor_loss	0.99
17:42316784:C:CA	donor_loss	0.99
17:42316785:T:TA	donor_loss	0.99
17:42316786:CACCA:C	donor_loss	0.99
17:42316787:ACC:A	donor_loss	0.99
17:42316788:C:CG	donor_loss	0.99
17:42315797:GACTC:G	acceptor_gain	0.98
17:42315798:ACT:A	acceptor_gain	0.98
17:42315799:CTC:C	acceptor_gain	0.98
17:42315800:TCT:T	acceptor_gain	0.98
17:42315801:C:G	acceptor_gain	0.98
17:42315810:C:CT	acceptor_gain	0.98
17:42315811:A:T	acceptor_gain	0.98
17:42316787:A:AC	donor_gain	0.99
17:42316788:C:CC	donor_gain	0.99
17:42316788:CCAA:C	donor_gain	0.97
17:42316787:AC:A	donor_gain	0.93
17:42316788:CC:C	donor_gain	0.93
17:42316799:T:TA	donor_gain	0.92
17:42316788:CCA:C	donor_gain	0.90
17:42315814:C:CT	acceptor_gain	0.87
17:42315815:A:T	acceptor_gain	0.83
17:42316820:TTC:T	donor_gain	0.83
17:42315717:T:C	donor_gain	0.81

Pathway ID	Pathway Name	Disease?
R-HSA-1059683	Interleukin-6 signaling	No
R-HSA-6783783	Interleukin-10 signaling	No
R-HSA-6785807	Interleukin-4 and Interleukin-13 signaling	No
R-HSA-8983432	Interleukin-15 signaling	No
R-HSA-8985947	Interleukin-9 signaling	No
R-HSA-9020933	Interleukin-23 signaling	No
R-HSA-9020956	Interleukin-27 signaling	No
R-HSA-9020958	Interleukin-21 signaling	No
R-HSA-8854691	Interleukin-20 family signaling	No
R-HSA-8984722	Interleukin-35 Signalling	No
R-HSA-9008059	Interleukin-37 signaling	No
R-HSA-1266695	Interleukin-7 signaling	No
R-HSA-198745	Signalling to STAT3	No
R-HSA-982772	Growth hormone receptor signaling	No
R-HSA-2586552	Signaling by Leptin	No
R-HSA-1433557	Signaling by SCF-KIT	No
R-HSA-186763	Downstream signal transduction	No
R-HSA-201556	Signaling by ALK	No
R-HSA-8849474	PTK6 Activates STAT3	No
R-HSA-8875791	MET activates STAT3	No
R-HSA-9674555	Signaling by CSF3 (G-CSF)	No
R-HSA-9680350	Signaling by CSF1 (M-CSF) in myeloid cells	No
R-HSA-111453	BH3-only proteins associate with anti-apoptotic BCL-2	No
R-HSA-2559582	Senescence-Associated Secretory Phenotype (SASP)	No
R-HSA-390471	Association of TriC/CCT with target proteins	No
R-HSA-452723	Transcriptional regulation of pluripotent stem cells	No
R-HSA-2892247	POU5F1, SOX2, NANOG activate proliferation genes	No
R-HSA-9616222	Transcriptional regulation of granulopoiesis	No
R-HSA-9705462	Inactivation of CSF3 (G-CSF) signaling	No
R-HSA-9707564	Cytoprotection by HMOX1	No
R-HSA-9833482	PKR-mediated signaling	No
R-HSA-9909649	Regulation of PD-L1(CD274) transcription	No
R-HSA-9701898	STAT3 nuclear events downstream of ALK signaling	No
R-HSA-1839117	Signaling by cytosolic FGFR1 fusion mutants	Yes
R-HSA-9670439	Signaling by phosphorylated KIT mutants	Yes
R-HSA-9673767	Signaling by PDGFRA transmembrane mutants	Yes
R-HSA-9673770	Signaling by PDGFRA extracellular domain mutants	Yes
R-HSA-9725370	Signaling by ALK fusions and activated point mutants	Yes
R-HSA-9725371	Nuclear events stimulated by ALK signaling in cancer	Yes

GO ID	Term
GO:0007259	cell surface receptor signaling pathway via JAK-STAT
GO:0070102	interleukin-6-mediated signaling pathway
GO:0019221	cytokine-mediated signaling pathway
GO:0045944	positive regulation of transcription by RNA polymerase II
GO:0006357	regulation of transcription by RNA polymerase II
GO:0006954	inflammatory response
GO:0006953	acute-phase response
GO:0008283	cell population proliferation
GO:0030154	cell differentiation
GO:0045893	positive regulation of DNA-templated transcription
GO:0010628	positive regulation of gene expression
GO:0007165	signal transduction
GO:0048708	astrocyte differentiation
GO:0072538	T-helper 17 type immune response
GO:0045766	positive regulation of angiogenesis
GO:0060396	growth hormone receptor signaling pathway
GO:0033210	leptin-mediated signaling pathway
GO:0035019	somatic stem cell population maintenance
GO:0001666	response to hypoxia
GO:0042593	glucose homeostasis

GO ID	Term
GO:0003700	DNA-binding transcription factor activity
GO:0001228	DNA-binding transcription activator activity, RNA polymerase II-specific
GO:0000981	DNA-binding transcription factor activity, RNA polymerase II-specific
GO:0003677	DNA binding
GO:0042803	protein homodimerization activity
GO:0046983	protein dimerization activity
GO:0042802	identical protein binding
GO:0019901	protein kinase binding
GO:0019903	protein phosphatase binding
GO:0005102	signaling receptor binding
GO:0003723	RNA binding
GO:0070878	primary miRNA binding
GO:0106222	lncRNA binding
GO:0031490	chromatin DNA binding
GO:0035591	signaling adaptor activity
GO:0035259	nuclear glucocorticoid receptor binding
GO:0031730	CCR5 chemokine receptor binding
GO:0061629	RNA polymerase II-specific DNA-binding transcription factor binding
GO:0140297	DNA-binding transcription factor binding
GO:0000976	transcription cis-regulatory region binding

GO ID	Term
GO:0005634	nucleus
GO:0005654	nucleoplasm
GO:0005737	cytoplasm
GO:0005829	cytosol
GO:0005886	plasma membrane
GO:0000785	chromatin
GO:0005667	transcription regulator complex
GO:0005743	mitochondrial inner membrane
GO:0014069	postsynaptic density
GO:0090575	RNA polymerase II transcription regulator complex
GO:0098685	Schaffer collateral - CA1 synapse
GO:0098978	glutamatergic synapse

Interacting Protein	UniProt	Score
JAK1	O60674	999
JAK2	P23458	999
SRC	P12931	996
JUN	P05412	994
EP300	Q09472	992
PIK3CA	Q9Y6X2	988
EGFR	P00533	986
FOS	P01100	985
STAT1	P42224	982
STAT5B	P42229	974
TP53	P04637	970
STAT2	P51692	968
CUEDC2	Q9NZQ7	968
JAK3	P52333	967
IL10	Q13651	967
IL6	P05231	965
SOCS3	Q8IY63	965
PIAS3	Q9BZS1	965
EZH2	Q15910	964
SOCS2	O14543	961
TYK2	P29597	960
RELA	Q04206	960
NANOG	Q9H9S0	952
MAPK1	P28482	951
MET	P08581	948
LIF	P42702	940
IRF9	Q15306	939
STMN1	P16949	937
PTPN11	Q06124	936
NR3C1	P04150	932
AKT1	P31749	926
HSP90AA1	P07900	923
HIF1A	Q16665	923
CEBPB	P17676	920
IL10RA	P22301	916
DNMT1	P26358	916
CDKN1A	Q9P0J0	910
EGF	P01133	908
IFNG	P01579	905
IL6ST	P08887	903
NFKB1	P19838	903
HDAC1	Q13547	903
ERBB2	P21860	902
IL6R	P40189	900
CCND1	P24385	899
SUMO1	Q9UGK3	899
FOXM1	Q08050	892
ANXA2	Q7Z403	891
CTNNB1	P35222	887
IL12A	Q16552	886

UniProt	Similarity	Description
P42227	1.000	STAT3 (identical)
P52631	1.000	STAT3 ortholog
Q19S50	1.000	STAT3 ortholog
P61635	0.999	STAT6
A4FUD6	0.999	STAT3 ortholog
P40763	1.000	STAT3 (self)
P42224	0.999	STAT1
P42229	0.999	STAT5B
P42230	0.999	STAT5A
Q6DV79	0.999	STAT3 ortholog
Q7ZXK3	0.999	STAT3 ortholog
Q62771	0.999	STAT3 (mouse)

UniProt	Identity (%)	Bitscore
P40763	99.9	1527
P42227	99.9	1526
P52631	99.9	1527
Q62771	98.0	1538
P42230	98.0	1537
Q9TUM3	98.0	1531
Q9TUZ0	98.0	1531
P52632	98.7	1536
P42232	98.7	1535
P51692	97.2	1521
Q9TUZ1	97.0	1528
P42229	97.0	1519
Q95115	97.0	1523
Q6DV79	97.5	1484
P42224	96.3	1435
Q764M5	96.3	1436
Q7ZXK3	96.1	1466
Q9PVX8	96.1	1461

Motif ID	Name	Collection	Class	Family
MA0144.2	STAT3	CORE	STAT domain factors	STAT factors
MA0144.3	STAT3	CORE	STAT domain factors	STAT factors

Target Gene	Regulation	Confidence
BCL2	Activation	High
BCL2L1	Activation	High
BIRC5 (Survivin)	Activation	High
CCND1 (Cyclin D1)	Activation	High
MYC	Activation	High
VEGFA	Activation	High
CD274 (PD-L1)	Activation	High
SOCS3	Activation	High
IL10	Activation	High
A2M	Unknown	High
ABCB1	Unknown	High
ADIPOQ	Unknown	High
AGT	Unknown	High
AGRP	Unknown	High
BATF	Activation	High
BCL3	Activation	High
BECN1	Unknown	High
BIRC3	Activation	High
BMPR2	Unknown	High
BST2	Unknown	High
CAV1	Unknown	High
CCL2	Activation	High
CCL11	Activation	High
CD46	Activation	High
CD74	Unknown	High
CDC25A	Unknown	High
CDKN1A (p21)	Activation	High
CDKN1B (p27)	Unknown	High
HGF	Activation	Medium
TGFB1	Activation	Medium
IL6	Activation	Medium
RORC	Activation	Medium
CEBPD	Activation	Medium
S100A9	Activation	Medium
CASP3	Activation	Low
AHR	Activation	Low
AKAP12	Activation	Low
AKT1	Unknown	Low
APLN	Activation	Low
ARID5A	Activation	Low
BACE1	Unknown	Low
BAD	Activation	Low
BCL6	Activation	Low
CCDC88A	Activation	Low
CCL20	Activation	Low
CCNE1	Activation	Low
CDH17	Unknown	Low
CDX2	Unknown	Low
CDKN2D	Activation	Low
FOXP3	Repression	Medium

Regulator	Regulation	Confidence
CTNNB1 (β-catenin)	Activation	High
HMGA1	Activation	High
HIC1	Activation	-
JAK1	Activation	-
PLK1	Activation	-
POLR2H	Activation	-
KAT5	Repression	-
PPARG	Repression	-
SIN3A	Repression	-
ATF4	Unknown	Low
BCL6	Unknown	Low
CEBPA	Unknown	-
CEBPB	Unknown	Low
HIF1A	Unknown	Low
MYC	Unknown	Low
PIAS3	Unknown	-
RELA	Unknown	-
STAT1	Unknown	-
SPI1	Unknown	-
BRCA1	Unknown	-

Source	Target	Effect	Mechanism	Score
EGFR	STAT3	up-regulates	phosphorylation	0.88
JAK2	STAT3	up-regulates	phosphorylation	0.82
JAK1	STAT3	up-regulates	phosphorylation	0.80
SRC	STAT3	up-regulates	phosphorylation	0.79
JAK3	STAT3	up-regulates	phosphorylation	0.79
LEPR	STAT3	up-regulates	phosphorylation	0.76
IL6	STAT3	up-regulates	-	0.76
MTOR	STAT3	up-regulates	phosphorylation	0.75
PIAS3	STAT3	down-regulates	sumoylation	0.73
MAPK3	STAT3	up-regulates	phosphorylation	0.72
SOCS3	STAT3	down-regulates	-	0.71
TYK2	STAT3	up-regulates	phosphorylation	0.69
FGFR3	STAT3	up-regulates	phosphorylation	0.63
HCK	STAT3	up-regulates	phosphorylation	0.62
MAPK14	STAT3	up-regulates	phosphorylation	0.62
PRKCD	STAT3	up-regulates	phosphorylation	0.60
MAPK8	STAT3	up-regulates	phosphorylation	0.57
IRAK1	STAT3	up-regulates	phosphorylation	0.55
PTPN1	STAT3	down-regulates	dephosphorylation	0.55
PTPRD	STAT3	down-regulates	dephosphorylation	0.52
MAPK9	STAT3	up-regulates	phosphorylation	0.48
PTPN6	STAT3	down-regulates	dephosphorylation	0.46
PKM	STAT3	up-regulates	phosphorylation	0.44
ALK	STAT3	up-regulates	binding	0.44
CDK5	STAT3	up-regulates	phosphorylation	0.40
FGFR4	STAT3	up-regulates	phosphorylation	0.40
PRKCE	STAT3	up-regulates	phosphorylation	0.40
RPS6KA5	STAT3	up-regulates	phosphorylation	0.39
NLK	STAT3	up-regulates	phosphorylation	0.35
DAB2IP	STAT3	down-regulates	binding	0.35

ChEMBL Target ID	Name	Type
CHEMBL4026	Signal transducer and activator of transcription 3	SINGLE PROTEIN
CHEMBL4296101	PTPN9/STAT3	PROTEIN-PROTEIN INTERACTION
CHEMBL4523691	Protein cereblon/STAT3	PROTEIN-PROTEIN INTERACTION
CHEMBL5482983	JAK2-STAT3	PROTEIN COMPLEX

Attribute	Value
PharmGKB ID	PA337
VIP Gene	★ Yes (Very Important Pharmacogene)
Has Variant Annotation	Yes
Has CPIC Guideline	No

ChEMBL ID	Name	Type	Highest Phase
CHEMBL1078178	MOMELOTINIB	Small molecule	Phase 4 (Approved)
CHEMBL1401	NITAZOXANIDE	Small molecule	Phase 4 (Approved)
CHEMBL140	CURCUMIN	Small molecule	Phase 3
CHEMBL1096927	LEVOMENOL	Small molecule	Phase 2
CHEMBL1231124	AZD-1480	Small molecule	Phase 2
CHEMBL1081584	LOGANIN	Small molecule	Phase 0
CHEMBL1209803	MORRONISIDE	Small molecule	Phase 0
CHEMBL128729	-	Small molecule	Phase 0
CHEMBL1289974	-	Small molecule	Phase 0
CHEMBL1299373	-	Small molecule	Phase 0

Compound	Effect	Mechanism
S3I-201	down-regulates	chemical inhibition
5,15-Diphenyl-21H,23H-porphine	down-regulates activity	chemical inhibition

Attribute	Value
Expression Breadth	Ubiquitous
Total Present Calls	301
Total Absent Calls	2
Max Expression Score	99.31
Average Expression Score	93.72
Gold Quality Conditions	300

Tissue/Cell Type	Expression	Score	Quality
Type B pancreatic cell	present	99.31	gold
Pericardium	present	99.12	gold
Lower lobe of lung	present	99.05	gold
Mammary duct	present	98.47	gold
Nipple	present	98.41	gold
Heart right ventricle	present	98.29	gold
Upper lobe of lung	present	98.23	gold
Upper lobe of left lung	present	98.22	gold
Islet of Langerhans	present	98.14	gold
Vena cava	present	98.13	gold
Colonic epithelium	present	98.12	gold
Trachea	present	98.00	gold
Epithelium of mammary gland	present	98.00	gold
Cartilage tissue	present	97.93	gold
Dorsal root ganglion	present	97.88	gold
Penis	present	97.87	gold
Left uterine tube	present	97.86	gold
Trigeminal ganglion	present	97.83	gold
Blood	present	97.82	gold
Pharyngeal mucosa	present	97.80	gold
Superior surface of tongue	present	97.74	gold
Urethra	present	97.71	gold
Gall bladder	present	97.70	gold
Saphenous vein	present	97.69	gold
Synovial joint	present	97.67	gold
Right lung	present	97.64	gold
Peritoneum	present	97.63	gold
Omental fat pad	present	97.62	gold
Decidua	present	97.62	gold
Left ventricle myocardium	present	97.59	gold

Experiment ID	Description	Cells
E-CURD-85	T cells from blood, synovial fluid and tissue in psoriatic arthritis	111,869
E-HCAD-29	GM-CSF-producing T helper cells	78,686
E-GEOD-124472	Human embryonic kidney outer/inner cortical and organoid cells	18,079
E-GEOD-114530	Human fetal kidneys	22,148
E-MTAB-8911	Clonally expanded T-lymphocytes in chronic GVHD	19,075
E-MTAB-8884	Chronic myelomonocytic leukemia stem cells	9,386
E-CURD-135	Kidney organoid and adult human kidney transcriptomes	6,192
E-CURD-89	Immune cells from colon lamina propria and mesenteric lymph nodes	1,526
E-MTAB-7008	Endoderm differentiation from iPSCs	1,024

Disease	Disease ID	Inheritance	Evidence
Hyper-IgE recurrent infection syndrome 1, AD	OMIM:147060	Autosomal dominant	Strong
STAT3-related early-onset multisystem autoimmune disease	OMIM:615952	Autosomal dominant	Strong
Permanent neonatal diabetes mellitus	ORPHANET:99885	Autosomal dominant	Supportive
Acute promyelocytic leukemia	ORPHANET:520	-	-
T-cell large granular lymphocyte leukemia	ORPHANET:86872	-	-
Chronic lymphoproliferative disorder of NK cells	ORPHANET:512017	-	-
Breast implant-associated anaplastic large cell lymphoma	ORPHANET:667662	-	-

HPO ID	Phenotype
HP:0000006	Autosomal dominant inheritance
HP:0002719	Recurrent infections
HP:0002726	Recurrent Staphylococcus aureus infections
HP:0002728	Chronic mucocutaneous candidiasis
HP:0001880	Increased total eosinophil count
HP:0000964	Eczematoid dermatitis
HP:0000988	Skin rash
HP:0001508	Failure to thrive
HP:0000280	Coarse facial features
HP:0002757	Recurrent fractures
HP:0000939	Osteoporosis
HP:0002110	Bronchiectasis
HP:0002205	Recurrent respiratory infections
HP:0001873	Thrombocytopenia
HP:0001890	Autoimmune hemolytic anemia
HP:0001904	Autoimmune neutropenia
HP:0001973	Autoimmune thrombocytopenia
HP:0002014	Diarrhea
HP:0001263	Global developmental delay
HP:0001945	Fever
HP:0002716	Lymphadenopathy
HP:0001433	Hepatosplenomegaly
HP:0000857	Neonatal insulin-dependent diabetes mellitus
HP:0000821	Hypothyroidism
HP:0001627	Abnormal heart morphology
HP:0001738	Exocrine pancreatic insufficiency
HP:0002608	Celiac disease
HP:0002665	Lymphoma
HP:0001903	Anemia
HP:0002754	Osteomyelitis