Provide a comprehensive cross-database identifier and functional mapping reference for human TGFB1. 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 TGFB1. 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

Section 1: Gene Identifiers
DatabaseIdentifierNotes HGNC IDHGNC:11766Approved HGNC SymbolTGFB1Approved symbol Full NameTransforming growth factor beta 1 Ensembl GeneENSG00000105329 NCBI Entrez Gene7040 OMIM190180Gene/locus Locus Typeprotein-coding gene Genomic Location AttributeValue Chromosome19 Cytogenetic Band19q13.2 Start Position41,301,587 End Position41,353,961 StrandNegative (-) Genome AssemblyGRCh38 Genomic AccessionNC_000019.10 Gene Aliases & Previous Symbols Current Aliases: CED, …

Transcript ID	Biotype	Start	End	Strand
ENST00000221930	protein_coding	41,330,323	41,353,922	-
ENST00000597453	retained_intron	41,342,021	41,348,341	-
ENST00000598758	protein_coding_CDS_not_defined	41,301,587	41,342,030	-
ENST00000600196	protein_coding	41,330,915	41,353,044	-
ENST00000677934	protein_coding	41,330,915	41,353,044	-
ENST00000890114	protein_coding	41,329,729	41,353,961	-
ENST00000966383	protein_coding	41,330,909	41,353,922	-
ENST00000966384	protein_coding	41,330,916	41,353,674	-

Accession	Type	Status	MANE Select
NP_000651	protein	REVIEWED	✓ Yes
XP_011525544	predicted_protein	PREDICTED	No
XP_054177872	predicted_protein	PREDICTED	No

Exon ID	Start	End	Strand	Chromosome
ENSE00001136703	41,352,690	41,353,922	-	19
ENSE00000708416	41,348,295	41,348,455	-	19
ENSE00003463661	41,344,747	41,344,864	-	19
ENSE00003650791	41,342,170	41,342,247	-	19
ENSE00000842441	41,341,883	41,342,030	-	19
ENSE00000708412	41,332,128	41,332,281	-	19
ENSE00001196164	41,330,323	41,331,210	-	19

Property	Value
Length	390 amino acids
Molecular Mass	44,325 Da

ID	Name	Type
IPR001111	TGF-b_propeptide	Domain
IPR001839	TGF-b_C	Domain
IPR003939	TGFb1	Family
IPR015615	TGF-beta-like	Family
IPR016319	TGF-beta	Family
IPR017948	TGFb_CS	Conserved_site
IPR029034	Cystine-knot_cytokine	Homologous_superfamily

TGFB1 Gene Complete Identifier and Functional Mapping Reference

Structured Data Sources

Database	Identifier	Notes
HGNC ID	HGNC:11766	Approved
HGNC Symbol	TGFB1	Approved symbol
Full Name	Transforming growth factor beta 1
Ensembl Gene	ENSG00000105329
NCBI Entrez Gene	7040
OMIM	190180	Gene/locus
Locus Type	protein-coding gene

Attribute	Value
Chromosome	19
Cytogenetic Band	19q13.2
Start Position	41,301,587
End Position	41,353,961
Strand	Negative (-)
Genome Assembly	GRCh38
Genomic Accession	NC_000019.10

Accession	Type	Status	MANE Select
NM_000660	mRNA	REVIEWED	✓ Yes (Canonical)
XM_011527242	mRNA	PREDICTED	No
XM_054321897	mRNA	PREDICTED	No

Accession	Type
NP_000651	Reviewed (MANE Select)
XP_011525544	Predicted
XP_054177872	Predicted

PDB ID	Method	Resolution (Å)	Title
1KLA	SOLUTION NMR	-	Solution structure of TGF-B1, models 1-17
1KLC	SOLUTION NMR	-	Solution structure of TGF-B1, minimized average
1KLD	SOLUTION NMR	-	Solution structure of TGF-B1, models 18-33
3KFD	X-RAY DIFFRACTION	2.995	Ternary complex of TGF-b1, isoform-specific recognition
4KV5	X-RAY DIFFRACTION	3.0	scFv GC1009 in complex with TGF-beta1
5FFO	X-RAY DIFFRACTION	3.49	Integrin alpha V beta 6 with pro-TGF-beta
5VQP	X-RAY DIFFRACTION	2.9	Crystal structure of human pro-TGF-beta1
6GFF	X-RAY DIFFRACTION	3.1	GARP (LRRC32) with latent TGF-beta1 and MHG-8 Fab
6OM2	X-RAY DIFFRACTION	2.77	Integrin alphaV beta8 with proTGF-beta1 ligand peptide
6P7J	X-RAY DIFFRACTION	3.501	Latency Associated Peptide unbound to TGF-beta1
7Y1R	ELECTRON MICROSCOPY	4.01	Human L-TGF-beta1 with anchor protein LRRC33
7Y1T	ELECTRON MICROSCOPY	3.24	Integrin alphaV/beta8 and L-TGF-beta1 at 1:2 ratio
8C7H	ELECTRON MICROSCOPY	2.7	latTGF-beta LHG-10 Fab complex
8REW	ELECTRON MICROSCOPY	2.98	GARP-lTGFbeta1 with activating antibody Fab
8UDZ	X-RAY DIFFRACTION	2.21	LTBP-49247 Fab with TGFbeta1 Small Latent Complex
8VSC	ELECTRON MICROSCOPY	3.0	L-TGF-b1/GARP
8VSD	ELECTRON MICROSCOPY	3.2	avb8/L-TGF-b1/GARP
9FDY	ELECTRON MICROSCOPY	3.4	Betaglycan Orphan Domain with TGF-b1 and TGFBRII
9FKP	ELECTRON MICROSCOPY	3.72	Zebrafish Betaglycan with TGF-b1 and TGFBRII
9VJJ	X-RAY DIFFRACTION	2.477	Human Latent TGF-beta1 with SOF10

Species	Gene ID	Symbol	Biotype
Mouse (Mus musculus)	ENSMUSG00000002603	Tgfb1	protein_coding
Rat (Rattus norvegicus)	ENSRNOG00000020652	Tgfb1	protein_coding
Zebrafish (Danio rerio)	ENSDARG00000034895	tgfb1b	protein_coding
Zebrafish (Danio rerio)	ENSDARG00000041502	tgfb1a	protein_coding
Fruit fly (Drosophila melanogaster)	No direct ortholog	-	-
Worm (C. elegans)	No direct ortholog	-	-
Yeast (S. cerevisiae)	No data available	-	-

Classification	Count (Approx)
Pathogenic	~5
Likely Pathogenic	~2
Pathogenic/Likely Pathogenic	~3
Uncertain Significance (VUS)	~150
Likely Benign	~150
Benign	~50
Benign/Likely Benign	~10
Conflicting	~5

ClinVar ID	HGVS Notation	Classification	Associated Condition
12528	c.673T>C (p.Cys225Arg)	Pathogenic	Camurati-Engelmann disease
12529	c.653G>A (p.Arg218His)	Pathogenic/Likely pathogenic	Camurati-Engelmann disease
12531	c.652C>T (p.Arg218Cys)	Pathogenic	Camurati-Engelmann disease
12533	c.667T>C (p.Cys223Arg)	Pathogenic	Camurati-Engelmann disease

Variant	Gene	Effect	Delta Score
19:41301667:G:T	TGFB1	donor_gain	1.00
19:41302643:T:A	TGFB1	acceptor_gain	1.00
19:41302649:A:AG	TGFB1	acceptor_gain	1.00
19:41301705:G:T	TGFB1	donor_loss	1.00
19:41301706:T:A	TGFB1	donor_loss	1.00
19:41301662:G:GT	TGFB1	donor_gain	0.99
19:41301671:G:GT	TGFB1	donor_gain	0.99
19:41302650:C:G	TGFB1	acceptor_gain	0.99
19:41302660:CCTA:C	TGFB1	acceptor_loss	0.99
19:41302662:TAGCC:T	TGFB1	acceptor_loss	0.99
19:41302663:A:AC	TGFB1	acceptor_loss	0.99
19:41302663:A:AG	TGFB1	acceptor_gain	0.99
19:41302664:G:GC	TGFB1	acceptor_gain	0.99
19:41302664:G:GT	TGFB1	acceptor_loss	0.99
19:41302664:GC:G	TGFB1	acceptor_gain	0.99
19:41302664:GCC:G	TGFB1	acceptor_gain	0.99
19:41302664:GCCA:G	TGFB1	acceptor_gain	0.99
19:41302766:G:GT	TGFB1	donor_gain	0.99
19:41301700:GAAAG:G	TGFB1	donor_gain	0.99
19:41302644:G:A	TGFB1	acceptor_gain	1.00
19:41302645:G:A	TGFB1	acceptor_gain	0.98
19:41302643:T:TA	TGFB1	acceptor_loss	0.98
19:41302664:GCCAA:G	TGFB1	acceptor_gain	0.98
19:41301667:G:GT	TGFB1	donor_gain	0.98
19:41301705:G:GG	TGFB1	donor_gain	0.98
19:41301619:T:A	TGFB1	acceptor_gain	0.89
19:41301619:TGACG:T	TGFB1	acceptor_gain	0.97
19:41301663:A:T	TGFB1	donor_gain	0.90
19:41302667:A:AG	TGFB1	acceptor_gain	0.93
19:41302664:G:T	TGFB1	acceptor_gain	0.92
19:41302659:TCCTA:T	TGFB1	acceptor_gain	0.90

Variant	Protein Change	AM Pathogenicity	Classification
19:41331058:G:C	C389W	0.999	likely_pathogenic
19:41331059:C:A	C389F	0.999	likely_pathogenic
19:41331059:C:G	C389S	1.000	likely_pathogenic
19:41331059:C:T	C389Y	0.999	likely_pathogenic
19:41331060:A:G	C389R	1.000	likely_pathogenic
19:41331060:A:T	C389S	1.000	likely_pathogenic
19:41331064:G:C	C387W	1.000	likely_pathogenic
19:41331065:C:A	C387F	1.000	likely_pathogenic
19:41331065:C:G	C387S	1.000	likely_pathogenic
19:41331065:C:T	C387Y	1.000	likely_pathogenic
19:41331066:A:G	C387R	0.999	likely_pathogenic
19:41331066:A:T	C387S	1.000	likely_pathogenic
19:41331079:C:A	M382I	0.999	likely_pathogenic
19:41331079:C:G	M382I	0.999	likely_pathogenic
19:41331079:C:T	M382I	0.999	likely_pathogenic
19:41331080:A:C	M382R	0.999	likely_pathogenic
19:41331080:A:G	M382T	0.998	likely_pathogenic
19:41331080:A:T	M382K	0.999	likely_pathogenic
19:41331055:G:C	S390R	0.996	likely_pathogenic
19:41331055:G:T	S390R	0.996	likely_pathogenic
19:41331056:C:A	S390I	0.975	likely_pathogenic
19:41331056:C:T	S390N	0.948	likely_pathogenic
19:41331057:T:A	S390C	0.943	likely_pathogenic
19:41331057:T:G	S390R	0.996	likely_pathogenic
19:41331060:A:C	C389G	0.992	likely_pathogenic
19:41331066:A:C	C387G	0.995	likely_pathogenic
19:41331069:A:G	S386P	0.995	likely_pathogenic
19:41331082:G:C	N381K	0.983	likely_pathogenic
19:41331082:G:T	N381K	0.983	likely_pathogenic
19:41331083:T:A	N381I	0.996	likely_pathogenic
19:41331074:A:C	V384G	0.982	likely_pathogenic
19:41331074:A:G	V384A	0.974	likely_pathogenic
19:41331074:A:T	V384E	0.997	likely_pathogenic
19:41331075:C:A	V384L	0.988	likely_pathogenic
19:41331075:C:G	V384L	0.988	likely_pathogenic
19:41331075:C:T	V384M	0.997	likely_pathogenic
19:41331086:G:A	S380F	0.989	likely_pathogenic
19:41331086:G:C	S380C	0.977	likely_pathogenic
19:41331086:G:T	S380Y	0.971	likely_pathogenic
19:41331089:A:C	L379R	0.997	likely_pathogenic
19:41331089:A:G	L379P	1.000	likely_pathogenic
19:41331089:A:T	L379Q	0.999	likely_pathogenic
19:41331094:C:A	E377D	0.924	likely_pathogenic
19:41331096:C:T	E377K	0.980	likely_pathogenic
19:41331071:C:G	R385P	0.953	likely_pathogenic
19:41331081:T:A	M382L	0.944	likely_pathogenic
19:41331081:T:C	M382V	0.979	likely_pathogenic
19:41331061:C:A	K388N	0.968	likely_pathogenic
19:41331062:T:A	K388M	0.913	likely_pathogenic
19:41331063:T:C	K388E	0.936	likely_pathogenic

Pathway ID	Name	Disease Pathway
R-HSA-114608	Platelet degranulation	No
R-HSA-168277	Influenza Virus Induced Apoptosis	Yes
R-HSA-202733	Cell surface interactions at the vascular wall	No
R-HSA-2129379	Molecules associated with elastic fibres	No
R-HSA-2173788	Downregulation of TGF-beta receptor signaling	No
R-HSA-2173789	TGF-beta receptor signaling activates SMADs	No
R-HSA-2173791	TGF-beta receptor signaling in EMT	No
R-HSA-3000170	Syndecan interactions	No
R-HSA-3000178	ECM proteoglycans	No
R-HSA-3304356	SMAD2/3 Phosphorylation Motif Mutants in Cancer	Yes
R-HSA-3642279	TGFBR2 MSI Frameshift Mutants in Cancer	Yes
R-HSA-3645790	TGFBR2 Kinase Domain Mutants in Cancer	Yes
R-HSA-3656532	TGFBR1 KD Mutants in Cancer	Yes
R-HSA-3656535	TGFBR1 LBD Mutants in Cancer	Yes
R-HSA-381340	Transcriptional regulation of white adipocyte differentiation	No
R-HSA-5689603	UCH proteinases	No
R-HSA-6785807	Interleukin-4 and Interleukin-13 signaling	No
R-HSA-8941855	RUNX3 regulates CDKN1A transcription	No
R-HSA-8941858	Regulation of RUNX3 expression and activity	No
R-HSA-8951936	RUNX3 regulates p14-ARF	No
R-HSA-9839389	TGFBR3 regulates TGF-beta signaling	No

GO ID	Term Name
GO:0007179	transforming growth factor beta receptor signaling pathway
GO:0001837	epithelial to mesenchymal transition
GO:0008285	negative regulation of cell population proliferation
GO:0008284	positive regulation of cell population proliferation
GO:0030335	positive regulation of cell migration
GO:0010628	positive regulation of gene expression
GO:0010629	negative regulation of gene expression
GO:0042130	negative regulation of T cell proliferation
GO:0045591	positive regulation of regulatory T cell differentiation
GO:0045944	positive regulation of transcription by RNA polymerase II
GO:0032967	positive regulation of collagen biosynthetic process
GO:0001570	vasculogenesis
GO:0002040	sprouting angiogenesis
GO:0030316	osteoclast differentiation
GO:0048661	positive regulation of smooth muscle cell proliferation
GO:0036446	myofibroblast differentiation
GO:0050729	positive regulation of inflammatory response
GO:0060391	positive regulation of SMAD protein signal transduction
GO:0071560	cellular response to transforming growth factor beta stimulus
GO:0045066	regulatory T cell differentiation

GO ID	Term Name
GO:0005125	cytokine activity
GO:0008083	growth factor activity
GO:0005114	type II transforming growth factor beta receptor binding
GO:0034713	type I transforming growth factor beta receptor binding
GO:0034714	type III transforming growth factor beta receptor binding
GO:0042802	identical protein binding
GO:0019899	enzyme binding
GO:0043539	protein serine/threonine kinase activator activity
GO:0044877	protein-containing complex binding

GO ID	Term Name
GO:0005576	extracellular region
GO:0005615	extracellular space
GO:0031012	extracellular matrix
GO:0031093	platelet alpha granule lumen
GO:0005886	plasma membrane
GO:0009986	cell surface
GO:0005634	nucleus
GO:0005737	cytoplasm
GO:0005796	Golgi lumen
GO:0030424	axon
GO:0043025	neuronal cell body
GO:0072562	blood microparticle

UniProt ID	Gene	Score	Description
P36897	TGFBR1	999	TGF-beta receptor type I
P37173	TGFBR2	999	TGF-beta receptor type II
P17813	ENG	997	Endoglin
P22064	LTBP1	996	Latent TGF-beta binding protein 1
P07585	DCN	993	Decorin
Q03167	TGFBR3	992	TGF-beta receptor type III
Q8N2S1	LTBP4	990	Latent TGF-beta binding protein 4
O15105	SMAD7	978	SMAD family member 7
P84022	SMAD3	978	SMAD family member 3
P01343	GDF3	976	Growth differentiation factor 3
Q9NS15	LTBP3	975	Latent TGF-beta binding protein 3
P00533	EGFR	973	Epidermal growth factor receptor
P07996	TSP1	973	Thrombospondin 1
P09038	FGF2	971	Fibroblast growth factor 2
P02751	FN1	969	Fibronectin 1
P29279	CTGF/CCN2	967	Cellular communication network factor 2
Q15796	SMAD2	966	SMAD family member 2
Q14767	LTBP2	954	Latent TGF-beta binding protein 2
O14625	CYR61	947	Cysteine-rich angiogenic inducer 61
O14786	NRP1	944	Neuropilin-1
P13247	SERPINE1	940	Plasminogen activator inhibitor 1
P01375	TNF	936	Tumor necrosis factor
P05231	IL6	932	Interleukin-6
P01584	IL1B	924	Interleukin-1 beta
Q13485	SMAD4	917	SMAD family member 4
Q14392	LTBP1	913	Latent TGF-beta binding protein 1
P01023	A2M	910	Alpha-2-macroglobulin
P01133	EGF	904	Epidermal growth factor
P22301	IL10	891	Interleukin-10
P01579	IFNG	887	Interferon gamma
P10600	TGFB3	885	Transforming growth factor beta 3
P37023	ACVRL1	884	Activin receptor-like kinase 1
Q6YHK3	CD109	884	CD109 antigen
P35555	FBN1	877	Fibrillin 1
P14780	MMP9	873	Matrix metallopeptidase 9
P14210	HGF	871	Hepatocyte growth factor
P01730	CD4	866	CD4 antigen
Q9BZS1	FOXP3	855	Forkhead box P3
P05112	IL4	850	Interleukin-4
P08253	MMP2	850	Matrix metallopeptidase 2
P31749	AKT1	846	AKT serine/threonine kinase 1
P21781	FGF7	845	Fibroblast growth factor 7
Q16552	IL17A	845	Interleukin-17A
P13500	CCL2	844	C-C motif chemokine ligand 2
P15502	ELN	840	Elastin
O43541	SMAD6	837	SMAD family member 6
Q9BXN1	ASPORIN	830	Asporin
O76093	FGF18	825	Fibroblast growth factor 18
O15520	FGF10	824	Fibroblast growth factor 10
P10767	FGF6	824	Fibroblast growth factor 6

Partner Gene	Interaction Type	Confidence Score
LRRC32 (GARP)	physical association	0.850
LTBP1	direct interaction	0.640
TGFB1 (homodimer)	direct interaction	0.520
ITGAV	physical association	0.490
MEOX2	physical association	0.560
PSG1	direct interaction	0.560
ENG	direct interaction	0.440
TGFBR3	direct interaction	0.440
TGFBR1	direct interaction	0.440
Fstl1	direct interaction	0.440
LTBP4	physical association	0.520
COL5A1	physical association	0.370
LAMB1	physical association	-

UniProt ID	Top Similarity	Average Similarity
P18331	1.000	0.982
P61811	1.000	0.964
P61812	1.000	0.964
Q04998	1.000	0.982
P17125	0.999	0.986
P17246	0.999	0.983
P04202	0.999	0.983
P18341	0.999	0.983
P21214	0.999	0.966
P50414	0.999	0.983
P43032	0.999	0.982
P07995	0.999	0.982
O75610	0.999	0.959
P97299	0.999	0.959
Q863H1	0.999	0.959
Q9ERR7	0.999	0.955
Q68US5	0.999	0.965
Q38L25	0.999	0.964
O00292	0.999	0.959
Q96HF1	0.999	0.959

UniProt ID	Top Identity (%)	Top Bitscore
P61811	100.0	838
P61812	100.0	838
P17125	99.3	840
Q07258	99.3	840
Q38L25	99.3	834
P09858	99.3	832
P18331	99.5	811
P50414	99.5	792
P18341	99.5	792
Q04998	99.5	810
P09533	99.0	791
P01137	99.0	792
P21214	98.8	829
P04202	98.7	798
P17246	98.7	799
P10600	97.8	835
Q38HS2	96.9	773
P27090	96.6	810
P07995	96.5	757
P43032	96.5	748

TF Gene	Regulation	Confidence
SP1	Activation	High
STAT3	Activation	High
RELA (NFκB)	Activation	High
JUN	Activation	High
FOS	Activation	High
HIF1A	Activation	High
SMAD2	Activation	High
CEBPB	Activation	High
EGR1	Activation	High
E2F1	Activation	High
KLF6	Activation	High
KLF10	Activation	High
SREBF1	Activation	High
TFE3	Activation	High
TFAP4	Activation	High
ATF2	Activation	High
RXRA	Activation	High
PPARD	Activation	High
PPARG	Activation	High
AR	Activation	High
SMAD3	Repression	High
AHR	Repression	High
PPARA	Repression	High
MYC	Unknown	High
NFKB1	Unknown	High
SMAD4	Unknown	High
KLF4	Unknown	High
PURA	Unknown	High
FOXC1	Unknown	High
GLI2	Unknown	High
GLI3	Unknown	High
ELF3	Activation	High
DLX2	Activation	High
SMAD7	Activation	High
ASCL1	-	High
GATA6	-	High
KLF2	Repression	-
NR3C1	Repression	-
LRP1	Repression	-
BCL11B	Repression	-
FOXC2	Activation	-
FOXO1	Activation	-
FOXP3	Activation	-
LMO2	Activation	-
CREB1	Activation	-
REL	Activation	Low
NFE2L2	Activation	Low
NANOG	Activation	Low
STAT6	Activation	Low
ID1	Activation	Low

Target Gene	Regulation
COL1A1	Activation
COL1A2	Activation
COL2A1	Activation
COL3A1	Activation
COL4A1	Activation
ACTA2	Activation
CCN2 (CTGF)	Activation
ENG	Activation
ELN	Activation
FGFR1	Activation
ITGA2	Activation
CDKN2B (p15)	Activation
ADAMTS4	Activation
ANKH	Activation
BGLAP	Repression
CILP	Activation
ENPP1	Activation
HBA1	Activation
HBB	Activation
IDE	Activation
CCNA2	Repression
CDH1	Repression
CDK4	Repression
DNAH10	Repression
ITGA3	Repression

ChEMBL Target ID	Target Name	Type
CHEMBL1795178	Transforming growth factor beta-1 proprotein	SINGLE PROTEIN
CHEMBL3988637	Transforming growth factor beta	PROTEIN FAMILY
CHEMBL4296077	TGF-beta1/SMAD3	PROTEIN-PROTEIN INTERACTION

ChEMBL ID	Name	Type	Highest Dev. Phase
CHEMBL3260567	VACTOSERTIB	Small molecule	Phase 2
CHEMBL4448117	-	Unknown	0
CHEMBL5078185	-	Unknown	0
CHEMBL5272606	-	-	0
CHEMBL5280211	-	-	0

Property	Value
Expression Breadth	Ubiquitous
Total Present Calls	204
Max Expression Score	99.08

Rank	Tissue	Expression Score	Call Quality
1	Granulocyte	99.08	Gold
2	Monocyte	98.51	Gold
3	Leukocyte	98.47	Gold
4	Mononuclear cell	98.43	Gold
5	Stromal cell of endometrium	98.27	Gold
6	Ascending aorta	96.77	Gold
7	Thoracic aorta	96.75	Gold
8	Descending thoracic aorta	96.68	Gold
9	Right coronary artery	96.46	Gold
10	Spleen	96.43	Gold
11	Lower esophagus mucosa	96.32	Gold
12	Right lung	95.95	Gold
13	Endocervix	95.60	Gold
14	Blood	95.46	Gold
15	Aorta	95.39	Gold
16	Upper lobe of left lung	95.20	Gold
17	Left coronary artery	95.04	Gold
18	Bone marrow cell	94.85	Gold
19	Ectocervix	94.61	Gold
20	Coronary artery	94.59	Gold
21	Upper lobe of lung	94.55	Gold
22	Popliteal artery	94.50	Gold
23	Tibial artery	94.50	Gold
24	Mucosa of stomach	93.90	Gold
25	Body of uterus	93.65	Gold
26	Lymph node	93.14	Gold
27	Omental fat pad	92.73	Gold
28	Peritoneum	92.67	Gold
29	Metanephros cortex	92.50	Gold
30	Left uterine tube	92.39	Gold

Experiment ID	Description	Species	Cell Count
E-ANND-5	Mapping the developing human immune system across organs	H. sapiens	911,873
E-GEOD-139324	Immune landscape of viral- and carcinogen-derived head and neck cancer	H. sapiens	204,315
E-GEOD-135922	Single-cell transcriptomics of human retinal pigment epithelium and choroid	H. sapiens	55,571
E-MTAB-8205	Single-cell RNA-seq of hPSC-derived endothelial-to-haematopoietic transition	H. sapiens	25,764
E-MTAB-8911	mTOR mutation in T-lymphocytes associated with chronic GVHD	H. sapiens	19,075
E-MTAB-11011	Single Cell Analysis of B cells in COVID-19	H. sapiens	15,100
E-GEOD-106540	Precursors of CD4+ cytotoxic T lymphocytes	H. sapiens	2,244
E-GEOD-75367	Circulating breast cancer cells	H. sapiens	74

Disease	OMIM/Orphanet ID	Inheritance	Classification	Submitter
Camurati-Engelmann disease	OMIM:131300	Autosomal dominant	Definitive	Ambry Genetics, G2P
Camurati-Engelmann disease	OMIM:131300	Autosomal dominant	Strong	Genomics England PanelApp, Labcorp, PanelApp Australia
Camurati-Engelmann disease	ORPHANET:1328	Autosomal dominant	Supportive	Orphanet
Inflammatory bowel disease, immunodeficiency, and encephalopathy	OMIM:618213	Autosomal recessive	Strong	Labcorp Genetics
Inflammatory bowel disease, immunodeficiency, and encephalopathy	OMIM:618213	Autosomal recessive	Moderate	PanelApp Australia
Inflammatory bowel disease, immunodeficiency, and encephalopathy	OMIM:618213	Autosomal recessive	Limited	Ambry Genetics
Inflammatory bowel disease, immunodeficiency, and encephalopathy	ORPHANET:565788	Autosomal recessive	Supportive	Orphanet
Cystic fibrosis (modifier)	ORPHANET:586	Autosomal recessive	Supportive	Orphanet

Orphanet ID	Disease Name	Type	Gene Count	Phenotype Count
1328	Camurati-Engelmann disease	Malformation syndrome	1	54
565788	Infantile inflammatory bowel disease with neurological involvement	Disease	1	0
586	Cystic fibrosis	Disease	19	35

HPO ID	Phenotype Term
HP:0000006	Autosomal dominant inheritance
HP:0000007	Autosomal recessive inheritance
HP:0002653	Bone pain
HP:0003034	Diaphyseal sclerosis
HP:0000940	Abnormal diaphysis morphology
HP:0002652	Skeletal dysplasia
HP:0001324	Muscle weakness
HP:0003388	Easy fatigability
HP:0002515	Waddling gait
HP:0001763	Pes planus
HP:0002808	Kyphosis
HP:0002650	Scoliosis
HP:0003307	Hyperlordosis
HP:0002857	Genu valgum
HP:0002673	Coxa valga
HP:0002694	Sclerosis of skull base
HP:0000929	Abnormal skull morphology
HP:0002007	Frontal bossing
HP:0000303	Mandibular prognathia
HP:0000520	Proptosis
HP:0000648	Optic atrophy
HP:0000651	Diplopia
HP:0001293	Cranial nerve compression
HP:0000365	Hearing impairment
HP:0001298	Encephalopathy
HP:0001263	Global developmental delay
HP:0002059	Cerebral atrophy
HP:0002079	Hypoplasia of the corpus callosum
HP:0002188	Delayed CNS myelination
HP:0001251	Ataxia
HP:0001257	Spasticity
HP:0002014	Diarrhea
HP:0002024	Malabsorption
HP:0002110	Bronchiectasis
HP:0002205	Recurrent respiratory infections
HP:0001639	Hypertrophic cardiomyopathy
HP:0001508	Failure to thrive
HP:0001533	Slender build
HP:0001903	Anemia
HP:0001882	Decreased total leukocyte count
HP:0001974	Increased total leukocyte count
HP:0003212	Increased circulating IgE concentration
HP:0003237	Increased circulating IgG concentration
HP:0002910	Elevated hepatic transaminases
HP:0001392	Abnormality of the liver
HP:0001394	Cirrhosis
HP:0001733	Pancreatitis
HP:0001738	Exocrine pancreatic insufficiency
HP:0000716	Depression
HP:0000739	Anxiety

Study ID	Trait/Disease	Mapped Gene	P-value
GCST010866_163	Coronary artery disease	TGFB1	1×10⁻²⁶
GCST005195_133	Coronary artery disease	TGFB1	2×10⁻¹⁷
GCST005194_75	Coronary artery disease	TGFB1	4×10⁻¹⁷
GCST005196_249	Coronary artery disease	TGFB1	4×10⁻¹⁶
GCST005196_248	Coronary artery disease	TGFB1	7×10⁻¹⁵
GCST90013664_34	Aspartate aminotransferase levels	CCDC97, TGFB1	2×10⁻²⁵
GCST008613_2	Hematuria	CCDC97, TGFB1	1×10⁻¹¹
GCST90002402_208	Platelet count	CCDC97, TGFB1	2×10⁻¹¹
GCST007269_321	Pulse pressure	TGFB1	8×10⁻¹¹
GCST008617_4	Hematuria (moderate to severe)	CCDC97, TGFB1	2×10⁻⁹
GCST90013663_33	Alanine aminotransferase levels	CCDC97, TGFB1	4×10⁻⁹
GCST002454_12	Colorectal cancer	TMEM91	1×10⁻⁸
GCST004787_13	Coronary artery disease (MI, PTCA, CABG, angina, IHD)	TGFB1	4×10⁻⁸
GCST007990_15	Coronary artery disease	TGFB1	2×10⁻⁸
GCST008618_1	Hematuria (mild)	CCDC97, TGFB1	9×10⁻⁸
GCST004898_3	Preterm birth (maternal effect)	TGFB1	5×10⁻⁷
GCST003494_2	Colorectal cancer	TMEM91	4×10⁻⁷
GCST007856_118	Colorectal cancer or advanced adenoma	TMEM91	1×10⁻⁶
GCST008114_4	Type 2 diabetes	TGFB1	1×10⁻⁶

Category	Count
Ensembl Transcripts	8
PDB Structures	20
ClinVar Variants	408
SpliceAI Predictions	2,395
AlphaMissense Predictions	2,513
Reactome Pathways	21
GO Terms	196
STRING Interactions	7,020
IntAct Interactions	232
GWAS Associations	19
HPO Phenotypes	149
Disease Associations	11