Use cases library

Each use case below shows a complete K Pro workflow from question to result. Prompts are copy-pasteable. Follow them in sequence: each step builds on the context of the previous one.

Use case 1: Pan-cancer target prioritization

Goal. Identify cancer indications where a candidate gene is overexpressed, then check whether that overexpression correlates with patient outcomes. Useful for ADC target prioritization.

Datasets used. TCGA (pan-cancer).

Prerequisites. A candidate gene (HGNC symbol). The example uses NECTIN4.

Step 1: Pan-cancer ranking

Prompt:

Compare the expression of NECTIN4 across all TCGA cancer types. Show me a pan-cancer overview ranked by median expression level.

Expected result: A ranked table or visualization of NECTIN4 expression across TCGA indications.

Step 2: Survival correlation in top indications

Prompt:

For the top 3 indications with highest NECTIN4 overexpression, show me the correlation between NECTIN4 expression and overall survival

Expected result: Survival analyses for each of the top 3 indications.

Tip: Specify "compared to healthy counterparts" in Step 1 for more meaningful target prioritization.

A-S-R-T-C breakdown for Step 1: Compare [A] NECTIN4 [S] at Bulk RNA level [R] as a ranked table [T] across all TCGA cancer types [C].

Next steps to explore: Drill into single-cell expression in the top indication (use the Chain of Thought sequence in the Prompting guide).

---

Use case 2: Biomarker exploration

Goal. Characterize a TCGA cohort across clinical and molecular variables, then identify the worst-prognosis subgroup and its molecular features. Useful for biomarker hypothesis generation.

Datasets used. TCGA-LUAD.

Prerequisites. None.

Step 1: Literature summary

Prompt:

I have a drug targeting both EP2 and EP4 in cancer. Identify most relevant genes for the prostaglandin pathway activity in oncology that I could use as a biomarker.

Expected result: A comprehensive stratification panel covering gene biosynthesis, receptor expression, degradation and transport.

Step 2: Biomarker exploration using BulkRNA

Prompt:

Which TCGA cancer indication expresses the highest PTGS2 expression, and what is the relative expression level compared to other indications?

Expected result: Gene expression across cancer types in TCGA datasets with population summary.

Tip: List the specific variables you want characterized upfront in Step 1 — K Pro works best when it knows exactly what you're looking for.

Step 3: Biomarker Exploration using ScRNA

Prompt:

Show me the percentage of cells expressing PTGS2 per patient per cell type across mosaic indications?

Expected result: Gene expression across cancer types in TCGA datasets with population summary.

Tip: List the specific variables you want characterized upfront in Step 1 — K Pro works best when it knows exactly what you're looking for.

---

Use case 3: Literature review on a drug target

Goal. Build an evidence base for a candidate target by surveying recent publications and probing for predictive-biomarker evidence. Useful for in-licensing or target validation due-diligence.

Datasets used. PubMed (via Consensus).

Prerequisites. A target gene + indication. The example uses TROP2 in triple-negative breast cancer.

Step 1: Target landscape in indication

Prompt:

Find publications investigating TROP2 as a therapeutic target in triple-negative breast cancer. Include any data on TROP2 expression levels and their correlation with clinical outcomes.

Expected result: A curated list of relevant publications with key findings, expression data, and clinical correlations.

Step 2: Predictive-biomarker evidence

Prompt:

Based on these publications, what is the evidence for using TROP2 expression as a patient selection biomarker for ADC therapies?

Expected result: A synthesis of biomarker-relevant evidence from the publications surfaced in Step 1.

Tip: Combine the target name with a specific indication AND the type of evidence you need (expression, outcomes, mechanisms). Vague prompts like "tell me about TROP2" return overly broad results.

---

Use case 4: Cross-dataset discovery linking genomics, immunotherapy response, and literature

Goal. Identify genes that are both statistically associated with a mutation and an immunotherapy outcome, cross-reference with literature on the relevant biology, and then check spatial expression patterns. Useful for novel-mechanism discovery in a known molecular context.

Datasets used. TCGA-HNSC

Prerequisites. A mutation status of interest + an outcome variable. The example uses VHL mutation status + immune checkpoint inhibitor response.

Step 1: Identify candidate genes

Prompt:

In the TCGA-HNSC cohort, identify genes whose expression is significantly associated with both TP53 mutation. Cross-reference findings with published literature on TP53-related immune evasion mechanisms.

Expected result: A list of candidate genes with statistical associations, linked to supporting literature evidence.

Step 2: Spatial expression of top candidates

Prompt:

Can you plot the expression of the top5 candidate genes across Tumor islets, edge, stroma stratified by TP53 mutation status in mosaic HNSC patients?

Expected result: Spatial expression maps for the top 3 candidate genes (where MOSAIC data is available for the relevant indication).

Tip: This is a multi-step, multi-agent use case. Be explicit about both the data analysis you want AND the literature cross-reference — K Pro maintains conversation history within a session, so context from Step 1 carries into Step 2.