Provide a comprehensive cross-database identifier and functional mapping reference for human ESR1. 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 ESR1. 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 Primary Gene Identifiers
DatabaseIdentifierDescription HGNCHGNC:3467Approved symbol: ESR1 EnsemblENSG00000091831Ensembl gene ID NCBI Entrez2099Entrez Gene ID OMIM133430Gene/locus MIM number Gene Information AttributeValue Approved NameEstrogen receptor 1 Locus TypeGene with protein product Locus GroupProtein-coding gene StatusApproved Gene GroupEstrogen receptors Previous SymbolsESR AliasesER, NR3A1, Era, ER-alpha, ESRA, ESTRR Genomic Location AttributeValue …

Attribute	Value
Chromosome	6
Cytogenetic Band	6q25.1-q25.2
Start Position	151,651,284 (GRCh38)
End Position	152,129,619 (GRCh38)
Strand	+ (plus/forward)
Genome Assembly	GRCh38/hg38
Gene Span	~478 kb

Transcript ID	Biotype	Start	End	Strand
ENST00000206249	protein_coding	151,807,682	152,103,274	+
ENST00000338799	protein_coding	151,804,431	152,099,053	+
ENST00000404742	protein_coding	151,690,496	151,808,166	+
ENST00000406599	protein_coding	151,807,679	152,098,978	+
ENST00000415488	protein_coding	151,880,657	152,061,059	+
ENST00000427531	protein_coding	151,809,107	152,129,619	+
ENST00000440973	protein_coding	151,690,496	152,103,274	+
ENST00000443427	protein_coding	151,807,319	152,103,274	+
ENST00000446550	protein_coding	151,807,196	151,808,259	+
ENST00000456483	protein_coding	151,807,679	152,098,978	+
ENST00000473497	protein_coding_CDS_not_defined	151,656,691	151,807,857	+
ENST00000482101	protein_coding_CDS_not_defined	151,944,172	151,984,165	+
ENST00000488573	protein_coding_CDS_not_defined	151,808,105	151,811,278	+
ENST00000641399	protein_coding_CDS_not_defined	151,936,130	152,118,399	+
ENST00000858333	protein_coding	151,690,530	152,100,579	+
ENST00000858334	protein_coding	151,807,168	152,101,388	+
ENST00000858335	protein_coding	151,807,663	152,099,792	+
ENST00000947759	protein_coding	151,651,284	152,099,200	+

Exon ID	Start	End	Length
ENSE00001877305	151,807,682	151,808,364	683 bp
ENSE00003705805	151,842,597	151,842,787	191 bp
ENSE00003721187	151,880,655	151,880,771	117 bp
ENSE00002178920	151,944,173	151,944,508	336 bp
ENSE00000813753	152,011,656	152,011,794	139 bp
ENSE00003743537	152,060,991	152,061,124	134 bp
ENSE00003736522	152,094,385	152,094,568	184 bp
ENSE00001128501	152,098,732	152,103,274	4,543 bp

RefSeq ID	Symbol	Status	Canonical
NP_000116	ESR1	REVIEWED	Yes ✓
NP_001116212	ESR1	REVIEWED	No
NP_001116213	ESR1	REVIEWED	No
NP_001116214	ESR1	REVIEWED	No
NP_001278159	ESR1	REVIEWED	No
NP_001278170	ESR1	REVIEWED	No
NP_001315029	ESR1	REVIEWED	No
NP_001372497	ESR1	REVIEWED	No
NP_001372498	ESR1	REVIEWED	No
NP_001372499	ESR1	REVIEWED	No
NP_001372500	ESR1	REVIEWED	No
NP_001372501	ESR1	REVIEWED	No

InterPro ID	Name	Type
IPR000536	Nucl_hrmn_rcpt_lig-bd	Domain
IPR001292	Estr_rcpt	Family
IPR001628	Znf_hrmn_rcpt	Domain
IPR001723	Nuclear_hrmn_rcpt	Family
IPR013088	Znf_NHR/GATA	Homologous_superfamily
IPR024178	Est_rcpt/est-rel_rcp	Family
IPR024736	Oestrogen-typ_rcpt_final_C_dom	Domain
IPR035500	NHR-like_dom_sf	Homologous_superfamily
IPR046944	Estr_rcpt_N	Domain
IPR050200	Nuclear_hormone_rcpt_NR3	Family

ESR1 Gene Complete Identifier and Functional Mapping Reference

Structured Data Sources

Database	Identifier	Description
HGNC	HGNC:3467	Approved symbol: ESR1
Ensembl	ENSG00000091831	Ensembl gene ID
NCBI Entrez	2099	Entrez Gene ID
OMIM	133430	Gene/locus MIM number

Attribute	Value
Approved Name	Estrogen receptor 1
Locus Type	Gene with protein product
Locus Group	Protein-coding gene
Status	Approved
Gene Group	Estrogen receptors
Previous Symbols	ESR
Aliases	ER, NR3A1, Era, ER-alpha, ESRA, ESTRR

RefSeq ID	Symbol	Type	Status	MANE Select
NM_000125	ESR1	mRNA	REVIEWED	Yes ✓
NM_001122740	ESR1	mRNA	REVIEWED	No
NM_001122741	ESR1	mRNA	REVIEWED	No
NM_001122742	ESR1	mRNA	REVIEWED	No
NM_001291230	ESR1	mRNA	REVIEWED	No
NM_001291241	ESR1	mRNA	REVIEWED	No
NM_001328100	ESR1	mRNA	REVIEWED	No
NM_001385568	ESR1	mRNA	REVIEWED	No
NM_001385569	ESR1	mRNA	REVIEWED	No
NM_001385570	ESR1	mRNA	REVIEWED	No
NM_001385571	ESR1	mRNA	REVIEWED	No
NM_001385572	ESR1	mRNA	REVIEWED	No

PDB ID	Resolution	Method	Description
5DXE	1.50 Å	X-ray	LBD with Stapled Peptide SRC2-P4 and Estradiol
5UFX	1.55 Å	X-ray	LBD in Complex with OP1074
5UFW	1.58 Å	X-ray	LBD in Complex with OP1154
5KCT	1.60 Å	X-ray	LBD Y537S with OBHS-N derivative
1XPC	1.60 Å	X-ray	LBD with compound 19
3UUD	1.60 Å	X-ray	LBD Y537S with estradiol
5N10	1.60 Å	X-ray	Binary bivalent supramolecular platform
5W9D	1.65 Å	X-ray	LBD C381S,C417S,C530S with Endoxifen
6CBZ	1.65 Å	X-ray	LBD Y537S with Estradiol and GRIP Peptide
3CBP	1.42 Å	X-ray	SET7/9-ER-Sinefungin complex
1XP6	1.70 Å	X-ray	LBD with compound 16
2QXS	1.70 Å	X-ray	LBD 536S mutant with Raloxifene
5KCC	2.39 Å	X-ray	LBD Y537S with OBHS-N
1XP9	1.80 Å	X-ray	LBD with compound 18
1XP1	1.80 Å	X-ray	LBD with compound 15
4MGA	1.80 Å	X-ray	LBD Y537S with 4-tert-octylphenol
2B1Z	1.78 Å	X-ray	LBD with 17methyl-17alpha-dihydroequilenin
5KCW	1.91 Å	X-ray	LBD Y537S with N-trifluoroethyl OBHS-N
3ERT	1.90 Å	X-ray	LBD with 4-hydroxytamoxifen
1SJ0	1.90 Å	X-ray	LBD with antagonist ligand
6CHZ	1.68 Å	X-ray	LBD Y537S with antagonist H3B-9224
6CHW	1.89 Å	X-ray	LBD Y537S covalently bound to H3B-5942
1L2I	1.95 Å	X-ray	LBD with THC and GRIP1 peptide
1X7R	2.00 Å	X-ray	LBD with Genistein
2OUZ	2.00 Å	X-ray	LBD with Lasofoxifene

Organism	Ensembl Gene ID	Symbol	Biotype
Mouse (Mus musculus)	ENSMUSG00000019768	Esr1	protein_coding
Rat (Rattus norvegicus)	ENSRNOG00000019358	Esr1	protein_coding
Zebrafish (Danio rerio)	ENSDARG00000004111	esr1	protein_coding
Fruit fly (Drosophila melanogaster)	FBGN0035849	ERR	protein_coding
Worm (C. elegans)	No direct ortholog	-	-
Yeast (S. cerevisiae)	No ortholog	-	-

Classification	Count
Pathogenic	2
Likely Pathogenic	0
Uncertain Significance (VUS)	~25
Likely Benign	~80
Benign	~90
Risk Factor	2
Conflicting	~10

ClinVar ID	HGVS Notation	Variant Type	Classification
16590	NM_000125.4:c.1339_1340delinsGC (p.Cys447Ala)	Indel	Pathogenic
16592	NM_000125.4:c.469C>T (p.Arg157Ter)	SNV	Pathogenic

ClinVar ID	HGVS Notation	Variant Type
16594	NM_000125.4:c.453-397T>C	SNV
208354	NM_000125.4:c.908A>G (p.Lys303Arg)	SNV

Variant	Effect	Delta Score
6:151690665:G:GG	donor_gain	1.00
6:151690663:AAG:A	donor_loss	0.98
6:151690664:AG:A	donor_loss	0.98
6:151690665:G:A	donor_loss	0.98
6:151690666:TAG:T	donor_loss	0.98
6:151690668:GGTA:G	donor_loss	0.94
6:151690595:TCC:T	donor_gain	0.92
6:151690663:AA:A	donor_gain	0.90
6:151690667:AG:A	donor_loss	0.86
6:151690660:TTCAA:T	donor_gain	0.84
6:151699907:A:G	donor_gain	0.83
6:151690669:G:C	donor_loss	0.81
6:151690596:C:A	donor_gain	0.79
6:151690649:A:AG	donor_gain	0.77
6:151699959:GA:G	donor_gain	0.73
6:151690662:CAA:C	donor_gain	0.67
6:151690863:AC:A	donor_gain	0.66
6:151697479:A:AG	donor_gain	0.63
6:151690666:T:C	donor_gain	0.62
6:151697494:G:GT	donor_gain	0.62

Variant	Protein Change	Pathogenicity Score	Classification
6:151807935:A:T	K8I	0.841	likely_pathogenic
6:151807921:G:A	M3I	0.733	likely_pathogenic
6:151807921:G:C	M3I	0.733	likely_pathogenic
6:151807921:G:T	M3I	0.733	likely_pathogenic
6:151807936:A:C	K8N	0.698	likely_pathogenic
6:151807936:A:T	K8N	0.698	likely_pathogenic
6:151807943:G:T	G11W	0.745	likely_pathogenic
6:151807943:G:A	G11R	0.595	likely_pathogenic
6:151807943:G:C	G11R	0.595	likely_pathogenic

CCDS ID
CCDS5234
CCDS87457

Variant	Protein Change	Pathogenicity Score	Classification
6:151807920:T:A	M3K	0.514	ambiguous
6:151807917:C:T	T2I	0.490	ambiguous
6:151807920:T:G	M3R	0.481	ambiguous
6:151807956:T:C	L15P	0.373	ambiguous

Pathway ID	Pathway Name	Disease Pathway
R-HSA-8939211	ESR-mediated signaling	No
R-HSA-9018519	Estrogen-dependent gene expression	No
R-HSA-9009391	Extra-nuclear estrogen signaling	No
R-HSA-383280	Nuclear Receptor transcription pathway	No
R-HSA-8931987	RUNX1 regulates estrogen receptor mediated transcription	No
R-HSA-1257604	PIP3 activates AKT signaling	No
R-HSA-1251985	Nuclear signaling by ERBB4	No
R-HSA-2219530	Constitutive Signaling by Aberrant PI3K in Cancer	Yes
R-HSA-6811558	PI5P, PP2A and IER3 Regulate PI3K/AKT Signaling	No
R-HSA-4090294	SUMOylation of intracellular receptors	No
R-HSA-5689896	Ovarian tumor domain proteases	No
R-HSA-8866910	TFAP2 family regulates transcription of growth factors	No
R-HSA-8939256	RUNX1 regulates transcription of genes involved in WNT signaling	No
R-HSA-8939902	Regulation of RUNX2 expression and activity	No
R-HSA-9841251	Mitochondrial unfolded protein response (UPRmt)	No
R-HSA-9927418	Developmental Lineage of Mammary Gland Luminal Epithelial Cells	No
R-HSA-9927426	Developmental Lineage of Mammary Gland Alveolar Cells	No

GO ID	Term Name
GO:0030520	estrogen receptor signaling pathway
GO:0030518	nuclear receptor-mediated steroid hormone signaling pathway
GO:0043401	steroid hormone receptor signaling pathway
GO:0043627	response to estrogen
GO:0071391	cellular response to estrogen stimulus
GO:0071392	cellular response to estradiol stimulus
GO:0032355	response to estradiol
GO:0045944	positive regulation of transcription by RNA polymerase II
GO:0045893	positive regulation of DNA-templated transcription
GO:0000122	negative regulation of transcription by RNA polymerase II
GO:0006357	regulation of transcription by RNA polymerase II
GO:0006355	regulation of DNA-templated transcription
GO:0006338	chromatin remodeling
GO:0007165	signal transduction
GO:0060065	uterus development
GO:0060068	vagina development
GO:0060749	mammary gland alveolus development
GO:0060745	mammary gland branching involved in pregnancy
GO:0060750	epithelial cell proliferation involved in mammary gland duct elongation
GO:0048863	stem cell differentiation

GO ID	Term Name
GO:0030284	nuclear estrogen receptor activity
GO:0004879	nuclear receptor activity
GO:0034056	estrogen response element binding
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:0000978	RNA polymerase II cis-regulatory region sequence-specific DNA binding
GO:1990837	sequence-specific double-stranded DNA binding
GO:0003682	chromatin binding
GO:0005496	steroid binding
GO:0030331	nuclear estrogen receptor binding
GO:0001221	transcription coregulator binding
GO:0001222	transcription corepressor binding
GO:0001223	transcription coactivator binding
GO:0042802	identical protein binding
GO:0005516	calmodulin binding
GO:0008013	beta-catenin binding
GO:0008270	zinc ion binding
GO:0071889	14-3-3 protein binding
GO:0019899	enzyme binding

GO ID	Term Name
GO:0005634	nucleus
GO:0005654	nucleoplasm
GO:0000785	chromatin
GO:0000791	euchromatin
GO:0005667	transcription regulator complex
GO:0005737	cytoplasm
GO:0005829	cytosol
GO:0005886	plasma membrane
GO:0005794	Golgi apparatus
GO:0016020	membrane
GO:0032991	protein-containing complex

UniProt ID	Protein Name	Score
Q9Y6Q9	NCOA3 (SRC-3)	997
P03372	ESR1 (homodimer)	997
P12931	SRC	996
P05412	JUN (c-Jun)	995
P38398	BRCA1	995
P01100	FOS (c-Fos)	994
P08069	IGF1R	994
Q03135	CAV1	992
P55317	FOXA1	990
P07900	HSP90AA1	988
P48552	NRIP1 (RIP140)	988
O75376	NCOR1	987
Q13547	HDAC1	987
Q15788	NCOA1 (SRC-1)	986
Q14344	GNA13	985
P08238	HSP90AB1	983
P27482	CALML3	981
P08047	SP1	979
P10275	AR (Androgen receptor)	979
Q15596	NCOA2 (SRC-2)	979
Q8TD86	DDX5	979
Q92841	DDX17	979
Q96GE6	MYBBP1A	979
Q9NZT1	CALML5	979
P00533	EGFR	974
P04637	TP53	974
P24385	CCND1	972
P27986	PIK3R1	971
P04626	ERBB2 (HER2)	966
P01343	PRL (Prolactin)	964
P29353	SHC1	962
P35222	CTNNB1 (beta-catenin)	952

UniProt ID	Top Similarity	Avg Similarity
B3SV56	1.0000	0.9930
Q07917	1.0000	0.9935
Q08E02	1.0000	0.9931
P70662	1.0000	0.9823
Q86U70	1.0000	0.9822
A0P8Z4	0.9999	0.9943
O15350	0.9999	0.9879
O93511	0.9999	0.9928
P06211	0.9999	0.9953
P19785	0.9999	0.9953

UniProt ID	Top Identity	BitScore
P04150	99.4%	1506
P06401	98.6%	1692
P08235	98.7%	1781
Q4JM28	99.6%	1812
Q3YC04	99.2%	1795

Matrix ID	Collection	Class	Family
MA0112.1	CORE	Nuclear receptors with C4 zinc fingers	Steroid hormone receptors (NR3)
MA0112.2	CORE	Nuclear receptors with C4 zinc fingers	Steroid hormone receptors (NR3)
MA0112.3	CORE	Nuclear receptors with C4 zinc fingers	Steroid hormone receptors (NR3)
MA0112.4	CORE	Nuclear receptors with C4 zinc fingers	Steroid hormone receptors (NR3)

Target Gene	Regulation	Confidence
CCND1	Activation	High
BCL2	Activation	High
BIRC5 (Survivin)	Activation	High
MYC	Unknown	High
TFF1 (pS2)	Activation	High
GREB1	Activation	High
BRCA1	Unknown	High
BRCA2	Unknown	High
CDKN1A (p21)	Activation	High
CDKN1B (p27)	Repression	High
CDKN1C (p57)	Repression	High
CDC25A	Activation	High
CYP19A1 (Aromatase)	Activation	High
CAV1	Repression	High
CTSD (Cathepsin D)	Unknown	High
AMH	Activation	High
AICDA	Activation	High
BMP2	Activation	High
AURKA	Unknown	High
AP1	Activation	High
CXCL8 (IL-8)	Activation	High
CRH	Repression	High
CRHBP	Activation	High
BTG2	Repression	High
CD24	Repression	High
CDH1 (E-cadherin)	Unknown	High
DACH1	Activation	High
DCT	Activation	High
CYP1A1	Repression	High
CYP2C19	Repression	High

Entity	Effect	Mechanism
17beta-estradiol	Up-regulates	Chemical activation
EGFR	Up-regulates	Phosphorylation
ERBB2	Up-regulates	Phosphorylation
MAPK1/3 (ERK1/2)	Up-regulates	Phosphorylation
AKT	Up-regulates	Phosphorylation
PRKACA (PKA)	Up-regulates	Phosphorylation
GSK3B	Up-regulates	Phosphorylation
ABL1	Up-regulates	Phosphorylation
CDK2	Up-regulates	Phosphorylation
BRCA1	Down-regulates	Activity
DUSP22	Down-regulates	Dephosphorylation

Drug	Effect	Mechanism
Tamoxifen	Down-regulates	Chemical inhibition
Fulvestrant	Down-regulates	Chemical inhibition
Raloxifene	Down-regulates	Chemical inhibition
Estradiol	Up-regulates	Chemical activation
Estrone	Up-regulates	Chemical activation
Estriol	Up-regulates	Chemical activation
Tibolone	Up-regulates	Chemical activation
Diethylstilbestrol	Up-regulates	Chemical activation
Bisphenol A	Up-regulates	Chemical activation

ChEMBL ID	Drug Name	Mechanism
CHEMBL83	TAMOXIFEN	Antagonist
CHEMBL786	TAMOXIFEN CITRATE	Antagonist
CHEMBL81	RALOXIFENE	Antagonist
CHEMBL1116	RALOXIFENE HYDROCHLORIDE	Antagonist
CHEMBL46740	BAZEDOXIFENE	Antagonist
CHEMBL328190	LASOFOXIFENE	Antagonist
CHEMBL2355051	CLOMIPHENE	Mixed agonist/antagonist

ChEMBL ID	Drug Name	Mechanism
CHEMBL1358	FULVESTRANT	Pure antagonist/degrader
CHEMBL4297509	ELACESTRANT	Oral SERD

ChEMBL ID	Drug Name
CHEMBL135	ESTRADIOL
CHEMBL691	ETHINYL ESTRADIOL
CHEMBL1405	ESTRONE
CHEMBL193482	ESTRIOL
CHEMBL1511	ESTRADIOL VALERATE
CHEMBL1200430	ESTRADIOL ACETATE
CHEMBL1200973	ESTRADIOL CYPIONATE
CHEMBL1201151	MESTRANOL
CHEMBL411	DIETHYLSTILBESTROL
CHEMBL1018	DIENESTROL
CHEMBL9225	HEXESTROL
CHEMBL1230314	ESTETROL ANHYDROUS
CHEMBL141305	CYCLOFENIL
CHEMBL1201165	QUINESTROL
CHEMBL1200761	CHLOROTRIANISENE

ChEMBL ID	Drug Name
CHEMBL1162	NORETHINDRONE
CHEMBL1389	LEVONORGESTREL
CHEMBL1531	ETONOGESTREL
CHEMBL1533	DESOGESTREL
CHEMBL1387	NORETHYNODREL
CHEMBL1200624	ETHYNODIOL DIACETATE
CHEMBL1276308	MIFEPRISTONE
CHEMBL260538	ULIPRISTAL ACETATE
CHEMBL1479	DANAZOL
CHEMBL1393	SPIRONOLACTONE

ChEMBL ID	Drug Name	Primary Use
CHEMBL1756	ESTRAMUSTINE PHOSPHATE	Prostate cancer
CHEMBL1023	BEXAROTENE	Cutaneous T-cell lymphoma
CHEMBL1289601	LENVATINIB	Thyroid cancer
CHEMBL3545185	SELINEXOR	Multiple myeloma
CHEMBL408513	BELINOSTAT	Peripheral T-cell lymphoma

ChEMBL ID	Drug Name	Mechanism
CHEMBL1093458	ENDOXIFEN	Active tamoxifen metabolite
CHEMBL489	AFIMOXIFENE	Topical SERM
CHEMBL4475463	AMCENESTRANT	Oral SERD
CHEMBL4650316	GIREDESTRANT	Oral SERD
CHEMBL4650365	CAMIZESTRANT	Oral SERD
CHEMBL5095183	IMLUNESTRANT	Oral SERD
CHEMBL5095210	VEPDEGESTRANT	PROTAC degrader

Attribute	Value
Expression Breadth	Ubiquitous
Total Present Calls	216
Total Absent Calls	70
Total Conditions	286
Max Expression Score	97.49
Average Expression Score	68.11
Gold Quality Count	255

Rank	Tissue (UBERON ID)	Expression Score	Quality
1	Oviduct epithelium (UBERON:0004804)	97.49	Gold
2	Cervix epithelium (UBERON:0004801)	96.89	Gold
3	Mammalian vulva (UBERON:0000997)	96.85	Gold
4	Endometrium (UBERON:0001295)	96.64	Gold
5	Uterine cervix (UBERON:0000002)	96.04	Gold
6	Cervix squamous epithelium (UBERON:0006922)	95.98	Gold
7	Fallopian tube (UBERON:0003889)	95.94	Gold
8	Endocervix (UBERON:0000458)	95.16	Gold
9	Right uterine tube (UBERON:0001302)	94.72	Gold
10	Uterus (UBERON:0000995)	94.53	Gold
11	Ectocervix (UBERON:0012249)	94.34	Gold
12	Epithelium of mammary gland (UBERON:0003244)	94.10	Gold
13	Mammary duct (UBERON:0001765)	93.85	Gold
14	Body of uterus (UBERON:0009853)	93.61	Gold
15	Vagina (UBERON:0000996)	93.35	Gold
16	Caput epididymis (UBERON:0004358)	92.43	Gold
17	Germinal epithelium of ovary (UBERON:0001304)	91.68	Gold
18	Calcaneal tendon (UBERON:0003701)	91.13	Gold
19	Urethra (UBERON:0000057)	90.87	Gold
20	Myometrium (UBERON:0001296)	90.85	Gold
21	Tibia (UBERON:0000979)	90.56	Gold
22	Mammary gland (UBERON:0001911)	89.63	Gold
23	Thoracic mammary gland (UBERON:0005200)	89.62	Gold
24	Left uterine tube (UBERON:0001303)	89.21	Gold
25	Adult organism (UBERON:0007023)	88.52	Gold
26	Female reproductive system (UBERON:0000474)	88.11	Gold
27	Nipple (UBERON:0002030)	86.20	Gold
28	Tendon (UBERON:0000043)	85.42	Gold
29	Decidua (UBERON:0002450)	83.72	Gold
30	Right lobe of liver (UBERON:0001114)	83.44	Gold

Disease	OMIM ID	Classification	Inheritance	Submitter
Estrogen Resistance Syndrome	OMIM:615363	Limited	Autosomal Recessive	Ambry Genetics
Estrogen Resistance Syndrome	OMIM:615363	Limited	Autosomal Recessive	Labcorp Genetics
Estrogen Resistance Syndrome	ORPHANET:785	Supportive	Autosomal Recessive	Orphanet

HPO ID	Phenotype
HP:0000013	Hypoplasia of the uterus
HP:0000147	Polycystic ovaries
HP:0000786	Primary amenorrhea
HP:0008675	Enlarged polycystic ovaries
HP:0003187	Breast hypoplasia
HP:0100783	Breast aplasia
HP:0008187	Absence of secondary sex characteristics
HP:0008197	Absence of pubertal development
HP:0100133	Abnormality of the pubic hair

HPO ID	Phenotype
HP:0000098	Tall stature
HP:0001548	Overgrowth
HP:0000938	Osteopenia
HP:0000939	Osteoporosis
HP:0002663	Delayed epiphyseal ossification
HP:0002750	Delayed skeletal maturation
HP:0003799	Marked delay in bone age
HP:0010639	Elevated alkaline phosphatase of bone origin
HP:0031428	Increased circulating osteocalcin level