Powered by

Chat Interface

cBioPortalChat is an AI-powered chat interface that lets you explore cBioPortal data with natural language. It's live and open to everyone — just open the chat and start asking questions.

What is the Chat Interface?

The cBioPortal chat interface (cBioPortalChat) lets you ask cBioPortal questions in plain English. It uses Claude (Anthropic's LLM, provided via Amazon Bedrock) and combines two capabilities in a single agent:

  • Database queries — answers about studies, patients, samples, mutations, copy-number changes, clinical attributes, and treatments by querying cBioPortal's underlying database.
  • Web navigation — generates direct links into cBioPortal views (study summaries, OncoPrint, patient view, group comparison) when you describe what you want to look at.

You don't need to pick which one you want — the agent decides which tools to call based on your question.

Earlier prototypes: through 2026-Q2 the platform exposed two separate agents (cBioDBAgent and cBioNavigator) that the user had to choose between. These have been merged into a single cBioPortalChat agent. The combined agent has access to all of the tools the two earlier prototypes had.

What you can ask

Explore data — find studies, datasets, and available molecular data:

Navigate cBioPortal — generate direct links to views:

Analyze data — compare genes, cancer types, profiles, cohorts, and outcomes:

Tips for Using the Chat Interface

  • Be specific — include study names, gene symbols (UPPERCASE HUGO format), and data types when possible.
  • Ask follow-up questions — the chat keeps conversation context, so you can refine in sequence.
  • Try rephrasing — different angles often surface different views of the same data.
  • Ask about the schema — you can ask the agent to explain available fields and tables to help frame more effective queries.
  • Statistical claims need external tools — the agent can return summary data and generate links (including Kaplan–Meier plots), but it cannot compute statistical test results (p-values, hazard ratios, odds ratios). Use cBioPortal's Group Comparison tab, R, or Python to run the test.

Getting Started

  1. Open cBioPortalChat.
  2. Type your question in the chat input.
  3. Review the AI-generated response.
  4. Ask follow-up questions to dive deeper.

Feedback and Support

The chat interface is actively being developed and improved. Your feedback drives it:

  • Use the thumbs up/down buttons — every chat response has 👍 / 👎 buttons. Please use them to rate quality and accuracy. This feedback directly improves the agent's answers.
  • Report issues or suggestions — for anything beyond a quick rating, please reach out through the cBioPortal Google Group.

Privacy

cBioPortalChat is operated by the cBioPortal team. To provide the service and improve it over time, we collect and store the following:

  • Your account identifier — you sign in with Google; we store your Google account email and display name to identify your conversations across sessions.
  • Your conversations — the full text of every message you send and every response the AI generates is stored in our database, so you can revisit past chats and so we can debug and improve the assistant. Team members may read individual conversations during triage of thumbs-down feedback, quality evaluation, or investigation of production issues.
  • Feedback signals — your 👍 / 👎 ratings on responses are stored alongside the conversation they refer to and used to prioritize improvements to prompts, tools, and evaluation suites.
  • Usage metrics — page views and session information are collected via Google Analytics to understand aggregate usage patterns. We also record model-call metadata (input/output token counts, latency, cost) via Langfuse for cost tracking and performance monitoring; conversation text is included in these Langfuse traces.

Data flow to third parties during normal operation:

  • Amazon Bedrock (AWS) — the text of every message you send is sent to AWS Bedrock in the us-east-1 region to generate the AI response. AWS's Bedrock data protection documentation covers how Bedrock handles inputs and outputs; the short version is that content processed through the service is not used to train the underlying models and is not shared with model providers.
  • Anthropic — the underlying model (Claude Sonnet) is Anthropic's, but requests are served through Bedrock and do not reach Anthropic's own API; Anthropic does not receive your data.
  • Google — used only for sign-in (OAuth) and analytics.

We do not sell your data, share it with advertising networks, or provide it to third parties beyond the infrastructure providers above. Data is retained indefinitely today so we can debug regressions and evaluate model changes; contact us via the Google Group if you'd like your account and conversation history deleted.

Do not paste protected health information (PHI), personally identifying information about patients, or other sensitive data into the chat. cBioPortalChat is a research tool for exploring published cancer-genomics datasets.

Technical Details

Architecture

  • User interface: LibreChat, an open-source chat front-end.
  • AI model: Claude, provided via Amazon Bedrock.
  • Tooling layer: the agent calls Model Context Protocol (MCP) servers for its data and navigation capabilities:
    • A database MCP (built on cBioPortal's ClickHouse database) for study, sample, mutation, and clinical-attribute queries.
    • A navigator MCP that converts intent into cBioPortal URLs.

A single unified agent has access to all of these tools and decides which to invoke for each turn.

For more information about the MCP servers and how to build your own integrations, see the Model Context Protocol documentation.

© Copyright 2026. All rights reserved.