Files

5.4 KiB

title, task, lineage_type, upstream_source, upstream_sha, imported_at, prompt_class, upstream_changes, author, validated
title task lineage_type upstream_source upstream_sha imported_at prompt_class upstream_changes author validated
Report Template: Immunotherapy Response Prediction import https://github.com/mims-harvard/ToolUniverse/blob/e2520a96/skills/tooluniverse-immunotherapy-response-prediction/REPORT_TEMPLATE.md e2520a96 2026-06-26 prompt accepted upstream false

Report Template: Immunotherapy Response Prediction

Save report as immunotherapy_response_prediction_{cancer_type}.md

# Immunotherapy Response Prediction Report

## Executive Summary
[2-3 sentence summary: cancer type, ICI Response Score, recommendation]

## ICI Response Score: XX/100
**Response Likelihood: [HIGH/MODERATE/LOW]**
**Confidence: [HIGH/MODERATE/LOW]**
**Expected ORR: XX-XX%**

### Score Breakdown
| Component | Value | Score | Max |
|-----------|-------|-------|-----|
| TMB | XX mut/Mb | XX | 30 |
| MSI Status | MSI-H/MSS | XX | 25 |
| PD-L1 | XX% | XX | 20 |
| Neoantigen Load | XX est. | XX | 15 |
| Sensitivity Bonus | +XX | XX | 10 |
| Resistance Penalty | -XX | XX | -20 |
| **TOTAL** | | **XX** | **100** |

## Patient Profile
- **Cancer Type**: [cancer]
- **Mutations**: [list]
- **TMB**: XX mut/Mb [classification]
- **MSI Status**: [MSI-H/MSS/Unknown]
- **PD-L1**: XX% [scoring method]

## Biomarker Analysis

### TMB Analysis
[TMB classification, cancer-specific context, FDA TMB-H status]

### MSI/MMR Status
[MSI status, MMR gene mutations, FDA MSI-H approvals]

### PD-L1 Expression
[PD-L1 level, cancer-specific thresholds, scoring method]

### Neoantigen Burden
[Estimated neoantigen count, quality assessment, mutation types]

## Mutation Analysis

### Driver Mutations
[Analysis of each mutation - oncogenic role, ICI implications]

### Resistance Mutations
[Any STK11, PTEN, JAK1/2, B2M, KEAP1 etc. with penalties]

### Sensitivity Mutations
[Any POLE, PBRM1, DDR genes with bonuses]

## Immune Microenvironment
[Hot/cold classification, immune gene expression data]

## ICI Drug Recommendation

### Primary Recommendation
**[Drug name]** - [monotherapy/combination]
- Evidence: [FDA approval, trial data]
- Expected response: XX-XX%
- Key trial: [trial name/NCT#]

### Alternative Options
1. [Alternative 1] - [rationale]
2. [Alternative 2] - [rationale]

### Combination Strategies
[ICI+ICI, ICI+chemo, ICI+targeted recommendations]

## Clinical Evidence
[Key trials, response rates, PFS/OS data for this cancer + biomarker profile]

## Resistance Risk
- **Risk Level**: [LOW/MODERATE/HIGH]
- **Key Factors**: [list resistance mutations/mechanisms]
- **Mitigation**: [combination strategies]

## Monitoring Plan
- **Response assessment**: [schedule]
- **Biomarkers to track**: [ctDNA, imaging, labs]
- **irAE monitoring**: [schedule]
- **Resistance monitoring**: [when to suspect progression]

## Alternative Strategies (if ICI unlikely effective)
[Targeted therapy, chemotherapy, clinical trials]

## Evidence Grading
| Finding | Evidence Tier | Source |
|---------|-------------|--------|
| [finding 1] | T1 (FDA/Guidelines) | [source] |
| [finding 2] | T2 (Clinical trial) | [source] |

## Data Completeness
| Biomarker | Status | Impact |
|-----------|--------|--------|
| TMB | Provided/Estimated/Unknown | XX points |
| MSI | Provided/Unknown | XX points |
| PD-L1 | Provided/Unknown | XX points |
| Neoantigen | Estimated | XX points |
| Mutations | X provided | +/-XX points |

## Missing Data Recommendations
[What additional tests would improve prediction accuracy]

---
*Generated by ToolUniverse Immunotherapy Response Prediction Skill*
*Sources: OpenTargets, CIViC, FDA, DrugBank, PubMed, IEDB, HPA, cBioPortal*

Use Case Examples

Use Case 1: NSCLC with High TMB

Input: "NSCLC, TMB 25, PD-L1 80%, no STK11 mutation" Expected: ICI Score 70-85, HIGH response, pembrolizumab monotherapy recommended

Use Case 2: Melanoma with BRAF

Input: "Melanoma, BRAF V600E, TMB 15, PD-L1 50%" Expected: ICI Score 50-65, MODERATE response, discuss ICI vs BRAF-targeted

Use Case 3: MSI-H Colorectal

Input: "Colorectal cancer, MSI-high, TMB 40" Expected: ICI Score 80-95, HIGH response, pembrolizumab first-line

Use Case 4: Low Biomarker NSCLC

Input: "NSCLC, TMB 2, PD-L1 <1%, STK11 mutation" Expected: ICI Score 5-20, LOW response, chemotherapy preferred

Use Case 5: Bladder Cancer

Input: "Bladder cancer, TMB 12, PD-L1 10%, no resistance mutations" Expected: ICI Score 45-55, MODERATE response, ICI+chemo or maintenance

Use Case 6: Checkpoint Inhibitor Selection

Input: "Which ICI for NSCLC with PD-L1 90%?" Expected: Pembrolizumab monotherapy first-line, evidence from KEYNOTE-024

Completeness Checklist

  • Cancer type resolved to EFO ID
  • All mutations parsed and genes resolved
  • TMB classified with cancer-specific context
  • MSI/MMR status assessed
  • PD-L1 integrated (or flagged as unknown)
  • Neoantigen burden estimated
  • Resistance mutations checked (STK11, PTEN, JAK1/2, B2M, KEAP1)
  • Sensitivity mutations checked (POLE, PBRM1, DDR)
  • FDA-approved ICIs identified for this cancer
  • Clinical trial evidence retrieved
  • ICI Response Score calculated with component breakdown
  • Drug recommendation provided with evidence
  • Monitoring plan included
  • Alternative strategies for low responders
  • Evidence grading applied to all findings
  • Data completeness documented
  • Missing data recommendations provided
  • Report saved to file