> For the complete documentation index, see [llms.txt](https://docs.owkin.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.owkin.com/what-you-can-do-with-k-pro/prompting-guide-and-prompt-library-1.md). # 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. [*A-S-R-T-C breakdown for Step 1*](https://docs.owkin.com/getting-started/prompting-guide-and-prompt-library)*:* 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. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.owkin.com/what-you-can-do-with-k-pro/prompting-guide-and-prompt-library-1.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.