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

COMPREHENSIVE CROSS-DATABASE IDENTIFIER AND FUNCTIONAL MAPPING REFERENCE Human EGFR (Epidermal Growth Factor Receptor)
Section 1: Gene Identifiers Primary Gene Identifiers
DatabaseIdentifierNotes HGNCHGNC:3236Approved symbol: EGFR EnsemblENSG00000146648 NCBI Entrez1956 OMIM131550Gene/Locus Gene Names & Aliases Approved Name: Epidermal growth factor receptor Previous Names: Epidermal growth factor receptor (avian erythroblastic leukemia viral (v-erb-b) oncogene homolog) Aliases: ERBB, ERBB1, …

Attribute	Value
Chromosome	7
Cytogenetic Band	7p11.2
Start Position	55,018,820 (GRCh38)
End Position	55,211,628 (GRCh38)
Strand	+ (Plus/Forward)
Genomic Accession	NC_000007.14
Gene Length	~192,808 bp

Transcript ID	Biotype	Start	End	UTR Info
ENST00000275493	protein_coding	55,019,017	55,211,628	CANONICAL
ENST00000342916	protein_coding	55,019,032	55,168,635
ENST00000344576	protein_coding	55,019,017	55,171,037
ENST00000420316	protein_coding	55,019,034	55,156,951
ENST00000450046	protein_coding	55,109,723	55,211,536
ENST00000455089	protein_coding	55,019,021	55,203,076
ENST00000459688	protein_coding_CDS_not_defined	55,019,131	55,046,004
ENST00000463948	protein_coding_CDS_not_defined	55,019,151	55,119,401
ENST00000485503	retained_intron	55,192,811	55,200,802
ENST00000700144	retained_intron	55,019,088	55,157,014
ENST00000700145	protein_coding	55,163,753	55,205,865
ENST00000700146	retained_intron	55,198,272	55,208,067
ENST00000700147	retained_intron	55,200,573	55,206,016
ENST00000898199	protein_coding	55,018,820	55,205,898
ENST00000898200	protein_coding	55,019,017	55,205,911
ENST00000898201	protein_coding	55,019,017	55,205,911
ENST00000898202	protein_coding	55,019,104	55,205,911

Accession	Type	Status	MANE Select
NM_005228	mRNA	REVIEWED	✓ YES
NM_001346897	mRNA	REVIEWED
NM_001346898	mRNA	REVIEWED
NM_001346899	mRNA	REVIEWED
NM_001346900	mRNA	REVIEWED
NM_001346941	mRNA	REVIEWED
NM_201282	mRNA	REVIEWED
NM_201283	mRNA	REVIEWED
NM_201284	mRNA	REVIEWED

Exon ID	Start	End	Length
ENSE00001841347	55,019,017	55,019,365	349 bp
ENSE00003541288	55,142,286	55,142,437	152 bp
ENSE00001704157	55,143,305	55,143,488	184 bp
ENSE00001798125	55,146,606	55,146,740	135 bp
ENSE00001683983	55,151,294	55,151,362	69 bp
ENSE00001652975	55,152,546	55,152,664	119 bp
ENSE00001623732	55,154,011	55,154,152	142 bp
ENSE00001751179	55,155,830	55,155,946	117 bp
ENSE00001084929	55,156,533	55,156,659	127 bp
ENSE00001084931	55,156,759	55,156,832	74 bp
ENSE00001084926	55,157,663	55,157,753	91 bp
ENSE00001084941	55,160,139	55,160,338	200 bp
ENSE00001084939	55,161,499	55,161,631	133 bp
ENSE00001084927	55,163,733	55,163,823	91 bp
ENSE00001627115	55,165,280	55,165,437	158 bp
ENSE00001768076	55,171,175	55,171,213	39 bp
ENSE00002684637	55,172,983	55,173,124	142 bp
ENSE00001778519	55,173,921	55,174,043	123 bp
ENSE00001756460	55,174,722	55,174,820	99 bp
ENSE00001601336	55,181,293	55,181,478	186 bp
ENSE00001681524	55,191,719	55,191,874	156 bp
ENSE00001631695	55,192,766	55,192,841	76 bp
ENSE00003625684	55,198,717	55,198,863	147 bp
ENSE00001790701	55,200,316	55,200,413	98 bp
ENSE00001801208	55,201,188	55,201,355	168 bp
ENSE00001773562	55,201,735	55,201,782	48 bp
ENSE00001795780	55,202,517	55,202,625	109 bp
ENSE00001245887	55,205,256	55,211,628	6,373 bp

Accession	Status	Name
P00533	✓ Reviewed (Swiss-Prot)	Epidermal growth factor receptor
A0A8V8TPW8	Unreviewed
C9JYS6	Unreviewed
Q504U8	Unreviewed

EGFR Gene Complete Identifier and Functional Mapping Reference

Structured Data Sources

Database	Identifier	Notes
HGNC	HGNC:3236	Approved symbol: EGFR
Ensembl	ENSG00000146648
NCBI Entrez	1956
OMIM	131550	Gene/Locus

Property	Value
Length	1,210 amino acids
Mass	134,277 Da
Alternative Names	Proto-oncogene c-ErbB-1; Receptor tyrosine-protein kinase erbB-1

Accession	Status	MANE Select
NP_005219	REVIEWED	✓ YES
NP_001333826	REVIEWED
NP_001333827	REVIEWED
NP_001333828	REVIEWED
NP_001333829	REVIEWED
NP_001333870	REVIEWED
NP_958439	REVIEWED
NP_958440	REVIEWED
NP_958441	REVIEWED

InterPro ID	Name	Type
IPR000494	Rcpt_L-dom	Domain
IPR000719	Prot_kinase_dom	Domain
IPR001245	Ser-Thr/Tyr_kinase_cat_dom	Domain
IPR006211	Furin-like_Cys-rich_dom	Domain
IPR006212	Furin_repeat	Repeat
IPR008266	Tyr_kinase_AS	Active_site
IPR009030	Growth_fac_rcpt_cys_sf	Homologous_superfamily
IPR011009	Kinase-like_dom_sf	Homologous_superfamily
IPR016245	Tyr_kinase_EGF/ERB/XmrK_rcpt	Family
IPR017441	Protein_kinase_ATP_BS	Binding_site
IPR020635	Tyr_kinase_cat_dom	Domain
IPR032778	GF_recep_IV	Domain
IPR036941	Rcpt_L-dom_sf	Homologous_superfamily
IPR049328	TM_ErbB1	Domain
IPR050122	RTK	Family

PDB ID	Method	Resolution	Description
3POZ	X-RAY	1.50 Å	EGFR kinase domain with TAK-285
5CNO	X-RAY	1.55 Å	EGFR kinase domain mutant V924R
3VRP	X-RAY	1.52 Å	Cbl-c TKB with phospho-EGFR peptide
5HG5	X-RAY	1.52 Å	EGFR L858R/T790M/V948R with inhibitor
3G5Y	X-RAY	1.59 Å	Antibodies targeting tumor EGFR
3W33	X-RAY	1.70 Å	EGFR kinase domain with compound 19b
4I22	X-RAY	1.71 Å	EGFR L858R+T790M with gefitinib
3W32	X-RAY	1.80 Å	EGFR kinase domain with compound 20a
3P0Y	X-RAY	1.80 Å	anti-EGFR/HER3 Fab DL11 complex
4I24	X-RAY	1.80 Å	EGFR T790M with dacomitinib
4WKQ	X-RAY	1.85 Å	EGFR kinase domain with gefitinib
5HG7	X-RAY	1.85 Å	EGFR mutant with PF-06459988
5GNK	X-RAY	1.80 Å	EGFR T790M with LXX-6-34
3W2S	X-RAY	1.90 Å	EGFR kinase domain with compound 4
5CNN	X-RAY	1.90 Å	EGFR kinase domain mutant I682Q
4WRG	X-RAY	1.90 Å	EGFR kinase domain structure
4ZSE	X-RAY	1.97 Å	EGFR T790M/V948R crystal form II
2RGP	X-RAY	2.00 Å	EGFR with hydrazone dual inhibitor
3VRR	X-RAY	2.00 Å	Cbl-c PL mutant with phospho-EGFR
3W2P	X-RAY	2.05 Å	EGFR T790M/L858R with compound 2
3W2R	X-RAY	2.05 Å	EGFR T790M/L858R with compound 4
4UV7	X-RAY	2.10 Å	EGFR extracellular domain with GC1118A
3OB2	X-RAY	2.10 Å	c-Cbl TKB with double phosphorylated EGFR
5CAS	X-RAY	2.10 Å	EGFR TMLR with compound 41a
3W2Q	X-RAY	2.20 Å	EGFR T790M/L858R with HKI-272
5CAU	X-RAY	2.25 Å	EGFR TMLR with compound 41b
3PFV	X-RAY	2.27 Å	Cbl-b TKB with EGFR pY1069 peptide
3BEL	X-RAY	2.30 Å	EGFR with oxime inhibitor
5D41	X-RAY	2.31 Å	EGFR with mutant selective allosteric inhibitor
3VJN	X-RAY	2.34 Å	EGFR G719S/T790M with AMPPNP
3W2O	X-RAY	2.35 Å	EGFR T790M/L858R with TAK-285
1XKK	X-RAY	2.40 Å	EGFR kinase with GW572016 (lapatinib)
5CAP	X-RAY	2.40 Å	EGFR TMLR with compound 30
5HCY	X-RAY	2.46 Å	EGFR TMLR with azaindole compound 13
2ITN	X-RAY	2.47 Å	EGFR G719S with AMP-PNP
2ITV	X-RAY	2.47 Å	EGFR L858R with AMP-PNP
3UG2	X-RAY	2.50 Å	EGFR G719S/T790M with gefitinib
4RJ8	X-RAY	2.50 Å	EGFR T790M/L858R with compound 8
4LQM	X-RAY	2.50 Å	EGFR L858R with PD168393
1MOX	X-RAY	2.50 Å	EGFR extracellular domain with TGF-alpha
4CAO	X-RAY	2.60 Å	EGFR TMLR with compound 29
1M14	X-RAY	2.60 Å	Tyrosine Kinase Domain from EGFR
1M17	X-RAY	2.60 Å	EGFR kinase with erlotinib
2GS6	X-RAY	2.60 Å	Active EGFR with ATP analog-peptide
2GS7	X-RAY	2.60 Å	Inactive EGFR with AMP-PNP
3BUO	X-RAY	2.60 Å	c-Cbl-TKB with EGF receptor
5EDR	X-RAY	2.60 Å	EGFR T790M/L858R with compound 27
5HCX	X-RAY	2.60 Å	EGFR TMLR with azabenzimidazole compound 7
1YY9	X-RAY	2.61 Å	EGFR extracellular with cetuximab Fab
5FED	X-RAY	2.65 Å	EGFR with covalent aminobenzimidazole inhibitor

PDB ID	Method	Description
1Z9I	SOLUTION NMR	Juxtamembrane domain model
2KS1	SOLUTION NMR	ErbB1/ErbB2 TM heterodimer
2M0B	SOLUTION NMR	Homodimeric TM domain in micelles
2M20	SOLUTION NMR	TM-JM segment in bicelles
2N5S	SOLUTION NMR	TM and JM domains in DPC micelles

Organism	Gene ID	Symbol	Biotype
Mouse (Mus musculus)	ENSMUSG00000020122	Egfr	protein_coding
Rat (Rattus norvegicus)	ENSRNOG00000004332	Egfr	protein_coding
Zebrafish (Danio rerio)	ENSDARG00000013847	egfra	protein_coding
Zebrafish (Danio rerio)	ENSDARG00000056909	-	protein_coding
Fruit fly (D. melanogaster)	FBGN0003731	Egfr	protein_coding

Organism	Entrez ID	RefSeq mRNA	RefSeq Protein
Mouse	13649	NM_007912, NM_207655	NP_031938, NP_997538
Rat	24329	NM_031507	NP_113695
Drosophila	37455	NM_057410, NM_057411	NP_476758, NP_476759

ClinVar ID	HGVS Notation	Variant Type	Review Status
45225	c.2156G>C (p.Gly719Ala)	SNV	criteria provided
45251	c.2303G>T (p.Ser768Ile)	SNV	criteria provided
45279	c.2500G>T (p.Val834Leu)	SNV	criteria provided
177620	c.2236_2250del (p.Glu746_Ala750del)	Deletion	criteria provided
45220	c.2127_2129del (p.Glu709_Thr710delinsAsp)	Deletion	criteria provided
157499	c.1283G>A (p.Gly428Asp)	SNV	criteria provided
254143	c.977G>T (p.Cys326Phe)	SNV	no criteria
638163	c.2303_2305delinsTCT (p.Ser768_Val769delinsIleLeu)	Indel	criteria provided
1005727	c.1605C>A (p.Cys535Ter)	SNV	criteria provided
1016241	c.2917C>T (p.Arg973Ter)	SNV	criteria provided
1016463	c.1536del (p.Glu513fs)	Deletion	criteria provided
1023925	c.2545C>T (p.Gln849Ter)	SNV	criteria provided
1042058	g.(?55086755)(55274084_?)del	Deletion	criteria provided
1043841	c.2577del (p.Lys860fs)	Deletion	criteria provided
1045120	c.1418del (p.Asn473fs)	Deletion	criteria provided
1058215	c.2650G>T (p.Glu884Ter)	SNV	criteria provided
1425739	c.2921_2928del (p.Asp974fs)	Deletion	criteria provided
1429922	c.877A>T (p.Lys293Ter)	SNV	criteria provided
1441678	c.3061C>T (p.Gln1021Ter)	SNV	criteria provided
1444704	c.2289del (p.Tyr764fs)	Deletion	criteria provided
1453945	c.1860_1861delinsAA (p.Cys620_His621delinsTer)	Indel	criteria provided
1457850	c.113del (p.Leu38fs)	Deletion	criteria provided
1459376	c.763C>T (p.Arg255Ter)	SNV	criteria provided
1508578	c.2720T>A (p.Leu907Ter)	SNV	criteria provided
2032844	c.492_511del (p.Trp164_Asp171delinsTer)	Deletion	criteria provided
2115063	c.977_978del (p.Lys325_Cys326insTer)	Microsatellite	criteria provided
2129131	c.2927del (p.Gln976fs)	Deletion	criteria provided
2578363	c.2317delinsAACCCCT (p.His773delinsAsnProTyr)	Indel	criteria provided
2582257	c.1792G>A (p.Gly598Arg)	SNV	no criteria
2582258	c.2561C>T (p.Thr854Ile)	SNV	no criteria
2582280	c.1786C>T (p.Pro596Ser)	SNV	no criteria
2582281	c.2287G>A (p.Ala763Thr)	SNV	no criteria

Variant	Effect	Delta Score
7:55019361:GAAAG:G	donor_gain	0.99
7:55019362:AAAGG:A	donor_loss	0.99
7:55019363:AAGGT:A	donor_loss	0.99
7:55019364:AGGT:A	donor_loss	0.99
7:55019365:GGTA:G	donor_loss	0.99
7:55019366:G:A	donor_loss	0.99
7:55019367:T:G	donor_loss	0.99
7:55019366:G:GG	donor_gain	0.97
7:55019364:AG:A	donor_gain	0.89
7:55019365:GG:G	donor_gain	0.89
7:55020707:GTT:G	donor_gain	0.85
7:55020708:TTT:T	donor_gain	0.85
7:55019363:AAG:A	donor_gain	0.85
7:55019339:C:T	donor_gain	0.83
7:55019845:G:T	donor_gain	0.71
7:55019362:AAAG:A	donor_gain	0.71

CCDS ID
CCDS5514
CCDS5515
CCDS5516
CCDS47587
CCDS87507
CCDS94105

Pathway ID	Name	Disease Pathway
R-HSA-177929	Signaling by EGFR	No
R-HSA-1227986	Signaling by ERBB2	No
R-HSA-1236394	Signaling by ERBB4	No
R-HSA-182971	EGFR downregulation	No
R-HSA-179812	GRB2 events in EGFR signaling	No
R-HSA-180292	GAB1 signalosome	No
R-HSA-180336	SHC1 events in EGFR signaling	No
R-HSA-212718	EGFR interacts with phospholipase C-gamma	No
R-HSA-1250196	SHC1 events in ERBB2 signaling	No
R-HSA-1251932	PLCG1 events in ERBB2 signaling	No
R-HSA-1257604	PIP3 activates AKT signaling	No
R-HSA-1963640	GRB2 events in ERBB2 signaling	No
R-HSA-1963642	PI3K events in ERBB2 signaling	No
R-HSA-5673001	RAF/MAP kinase cascade	No
R-HSA-6785631	ERBB2 Regulates Cell Motility	No
R-HSA-6811558	PI5P, PP2A and IER3 Regulate PI3K/AKT Signaling	No
R-HSA-8847993	ERBB2 Activates PTK6 Signaling	No
R-HSA-8856825	Cargo recognition for clathrin-mediated endocytosis	No
R-HSA-8856828	Clathrin-mediated endocytosis	No
R-HSA-8857538	PTK6 promotes HIF1A stabilization	No
R-HSA-8863795	Downregulation of ERBB2 signaling	No
R-HSA-9009391	Extra-nuclear estrogen signaling	No
R-HSA-1236382	Constitutive Signaling by Ligand-Responsive EGFR Cancer Variants	Yes
R-HSA-2219530	Constitutive Signaling by Aberrant PI3K in Cancer	Yes
R-HSA-5637810	Constitutive Signaling by EGFRvIII	Yes
R-HSA-5638303	Inhibition of Signaling by Overexpressed EGFR	Yes
R-HSA-9664565	Signaling by ERBB2 KD Mutants	Yes
R-HSA-9665348	Signaling by ERBB2 ECD mutants	Yes
R-HSA-9665686	Signaling by ERBB2 TMD/JMD mutants	Yes
R-HSA-9609690	HCMV Early Events	Yes
R-HSA-9820960	Respiratory syncytial virus (RSV) attachment and entry	Yes

GO ID	Term
GO:0005006	epidermal growth factor receptor activity
GO:0004713	protein tyrosine kinase activity
GO:0004714	transmembrane receptor protein tyrosine kinase activity
GO:0004709	MAP kinase kinase kinase activity
GO:0004888	transmembrane signaling receptor activity
GO:0005524	ATP binding
GO:0048408	epidermal growth factor binding
GO:0001618	virus receptor activity
GO:0003682	chromatin binding
GO:0003690	double-stranded DNA binding
GO:0019899	enzyme binding
GO:0019900	kinase binding
GO:0019903	protein phosphatase binding
GO:0030296	protein tyrosine kinase activator activity
GO:0031625	ubiquitin protein ligase binding
GO:0042802	identical protein binding
GO:0045296	cadherin binding
GO:0051015	actin filament binding
GO:0051117	ATPase binding

GO ID	Term
GO:0007173	epidermal growth factor receptor signaling pathway
GO:0007165	signal transduction
GO:0007166	cell surface receptor signaling pathway
GO:0008284	positive regulation of cell population proliferation
GO:0030307	positive regulation of cell growth
GO:0030335	positive regulation of cell migration
GO:0042327	positive regulation of phosphorylation
GO:0043066	negative regulation of apoptotic process
GO:0043410	positive regulation of MAPK cascade
GO:0045742	positive regulation of EGFR signaling pathway
GO:0070374	positive regulation of ERK1 and ERK2 cascade
GO:0051897	positive regulation of PI3K/AKT signal transduction
GO:0001934	positive regulation of protein phosphorylation
GO:0045944	positive regulation of transcription by RNA polymerase II
GO:0050679	positive regulation of epithelial cell proliferation
GO:0038134	ERBB2-EGFR signaling pathway
GO:0071364	cellular response to epidermal growth factor stimulus

GO ID	Term
GO:0005886	plasma membrane
GO:0009986	cell surface
GO:0005634	nucleus
GO:0005737	cytoplasm
GO:0005829	cytosol
GO:0005768	endosome
GO:0005794	Golgi apparatus
GO:0000139	Golgi membrane
GO:0005789	endoplasmic reticulum membrane
GO:0005925	focal adhesion
GO:0005929	cilium
GO:0010008	endosome membrane
GO:0016020	membrane
GO:0016323	basolateral plasma membrane
GO:0030054	cell junction
GO:0030669	clathrin-coated endocytic vesicle membrane
GO:0031901	early endosome membrane
GO:0032587	ruffle membrane
GO:0043235	receptor complex
GO:0045121	membrane raft

Partner UniProt	Partner Gene	Score
P00533	EGFR (self)	999
P01133	EGF	999
P01135	TGFA	998
Q99075	HBEGF	998
P29354	SRC	997
P98202	ERBB3	997
O14944	EREG (Epiregulin)	996
P15514	AREG (Amphiregulin)	996
P12830	CDH1	995
P16070	CD44	995
P22681	CBL	995
P35070	BTC (Betacellulin)	995
P13931	PLCG1	994
P29353	SHC1	994
P07900	HSP90AA1	993
P08238	HSP90AB1	993
Q6UW88	EPGN	992
Q06124	PTPN11	991
P12931	SRC	988
Q03135	CAV1	987
P07585	DCN	986
P40763	STAT3	986
Q13480	GAB1	986
P21860	ERBB3	984
P04626	ERBB2	983
P08581	MET	979
P18031	PTPN1	978
P42336	PIK3CA	977
Q14956	GPNMB	977
Q15303	ERBB4	977
P03372	ESR1	974
P01137	TGFB1	973
P08069	IGF1R	973
P09619	PDGFRB	971
P17936	IGFBP3	971
Q14451	GRB7	967
O14511	NRG2	959
Q13882	PTK6	948
P14210	HGF	947
P05231	IL6	943
Q07889	SOS1	943
Q9UKV8	AGO2	941
P35222	CTNNB1	940
P48509	NGFR	940
P13866	SLC2A1	938
P42229	STAT5A	933
P01112	HRAS	931
P01308	INS	930
P60484	PIK3R1	926
Q05397	FAK1/PTK2	926

Partner	Interaction Type	Confidence
GRB2	physical association	0.980
EGF	direct interaction	0.970
CBL	physical association	0.960
ERBB2	physical association	0.950
PTPN1	colocalization	0.900
CALM1	physical association	0.830
TGFA	direct interaction	0.780
GAPDH	association	0.790
RUBCN	physical association	0.650
GOLM1	physical association	0.640

UniProt	Top Similarity	Avg Similarity
P21860 (ERBB3)	1.000	0.964
Q5RB22 (Chimpanzee)	1.000	0.964
Q61526 (Mouse Erbb3)	0.999	0.965
Q62799 (Rat Erbb3)	0.999	0.965
P55245	0.999	0.954
P04626 (ERBB2)	0.999	0.952
P06494	0.999	0.960
O18735	0.999	0.954

UniProt	Identity	Bitscore
P00534	100.0%	1210
P00535	99.5%	1211
Q61527 (Mouse Erbb4)	98.8%	2628
Q62956 (Rat Erbb4)	98.8%	2631
P21860 (ERBB3)	98.0%	2625
Q5RB22	98.0%	2627
P48025	97.3%	1268
Q15303 (ERBB4)	97.3%	2605
Q61526 (Mouse Erbb3)	96.7%	2553
Q62799 (Rat Erbb3)	96.7%	2551
O19064	95.3%	2239
P06494	94.9%	2473
P70424	94.9%	2472

TF Gene	Confidence
AP1	High
AR	High
BCL11B	High
BCL3	High
EGR1	High
FOS	High
HOXB7	High
JUN	High
JUNB	High
NFKB1	High
NFKB	High
SOX2	High
STAT3	High
TP53	High
YBX1	High
YY1	High

TF Gene	Confidence
BRCA1	-
EMX2	-
GCFC2	High
GLI1	-
HDAC1	-
KLF10	High
LRRFIP1	High
PML	-
PPARG	High
RARA	-
SP1	High
TP63	High
VDR	High
WT1	High

Target ID	Target Name	Type
CHEMBL203	Epidermal growth factor receptor	SINGLE PROTEIN
CHEMBL2111431	EGFR and ERBB2 (HER1 and HER2)	PROTEIN FAMILY
CHEMBL2363049	Epidermal growth factor receptor	PROTEIN FAMILY

ChEMBL ID	Drug Name	Type	Indication
CHEMBL553	ERLOTINIB	Small molecule	NSCLC, Pancreatic cancer
CHEMBL1079742	ERLOTINIB HYDROCHLORIDE	Small molecule	NSCLC
CHEMBL939	GEFITINIB	Small molecule	NSCLC
CHEMBL1173655	AFATINIB	Small molecule	NSCLC
CHEMBL2105712	AFATINIB DIMALEATE	Small molecule	NSCLC
CHEMBL554	LAPATINIB	Small molecule	HER2+ breast cancer
CHEMBL1201179	LAPATINIB DITOSYLATE	Small molecule	HER2+ breast cancer
CHEMBL3353410	OSIMERTINIB	Small molecule	NSCLC (T790M+)
CHEMBL2105719	DACOMITINIB	Small molecule	NSCLC
CHEMBL2110732	DACOMITINIB ANHYDROUS	Small molecule	NSCLC
CHEMBL180022	NERATINIB	Small molecule	HER2+ breast cancer
CHEMBL4650319	MOBOCERTINIB	Small molecule	NSCLC (EGFR exon 20 insertion)
CHEMBL4558324	LAZERTINIB	Small molecule	NSCLC
CHEMBL3786343	OLMUTINIB	Small molecule	NSCLC
CHEMBL24828	VANDETANIB	Small molecule	Medullary thyroid cancer
CHEMBL3989868	TUCATINIB	Small molecule	HER2+ breast cancer

ChEMBL ID	Drug Name	Type
CHEMBL535	SUNITINIB	Small molecule
CHEMBL1336	SORAFENIB	Small molecule
CHEMBL1171837	PONATINIB	Small molecule
CHEMBL1289926	AXITINIB	Small molecule
CHEMBL2105717	CABOZANTINIB	Small molecule
CHEMBL601719	CRIZOTINIB	Small molecule
CHEMBL941	IMATINIB	Small molecule
CHEMBL1421	DASATINIB	Small molecule
CHEMBL5416410	DASATINIB	Small molecule
CHEMBL288441	BOSUTINIB	Small molecule
CHEMBL1229517	VEMURAFENIB	Small molecule
CHEMBL1738797	ALECTINIB	Small molecule
CHEMBL2403108	CERITINIB	Small molecule
CHEMBL3286830	LORLATINIB	Small molecule
CHEMBL3545311	BRIGATINIB	Small molecule
CHEMBL3301622	GILTERITINIB	Small molecule
CHEMBL608533	MIDOSTAURIN	Small molecule

ChEMBL ID	Drug Name	Type
CHEMBL1873475	IBRUTINIB	Small molecule
CHEMBL3707348	ACALABRUTINIB	Small molecule
CHEMBL3936761	ZANUBRUTINIB	Small molecule
CHEMBL1614701	SELUMETINIB	Small molecule
CHEMBL3301610	ABEMACICLIB	Small molecule
CHEMBL98	VORINOSTAT	Small molecule

Attribute	Value
PharmGKB ID	PA7360
VIP Gene	Yes (Very Important Pharmacogene)
Has Variant Annotations	Yes
Has CPIC Guideline	No

Property	Value
Expression Pattern	Ubiquitous
Total Present Calls	285
Total Absent Calls	13
Total Conditions	298
Max Expression Score	99.12
Average Expression Score	83.64
Gold Quality Count	285

Tissue (UBERON ID)	Score	Quality
Nipple (UBERON:0002030)	99.12	Gold
Gingiva (UBERON:0001828)	98.63	Gold
Gingival epithelium (UBERON:0001949)	98.62	Gold
Placenta (UBERON:0001987)	98.56	Gold
Mammalian vulva (UBERON:0000997)	98.48	Gold
Tongue squamous epithelium (UBERON:0006919)	98.32	Gold
Skin of hip (UBERON:0001554)	98.28	Gold
Superficial temporal artery (UBERON:0001614)	97.94	Gold
Decidua (UBERON:0002450)	97.78	Gold
Penis (UBERON:0000989)	97.65	Gold
Pharyngeal mucosa (UBERON:0000355)	97.63	Gold
Mucosa of paranasal sinus (UBERON:0005030)	97.49	Gold
Urethra (UBERON:0000057)	97.31	Gold
Saphenous vein (UBERON:0007318)	97.30	Gold
Lower lobe of lung (UBERON:0008949)	96.72	Gold
Oral cavity (UBERON:0000167)	96.61	Gold
Sural nerve (UBERON:0015488)	96.43	Gold
Superior surface of tongue (UBERON:0007371)	96.40	Gold
Upper leg skin (UBERON:0004262)	96.33	Gold
Mammary duct (UBERON:0001765)	96.28	Gold
Tongue (UBERON:0001723)	96.21	Gold
Upper arm skin (UBERON:0004263)	96.11	Gold
Hair follicle (UBERON:0002073)	95.77	Gold
Synovial joint (UBERON:0002217)	95.73	Gold
Zone of skin (UBERON:0000014)	95.68	Gold
Body of tongue (UBERON:0011876)	95.67	Gold
Cauda epididymis (UBERON:0004360)	95.66	Gold
Cervix epithelium (UBERON:0004801)	95.56	Gold
Skin of leg (UBERON:0001511)	95.49	Gold
Skin of abdomen (UBERON:0001416)	95.43	Gold

Dataset ID	Description	Species	Cell Count
E-ANND-2	GTEx: snRNAseq atlas	Homo sapiens	209,126
E-MTAB-6701	Human first trimester fetal-maternal interface (10x)	Homo sapiens	135,071
E-CURD-114	Human airway epithelium smoking effects	Homo sapiens	81,801
E-MTAB-11268	Human hypertrophied heart atlas	Homo sapiens	64,898
E-MTAB-9435	IDHwt glioblastoma tumors	Homo sapiens	62,867
E-HCAD-24	Human first-trimester placenta and decidua	Homo sapiens	24,780
E-MTAB-8559	Ovarian cancer ex vivo models	Homo sapiens	20,982
E-GEOD-84465	Glioblastoma migrating front cells	Homo sapiens	3,588
E-MTAB-10596	Human dental follicle organoids	Homo sapiens	3,388
E-MTAB-10137	Human dermal blood vascular endothelium	Homo sapiens	1,523
E-ENAD-27	Human islet cells in type 2 diabetes	Homo sapiens	1,145

Disease	OMIM/MONDO	Inheritance	Classification	Submitter
Lung cancer	OMIM:211980	Autosomal dominant	Definitive	Ambry Genetics, G2P
Inflammatory skin and bowel disease, neonatal, 2 (NISBD2)	OMIM:616069	Autosomal recessive	Strong/Moderate	Labcorp, Ambry, G2P
Neonatal inflammatory skin and bowel disease	ORPHANET:294023	Autosomal recessive	Supportive	Orphanet

Orphanet ID	Disease Name	Type
251576	Gliosarcoma	Histopathological subtype
251579	Giant cell glioblastoma	Histopathological subtype

HPO ID	Phenotype
HP:0000006	Autosomal dominant inheritance
HP:0000007	Autosomal recessive inheritance
HP:0030358	Non-small cell lung carcinoma
HP:0030078	Lung adenocarcinoma
HP:0006519	Alveolar cell carcinoma
HP:0000527	Long eyelashes
HP:0000822	Hypertension
HP:0001442	Typified by somatic mosaicism
HP:0001508	Failure to thrive
HP:0001561	Polyhydramnios
HP:0001680	Coarctation of aorta
HP:0001944	Dehydration
HP:0002013	Vomiting
HP:0003212	Increased circulating IgE concentration
HP:0003577	Congenital onset
HP:0005208	Secretory diarrhea
HP:0006532	Recurrent pneumonia
HP:0025092	Epidermal acanthosis
HP:0100501	Recurrent bronchiolitis
HP:0200034	Papule
HP:0200039	Pustule

Study	Trait	P-value
GCST004349_12	Glioblastoma	5×10⁻³⁴
GCST004347_14	Glioma	4×10⁻²⁷
GCST004349_6	Glioblastoma	5×10⁻²³
GCST90002400_91	Plateletcrit	6×10⁻¹⁸
GCST90002401_81	Platelet distribution width	1×10⁻¹⁷
GCST006480_2	Glioblastoma (age-stratified)	4×10⁻¹⁶
GCST005932_8	Glioblastoma	3×10⁻¹⁶
GCST90014033_78	Haemorrhoidal disease	3×10⁻¹³
GCST005932_10	Glioblastoma	1×10⁻¹²
GCST90002402_65	Platelet count	1×10⁻¹²
GCST006480_15	Glioblastoma (age-stratified)	2×10⁻¹²
GCST005931_12	Glioma	7×10⁻¹²
GCST005931_14	Glioma	5×10⁻¹²
GCST005932_9	Glioblastoma	1×10⁻¹¹
GCST006480_3	Glioblastoma (age-stratified)	2×10⁻¹¹
GCST006480_9	Glioblastoma (age-stratified)	7×10⁻¹²
GCST006480_4	Glioblastoma (age-stratified)	2×10⁻¹⁰
GCST005931_13	Glioma	2×10⁻⁹
GCST90002391_152	Mean corpuscular hemoglobin concentration	2×10⁻⁹
GCST006480_16	Glioblastoma (age-stratified)	2×10⁻⁹
GCST90002393_38	Monocyte count	4×10⁻⁹
GCST009391_2084	Metabolite levels	4×10⁻⁹
GCST90002397_16	Mean spheric corpuscular volume	3×10⁻⁹
GCST004348_9	Non-glioblastoma glioma	2×10⁻⁸
GCST001058_7	Glioma	8×10⁻⁸
GCST001058_1	Glioma	7×10⁻⁸
GCST006480_17	Glioblastoma (age-stratified)	6×10⁻⁸

Category	Count
Ensembl Transcripts	17
RefSeq mRNA Transcripts	9+
CCDS IDs	6
Exons (canonical)	28
UniProt Entries	4
Protein Length	1,210 aa
InterPro Domains	15
PDB Structures	378
ClinVar Variants	3,790
Pathogenic Variants	63
AlphaMissense Predictions	8,041
SpliceAI Predictions	4,358
Reactome Pathways	37
GO Terms	104+
STRING Interactions	11,600+
IntAct Interactions	1,747
FDA-Approved Targeting Drugs	70
GWAS Associations	35
Single-Cell Datasets	11
Orthologs (key species)	5