Provide a comprehensive cross-database identifier and functional mapping reference for human PTEN. 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 PTEN. 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 Core Gene Identifiers
DatabaseIdentifierDescription HGNCHGNC:9588Approved symbol: PTEN EnsemblENSG00000171862Human gene NCBI Entrez5728protein-coding gene OMIM601728Gene/locus MIM number CCDSCCDS31238Consensus CDS Genomic Location AttributeValue Chromosome10 Cytogenetic Band10q23.31 Start Position87,862,638 End Position87,971,930 Strand+ (forward) Genome AssemblyGRCh38/hg38 Gene Length109,293 bp Section 2: Transcript Identifiers Ensembl Transcripts Total Transcript …

Transcript ID	Biotype	Start	End	Strand
ENST00000371953	protein_coding	87,863,625	87,971,930	+
ENST00000472832	protein_coding	87,864,329	87,961,309	+
ENST00000688308	protein_coding	87,862,638	87,966,885	+
ENST00000693560	protein_coding	87,863,438	87,971,930	+
ENST00000700021	protein_coding	87,863,795	87,966,885	+
ENST00000700029	protein_coding	87,863,625	87,966,885	+
ENST00000713839	protein_coding	87,863,633	87,966,885	+
ENST00000686459	nonsense_mediated_decay	87,864,328	87,966,671	+
ENST00000688922	nonsense_mediated_decay	87,864,329	87,966,885	+
ENST00000700022	nonsense_mediated_decay	87,864,079	87,966,805	+
ENST00000706955	nonsense_mediated_decay	87,863,625	87,971,930	+
ENST00000710265	nonsense_mediated_decay	87,863,625	87,971,930	+
ENST00000713837	nonsense_mediated_decay	87,863,625	87,971,930	+
ENST00000416679	retained_intron	87,878,692	87,880,427	+
ENST00000462694	retained_intron	87,864,468	87,894,326	+
ENST00000498703	retained_intron	87,925,523	87,933,487	+
ENST00000688158	retained_intron	87,874,919	87,971,930	+
ENST00000700023	retained_intron	87,941,120	87,965,530	+
ENST00000700024	retained_intron	87,950,234	87,966,870	+
ENST00000700025	retained_intron	87,950,857	87,962,450	+
ENST00000700026	retained_intron	87,957,582	87,962,052	+
ENST00000487939	protein_coding_CDS_not_defined	87,864,449	87,867,049	+

RefSeq ID	Type	Status	MANE Select
NM_000314	mRNA	REVIEWED	YES (Canonical)
NM_001304717	mRNA	REVIEWED	No
NM_001304718	mRNA	REVIEWED	No

RefSeq ID	Type	Status	MANE Select
NP_000305	protein	REVIEWED	YES (Canonical)
NP_001291646	protein	REVIEWED	No
NP_001291647	protein	REVIEWED	No

Exon ID	Start	End	Length
ENSE00004011725	87,863,625	87,864,548	924 bp
ENSE00001156351	87,894,025	87,894,109	85 bp
ENSE00001156344	87,925,513	87,925,557	45 bp
ENSE00003595610	87,931,046	87,931,089	44 bp
ENSE00001156330	87,933,013	87,933,251	239 bp
ENSE00001156327	87,952,118	87,952,259	142 bp
ENSE00003725338	87,957,853	87,958,019	167 bp
ENSE00001156315	87,960,894	87,961,118	225 bp
ENSE00001456541	87,965,287	87,971,930	6,644 bp

UniProt ID	Name	Status	Species	Length
P60484	PTEN	Reviewed (Canonical)	Human	403 aa
C0HLV8	PTEN upstream ORF MP31	Reviewed	Human	-
C0HLV9	PTEN upstream ORF MP31	Reviewed	Human	-
O54857	Pten	Reviewed	Mouse	-
P60483	Pten	Reviewed	Rat	-
O08586	Pten	Reviewed	Mouse	-
Q9PUT6	Pten	Reviewed	Zebrafish	-
Q8T9S7	Pten	Reviewed	Drosophila	-

PTEN Gene Complete Identifier and Functional Mapping Reference

Structured Data Sources

Database	Identifier	Description
HGNC	HGNC:9588	Approved symbol: PTEN
Ensembl	ENSG00000171862	Human gene
NCBI Entrez	5728	protein-coding gene
OMIM	601728	Gene/locus MIM number
CCDS	CCDS31238	Consensus CDS

Attribute	Value
Chromosome	10
Cytogenetic Band	10q23.31
Start Position	87,862,638
End Position	87,971,930
Strand	+ (forward)
Genome Assembly	GRCh38/hg38
Gene Length	109,293 bp

Property	Value
Molecular Weight	47,166 Da
Sequence Length	403 amino acids
EC Numbers	3.1.3.16, 3.1.3.48, 3.1.3.67

ID	Name	Type
IPR000387	Tyr_Pase_dom	Domain
IPR003595	Tyr_Pase_cat	Domain
IPR014020	Tensin_C2-dom	Domain
IPR016130	Tyr_Pase_AS	Active Site
IPR017361	Bifunc_PIno_P3_Pase/Pase_PTEN	Family
IPR029021	Prot-tyrosine_phosphatase-like	Homologous Superfamily
IPR029023	Tensin_phosphatase	Domain
IPR035892	C2_domain_sf	Homologous Superfamily
IPR045101	PTP_PTEN	Domain
IPR051281	Dual-spec_lipid-protein_phosph	Family

PDB ID	Title	Method	Resolution
1D5R	Crystal Structure of the PTEN Tumor Suppressor	X-ray	2.1 Å
5BZZ	Human phosphatase PTEN in reduced state	X-ray	2.2 Å
8X3S	Human WDR5 in complex with PTEN	X-ray	1.87 Å
4O1V	SPOP/PTEN regulatory hub	X-ray	2.0 Å
7PC7	SNTG1 PDZ with acetylated PTEN motif	X-ray	2.1 Å
5BUG	PTEN oxidized by H2O2	X-ray	2.4 Å
5BZX	PTEN with bisperoxovanadium complex	X-ray	2.5 Å
7JUL	Non-phosphorylated PTEN	X-ray	2.53 Å
7JUK	PTEN with tetra-phosphorylated tail	X-ray	3.15 Å
7JVX	PTEN structural basis of regulation	X-ray	3.2 Å
7JTX	PTEN multi-site phosphorylation	X-ray	3.23 Å
2KYL	MAST2-PDZ with PTEN C-terminus	NMR	-

Organism	Gene ID	Symbol	Biotype
Mouse (Mus musculus)	ENSMUSG00000013663	Pten	protein_coding
Rat (Rattus norvegicus)	ENSRNOG00000020723	Pten	protein_coding
Zebrafish (Danio rerio)	ENSDARG00000056623	ptenb	protein_coding
Zebrafish (Danio rerio)	ENSDARG00000071018	ptena	protein_coding
Fruit fly (D. melanogaster)	FBGN0026379	Pten	protein_coding

Property	Value
Location	Chromosome 19: 32,734,897-32,803,560
Strand	+
Gene Length	68,664 bp

Gene ID	Symbol	Biotype
ENSG00000079308	TNS1	protein_coding
ENSG00000136205	TNS3	protein_coding
ENSG00000132958	TPTE2	protein_coding
ENSG00000274391	TPTE	protein_coding
ENSG00000122986	HVCN1	protein_coding
ENSG00000169758	TMEM266	protein_coding

Classification	Count
Pathogenic	100+
Likely Pathogenic	50+
Pathogenic/Likely Pathogenic	30+
Uncertain Significance (VUS)	2,000+
Likely Benign	100+
Benign	50+
Conflicting	100+

ClinVar ID	HGVS Notation	Type	Classification
141485	c.493-2A>G	splice	Pathogenic (expert panel)
1182096	c.209+4A>G	splice	Pathogenic (expert panel)
142018	c.389G>C (p.Arg130Pro)	missense	Pathogenic (expert panel)
1338262	c.373A>G (p.Lys125Glu)	missense	Pathogenic (expert panel)
142261	c.314G>A (p.Cys105Tyr)	missense	Pathogenic (expert panel)
142269	c.737C>T (p.Pro246Leu)	missense	Pathogenic (expert panel)
142423	c.802-2A>T	splice	Pathogenic (expert panel)
141654	c.50_51del (p.Gln17fs)	frameshift	Pathogenic (expert panel)
1067089	c.376G>C (p.Ala126Pro)	missense	Pathogenic
1067224	c.523G>A (p.Val175Met)	missense	Pathogenic
1068214	c.75G>C (p.Leu25Phe)	missense	Pathogenic
1014805	c.801G>C (p.Lys267Asn)	missense	Pathogenic
1176553	c.517C>G (p.Arg173Gly)	missense	Pathogenic
1195176	c.379G>T (p.Gly127Ter)	nonsense	Pathogenic
1195871	c.204C>A (p.Tyr68Ter)	nonsense	Pathogenic
142027	c.48T>A (p.Tyr16Ter)	nonsense	Pathogenic
1069915	c.184A>T (p.Lys62Ter)	nonsense	Pathogenic
1075939	c.250A>T (p.Arg84Ter)	nonsense	Pathogenic
1074078	c.304A>T (p.Lys102Ter)	nonsense	Pathogenic
1388819	c.465T>G (p.Tyr155Ter)	nonsense	Pathogenic
142636	c.493G>T (p.Gly165Ter)	nonsense	Pathogenic
1320461	c.601G>T (p.Glu201Ter)	nonsense	Pathogenic
142640	c.822G>A (p.Trp274Ter)	nonsense	Pathogenic
1456749	c.106G>T (p.Gly36Ter)	nonsense	Pathogenic
1422662	c.43A>T (p.Arg15Ter)	nonsense	Pathogenic
1317879	c.634+1G>T	splice	Pathogenic
1393293	c.801+2T>C	splice	Pathogenic
1215488	c.44_45del (p.Arg15fs)	frameshift	Pathogenic
1069314	c.502_503del (p.Ile168fs)	frameshift	Pathogenic
1072117	c.672dup (p.Tyr225fs)	frameshift	Pathogenic
142259	c.741dup (p.Pro248fs)	frameshift	Pathogenic
140898	c.772_773del (p.Phe258fs)	frameshift	Pathogenic
1372311	c.641dup (p.Phe215fs)	frameshift	Pathogenic
1330013	c.672_673insC (p.Tyr225fs)	frameshift	Pathogenic
1415847	c.590del (p.Lys197fs)	frameshift	Pathogenic
1453956	c.201dup (p.Tyr68fs)	frameshift	Pathogenic
1454161	c.270del (p.Phe90fs)	frameshift	Pathogenic
1458563	c.511dup (p.Gln171fs)	frameshift	Pathogenic
1458931	c.1007dup (p.Tyr336Ter)	frameshift	Pathogenic
1379224	c.143A>G (p.Asn48Ser)	missense	Pathogenic
1198486	c.511C>A (p.Gln171Lys)	missense	Pathogenic
1457954	c.3G>A (p.Met1Ile)	missense	Pathogenic
1076438	c.-541-5533del	large del	Pathogenic
1067457	g.(?89685260)(89685324_?)del	large del	Pathogenic
1076749	g.(?89685260)(89725321_?)del	large del	Pathogenic
1069185	g.89711945_89711946insAlu	Alu insertion	Pathogenic
1043063	c.959T>C (p.Leu320Ser)	missense	Likely pathogenic (expert)
1066565	c.746T>G (p.Val249Gly)	missense	Likely pathogenic
1066605	c.80-2A>C	splice	Likely pathogenic
1067478	c.1026G>T (p.Lys342Asn)	missense	Likely pathogenic

Variant	Gene	Effect	Delta Score
10:87863244:G:C	PTEN	donor_gain	1.00
10:87863202:AC:A	PTEN	donor_gain	0.98
10:87863207:G:A	PTEN	donor_gain	0.97
10:87863257:G:A	PTEN	donor_gain	0.97
10:87863210:T:TA	PTEN	donor_gain	0.94
10:87863657:G:GT	PTEN	donor_gain	0.92
10:87863243:AG:A	PTEN	donor_gain	0.91
10:87863334:C:T	PTEN	donor_gain	0.89
10:87863333:GCAGC:G	PTEN	donor_gain	0.88
10:87863251:AT:A	PTEN	donor_gain	0.87
10:87863669:T:G	PTEN	donor_gain	0.87
10:87863283:C:T	PTEN	donor_gain	0.85
10:87863354:A:AG	PTEN	donor_gain	0.84
10:87863337:C:G	PTEN	donor_gain	0.84
10:87863639:G:GT	PTEN	donor_gain	0.78
10:87863197:AGCCT:A	PTEN	donor_loss	0.78
10:87863198:GCCTA:G	PTEN	donor_loss	0.78
10:87863199:CCTA:C	PTEN	donor_loss	0.78
10:87863200:CT:C	PTEN	donor_loss	0.78
10:87863201:TA:T	PTEN	donor_loss	0.78
10:87863657:G:T	PTEN	donor_gain	0.78
10:87863243:A:AC	PTEN	donor_gain	0.76
10:87863203:CCCTG:C	PTEN	donor_gain	0.76
10:87863705:GGAGA:G	PTEN	donor_gain	0.75
10:87863253:C:A	PTEN	donor_gain	0.75
10:87863396:C:G	PTEN	donor_gain	0.75
10:87863202:A:AC	PTEN	donor_gain	0.73
10:87863203:C:CC	PTEN	donor_gain	0.73
10:87863204:C:G	PTEN	donor_loss	0.73
10:87863347:C:T	PTEN	donor_gain	0.72

Variant	AA Change	Score	Class
10:87864506:A:G	K13E	1.000	likely_pathogenic
10:87864507:A:T	K13I	1.000	likely_pathogenic
10:87864508:A:C	K13N	1.000	likely_pathogenic
10:87864513:G:C	R15T	1.000	likely_pathogenic
10:87864513:G:T	R15I	1.000	likely_pathogenic
10:87864514:A:C	R15S	1.000	likely_pathogenic
10:87864495:T:A	V9D	1.000	likely_pathogenic
10:87864506:A:C	K13Q	0.999	likely_pathogenic
10:87864507:A:C	K13T	0.999	likely_pathogenic
10:87864498:G:T	S10I	0.999	likely_pathogenic
10:87864498:G:A	S10N	0.999	likely_pathogenic
10:87864499:C:A	S10R	0.999	likely_pathogenic
10:87864509:A:G	R14G	0.999	likely_pathogenic
10:87864512:A:G	R15G	0.999	likely_pathogenic
10:87864515:T:G	Y16D	0.999	likely_pathogenic
10:87864516:A:C	Y16S	0.998	likely_pathogenic
10:87864494:G:C	V9L	0.998	likely_pathogenic
10:87864495:T:C	V9A	0.998	likely_pathogenic
10:87864502:A:C	R11S	0.998	likely_pathogenic
10:87864511:G:T	R14S	0.998	likely_pathogenic
10:87864483:T:A	I5N	0.996	likely_pathogenic
10:87864513:G:A	R15K	0.996	likely_pathogenic
10:87864494:G:T	V9F	0.988	likely_pathogenic
10:87864495:T:G	V9G	0.995	likely_pathogenic
10:87864497:A:T	S10C	0.995	likely_pathogenic
10:87864501:G:T	R11I	0.995	likely_pathogenic
10:87864515:T:A	Y16N	0.995	likely_pathogenic
10:87864509:A:T	R14W	0.994	likely_pathogenic
10:87864512:A:G	R15G	0.994	likely_pathogenic
10:87864501:G:C	R11T	0.992	likely_pathogenic
10:87864510:G:C	R14T	0.991	likely_pathogenic
10:87864515:T:C	Y16H	0.991	likely_pathogenic
10:87864516:A:G	Y16C	0.990	likely_pathogenic
10:87864486:A:C	K6T	0.989	likely_pathogenic
10:87864485:A:G	K6E	0.990	likely_pathogenic
10:87864510:G:T	R14M	0.987	likely_pathogenic
10:87864498:G:C	S10T	0.986	likely_pathogenic
10:87864483:T:G	I5S	0.983	likely_pathogenic
10:87864504:A:T	N12I	0.973	likely_pathogenic
10:87864483:T:C	I5T	0.969	likely_pathogenic

Pathway ID	Pathway Name	Disease Pathway
R-HSA-199418	Negative regulation of the PI3K/AKT network	No
R-HSA-1660499	Synthesis of PIPs at the plasma membrane	No
R-HSA-1855204	Synthesis of IP3 and IP4 in the cytosol	No
R-HSA-202424	Downstream TCR signaling	No
R-HSA-5628897	TP53 Regulates Metabolic Genes	No
R-HSA-5689880	Ub-specific processing proteases	No
R-HSA-5689896	Ovarian tumor domain proteases	No
R-HSA-8943723	Regulation of PTEN mRNA translation	No
R-HSA-8948747	Regulation of PTEN localization	No
R-HSA-8948751	Regulation of PTEN stability and activity	No
R-HSA-8986944	Transcriptional Regulation by MECP2	No
R-HSA-5674404	PTEN Loss of Function in Cancer	Yes

GO ID	Term Name
GO:0016314	phosphatidylinositol-3,4,5-trisphosphate 3-phosphatase activity
GO:0004438	phosphatidylinositol-3-phosphate phosphatase activity
GO:0004721	phosphoprotein phosphatase activity
GO:0004722	protein serine/threonine phosphatase activity
GO:0004725	protein tyrosine phosphatase activity
GO:0051800	phosphatidylinositol-3,4-bisphosphate 3-phosphatase activity
GO:0030351	inositol-1,3,4,5,6-pentakisphosphate 3-phosphatase activity
GO:0051717	inositol-1,3,4,5-tetrakisphosphate 3-phosphatase activity
GO:0052866	phosphatidylinositol phosphate phosphatase activity
GO:0008013	beta-catenin binding
GO:0008289	lipid binding
GO:0019899	enzyme binding
GO:0010997	anaphase-promoting complex binding
GO:0030165	PDZ domain binding
GO:0042802	identical protein binding
GO:0140678	molecular function inhibitor activity
GO:1990381	ubiquitin-specific protease binding
GO:1990757	ubiquitin ligase activator activity

GO ID	Term Name
GO:0051898	negative regulation of PI3K/AKT signaling
GO:0051896	regulation of PI3K/AKT signal transduction
GO:0043491	PI3K/protein kinase B signal transduction
GO:0006470	protein dephosphorylation
GO:0046856	phosphatidylinositol dephosphorylation
GO:0006661	phosphatidylinositol biosynthetic process
GO:0006915	apoptotic process
GO:0008285	negative regulation of cell population proliferation
GO:0008284	positive regulation of cell population proliferation
GO:0016477	cell migration
GO:0030336	negative regulation of cell migration
GO:1902807	negative regulation of cell cycle G1/S phase transition
GO:2000134	negative regulation of G1/S transition of mitotic cell cycle
GO:0010719	negative regulation of EMT
GO:0033137	negative regulation of peptidyl-serine phosphorylation
GO:0007417	central nervous system development
GO:0007611	learning or memory
GO:0007416	synapse assembly
GO:0060997	dendritic spine morphogenesis
GO:0097107	postsynaptic density assembly

GO ID	Term Name
GO:0005634	nucleus
GO:0005654	nucleoplasm
GO:0005737	cytoplasm
GO:0005829	cytosol
GO:0005886	plasma membrane
GO:0009898	cytoplasmic side of plasma membrane
GO:0016324	apical plasma membrane
GO:0016605	PML body
GO:0005576	extracellular region
GO:0014069	postsynaptic density
GO:0043005	neuron projection
GO:0043197	dendritic spine
GO:0042995	cell projection
GO:0035749	myelin sheath adaxonal region
GO:0043220	Schmidt-Lanterman incisure

UniProt ID	Gene Symbol	Score
Q86UL8	SASH1	974
Q15831	STK11	971
P04637	TP53	969
Q70Z35	NEDD4L	969
P31749	AKT1	968
Q5TCQ9	PHLPP2	962
P42336	PIK3CA	949
P27986	PIK3R1	944
Q9NZM5	USP13	937
P01116	KRAS	930
P12830	CDH1	930
P15056	BRAF	928
P00533	EGFR	926
P42345	MTOR	923
Q13485	SMAD4	909
P42771	CDKN2A	908
O14745	SLC9A3R1	905
P23443	RPS6KB1	904
Q12959	DLG1	904
P49841	GSK3B	900
Q12778	FOXO1	895
Q13315	ATM	893
P49815	TSC2	890
P35222	CTNNB1	881
Q6P0Q8	MAGI2	878
P51587	BRCA2	877
Q03135	CAV1	872
P01106	MYC	871
P04626	ERBB2	864
P01111	NRAS	861
P10275	AR	853
Q9BT92	GPRC5A	853
P24385	CCND1	851
O15530	PDPK1	848
P08069	IGF1R	844
O43524	FOXO3	841
P21359	NF1	839
Q00987	MDM2	838
O75874	IDH1	836
P46527	CDKN1B	831
P37231	PPARG	830
Q969H0	FBXW7	830
P42338	PIK3CB	829
P12931	SRC	828
Q16665	HIF1A	827
P11802	CDK4	825
P01308	INS	823
Q14160	SCRIB	820
Q6R327	RICTOR	820
P48736	PIK3CG	818

UniProt	Top Similarity	Avg Similarity
O54857 (Mouse)	1.000	0.958
P60483 (Rat)	1.000	0.957
O08586 (Mouse)	1.000	0.957
Q13613 (MTMR3)	0.998	0.969
Q9Z2C4 (MTMR4)	0.998	0.971
Q13614 (MTMR4)	0.999	0.950
O60942 (MTMR3)	0.999	0.962
Q16667 (MTMR1)	0.997	0.950
Q9Z2D1 (MTMR1)	0.999	0.952

UniProt	Top Identity	Bitscore
P60483 (Rat)	100.0%	828
O54857 (Mouse)	99.8%	825
O08586 (Mouse)	99.8%	827
Q6XPS3	96.9%	814
Q99KY4	96.7%	2504
Q9GLM4	90.0%	3165
Q9HBL0	90.0%	3186
Q4R6N0	90.2%	811
Q9PUT6 (Zebrafish)	88.9%	713
P56180	87.6%	801

TF Gene	Regulation	Confidence
TP53	Repression	High
AR	Activation	High
ATF2	Activation	High
BMI1	Repression	-
CTNNB1	Repression	Low
DNMT1	-	High
EGR1	Activation	High
EZH2	Unknown	High
GATA2	Unknown	High
GATA4	Repression	-
GLI2	Repression	Low
HES1	Repression	High
HNF4A	-	High
JUN	Unknown	High
KDM5A	Repression	-
KDM5C	Repression	-
MTA1	Repression	High
MXD1	Repression	High
MYC	Unknown	Low
NFATC1	-	High
NFKB1	Activation	-
PPARG	Activation	High
RBPJ	Repression	High
RELA	Activation	High
SALL4	Repression	High
SMAD4	Activation	High
SNAI1	Activation	High
SP1	Unknown	High
STAT3	Activation	High
TET1	Activation	-
TFAP2A	Activation	High
VDR	Activation	-
YY1	Activation	High

Target Gene	Regulation
ABTB1	Activation
DUSP1	Activation
EGR2	Activation
HCLS1	Activation
NDRG1	Activation
NFIL3	Activation
PINK1	Activation
RAD51	-
SH2B2	Activation

Regulator	Effect	Mechanism	Direct
CSNK2A1	down-regulates activity	phosphorylation	Yes
CSNK2A2	down-regulates activity	phosphorylation	Yes
GSK3B	down-regulates activity	phosphorylation	Yes
STK11	down-regulates activity	phosphorylation	Yes
PLK1	down-regulates activity	phosphorylation	Yes
PLK3	down-regulates activity	phosphorylation	Yes
INSR	down-regulates activity	phosphorylation	Yes
PINK1	down-regulates activity	phosphorylation	Yes
SRC	up-regulates activity	phosphorylation	Yes
LCK	up-regulates activity	phosphorylation	Yes
FRK	up-regulates quantity	phosphorylation	Yes
ROCK1	up-regulates	phosphorylation	Yes
MAST2	up-regulates	phosphorylation	Yes
USP7	down-regulates activity	deubiquitination	Yes
WWP2	down-regulates quantity	ubiquitination	Yes
XIAP	down-regulates quantity	ubiquitination	Yes
MKRN1	down-regulates quantity	ubiquitination	Yes
PREX2	down-regulates activity	binding	Yes

Target	Effect	Mechanism
PIP3	down-regulates quantity	chemical modification
AKT1	down-regulates activity	-
PI3K	down-regulates activity	-
PIK3CA	down-regulates activity	-
PIK3CB	down-regulates activity	-
PTK2 (FAK)	down-regulates activity	dephosphorylation
SRC	down-regulates activity	dephosphorylation
IRS1	down-regulates activity	dephosphorylation
CREB1	down-regulates activity	dephosphorylation
STAT5A	down-regulates	dephosphorylation
IRF3	up-regulates activity	dephosphorylation
CFL1	up-regulates activity	dephosphorylation
MAPT	up-regulates activity	dephosphorylation
RAB7A	up-regulates activity	dephosphorylation
GLI1	down-regulates	-
RPS6KB1	down-regulates activity	-
AR	up-regulates activity	dephosphorylation

ChEMBL ID	Name	Type
CHEMBL2052032	PTEN	SINGLE PROTEIN
CHEMBL4523606	SPOP/PTEN	PROTEIN-PROTEIN INTERACTION

ChEMBL ID	Name	Type	Development Phase
CHEMBL301982	CELASTROL	Small molecule	0 (Preclinical)
CHEMBL2000194	-	Small molecule	0 (Preclinical)
CHEMBL2057662	-	Small molecule	0 (Preclinical)

Attribute	Value
PharmGKB ID	PA33942
Symbol	PTEN
VIP Gene	Yes
CPIC Guideline	No
Chromosome	chr10

Attribute	Value
Expression Breadth	Ubiquitous
Total Present Calls	256
Max Expression Score	99.31
Average Expression Score	94.10
Gold Quality Conditions	256

Tissue/Cell Type	Entity ID	Score	Quality
Sperm	CL:0000019	99.31	Gold
Endothelial cell	CL:0000115	99.21	Gold
Calcaneal tendon	UBERON:0003701	99.20	Gold
Upper arm skin	UBERON:0004263	99.15	Gold
Epithelial cell of pancreas	CL:0000083	99.00	Gold
Kidney epithelium	UBERON:0004819	98.91	Gold
Middle temporal gyrus	UBERON:0002771	98.68	Gold
Parietal pleura	UBERON:0002400	98.62	Gold
Ileal mucosa	UBERON:0000331	98.56	Gold
Cardiac muscle of right atrium	UBERON:0003379	98.40	Gold
Visceral pleura	UBERON:0002401	98.29	Gold
Gingival epithelium	UBERON:0001949	98.06	Gold
Gingiva	UBERON:0001828	98.00	Gold
Brodmann area 23	UBERON:0013554	98.00	Gold
Pancreatic ductal cell	CL:0002079	98.00	Gold
Tibialis anterior	UBERON:0001385	97.93	Gold
Mammary gland epithelium	UBERON:0003244	97.87	Gold
Mammary duct	UBERON:0001765	97.87	Gold
Blood	UBERON:0000178	97.86	Gold
Dorsal root ganglion	UBERON:0000044	97.84	Gold
Germinal epithelium of ovary	UBERON:0001304	97.84	Gold
Trigeminal ganglion	UBERON:0001675	97.76	Gold
Tibia	UBERON:0000979	97.71	Gold
Stromal cell of endometrium	CL:0002255	97.60	Gold
Esophagus squamous epithelium	UBERON:0006920	97.59	Gold
Mammalian vulva	UBERON:0000997	97.47	Gold
Superficial temporal artery	UBERON:0001614	97.45	Gold
Pericardium	UBERON:0002407	97.43	Gold
Trabecular bone tissue	UBERON:0002483	97.39	Gold
Thoracic mammary gland	UBERON:0005200	97.32	Gold

Experiment ID	Description	Species	Cells
E-MTAB-11268	Human hypertrophied heart atlas	Homo sapiens	64,898
E-MTAB-11121	Retinal organoids from hESCs	Homo sapiens	22,253
E-GEOD-81608	Human islet cells (non-diabetic/T2D)	Homo sapiens	1,600
E-ENAD-27	Human islet cell signatures	Homo sapiens	1,145
E-CURD-6	Normal human bone marrow	Homo sapiens	1,024
E-GEOD-124858	Bone marrow stromal cell subpopulations	Homo sapiens	247
E-GEOD-110499	Multiple myeloma bone marrow	Homo sapiens	173

Disease	Classification	MOI	Evidence
Cowden syndrome 1 (OMIM:158350)	Definitive	AD	Multiple submitters
Cowden syndrome 1	Strong	AD	Genomics England
Macrocephaly-autism syndrome (OMIM:605309)	Strong	AD	Multiple submitters
Glioma susceptibility 2 (OMIM:613028)	Limited	AD	Ambry Genetics
Leiomyosarcoma	Moderate	AR	Genomics England
Renal cell carcinoma	Moderate	AD	Genomics England
Bannayan-Riley-Ruvalcaba syndrome	Supportive	AD	Orphanet
Cowden disease	Supportive	AD	Orphanet
Proteus-like syndrome	Supportive	AD	Orphanet
Activated PI3K-delta syndrome	Supportive	AD	Orphanet
Lhermitte-Duclos disease	Supportive	AD	Orphanet

Orphanet ID	Disease Name	Type	Gene Count
109	Bannayan-Riley-Ruvalcaba syndrome	Clinical subtype	1
201	Cowden syndrome	Clinical subtype	9
210548	Macrocephaly-intellectual disability-autism syndrome	Disease	2
65285	Lhermitte-Duclos disease	Clinical subtype	1
79076	Juvenile polyposis of infancy	Clinical subtype	2
137608	Segmental outgrowth-lipomatosis-AVM-epidermal nevus syndrome	Clinical subtype	1
2969	Proteus-like syndrome	Clinical subtype	1
145	Hereditary breast and/or ovarian cancer syndrome	Disease	15
494547	Squamous cell carcinoma of hypopharynx	Disease	3
494550	Squamous cell carcinoma of larynx	Disease	3
500464	SCC of nasal cavity/paranasal sinuses	Disease	3
500478	SCC of oropharynx	Disease	3
502363	SCC of oral cavity	Disease	3
502366	SCC of lip	Disease	3

HPO ID	Phenotype
HP:0000256	Macrocephaly
HP:0001249	Intellectual disability
HP:0000717	Autism
HP:0001263	Global developmental delay
HP:0000750	Delayed speech and language development
HP:0001548	Overgrowth
HP:0004481	Progressive macrocephaly
HP:0005490	Postnatal macrocephaly
HP:0000098	Tall stature
HP:0001513	Obesity
HP:0000238	Hydrocephalus
HP:0001250	Seizure
HP:0001252	Hypotonia
HP:0002664	Neoplasm
HP:0004390	Hamartomatous polyposis
HP:0010566	Hamartoma
HP:0012032	Lipoma
HP:0001012	Multiple lipomas
HP:0001031	Subcutaneous lipoma
HP:0001028	Hemangioma
HP:0001048	Cavernous hemangioma
HP:0005306	Capillary hemangioma
HP:0000820	Abnormality of thyroid gland
HP:0000821	Hypothyroidism
HP:0000836	Hyperthyroidism
HP:0000853	Goiter
HP:0000854	Thyroid adenoma
HP:0002890	Thyroid carcinoma
HP:0006731	Follicular thyroid carcinoma
HP:0003002	Breast carcinoma
HP:0010619	Fibroadenoma of the breast
HP:0005584	Renal cell carcinoma
HP:0002858	Meningioma
HP:0002861	Melanoma
HP:0010784	Uterine neoplasm
HP:0007206	Hemimegalencephaly
HP:0001382	Joint hypermobility
HP:0000957	Cafe-au-lait spot
HP:0007565	Multiple cafe-au-lait spots
HP:0000995	Melanocytic nevus
HP:0001054	Numerous nevi
HP:0010816	Epidermal nevus
HP:0009720	Adenoma sebaceum
HP:0009721	Shagreen patch
HP:0000729	Autistic behavior
HP:0007018	ADHD
HP:0011098	Speech apraxia
HP:0002167	Abnormal speech pattern
HP:0002808	Kyphosis
HP:0002650	Scoliosis

Study ID	Trait	P-value
GCST90002381	Eosinophil count	2.0e-30
GCST90002382	Eosinophil percentage	5.0e-28
GCST90002396	Mean reticulocyte volume	9.0e-28
GCST90002398	Neutrophil count	7.0e-21
GCST90002407	White blood cell count	8.0e-20
GCST90002403	Red blood cell count	3.0e-16
GCST004606	Eosinophil count	2.0e-15
GCST90002392	Mean corpuscular volume	1.0e-14
GCST90002390	Mean corpuscular hemoglobin	2.0e-14
GCST004600	Eosinophil percentage	2.0e-14
GCST010653	TSH levels	1.0e-13
GCST90002402	Platelet count	1.0e-11
GCST90013405	ALT levels	2.0e-11
GCST010118	Type 2 diabetes	4.0e-10
GCST005976	Basophil count	2.0e-10
GCST006899	TSH levels	2.0e-10
GCST90002389	Lymphocyte percentage	1.0e-10
GCST007096	Pulse pressure	2.0e-09
GCST90020025	Waist-to-hip ratio (BMI adj)	2.0e-09
GCST90020027	Waist-hip index	2.0e-09
GCST90002400	Plateletcrit	3.0e-09
GCST90002399	Neutrophil percentage	6.0e-09
GCST90011898	ALT levels	6.0e-09
GCST90013420	Ambidextrousness	2.0e-08
GCST008362	Birth weight	2.0e-08
GCST004346	Psoriasis	3.0e-08
GCST009380	Type 2 diabetes (BMI adj)	5.0e-08
GCST009597	Multiple sclerosis	1.0e-07

Database	Records	Version
HGNC	Gene identifiers	Current
Ensembl	Gene/transcript/exon	GRCh38
NCBI Entrez	Gene	Current
UniProt	Protein	Current
RefSeq	Transcripts/proteins	Current
PDB	Structures	Current
AlphaFold	Predicted structure	v2
ClinVar	Clinical variants	Current
SpliceAI	Splice predictions	v1.3
AlphaMissense	Pathogenicity predictions	2023
Reactome	Pathways	Current
Gene Ontology	Functional annotations	Current
STRING	Protein interactions	v12
BioGRID	Physical interactions	Current
CollecTRI	TF-target relations	Current
SIGNOR	Signaling	Current
ChEMBL	Drug targets	v33
PharmGKB	Pharmacogenomics	Current
Bgee	Expression	v15
SCXA	Single-cell expression	Current
GenCC	Gene-disease validity	Current
Orphanet	Rare diseases	Current
HPO	Phenotypes	Current
GWAS Catalog	GWAS associations	Current