By name: 'chromosomal-instability-agent' description: 'AI-powered analysis of chromosomal instability (CIN) signatures for cancer prognosis, immunotherapy response prediction, and therapeutic vulnerability identification.' measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. allowed-tools: - read_file - run_shell_command
Chromosomal Instability Agent
The Chromosomal Instability Agent analyzes CIN signatures to predict cancer prognosis, immunotherapy response, and therapeutic vulnerabilities. It integrates copy number alterations, aneuploidy scores, and CIN-related gene expression for comprehensive genomic instability assessment.
When to Use This Skill
- When assessing tumor aneuploidy and chromosomal instability levels.
- To predict prognosis based on CIN signatures.
- For identifying tumors vulnerable to CIN-targeted therapies (PARP, ATR, WEE1).
- When analyzing immune evasion mechanisms related to CIN.
- To stratify patients for immunotherapy based on CIN status.
Core Capabilities
CIN Scoring: Calculate comprehensive CIN scores from copy number data.
Aneuploidy Quantification: Measure arm-level and focal copy number alterations.
CIN Gene Expression: Analyze CIN70 and other transcriptional signatures.
Immune Correlation: Assess CIN-immune microenvironment relationships.
Therapeutic Vulnerability: Identify CIN-targeted treatment options.
Prognostic Modeling: Predict outcomes based on CIN signatures.
CIN Metrics
| Metric | Calculation | Interpretation |
|---|---|---|
| Aneuploidy score | Arm-level alterations | Chromosome-level CIN |
| SCNA burden | Total CNV alterations | Overall instability |
| Weighted GII | Fraction altered genome | Focal vs broad changes |
| CIN70 | 70-gene signature | Transcriptional CIN |
| WGII | Weighted genome instability | Comprehensive score |
CIN70 Signature Genes
Core genes reflecting CIN phenotype:
- Mitotic checkpoint: BUB1, BUBR1, MAD2L1
- Kinetochore: CENPA, CENPF, NDC80
- DNA replication: MCM2-7, ORC1
- Cell cycle: CCNB1, CCNB2, CDK1, PLK1
- Chromosome segregation: AURKB, KIF2C, KIF11
Workflow
Input: Copy number data (segments), gene expression, mutation data.
CNV Analysis: Calculate arm-level and focal alterations.
Signature Scoring: Compute CIN70 and other transcriptional signatures.
Integration: Combine DNA and RNA-based CIN metrics.
Immune Analysis: Correlate CIN with TME composition.
Vulnerability Assessment: Identify targetable dependencies.
Output: CIN scores, prognosis, treatment recommendations.
Example Usage
User: "Analyze chromosomal instability in this breast cancer sample and identify treatment vulnerabilities."
Agent Action:
python3 Skills/Oncology/Chromosomal_Instability_Agent/cin_analyzer.py \
--cnv_segments tumor_cnv.tsv \
--expression rnaseq_tpm.tsv \
--mutations somatic.maf \
--tumor_type breast_cancer \
--signatures cin70,cin25 \
--output cin_report/
CIN and Immune Evasion
High CIN Associates With:
- Reduced immune infiltration
- Lower checkpoint inhibitor response
- Increased immune evasion
- cGAS-STING activation (paradoxical)
Mechanisms:
- Loss of tumor suppressors on chromosome arms
- Chronic inflammatory signaling
- Aneuploidy-induced stress responses
- Subclonal diversification
Therapeutic Vulnerabilities
| Target | Agents | CIN Context |
|---|---|---|
| PARP | Olaparib, etc. | High CIN + HRD |
| ATR | Berzosertib | Replication stress |
| WEE1 | Adavosertib | G2/M dependency |
| CHK1 | Prexasertib | Cell cycle checkpoint |
| KIF11 | Ispinesib | Mitotic dependency |
| Aurora kinases | Alisertib | Mitotic errors |
CIN-Based Patient Stratification
| CIN Level | Prognosis | ICI Response | Alternative Therapy |
|---|---|---|---|
| Low | Better | Better | Standard care |
| Intermediate | Variable | Variable | Combination therapy |
| High | Poor | Poor | CIN-targeted agents |
| Extreme | Very poor | Immune desert | Chemotherapy |
AI/ML Components
CIN Score Prediction:
- Random forest on CNV features
- Expression-based CIN inference
- Multi-modal integration
Prognosis Modeling:
- Cox regression with CIN features
- Cancer-type specific models
- Integration with clinical variables
Therapeutic Matching:
- GDSC/CCLE drug sensitivity
- CIN-drug response correlations
- Combination predictions
Pan-Cancer CIN Patterns
| Cancer Type | Typical CIN Level | Driver Events |
|---|---|---|
| Ovarian HGSOC | Very high | TP53, BRCA |
| Triple-neg breast | High | TP53, PI3K |
| Colorectal MSS | Moderate-high | APC, TP53 |
| Colorectal MSI | Low | MMR deficiency |
| Thyroid (PTC) | Low | BRAF, RAS |
| Melanoma | Moderate | BRAF, NRAS |
Prerequisites
- Python 3.10+
- GISTIC2 or similar for CNV analysis
- Gene signature databases
- Survival analysis packages
Related Skills
- HRD_Analysis_Agent - For HR-specific instability
- Pan_Cancer_MultiOmics_Agent - For pan-cancer context
- Tumor_Clonal_Evolution_Agent - For evolutionary dynamics
Research Applications
- Biomarker Development: CIN as predictive marker
- Drug Development: CIN-targeted therapy trials
- Evolution Studies: Track CIN changes over time
- Resistance Mechanisms: CIN and drug resistance
Author
AI Group - Biomedical AI Platform