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

Primary Gene Identifiers
DatabaseIdentifierDescription HGNCHGNC:795ATM serine/threonine kinase SymbolATMApproved symbol EnsemblENSG00000149311Human gene ID NCBI Entrez472Gene ID OMIM607585Gene/locus ID Genomic Location AttributeValue Chromosome11 Cytogenetic Band11q22.3 Start Position108,222,804 End Position108,369,102 Strand+ (forward) Gene Span~146.3 kb Gene Nomenclature - Approved Name - Previous Names - Previous Symbols - Aliases - Locus Type - Gene Groups ATM serine/threonine kinase Ataxia …

Transcript ID	Biotype	Start	End
ENST00000675843	protein_coding	108,223,067	108,369,102
ENST00000601453	protein_coding	108,222,804	108,369,102
ENST00000452508	protein_coding	108,222,823	108,369,102
ENST00000278616	protein_coding	108,223,411	108,367,264
ENST00000923922	protein_coding	108,223,080	108,369,102
ENST00000971291	protein_coding	108,223,077	108,366,048
ENST00000713844	protein_coding	108,223,120	108,365,723
ENST00000531525	protein_coding	108,223,067	108,295,996
ENST00000530958	protein_coding	108,223,103	108,236,534
ENST00000684029	protein_coding	108,224,768	108,236,578
...and 54 more transcripts (retained_intron, NMD, protein_coding_CDS_not_defined)

Accession	Type	Status
NM_000051	mRNA	REVIEWED - MANE Select
NP_000042	Protein	REVIEWED - MANE Select

Accession	Status
NM_001351834	REVIEWED
NM_001351835	REVIEWED
NM_001351836	REVIEWED

CCDS ID	Description
CCDS31669	Consensus CDS
CCDS86245	Consensus CDS

Exon ID	Start	End	Strand
ENSE00004021474	108,223,067	108,223,186	+
ENSE00003742933	108,227,595	108,227,696	+
ENSE00003725082	108,227,776	108,227,888	+
ENSE00003744805	108,229,178	108,229,323	+
ENSE00003129472	108,235,670	108,235,834	+
ENSE00004021469	108,243,953	108,244,118	+
ENSE00004021454	108,244,788	108,245,026	+
ENSE00004021457	108,246,964	108,247,127	+
ENSE00004021473	108,248,933	108,249,102	+
ENSE00004021493	108,250,701	108,251,072	+
...and 53 more exons
ENSE00004021453	108,365,325	108,369,102	+ (terminal)

ATM Gene Complete Identifier and Functional Mapping Reference

Structured Data Sources

Database	Identifier	Description
HGNC	HGNC:795	ATM serine/threonine kinase
Symbol	ATM	Approved symbol
Ensembl	ENSG00000149311	Human gene ID
NCBI Entrez	472	Gene ID
OMIM	607585	Gene/locus ID

Attribute	Value
Chromosome	11
Cytogenetic Band	11q22.3
Start Position	108,222,804
End Position	108,369,102
Strand	+ (forward)
Gene Span	~146.3 kb

- Approved Name	- Previous Names	- Previous Symbols	- Aliases	- Locus Type	- Gene Groups
ATM serine/threonine kinase	Ataxia telangiectasia mutated	ATA, ATDC, ATC, ATD	TEL1, TELO1	Gene with protein product (protein-coding)	Armadillo like helical domain containing, Phosphatidylinositol 3-kinase-related kinase family, BRCA1-associated genome surveillance complex
						Transcript Identifiers**

Accession	Status	Canonical
NP_000042	REVIEWED	MANE Select
NP_001338763	REVIEWED	-
NP_001338764	REVIEWED	-
NP_001338765	REVIEWED	-

InterPro ID	Name	Type
IPR000403	PI3/4_kinase_cat_dom	Domain
IPR003151	PIK-rel_kinase_FAT	Domain
IPR003152	FATC_dom	Domain
IPR014009	PIK_FAT	Domain
IPR021668	TAN	Domain
IPR044107	PIKKc_ATM	Domain
IPR018936	PI3/4_kinase_CS	Conserved_site
IPR011009	Kinase-like_dom_sf	Homologous_superfamily
IPR016024	ARM-type_fold	Homologous_superfamily
IPR036940	PI3/4_kinase_cat_sf	Homologous_superfamily
IPR038980	ATM_plant	Family

PDB ID	Title	Method	Resolution
7SIC	Human ATM Dimer	Cryo-EM	2.51 Å
7SID	Human ATM Dimer Bound to Nbs1	Cryo-EM	2.53 Å
8OXQ	ATM(Q2971A) dimeric C-terminal in complex with Mg AMP-PNP	Cryo-EM	2.5 Å
8OXP	ATM(Q2971A) in complex with Mg AMP-PNP	Cryo-EM	2.6 Å
7NI5	Human ATM kinase with bound inhibitor KU-55933	Cryo-EM	2.78 Å
7NI6	Human ATM kinase with bound ATPγS	Cryo-EM	2.8 Å
7NI4	Human ATM kinase domain with bound M4076 inhibitor	Cryo-EM	3.0 Å
8OXO	ATM activated by oxidative stress with p53 peptide	Cryo-EM	3.0 Å
8OXM	ATM activated by oxidative stress with p53 peptide	Cryo-EM	3.3 Å
6K9L	Human dimeric ATM kinase	Cryo-EM	4.27 Å
5NP0	Closed dimer of human ATM	Cryo-EM	5.7 Å
5NP1	Open protomer of human ATM	Cryo-EM	5.7 Å
6K9K	Monomeric human ATM kinase	Cryo-EM	7.82 Å
6HKA	FATC domain of ATM	Solution NMR	-

Organism	Gene ID	Symbol	Biotype
Mouse (Mus musculus)	ENSMUSG00000034218	Atm	protein_coding
Rat (Rattus norvegicus)	ENSRNOG00000029773	Atm	protein_coding
Zebrafish (Danio rerio)	ENSDARG00000002385	atm	protein_coding
Fruit fly (Drosophila)	No direct ortholog	-	-
Worm (C. elegans)	No direct ortholog	-	-
Yeast (S. cerevisiae)	TEL1 (functional analog)	-	-

Gene ID	Symbol	Description
ENSG00000175054	ATR	ATR serine/threonine kinase
ENSG00000253729	PRKDC	DNA-dependent protein kinase catalytic subunit
ENSG00000198793	MTOR	Mechanistic target of rapamycin kinase
ENSG00000157106	SMG1	SMG1 nonsense mediated mRNA decay
ENSG00000196367	TRRAP	Transformation/transcription domain associated protein

Classification	Count (approximate)
Pathogenic	>500
Likely Pathogenic	>300
Uncertain Significance (VUS)	>10,000
Likely Benign	>2,000
Benign	>1,500
Conflicting Classifications	>500

Variant ID	HGVS Notation	Type	Condition
1027442	c.2152dup (p.Cys718fs)	Duplication	Frameshift
1068534	c.6242T>A (p.Leu2081Ter)	SNV	Nonsense
1068785	c.8785A>T (p.Arg2929Ter)	SNV	Nonsense
1069197	c.1179G>A (p.Trp393Ter)	SNV	Nonsense
1069441	c.1262C>G (p.Ser421Ter)	SNV	Nonsense
1069650	c.3145_3146del (p.Leu1049fs)	Deletion	Frameshift
1069824	c.4668T>A (p.Tyr1556Ter)	SNV	Nonsense
1070072	c.8923del (p.Glu2975fs)	Deletion	Frameshift
1070576	c.1078del (p.Asp360fs)	Deletion	Frameshift
1070606	c.5383_5384del (p.Trp1795fs)	Deletion	Frameshift
1071816	c.856C>T (p.Gln286Ter)	SNV	Nonsense
1072054	c.3188dup (p.Met1064fs)	Duplication	Frameshift
1072739	c.4093del (p.Leu1365fs)	Deletion	Frameshift
1072740	c.7705del (p.Asp2569fs)	Deletion	Frameshift
1073216	c.5293C>T (p.Gln1765Ter)	SNV	Nonsense
1073457	c.2464_2466+2del	Deletion	Splice
1074091	c.5677_5680del (p.Glu1894fs)	Deletion	Frameshift
1074412	c.900dup (p.Gly301fs)	Duplication	Frameshift
1074638	c.8690del (p.Gly2897fs)	Deletion	Frameshift
1074652	c.3546_3547del (p.Asn1183fs)	Deletion	Frameshift
1074850	c.3758_3759del (p.Lys1253fs)	Deletion	Frameshift
1074976	c.728dup (p.Leu243fs)	Duplication	Frameshift
1075035	c.1762del (p.Asp588fs)	Deletion	Frameshift
1013733	c.3248A>G (p.His1083Arg)	SNV	Missense - Pathogenic
1067957	c.1802+1G>T	SNV	Splice site
...and many more

Variant	Effect	Delta Score
11:108222864:GC:G	donor_gain	0.98
11:108222865:C:CG	donor_gain	0.98
11:108222865:C:G	donor_gain	0.99
11:108223019:G:GT	donor_gain	0.99
11:108222959:A:AG	donor_gain	0.97
11:108222965:G:GT	donor_gain	0.96
11:108223056:G:GT	donor_gain	0.97
11:108223061:GGGA:G	donor_gain	0.96
11:108223062:G:GT	donor_gain	0.97
11:108223063:GAG:G	donor_gain	0.97
11:108223065:G:GG	donor_gain	0.98
...and more with scores >0.9

Variant	Protein Change	Pathogenicity Score	Class
11:108227647:T:C	L8P	0.992	likely_pathogenic
11:108227872:T:A	W57R	0.998	likely_pathogenic
11:108227872:T:C	W57R	0.998	likely_pathogenic
11:108227874:G:C	W57C	0.996	likely_pathogenic
11:108227874:G:T	W57C	0.996	likely_pathogenic
11:108227831:T:C	L43P	0.994	likely_pathogenic
11:108227692:G:C	R23P	0.992	likely_pathogenic
11:108227873:G:C	W57S	0.987	likely_pathogenic
11:108227792:T:C	F30S	0.985	likely_pathogenic
11:108227831:T:A	L43Q	0.980	likely_pathogenic
11:108227668:T:C	L15P	0.978	likely_pathogenic
11:108227801:T:C	L33P	0.978	likely_pathogenic
11:108227658:T:C	C12R	0.972	likely_pathogenic
11:108227647:T:A	L8Q	0.969	likely_pathogenic
11:108227833:G:C	D44H	0.968	likely_pathogenic
11:108227873:G:T	W57L	0.967	likely_pathogenic
11:108227831:T:G	L43R	0.966	likely_pathogenic
11:108227872:T:G	W57G	0.965	likely_pathogenic
11:108227647:T:G	L8R	0.963	likely_pathogenic
11:108227660:C:G	C12W	0.961	likely_pathogenic
...and more

Pathway ID	Name	Disease Pathway
R-HSA-5693548	Sensing of DNA Double Strand Breaks	No
R-HSA-5693565	Recruitment and ATM-mediated phosphorylation at DSBs	No
R-HSA-5693532	DNA Double-Strand Break Repair	No
R-HSA-5693571	Nonhomologous End-Joining (NHEJ)	No
R-HSA-5685942	HDR through Homologous Recombination (HRR)	No
R-HSA-5685938	HDR through Single Strand Annealing (SSA)	No
R-HSA-69473	G2/M DNA damage checkpoint	No
R-HSA-69563	p53-Dependent G1 DNA Damage Response	No
R-HSA-69541	Stabilization of p53	No
R-HSA-6804756	Regulation of TP53 Activity through Phosphorylation	No
R-HSA-3700989	Transcriptional Regulation by TP53	No
R-HSA-2559586	DNA Damage/Telomere Stress Induced Senescence	No
R-HSA-912446	Meiotic recombination	No
R-HSA-9664873	Pexophagy	No
R-HSA-73894	DNA Repair	No
R-HSA-1640170	Cell Cycle	No
R-HSA-69620	Cell Cycle Checkpoints	No
R-HSA-9675135	Diseases of DNA repair	Yes
R-HSA-9675136	Diseases of DNA Double-Strand Break Repair	Yes
R-HSA-9701192	Defective HRR due to BRCA1 loss of function	Yes
...and 41 more pathways

GO ID	Term
GO:0006302	double-strand break repair
GO:0006281	DNA repair
GO:0000077	DNA damage checkpoint signaling
GO:0006974	DNA damage response
GO:0042770	signal transduction in response to DNA damage
GO:0030330	DNA damage response, signal transduction by p53 class mediator
GO:0007095	mitotic G2 DNA damage checkpoint signaling
GO:0000724	double-strand break repair via homologous recombination
GO:0006303	double-strand break repair via nonhomologous end joining
GO:0010212	response to ionizing radiation
GO:0006468	protein phosphorylation
GO:0046777	protein autophosphorylation
GO:0000723	telomere maintenance
GO:0006979	response to oxidative stress
GO:0043065	positive regulation of apoptotic process
GO:0008630	intrinsic apoptotic signaling pathway in response to DNA damage
GO:0007131	reciprocal meiotic recombination
GO:0051726	regulation of cell cycle
GO:0033151	V(D)J recombination
GO:0050821	protein stabilization

GO ID	Term
GO:0004674	protein serine/threonine kinase activity
GO:0004677	DNA-dependent protein kinase activity
GO:0005524	ATP binding
GO:0003677	DNA binding
GO:0005515	protein binding
GO:0016301	kinase activity
GO:0016740	transferase activity
GO:0016303	1-phosphatidylinositol-3-kinase activity
GO:0000166	nucleotide binding
GO:0042802	identical protein binding
GO:0044877	protein-containing complex binding
GO:0035979	histone H2AXS139 kinase activity

GO ID	Term
GO:0005634	nucleus
GO:0005654	nucleoplasm
GO:0005829	cytosol
GO:0005737	cytoplasm
GO:0005694	chromosome
GO:0000781	chromosome, telomeric region
GO:0035861	site of double-strand break
GO:0005730	nucleolus
GO:0005813	centrosome
GO:0005819	spindle
GO:0005777	peroxisome
GO:0005782	peroxisomal matrix
GO:0031410	cytoplasmic vesicle
GO:0005856	cytoskeleton

UniProt ID	Gene	Confidence Score
O96017	CHK2	999
P38398	BRCA1	999
Q14676	MDC1	997
Q12888	TP53BP1	996
P43246	MSH2	995
Q8WXE1	ATRIP	995
P52701	MSH6	994
P40692	MLH1	992
P16104	H2AX	984
O14757	CHK1	975
P04637	TP53	975
P51587	BRCA2	972
Q9BXW9	FANCD2	968
P13010	XRCC5 (Ku80)	964
O43313	WRN	961
Q06609	RAD51	958
Q8N2W9	PIH1D1	956
Q00987	MDM2	955
Q9Y6K9	NEMO	949
P49959	MRE11	941
O60934	NBN (Nibrin)	936
Q92993	KAT5 (TIP60)	936
P12956	XRCC6 (Ku70)	931
O15297	TDP2	924
Q13547	HDAC1	923
...and more

UniProt	Top Similarity	Avg Similarity
Q17QT7	1.0000	0.9891
Q2KJI3	1.0000	0.9894
Q8BHZ0	1.0000	0.9890
Q921M7	1.0000	0.9893
Q9H0Q0	1.0000	0.9891
Q9NUQ9	1.0000	0.9894
Q8BKX6 (ATR)	0.9999	0.9926
Q96Q15 (SMG1)	0.9999	0.9925
P78527 (PRKDC)	0.9994	0.9936
Q62388 (Mouse Atm)	0.9991	0.9926

UniProt	Gene	Top Identity	Bitscore
Q8BKX6	ATR	97.7%	6960
Q96Q15	SMG1	97.7%	6960
Q6PQD5	Mouse Atm	88.4%	5360
Q13315	ATM (self)	88.4%	5370
Q62388	Mouse Atm	83.8%	5063
C5J7W8	-	73.4%	5246
Q9DE14	-	72.6%	3774
P32600	TEL1 (yeast)	68.5%	3249
P35169	SMG1	68.3%	3269

Target Gene	Regulation Type
BAX	Activation
BCL2	Repression
CDKN1A (p21)	Activation
E2F1	Activation
FAS	Activation
FOXM1	Activation
GADD45A	Activation
MCL1	Activation
PCNA	Unknown
PMAIP1 (NOXA)	Repression
SP1	Repression
TERF1	Repression
TNFRSF10B (TRAIL-R2)	Repression
VEGFA	Repression
KLRK1 (NKG2D)	Activation
COL3A1	Activation
DUSP1	Activation
...and more

Target	Effect	Score
TP53	Up-regulates (stabilization)	0.84
TP53BP1	Phosphorylation	0.87
BRCA1	Up-regulates	0.82
CHEK1	Up-regulates	0.84
CHEK2	Up-regulates	0.87
NBN	Binding	0.86
EXO1	Up-regulates	0.83
RAD50	Phosphorylation	0.81
RPA2	Up-regulates	0.81
H2AFX (H2AX)	Up-regulates	0.20
MDM2	Down-regulates	0.76
MDM4	Down-regulates	0.73
SMC1A	Up-regulates	0.70
SMC3	Phosphorylation	0.74

TF Gene	Regulation	Confidence
E2F1	Activation	High
FOXO3	Unknown	High
GRHL3	-	High
NFAT5	-	High
NR2C2	-	High
TP63	-	High
BRCA1	Activation	-
MYC	Activation	-
BTF3	Activation	-
TWIST1	Activation	-
TWIST2	Activation	-
E2F3	Activation	Low
SP1	Unknown	Low
AR	Unknown	-
RBBP8	Activation	-
RBPJ	Activation	Low

Target ID	Name	Type	Activity Count
CHEMBL3797	Serine-protein kinase ATM	Single Protein	3,924
CHEMBL3885635	ATM/ATR	Protein Family	-
CHEMBL6066129	VHL/ATM	Protein-Protein Interaction	-

ChEMBL ID	Name	Mechanism
CHEMBL1083993	Amiodarone Hydrochloride	Multi-target
CHEMBL1103	Furazolidone	Antibacterial
CHEMBL1200430	Estradiol Acetate	Hormone
CHEMBL1200493	Naftifine Hydrochloride	Antifungal
CHEMBL1200938	Methysergide Maleate	Anti-migraine
CHEMBL1200964	Amitriptyline Hydrochloride	Antidepressant
CHEMBL1409	Fluvoxamine Maleate	SSRI
CHEMBL1511	Estradiol Valerate	Hormone
CHEMBL1525	Permethrin	Insecticide
CHEMBL1670	Mitotane	Antineoplastic
CHEMBL1717	Ticlopidine Hydrochloride	Antiplatelet
CHEMBL405110	Methylene Blue	Multiple
CHEMBL421701	Dithiazanine Iodide	Anthelmintic
CHEMBL456	Ethacrynic Acid	Diuretic
CHEMBL498847	Secnidazole	Antibiotic
CHEMBL590	Menadione	Vitamin K3
CHEMBL672	Fenofibrate	Lipid lowering
CHEMBL932	Dipyridamole	Antiplatelet

ChEMBL ID	Name	Type
CHEMBL1879463	Dactolisib	Small molecule (ATM/PI3K inhibitor)
CHEMBL249856	Enoximone	Small molecule

ChEMBL ID	Name	Type
CHEMBL3989870	Berzosertib	ATR/ATM inhibitor
CHEMBL5314413	Lartesertib	ATM inhibitor
CHEMBL11417	Streptonigrin	Antitumor
CHEMBL1256686	Calcimycin	Ionophore

Compound	Effect
KU-60019	Chemical inhibition
KU-55933	Chemical inhibition
2-(4-morpholinyl)-6-(1-thianthrenyl)-4-pyranone	Chemical inhibition

Attribute	Value
Expression Breadth	Ubiquitous
Total Present Calls	286
Max Expression Score	97.33

Tissue	Expression Score	Rank
Calcaneal tendon	97.33	1,250
Colonic epithelium	97.24	1,290
Corpus callosum	96.41	1,670
Lymph node	96.36	1,700
Bone marrow cell	96.26	1,750
Body of pancreas	95.70	2,010
Adrenal tissue	95.39	2,150
Sural nerve	95.28	2,200
Tonsil	95.10	2,290
Tendon	94.86	2,400
Superficial temporal artery	94.55	2,540
Ventricular zone	94.50	2,570
Buccal mucosa cell	94.38	2,620
Leukocyte	94.37	2,630
Spleen	94.31	2,650
Monocyte	94.26	2,680
Mononuclear cell	94.26	2,670
Granulocyte	94.24	2,680
Left ovary	93.84	2,870
Male germ line stem cell (testis)	93.75	2,910
Right ovary	93.70	2,940
Pituitary gland	93.10	3,220
C1 cervical spinal cord	93.01	3,260
Nasopharynx epithelium	92.81	3,350
Trigeminal ganglion	92.74	3,390
Ganglionic eminence	92.73	3,390
Bone marrow	92.60	3,450
Blood	92.52	3,490
Vermiform appendix	92.50	3,500
Ovary	92.48	3,510

Dataset ID	Description	Cells
E-HCAD-31	Pancreatic islets cells (healthy & T2D)	38,217
E-MTAB-9221	COVID-19 whole blood	27,943
E-MTAB-8911	Chronic Graft-Versus-Host Disease	19,075
E-MTAB-11011	B cells in COVID-19	15,100
E-MTAB-9067	Fetal liver/bone marrow haematopoiesis	5,865
E-CURD-97	CD4+ Treg/Tmem cells	1,677
E-MTAB-7303	iPSC-dopamine neurons (Parkinson's)	123
E-MTAB-6386	PBMC-derived B cells	117

Disease	Classification	Inheritance	Evidence
Ataxia telangiectasia (OMIM:208900)	Definitive	Autosomal recessive	Multiple sources
Hereditary breast carcinoma (OMIM:114480)	Definitive	Autosomal dominant	Ambry Genetics
Prostate cancer (MONDO:0008315)	Moderate	Autosomal dominant	Ambry Genetics
Sarcoma (MONDO:0005089)	Moderate	Autosomal dominant	Genomics England
Hereditary nonpolyposis colon cancer	Limited	Autosomal dominant	Ambry Genetics
Gastric carcinoma (MONDO:0004950)	Limited	Autosomal dominant	Ambry Genetics

Orphanet ID	Disease Name	Type	Gene Count
100	Ataxia-telangiectasia	Disease	1
370109	Ataxia-telangiectasia variant	Disease	1
145	Hereditary breast and/or ovarian cancer syndrome	Disease	15
227535	Hereditary breast cancer	Disease	10
1331	Familial prostate cancer	Disease	15
440437	Familial colorectal cancer Type X	Disease	10
52416	Mantle cell lymphoma	Disease	3
67038	B-cell chronic lymphocytic leukemia	Disease	10

HPO ID	Phenotype
HP:0001251	Ataxia
HP:0002073	Progressive cerebellar ataxia
HP:0000524	Conjunctival telangiectasia
HP:0000252	Microcephaly
HP:0002721	Immunodeficiency
HP:0002720	Decreased circulating IgA concentration
HP:0004315	Decreased circulating IgG concentration
HP:0001888	Decreased total lymphocyte count
HP:0005403	Decreased total T cell count
HP:0005374	Cellular immunodeficiency
HP:0002205	Recurrent respiratory infections
HP:0002110	Bronchiectasis
HP:0001909	Leukemia
HP:0006721	Acute lymphoblastic leukemia
HP:0002665	Lymphoma
HP:0003002	Breast carcinoma
HP:0002664	Neoplasm
HP:0000819	Diabetes mellitus
HP:0001952	Glucose intolerance
HP:0003220	Abnormality of chromosome stability
HP:0000639	Nystagmus
HP:0001260	Dysarthria
HP:0001350	Slurred speech
HP:0002080	Intention tremor
HP:0001337	Tremor
HP:0001332	Dystonia
HP:0001266	Choreoathetosis
HP:0002075	Dysdiadochokinesis
HP:0002167	Abnormal speech pattern
HP:0004322	Short stature
HP:0001508	Failure to thrive
HP:0000823	Delayed puberty
HP:0000134	Female hypogonadism
HP:0000035	Abnormal testis morphology
HP:0007495	Prematurely aged appearance
HP:0002216	Premature graying of hair
HP:0000778	Hypoplasia of the thymus
HP:0006254	Elevated alpha-fetoprotein
HP:0002910	Elevated hepatic transaminase
HP:0000957	Cafe-au-lait spot
HP:0001288	Gait disturbance
HP:0002540	Inability to walk
HP:0001315	Reduced tendon reflexes
HP:0003202	Skeletal muscle atrophy
HP:0002861	Melanoma
HP:0006725	Pancreatic adenocarcinoma
HP:0002894	Neoplasm of the pancreas
HP:0002893	Pituitary adenoma
HP:0001402	Hepatocellular carcinoma
HP:0003006	Neuroblastoma

Study ID	Trait	P-value	Mapped Gene
GCST010304	Cutaneous malignant melanoma	2.0e-21	ATM
GCST010303	Nevus count or melanoma	4.0e-21	ATM
GCST90002381	Eosinophil count	3.0e-29	ATM
GCST90002382	Eosinophil percentage	8.0e-21	ATM
GCST010002	Refractive error	4.0e-19	C11orf65
GCST004624	Sum eosinophil basophil counts	6.0e-14	ATM
GCST004606	Eosinophil count	3.0e-13	ATM
GCST006462	Uterine fibroids	3.0e-12	ATM
GCST005996	Red blood cell count	1.0e-11	ATM
GCST008366	Leukocyte telomere length	7.0e-12	C11orf65
GCST007505	Nevus count or melanoma	8.0e-11	C11orf65, ATM
GCST90000032	Myeloproliferative neoplasms	2.0e-10	ATM
GCST90002388	Lymphocyte count	6.0e-10	C11orf65, ATM
GCST000927	Response to metformin (T2D)	3.0e-09	C11orf65
GCST001267	Melanoma	3.0e-09	ATM
GCST004710	Renal cell carcinoma	9.0e-09	ATM
GCST006085	Prostate cancer	8.0e-09	ATM
GCST004600	Eosinophil percentage	6.0e-09	ATM
GCST009856	Leukocyte telomere length	1.0e-08	ATM
GCST002318	Rheumatoid arthritis	1.0e-08	-