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

MAPT - COMPREHENSIVE CROSS-DATABASE IDENTIFIER AND FUNCTIONAL MAPPING REFERENCE Microtubule Associated Protein Tau
Section 1: Gene Identifiers
DatabaseIdentifierNotes HGNCHGNC:6893Approved symbol: MAPT EnsemblENSG00000186868Human gene NCBI Entrez4137 OMIM157140Gene/locus entry RefSeq GenomicNC_000017.11 Full Name: microtubule associated protein tau Genomic Location: AttributeValue Chromosome17 Cytoband17q21.31 Start Position45,894,358 End Position46,028,334 Strand+ (positive) Gene Length133,976 …

Gene Aliases	Locus Type	Gene Groups	Total Transcripts
MTBT1, tau, PPND, FTDP-17, TAU, MSTD, MTBT2, FLJ31424, MGC138549, PPP1R103, tau-40, Tau-PHF6, DDPAC, MAPTL	protein-coding gene	Protein phosphatase 1 regulatory subunits
			Transcript Identifiers**	52

Transcript ID	Biotype	Start	End	Length
ENST00000262410	protein_coding	45,894,554	46,028,334	133,780 bp
ENST00000334239	protein_coding	45,894,668	46,024,183	129,515 bp
ENST00000344290	protein_coding	45,894,560	46,024,425	129,865 bp
ENST00000351559	protein_coding	45,894,554	46,028,334	133,780 bp
ENST00000415613	protein_coding	45,962,338	46,024,171	61,833 bp
ENST00000420682	protein_coding	45,894,560	46,024,659	130,099 bp
ENST00000431008	protein_coding	45,962,338	46,024,171	61,833 bp
ENST00000446361	protein_coding	45,894,674	46,028,334	133,660 bp
ENST00000535772	protein_coding	45,894,551	46,024,225	129,674 bp
ENST00000570299	protein_coding_CDS_not_defined	45,894,576	46,018,730	124,154 bp
ENST00000571311	nonsense_mediated_decay	45,894,566	45,978,425	83,859 bp
ENST00000571987	protein_coding	45,962,338	46,024,171	61,833 bp
ENST00000572440	retained_intron	45,975,492	45,980,506	5,014 bp
ENST00000574436	protein_coding	45,962,338	46,024,171	61,833 bp
ENST00000576518	retained_intron	45,972,783	46,024,431	51,648 bp
ENST00000577017	protein_coding_CDS_not_defined	45,985,659	45,987,095	1,436 bp
ENST00000680542	nonsense_mediated_decay	45,894,663	46,025,873	131,210 bp
ENST00000680674	protein_coding	45,894,527	46,024,655	130,128 bp
ENST00000703922-ENST00000972120	various	various	various	-

Accession	Symbol	Status	MANE Select
NM_001377265	MAPT	REVIEWED	✓ MANE Select
NM_001123066	MAPT	REVIEWED
NM_001123067	MAPT	REVIEWED
NM_001203251	MAPT	REVIEWED
NM_001203252	MAPT	REVIEWED
NM_001377266	MAPT	REVIEWED
NM_001377267	MAPT	REVIEWED
NM_001377268	MAPT	REVIEWED
NM_005910	MAPT	REVIEWED
NM_016834	MAPT	REVIEWED
NM_016835	MAPT	REVIEWED
NM_016841	MAPT	REVIEWED

Exon ID	Start	End	Strand
ENSE00003903194	45,894,560	45,894,686	+
ENSE00003549966	45,962,321	45,962,470	+
ENSE00003598892	45,971,859	45,971,945	+
ENSE00003658894	45,978,375	45,978,440	+
ENSE00002672395	45,982,866	45,983,930	+
ENSE00003611335	45,987,040	45,987,095	+
ENSE00003682122	45,991,460	45,991,586	+
ENSE00003634058	45,996,399	45,996,664	+
ENSE00002405491	46,014,243	46,014,324	+
ENSE00003570976	46,018,618	46,018,730	+
ENSE00003990316	46,023,956	46,024,425	+

Accession	Status	Name
P10636	✓ Reviewed (Swiss-Prot)	Microtubule-associated protein tau
A0A7I2PJZ2	Unreviewed
A0A7I2PLE3	Unreviewed
A0A7P0T936	Unreviewed
I3L2Z2	Unreviewed

MAPT Gene Complete Identifier and Functional Mapping Reference

Structured Data Sources

Database	Identifier	Notes
HGNC	HGNC:6893	Approved symbol: MAPT
Ensembl	ENSG00000186868	Human gene
NCBI Entrez	4137
OMIM	157140	Gene/locus entry
RefSeq Genomic	NC_000017.11

Attribute	Value
Chromosome	17
Cytoband	17q21.31
Start Position	45,894,358
End Position	46,028,334
Strand	+ (positive)
Gene Length	133,976 bp

Accession	Symbol	Status	MANE Select
NP_001364194	MAPT	REVIEWED	✓ MANE Select
NP_001116538	MAPT	REVIEWED
NP_001116539	MAPT	REVIEWED
NP_001190180	MAPT	REVIEWED
NP_001190181	MAPT	REVIEWED
NP_001364195	MAPT	REVIEWED
NP_001364196	MAPT	REVIEWED
NP_001364197	MAPT	REVIEWED

InterPro ID	Short Name	Type
IPR001084	MAP_tubulin-bd_rpt	Repeat
IPR002955	Tau	Family
IPR027324	MAP2/MAP4/Tau	Family

PDB ID	Method	Resolution (Å)	Description
5O3L	Cryo-EM	3.4	Paired helical filament in Alzheimer's disease brain
5O3T	Cryo-EM	3.4	Straight filament in Alzheimer's disease brain
6GX5	Cryo-EM	3.2	Narrow Pick Filament from Pick's disease brain
6NWP	Cryo-EM	2.3	Chronic traumatic encephalopathy Type I Tau filament
6NWQ	Cryo-EM	3.4	CTE Type II Tau filament
6TJO	Cryo-EM	3.2	TypeI tau filaments - Corticobasal degeneration
6TJX	Cryo-EM	3.0	TypeII tau filaments - Corticobasal degeneration
7P65	Cryo-EM	2.7	Progressive supranuclear palsy tau filament
7P66	Cryo-EM	3.0	Globular glial tauopathy type 1 tau filament
7P6A	Cryo-EM	1.9	Limbic-predominant neuronal inclusion body 4R tauopathy
7P6D	Cryo-EM	3.3	Argyrophilic grain disease type 1 tau filament
8CAQ	Cryo-EM	2.3	Tau filaments Type I - Subacute Sclerosing Panencephalitis
8OT6	Cryo-EM	2.0	CTE typeI tau filament from Guam ALS/PDC
8P34	Cryo-EM	2.61	Tau filaments - DeltaK281 mutation
2MZ7	NMR	-	Structure of Tau(267-312) bound to Microtubules
5N5A	NMR	-	Structure of Tau(254-290) bound to F-actin
2ON9	X-ray	1.51	Amyloid forming peptide VQIVYK
5K7N	MicroED	1.1	VQIVYK peptide at high resolution
6ODG	X-ray	1.0	SVQIVY tau protein fragment
4FL5	X-ray	1.9	14-3-3 sigma with Tau pS214 peptide
5E2W	X-ray	1.5	Anti-TAU AT8 FAB with triply phosphorylated TAU peptide
6CVJ	Cryo-EM	3.2	Synthetic tau bound to microtubule
7PQC	Cryo-EM	4.1	tau-microtubule structural ensemble
8FYU	X-ray	1.85	CHIP-TPR domain with acetylated tau peptide
1I8H	NMR	-	PIN1 WW domain with phosphothreonine peptide

Method	Count
Cryo-EM (Electron Microscopy)	~220
X-ray Diffraction	~45
NMR	~6
Electron Crystallography	~3

Attribute	Value
AlphaFold ID	AF-P10636-F1
Sequence Length	5544 (all isoforms)
Global pLDDT	49.56
Fraction Very High Confidence	0.00

Note
MAPT is an intrinsically disordered protein, explaining the low AlphaFold confidence scores
	Cross-Species Orthologs**

Species	Ensembl Gene ID	Symbol	Biotype
Mouse (Mus musculus)	ENSMUSG00000018411	Mapt	protein_coding
Rat (Rattus norvegicus)	ENSRNOG00000005133	Mapt	protein_coding
Zebrafish (Danio rerio)	ENSDARG00000087616	maptb	protein_coding
Zebrafish (Danio rerio)	ENSDARG00000089314	mapta	protein_coding

Additional Entrez orthologs	Note
440 species	No direct orthologs found in Drosophila melanogaster, C. elegans, or S. cerevisiae (Tau is a vertebrate-specific protein)
		Clinical Variants & AI Predictions**

CCDS ID
CCDS11499
CCDS11500
CCDS11501
CCDS11502
CCDS45715
CCDS45716
CCDS56033
CCDS92345
CCDS92346
CCDS92347

Pfam
PF00418 (Tau/MAP)
	Structure Identifiers**

Classification	Count
Pathogenic	28
Likely Pathogenic	7
Uncertain Significance (VUS)	~100
Likely Benign	~200
Benign	~250
Conflicting	~16

Variant ID	HGVS Notation	Consequence	Review Status
14245	c.2078C>T (p.Pro693Leu)	Missense	Multiple submitters
14247	c.2392C>T (p.Arg798Trp)	Missense	Multiple submitters
14252	c.2185G>A (p.Val729Met)	Missense	Multiple submitters
14253	c.2013T>G (p.Asn671Lys)	Missense	Multiple submitters
14257	c.2064T>C (p.Asn688=)	Synonymous/splicing	Multiple submitters
14266	c.1972C>G (p.Leu658Val)	Missense	Multiple submitters
98212	c.1999-10G>T	Intronic/splice	Multiple submitters
98218	c.2091+3G>A	Splice donor	Multiple submitters
98222	c.2091+16C>T	Intronic/splice	Multiple submitters
14246	c.1991G>T (p.Gly664Val)	Missense	No criteria
14248	c.2091+14C>T	Splice region	No criteria
14251	c.2091+1G>A	Splice donor	No criteria
14254	c.2090G>A (p.Ser697Asn)	Missense	No criteria
14256	c.2077C>T (p.Pro693Ser)	Missense	No criteria
14258	c.2201A>T (p.Glu734Val)	Missense	No criteria
14259	c.1946A>C (p.Lys649Thr)	Missense	No criteria
14260	c.2282A>T (p.Lys761Ile)	Missense	No criteria
14262	c.2135C>T (p.Ser712Phe)	Missense	Single submitter
14263	c.14G>T (p.Arg5Leu)	Missense	No criteria
14267	c.2231C>T (p.Ser744Leu)	Missense	No criteria
14268	c.2126A>T (p.Lys709Met)	Missense	No criteria
14269	c.2084G>T (p.Gly695Val)	Missense	No criteria
2573094	c.2266C>T (p.Pro756Ser)	Missense	Single submitter
98219	c.2091+11T>C	Splice region	No criteria
98221	c.2091+13A>G	Splice region	No criteria
98226	c.2120T>G (p.Leu707Arg)	Missense	No criteria
98243	c.2060ATA[1] (p.Asn688del)	In-frame deletion	Single submitter
564448	17q21.31 CNV deletion	Copy number loss	No criteria

Variant ID	HGVS Notation	Consequence
2049744	c.2091+16C>G	Splice region
3075676	c.2077C>G (p.Pro693Ala)	Missense
3778831	c.2027T>A (p.Leu676His)	Missense
4056341	c.2010TAA[1] (p.Asn671del)	In-frame deletion
599620	c.2260C>T (p.His754Tyr)	Missense
807628	c.2266C>A (p.Pro756Thr)	Missense
986870	c.2242T>A (p.Ser748Thr)	Missense

Variant	Effect	Delta Score
17:45894684:CAGGT:C	donor_loss	1.0000
17:45894685:AGGTA:A	donor_loss	1.0000
17:45894686:GGTA:G	donor_loss	1.0000
17:45894687:G:GA	donor_loss	1.0000
17:45894687:G:GG	donor_gain	0.9900
17:45894688:T:A	donor_loss	0.9900
17:45894683:TCAG:T	donor_gain	0.9600
17:45894685:AG:A	donor_gain	0.9500
17:45894686:GG:G	donor_gain	0.9500
17:45894682:ATCAG:A	donor_gain	0.9000
17:45894684:CAG:C	donor_gain	0.8900
17:45896223:G:GT	donor_gain	0.8100
17:45896237:G:T	donor_gain	0.7600
17:45896223:G:T	donor_gain	0.7400
17:45895687:G:GG	donor_gain	0.7000
17:45895686:A:AG	donor_gain	0.6900
17:45895470:C:T	donor_gain	0.6700
17:45894956:G:GA	donor_gain	0.6400
17:45894955:TGG:T	donor_gain	0.6000
17:45895891:GC:G	donor_gain	0.5900

Variant	Protein Change	AM Score	Classification
17:45962359:T:C	F8L	0.892	likely_pathogenic
17:45962361:C:A	F8L	0.892	likely_pathogenic
17:45962361:C:G	F8L	0.892	likely_pathogenic
17:45962350:C:A	R5S	0.686	likely_pathogenic
17:45962351:G:C	R5P	0.569	likely_pathogenic

Note
Most highly pathogenic mutations cluster in the microtubule-binding repeat region (exons 9-13)
	Biological Pathways & Gene Ontology**

Pathway ID	Name	Disease Pathway
R-HSA-264870	Caspase-mediated cleavage of cytoskeletal proteins	No
R-HSA-9619483	Activation of AMPK downstream of NMDARs	No
R-HSA-9833482	PKR-mediated signaling	No

GO ID	Term
GO:0000226	microtubule cytoskeleton organization
GO:0001774	microglial cell activation
GO:0006974	DNA damage response
GO:0007416	synapse assembly
GO:0007611	learning or memory
GO:0007613	memory
GO:0010506	regulation of autophagy
GO:0019896	axonal transport of mitochondrion
GO:0021954	central nervous system neuron development
GO:0031110	regulation of microtubule polymerization or depolymerization
GO:0031116	positive regulation of microtubule polymerization
GO:0031175	neuron projection development
GO:0045773	positive regulation of axon extension
GO:0046785	microtubule polymerization
GO:0048167	regulation of synaptic plasticity
GO:0050808	synapse organization
GO:0051260	protein homooligomerization
GO:0061564	axon development
GO:0097435	supramolecular fiber organization
GO:1990000	amyloid fibril formation

GO ID	Term
GO:0003677	DNA binding
GO:0003680	minor groove of adenine-thymine-rich DNA binding
GO:0003690	double-stranded DNA binding
GO:0003697	single-stranded DNA binding
GO:0003723	RNA binding
GO:0003779	actin binding
GO:0004857	enzyme inhibitor activity
GO:0008017	microtubule binding
GO:0017124	SH3 domain binding
GO:0019899	enzyme binding
GO:0019901	protein kinase binding
GO:0030674	protein-macromolecule adaptor activity
GO:0034185	apolipoprotein binding
GO:0034452	dynactin binding
GO:0035091	phosphatidylinositol binding
GO:0042802	identical protein binding
GO:0051087	protein-folding chaperone binding
GO:0051721	protein phosphatase 2A binding
GO:0051879	Hsp90 protein binding
GO:0099609	microtubule lateral binding

GO ID	Term
GO:0005576	extracellular region
GO:0005634	nucleus
GO:0005737	cytoplasm
GO:0005739	mitochondrion
GO:0005829	cytosol
GO:0005874	microtubule
GO:0005886	plasma membrane
GO:0015630	microtubule cytoskeleton
GO:0030424	axon
GO:0030425	dendrite
GO:0030426	growth cone
GO:0030673	axolemma
GO:0043005	neuron projection
GO:0043025	neuronal cell body
GO:0043197	dendritic spine
GO:0044304	main axon
GO:0045121	membrane raft
GO:0045298	tubulin complex
GO:0097418	neurofibrillary tangle
GO:1904115	axon cytoplasm

UniProt ID	Gene	Confidence Score
P10636	MAPT (self)	986
P05067	APP (Amyloid precursor protein)	986
P21796	VDAC1	974
P02649	APOE	973
P37840	SNCA (Alpha-synuclein)	971
Q13148	TARDBP	970
P06241	FYN	958
Q00535	CDK5	948
P49841	GSK3B	943
P49768	PSEN1	933
P27348	YWHAQ (14-3-3 theta)	903
P35637	FUS	889
P23781	UCHL3	886
P49810	PSEN2	883
Q96LT7	TMEM106B	852
P04156	PRNP	834
P08247	SNAP25	828
P17600	SYN1	826
Q5S007	LRRK2	826
P22303	ACHE	811
P04271	S100B	802
O60260	PARK2 (Parkin)	790
Q8IWL8	SQSTM1	786
Q7Z3B3	WWOX	785
P07900	HSP90AA1	772
O43189	PHF1	772
P56817	BACE1	764
P07196	NEFL	761
Q9BXM7	PIAS4	751
Q9NUM4	TRIM13	750
P34932	HSPA4	745
P78352	DLG4	735
Q13492	PICALM	726
Q9NQ11	ATG4A	721
O00499	BIN1	719
P34998	CRHR1	717
Q14114	LRP8	713
P06276	BCHE	711
P42858	HTT (Huntingtin)	698
P55072	VCP	696
P23246	SFPQ	694
P12036	NEFH	693
P09936	UCHL1	690
P12931	SRC	686
P07197	NEFM	683
Q13501	SQSTM1	683
P00354	GAPDH	680

Partner	Type	Score
APP	Direct interaction	0.75
HSPA8	Direct interaction	0.67
MAPT (self)	Direct interaction	0.67
STUB1	Physical association	0.52
FYN	Physical association	0.59
GSK3B	Physical association	0.50
AKT1	Physical association	0.50
EGFR	Physical association	0.55

UniProt ID	Top Similarity	Avg Similarity
Q5YCW0	1.0000	0.9892
Q5YCW1	1.0000	0.9891
P10636 (self)	0.9999	0.9890
Q5S6V2	0.9999	0.9890
Q5YCV9	0.9999	0.9890
P10637 (MAP2)	0.9997	0.9895
P19332	0.9997	0.9896
O88778	0.9996	0.9878
O88737	0.9996	0.9870
Q3ZB98	0.9996	0.9833

UniProt ID	Top Identity (%)	Top Bitscore
P10636 (self)	95.0	1070
Q5YCW0	99.0	1096
Q5YCW1	99.0	1093
Q5S6V2	94.5	1072
Q5YCV9	93.6	1067
P10637 (MAP2)	90.6	966
P19332	90.9	968
O02828	89.8	447
P11137 (MAP4)	79.3	2385
P15146	89.0	2796
P20357	89.0	2806

TF Gene	Regulation	Source
AR	Activates MAPT	CollecTRI
DLX3	Unknown	CollecTRI
TFAP2A	Represses MAPT	CollecTRI

Kinase	Effect	Mechanism	Score
CDK5	Down-regulates activity	Phosphorylation	0.76
GSK3B	Down-regulates activity	Phosphorylation	0.74
CDK5/CDK5R1	Down-regulates activity	Phosphorylation	0.70
CAMK2A	Down-regulates activity	Phosphorylation	0.60
MAPK1	Down-regulates activity	Phosphorylation	0.57
FYN	Down-regulates	Phosphorylation	0.54
LRRK2	Down-regulates	Phosphorylation	0.53
MAPK12	Down-regulates activity	Phosphorylation	0.53
SYK	Down-regulates	Phosphorylation	0.47
TTBK1	Down-regulates	Phosphorylation	0.45
DYRK1A	Down-regulates	Phosphorylation	0.43
MARK1	Down-regulates activity	Phosphorylation	0.43
PRKACA	Down-regulates activity	Phosphorylation	0.43
GSK3A	Down-regulates activity	Phosphorylation	0.43
CSNK1D	Down-regulates	Phosphorylation	0.37
SGK1	Down-regulates	Phosphorylation	0.33
CAPN1	Down-regulates activity	Cleavage	0.33
MAPK14	Up-regulates	Phosphorylation	0.32
PHKG1	Down-regulates activity	Phosphorylation	0.31
CHEK2	Down-regulates	Phosphorylation	0.20

Phosphatase	Effect	Score
PP2B (Calcineurin)	Up-regulates	0.20
PPP2R1A (PP2A)	Down-regulates	0.20

ChEMBL Target ID	Name	Type
CHEMBL1293224	Microtubule-associated protein tau	SINGLE PROTEIN
CHEMBL4296122	KEAP1/Microtubule-associated protein tau	PPI
CHEMBL4296123	KEAP1/Cullin-3/Microtubule-associated protein tau	PPI
CHEMBL4296124	Cullin-3/Microtubule-associated protein tau	PPI
CHEMBL6066025	Protein cereblon/Microtubule-associated protein tau	PPI (PROTAC)

ChEMBL ID	Name	Type
CHEMBL1008	BEPRIDIL	Small molecule
CHEMBL101	PHENYLBUTAZONE	Small molecule
CHEMBL103	PROGESTERONE	Small molecule
CHEMBL104	CLOTRIMAZOLE	Small molecule
CHEMBL11	IMIPRAMINE	Small molecule
CHEMBL112	ACETAMINOPHEN	Small molecule
CHEMBL1112	ARIPIPRAZOLE	Small molecule
CHEMBL11359	CISPLATIN	Small molecule
CHEMBL117785	TETRABENAZINE	Small molecule
CHEMBL135	ESTRADIOL	Small molecule
CHEMBL1351	CARBOPLATIN	Small molecule
CHEMBL1083993	AMIODARONE	Small molecule
CHEMBL1200503	BROMOCRIPTINE	Small molecule
CHEMBL1200517	DIHYDROERGOTAMINE	Small molecule
CHEMBL1200561	DOXAZOSIN	Small molecule

ChEMBL ID	Name	Type
CHEMBL10316	IDAZOXAN	Small molecule
CHEMBL109480	TANESPIMYCIN	Small molecule
CHEMBL1130	DOXIFLURIDINE	Small molecule
CHEMBL119443	ERGONOVINE	Small molecule
CHEMBL1255653	SEPIAPTERIN	Small molecule
CHEMBL135400	ZOPICLONE	Small molecule

Attribute	Value
Expression Breadth	Ubiquitous
Total Present Calls	141
Max Expression Score	99.52

Tissue	Expression Score	Rank
Cortical plate	99.52	226
Superior frontal gyrus	98.76	580
Prefrontal cortex	98.51	694
Frontal cortex	98.45	724
Frontal lobe	98.45	724
Right frontal lobe	98.32	783
Cerebellum	98.29	797
Right hemisphere of cerebellum	98.29	796
Cerebellar cortex	98.28	802
Cerebellar hemisphere	98.28	804
Brodmann area 9	98.08	898
Primary visual cortex	98.03	921
Dorsolateral prefrontal cortex	97.88	989
Cerebral cortex	97.87	995
Anterior cingulate cortex	97.39	1220
Hypothalamus	97.34	1240
Ammon's horn (Hippocampus)	97.33	1240
Temporal lobe	97.32	1250
Amygdala	97.29	1270
Brain	96.91	1440
Putamen	96.68	1550
Corpus callosum	96.61	1580
Caudate nucleus	96.58	1600
Substantia nigra	96.45	1660
Nucleus accumbens	96.36	1700
Embryo	95.99	1870
Ganglionic eminence	95.99	1870
Gastrocnemius	95.59	2050
Skeletal muscle tissue	95.52	2090
Skeletal muscle organ	94.64	2500