Provide a comprehensive cross-database identifier and functional mapping reference for human CDK6. 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 CDK6. 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
DatabaseIdentifierNotes HGNC IDHGNC:1777Approved HGNC SymbolCDK6Approved symbol HGNC Namecyclin dependent kinase 6Full name Ensembl GeneENSG00000105810Human genome NCBI Entrez Gene1021 OMIM603368Gene/locus AliasesPLSTIRE, MCPH12Previous symbols Locus Groupprotein-coding gene Gene GroupCyclin dependent kinases Genomic Location AttributeValue Chromosome7 Cytogenetic Band7q21.2 Start Position92,604,921 End Position92,836,591 StrandMinus (-) Genomic AccessionNC_000007.14 …

Transcript ID	Biotype	Start	End	Notes
ENST00000265734	protein_coding	92,604,921	92,833,917	Canonical
ENST00000424848	protein_coding	92,604,921	92,836,573
ENST00000906279	protein_coding	92,612,104	92,836,591
ENST00000906280	protein_coding	92,609,875	92,834,095
ENST00000906281	protein_coding	92,611,541	92,833,959
ENST00000906282	protein_coding	92,613,905	92,835,935
ENST00000906283	protein_coding	92,614,452	92,833,954
ENST00000930022	protein_coding	92,614,452	92,833,959
ENST00000961497	protein_coding	92,614,467	92,833,933
ENST00000467166	retained_intron	92,614,714	92,618,277	Non-coding
ENST00000473078	retained_intron	92,671,235	92,725,710	Non-coding
ENST00000491250	protein_coding_CDS_not_defined	92,833,403	92,835,297

RefSeq ID	Type	Status	MANE Select
NM_001145306	mRNA	REVIEWED	✓ Yes
NM_001259	mRNA	REVIEWED	No
NP_001138778	protein	REVIEWED	✓ (MANE)
NP_001250	protein	REVIEWED	No

Exon ID	Start	End	Strand
ENSE00001337042	92,833,873	92,833,917	-
ENSE00001132651	92,833,091	92,833,690	-
ENSE00000877375	92,774,696	92,774,831	-
ENSE00000877376	92,725,626	92,725,793	-
ENSE00001764561	92,671,426	92,671,535	-
ENSE00000705202	92,623,036	92,623,086	-
ENSE00000705199	92,618,072	92,618,207	-
ENSE00001132644	92,604,921	92,615,286	-

RefSeq ID	Status	MANE
NP_001138778	REVIEWED	✓
NP_001250	REVIEWED

InterPro ID	Name	Type
IPR028788	CDK6	Family
IPR050108	CDK	Family
IPR000719	Prot_kinase_dom	Domain
IPR011009	Kinase-like_dom_sf	Homologous superfamily
IPR008271	Ser/Thr_kinase_AS	Active site
IPR017441	Protein_kinase_ATP_BS	Binding site

CDK6 Gene Complete Identifier and Functional Mapping Reference

Structured Data Sources

Database	Identifier	Notes
HGNC ID	HGNC:1777	Approved
HGNC Symbol	CDK6	Approved symbol
HGNC Name	cyclin dependent kinase 6	Full name
Ensembl Gene	ENSG00000105810	Human genome
NCBI Entrez Gene	1021
OMIM	603368	Gene/locus
Aliases	PLSTIRE, MCPH12	Previous symbols
Locus Group	protein-coding gene
Gene Group	Cyclin dependent kinases

Attribute	Value
Chromosome	7
Cytogenetic Band	7q21.2
Start Position	92,604,921
End Position	92,836,591
Strand	Minus (-)
Genomic Accession	NC_000007.14
Gene Span	~232 kb

PDB ID	Method	Resolution	Description
9PE8	X-ray	1.80 Å	CDK6 with PF-07220060
1BLX	X-ray	1.90 Å	P19INK4D/CDK6 complex
6OQO	X-ray	1.98 Å	CDK6 with Cpd24
9D8U	X-ray	2.00 Å	CDK6 with atirmociclib
9PE7	X-ray	2.05 Å	CDK6 with compound 6
5L2S	X-ray	2.27 Å	CDK6 with Abemaciclib
4AUA	X-ray	2.31 Å	Liganded CDK6
5L2T	X-ray	2.37 Å	CDK6 with Ribociclib
3NUP	X-ray	2.60 Å	Monomeric CDK6 with inhibitor
3NUX	X-ray	2.70 Å	Monomeric CDK6 with inhibitor
4EZ5	X-ray	2.70 Å	CDK6 with inhibitor
6OQL	X-ray	2.71 Å	CDK6 with Cpd13
5L2I	X-ray	2.75 Å	CDK6 with Palbociclib
8I0M	X-ray	2.78 Å	CDK6 with inhibitor
2F2C	X-ray	2.80 Å	CDK6-Vcyclin with aminopurvalanol
1BI8	X-ray	2.80 Å	CDK6-P19INK4D complex
4TTH	X-ray	2.90 Å	CDK6/Vcyclin with inhibitor
1G3N	X-ray	2.90 Å	P18INK4C-CDK6-K-cyclin ternary
1XO2	X-ray	2.90 Å	CDK6 with fisetin
2EUF	X-ray	3.00 Å	CDK6-Vcyclin with PD0332991
1JOW	X-ray	3.10 Å	CDK6 with viral cyclin
1BI7	X-ray	3.40 Å	CDK6-P16INK4A complex

Organism	Gene ID	Symbol	Biotype
Mouse (Mus musculus)	ENSMUSG00000040274	Cdk6	protein_coding
Rat (Rattus norvegicus)	ENSRNOG00000009258	Cdk6	protein_coding
Zebrafish (Danio rerio)	ENSDARG00000070228	cdk6	protein_coding
Drosophila melanogaster	No direct ortholog	-	CDK family members exist
C. elegans	No direct ortholog	-	CDK family members exist
S. cerevisiae	No direct ortholog	-	CDK family members exist

Classification	Count
Pathogenic	1
Likely Pathogenic	0
Uncertain Significance (VUS)	14
Likely Benign	11
Benign	16
Conflicting	1
Other/No Classification	10

ClinVar ID	HGVS Notation	Protein Change
2407985	c.700G>A	p.Val234Met
2479703	c.535G>T	p.Val179Leu
2532596	c.484G>A	p.Ala162Thr
2536616	c.659G>A	p.Arg220His
2537802	c.697G>A	p.Asp233Asn
3141600	c.160A>G	p.Met54Val
3141601	c.25G>C	p.Ala9Pro
3141602	c.395G>C	p.Gly132Ala
3141603	c.493G>A	p.Gly165Ser
434659	c.775G>A	p.Ala259Thr

Variant	Effect	Delta Score
7:92614796:G>C	donor_gain	0.99
7:92614991:T>A	donor_gain	0.99
7:92614780:A>AC	donor_gain	0.95
7:92614791:A>C	donor_gain	0.94
7:92614748:A>AC	donor_gain	0.93
7:92614785:A>C	donor_gain	0.93
7:92614807:A>AC	donor_gain	0.91
7:92614814:A>AC	donor_gain	0.83
7:92614815:C>CC	donor_gain	0.83
7:92615091:C>CT	donor_gain	0.76
7:92615037:T>TA	donor_gain	0.75
7:92614904:T>C	acceptor_gain	0.73
7:92610181:T>A	donor_gain	0.73
7:92610174:G>C	donor_gain	0.72
7:92614950:A>C	donor_gain	0.69
7:92615006:AG>A	donor_gain	0.68
7:92615004:AGAG>A	donor_gain	0.63
7:92614753:CAAA>C	donor_gain	0.62
7:92608580:AGCG>A	donor_gain	0.61
7:92615049:T>TA	donor_gain	0.61

Position Region	Sample Variants	AlphaMissense Class
C-terminal (310-326)	A326V, T325I, N324K, etc.	likely_benign (scores 0.05-0.21)
Mid-protein (200-309)	Various	likely_benign to ambiguous
N-terminal/kinase core	Higher pathogenicity scores	ambiguous to likely_pathogenic

Pathway ID	Pathway Name	Disease Pathway
R-HSA-69231	Cyclin D associated events in G1	No
R-HSA-2559580	Oxidative Stress Induced Senescence	No
R-HSA-2559582	Senescence-Associated Secretory Phenotype (SASP)	No
R-HSA-2559585	Oncogene Induced Senescence	No
R-HSA-8934593	Regulation of RUNX1 Expression and Activity	No
R-HSA-9754119	Drug-mediated inhibition of CDK4/CDK6 activity	No
R-HSA-9630794	Evasion of OIS Due to Defective p16INK4A binding	Yes
R-HSA-9632700	Evasion of OSIS Due to Defective p16INK4A binding	Yes
R-HSA-9661069	Defective binding of RB1 mutants to E2F1,2,3	Yes

GO ID	Term
GO:0004693	cyclin-dependent protein serine/threonine kinase activity
GO:0005524	ATP binding
GO:0030332	cyclin binding
GO:0098770	FBXO family protein binding
GO:0106310	protein serine kinase activity

GO ID	Term
GO:0000307	cyclin-dependent protein kinase holoenzyme complex
GO:0097131	cyclin D1-CDK6 complex
GO:0097132	cyclin D2-CDK6 complex
GO:0097133	cyclin D3-CDK6 complex
GO:0005634	nucleus
GO:0005654	nucleoplasm
GO:0005737	cytoplasm
GO:0005813	centrosome
GO:0005829	cytosol
GO:0001726	ruffle

GO ID	Term
GO:0000082	G1/S transition of mitotic cell cycle
GO:0051726	regulation of cell cycle
GO:0051301	cell division
GO:0000122	negative regulation of transcription by RNA polymerase II
GO:0001954	positive regulation of cell-matrix adhesion
GO:0003323	type B pancreatic cell development
GO:0006974	DNA damage response
GO:0007165	signal transduction
GO:0007219	Notch signaling pathway
GO:0008285	negative regulation of cell population proliferation
GO:0009615	response to virus
GO:0010389	regulation of G2/M transition of mitotic cell cycle
GO:0010468	regulation of gene expression
GO:0010628	positive regulation of gene expression
GO:0014002	astrocyte development
GO:0021542	dentate gyrus development
GO:0021670	lateral ventricle development
GO:0033077	T cell differentiation in thymus
GO:0042063	gliogenesis
GO:0045786	negative regulation of cell cycle

UniProt ID	Gene	Score	Description
P42771	CDKN2A	999	p16INK4a - CDK inhibitor
Q96S94	CDKN2C	999	p18INK4c - CDK inhibitor
P24385	CCND1	998	Cyclin D1
P42772	CDKN2B	998	p15INK4b - CDK inhibitor
P30279	CCND2	997	Cyclin D2
P30281	CCND3	997	Cyclin D3
P42773	CDKN2D	997	p19INK4d - CDK inhibitor
P55273	CDKN2D	997	CDK inhibitor
P38936	CDKN1A	995	p21Cip1 - CDK inhibitor
P20248	CCNA2	994	Cyclin A2
P78396	CCNA1	987	Cyclin A1
P46527	CDKN1B	984	p27Kip1 - CDK inhibitor
P11802	CDK4	983	Cyclin-dependent kinase 4
P24941	CDK2	963	Cyclin-dependent kinase 2
P24864	CCNE1	885	Cyclin E1
Q16543	CDC37	883	Hsp90 co-chaperone
Q16667	CDKN3	877	CDK-associated phosphatase
P40763	STAT3	872	Signal transducer
Q01094	E2F1	856	E2F transcription factor 1
P06400	RB1	841	Retinoblastoma protein
P14635	CCNB1	839	Cyclin B1
P30304	CDC25A	806	Cell division cycle 25A
P49918	CDKN1C	782	p57Kip2 - CDK inhibitor
P60484	PTEN	774	Phosphatase and tensin homolog
P04637	TP53	771	Tumor protein p53

Partner Gene	Interaction Type	Confidence
CCND3	physical association	0.97
CDKN2C	physical association	0.97
CDKN2D	physical association	0.96
CDKN2A	direct interaction	0.95
CDKN2B	physical association	0.92
CCND1	association	0.88

UniProt	Identity	Bitscore	Description
P11802 (CDK4)	97.0%	599	Human CDK4
P30285 (CDK4)	98.7%	603	Mouse Cdk4
P35426 (CDK4)	98.7%	605	Rat Cdk4
Q64261 (CDK6)	96.3%	632	Mouse Cdk6
P97874	96.7%	2496	High similarity

UniProt	Similarity	Description
P11802 (CDK4)	0.9997	Human CDK4
P50750 (CDK9)	0.9999	Human CDK9
P50613 (CDK7)	0.9998	Human CDK7
Q03147 (CDK7)	0.9998	Mouse Cdk7
Q641Z4 (CDK6)	1.0000	Rat Cdk6

TF Gene	Regulation Type	Confidence
MYC	Activation	Low
NFKB2	Activation	-
NFKB	Activation	Low
RELA	Activation	-
GATA1	Repression	-
GLI3	Repression	-
NANOG	Repression	High
NR3C1	Repression	-
PAX6	Repression	High
SMAD6	Repression	High
SP1	Repression	High
TCF3	Repression	-
ZNF382	Repression	Low
AR	Unknown	-
MAFK	Unknown	High
SPI1	Unknown	High
ID1	Unknown	Low
KDM2A	Unknown	Low
MITF	Unknown	Low
MYB	Unknown	Low
RBPJ	Unknown	Low
RUNX1	Unknown	Low
STAT5B	Unknown	Low
TP53	Unknown	Low
TRIP6	Unknown	-

Target ID	Target Name	Type
CHEMBL2508	Cyclin-dependent kinase 6	SINGLE PROTEIN
CHEMBL2111455	CDK6/cyclin D1	PROTEIN COMPLEX
CHEMBL2111448	CDK6/cyclin D3	PROTEIN COMPLEX
CHEMBL3301386	CDK6/cyclin D2	PROTEIN COMPLEX
CHEMBL3885553	Cyclin-dependent kinase 4/6	PROTEIN FAMILY

ChEMBL ID	Drug Name	Type	Mechanism
CHEMBL189963	Palbociclib (Ibrance)	Small molecule	CDK4/6 inhibitor
CHEMBL3301610	Abemaciclib (Verzenio)	Small molecule	CDK4/6 inhibitor
CHEMBL3545110	Ribociclib (Kisqali)	Small molecule	CDK4/6 inhibitor
CHEMBL1078178	Momelotinib	Small molecule	JAK/CDK6 inhibitor
CHEMBL1336	Sorafenib	Small molecule	Multi-kinase inhibitor
CHEMBL2028663	Dabrafenib	Small molecule	BRAF/CDK6 inhibitor

ChEMBL ID	Drug Name	Type
CHEMBL2103840	Dinaciclib	Small molecule
CHEMBL3904602	Lerociclib	Small molecule
CHEMBL428690	Alvocidib (Flavopiridol)	Small molecule
CHEMBL50	Quercetin	Natural product
CHEMBL522892	Dovitinib	Small molecule
CHEMBL603469	Lestaurtinib	Small molecule

ChEMBL ID	Drug Name
CHEMBL14762	Seliciclib (Roscovitine)
CHEMBL1944698	Zotiraciclib
CHEMBL31574	Fisetin

Attribute	Value
Expression Pattern	Ubiquitous
Total Tissues with Expression	262
Max Expression Score	97.02
Average Expression Score	75.20
Gold Quality Conditions	273

Rank	Tissue (UBERON)	Expression Score	Quality
1	Adrenal tissue	97.02	Gold
2	Trabecular bone tissue	94.70	Gold
3	Pylorus	94.25	Gold
4	Caput epididymis	93.50	Gold
5	Cardia of stomach	92.26	Gold
6	Cartilage tissue	92.05	Gold
7	Mucosa of paranasal sinus	91.10	Gold
8	Nipple	90.80	Gold
9	Parietal pleura	90.43	Gold
10	Oral cavity	90.36	Gold
11	Mucosa of sigmoid colon	90.21	Gold
12	Inferior vagus X ganglion	88.96	Gold
13	Bone marrow	88.90	Gold
14	Renal medulla	88.48	Gold
15	Colonic epithelium	88.20	Gold
16	Pleura	88.18	Gold
17	Skin of hip	88.15	Gold
18	Cauda epididymis	88.01	Gold
19	Colonic mucosa	87.96	Gold
20	Male germ line stem cell in testis	87.70	Gold
21	Upper leg skin	87.47	Gold
22	Visceral pleura	87.43	Gold
23	Mammalian vulva	87.36	Gold
24	Jejunal mucosa	86.84	Gold
25	Superior surface of tongue	86.65	Gold
26	Mammary duct	86.56	Gold
27	Tibia	86.17	Gold
28	Pigmented layer of retina	85.91	Gold
29	Retina	85.89	Gold
30	Ventricular zone	85.70	Gold

Dataset ID	Description	Cells
E-HCAD-8	T cell activation atlas	126,870
E-MTAB-8495	Human biliary tree	160,459
E-CURD-77	COVID-19 lymphocyte atlas	62,076
E-HCAD-6	CD34+ bone marrow cells	34,596
E-MTAB-8884	CMML stem cells	9,386
E-MTAB-10432	Post-MI bone vascular niche	8,228
E-MTAB-9388	Human gastrulation atlas	1,195
E-GEOD-75140	Cerebral organoids	734
E-ENAD-20	PDX model (BRAF/MEK)	674
E-GEOD-86618	IPF lung epithelium	540
E-GEOD-100618	Haemopoietic progenitors	415
E-MTAB-4850	Antigen-specific T cells	63

Disease	Disease ID	Inheritance	Evidence
Primary Microcephaly 12, Autosomal Recessive (MCPH12)	OMIM:616080	AR	Limited (GenCC)
Autosomal Recessive Primary Microcephaly	ORPHANET:2512	AR	Supportive (Orphanet)

HPO ID	Phenotype Term
HP:0011451	Primary microcephaly
HP:0000252	Microcephaly
HP:0000007	Autosomal recessive inheritance
HP:0001263	Global developmental delay
HP:0001256	Mild intellectual disability
HP:0010864	Severe intellectual disability
HP:0001510	Growth delay
HP:0004322	Short stature
HP:0001250	Seizure
HP:0001347	Hyperreflexia
HP:0001274	Agenesis of corpus callosum
HP:0002119	Ventriculomegaly
HP:0001302	Pachygyria
HP:0009879	Simplified gyral pattern
HP:0002282	Gray matter heterotopia
HP:0007333	Hypoplasia of the frontal lobes
HP:0000340	Sloping forehead
HP:0000582	Upslanted palpebral fissure
HP:0000219	Thin upper lip vermilion
HP:0000076	Vesicoureteral reflux
HP:0000122	Unilateral renal agenesis
HP:0003103	Abnormal cortical bone morphology
HP:0003577	Congenital onset

Trait	Study ID	P-value
Basophil count	GCST90002379	1×10⁻¹⁴¹
Appendicular lean mass	GCST90000025	4×10⁻¹⁰⁶
Height	GCST000817	8×10⁻⁴⁷
Myeloid white cell count	GCST004626	3×10⁻⁷³
White blood cell count	GCST005973	2×10⁻⁷⁰
Sum neutrophil eosinophil counts	GCST004613	4×10⁻⁶⁴
Granulocyte count	GCST004614	2×10⁻⁶⁵
Monocyte count	GCST004625	4×10⁻⁵⁹
Neutrophil count	GCST004629	1×10⁻⁵⁸
Basophil percentage	GCST90002380	1×10⁻⁵⁴
Eosinophil count	GCST90002381	5×10⁻⁴⁹
Neutrophil count	GCST005974	4×10⁻⁴⁶
Hip circumference (BMI adj)	GCST012227	4×10⁻³⁷
Pulse pressure	GCST007269	2×10⁻³²
Basophil count	GCST004618	5×10⁻³¹
Height	GCST008839	6×10⁻³⁰
Monocyte percentage	GCST004609	6×10⁻²⁸
Granulocyte percentage	GCST004608	2×10⁻²⁸
Lymphocyte percentage	GCST004632	2×10⁻²⁷
Heel bone mineral density	GCST006979	5×10⁻²⁷
Pulse pressure	GCST007096	6×10⁻²⁵
Hip circumference (BMI adj)	GCST012227	2×10⁻²⁹
Waist circumference (BMI adj)	GCST012226	1×10⁻¹⁹
Body fat distribution	GCST007294	3×10⁻¹⁹
Eosinophil count	GCST004606	2×10⁻¹⁸
Height	GCST008163	4×10⁻¹⁸
Monocyte count	GCST005977	7×10⁻¹⁸
Eosinophil count	GCST005975	5×10⁻¹⁷
Body fat distribution (leg)	GCST007295	6×10⁻¹⁷
White blood cell count	GCST004610	2×10⁻⁶⁵

Category	Count
Total database cross-references	~16,000+
Ensembl transcripts	12
RefSeq transcripts (human)	4 (2 mRNA, 2 protein)
PDB structures	22
ClinVar variants	53
SpliceAI predictions	2,308
AlphaMissense predictions	2,126
GO annotations	48
Reactome pathways	9
STRING interactions	6,068+
IntAct interactions	281+
ChEMBL targeting molecules	100+
FDA-approved drugs	6
GWAS associations	132
HPO phenotypes	23
Expression tissues	262
Single-cell datasets	12