LinkedOmicsChat · Documentation

Everything you need to know

LinkedOmicsChat is a natural language interface to cancer multi-omics databases. Ask research questions in plain English and get structured, cited answers from real data sources.


Data Sources

Where the data comes from

Results are grounded in live API calls to these datasets and services. Different workflows query different sources in real time depending on the question.

LinkedOmics
Visit

Core multi-omics and analysis services used by the app, including TCGA survival, CPTAC-integrated expression and correlation analyses, drug target annotations, and treatment-response studies served through LinkedOmics-hosted APIs.

TCGA survivalCPTAC-integrated expressionDrug target lookupClinical trial studies
FunMap
Visit

Functional proteogenomic interaction network for discovering gene co-functional neighborhoods and pathway modules.

Gene functional neighborhoodProtein interaction graphModule-level enrichment
WebGestalt
Visit

Gene set enrichment analysis across GO, KEGG, WikiPathways, and other ontology databases.

Pathway enrichment (ORA)GSEA enrichmentNetwork topology-based analysis
CPTAC
Visit

Underlying proteomics and phosphoproteomics datasets used in LinkedOmics-supported proteogenomic analyses across 10 cohorts.

Protein abundancePhosphorylation sitesmRNA-protein correlationClinical metadata
PubMed
Visit

NCBI literature search integrated into the research workflow for evidence-backed answers.

Keyword and gene searchesRecent publication summariesAbstract-level evidence
MyGene.info
Visit

Identifier normalization service used to resolve Ensembl and UniProt identifiers to HGNC gene symbols before analysis.

Gene ID normalizationEnsembl to HGNCUniProt to HGNC

Example Queries

What you can ask

These are representative questions across analysis types. You can also click example chips on the welcome page to launch them directly.

Survival Analysis
  • "Is ESR1 associated with overall survival in breast cancer?
  • "Compare survival outcomes for high vs low MYC expression in LUAD
  • "Show me survival analysis for PIK3CA across all TCGA cancer types
Gene Expression
  • "What is the expression profile of EGFR across TCGA cancer types?
  • "Show tumor vs normal expression for TP53 in colorectal cancer
  • "Find genes co-expressed with BRCA1 in ovarian cancer
Proteomics
  • "Compare KRAS RNA and protein levels in pancreatic cancer
  • "Show EGFR phosphorylation sites in LUAD from CPTAC
  • "What is the mRNA–protein correlation for MYC in breast cancer?
Network & Pathway
  • "Find functional neighbors of TP53 in the FunMap network
  • "Run pathway enrichment for BRCA1 FunMap partners
  • "What pathways are enriched in PTEN-low tumors?
Multi-step
  • "Find BRCA1 drug targets, then show their survival associations in BRCA
  • "Get TP53 functional neighbors, then run WebGestalt enrichment on them
  • "Show KRAS expression in PDAC and find relevant clinical trials

Architecture

How a query becomes an answer

LinkedOmicsChat uses a LangGraph agent loop with MCP-connected tool servers. The LLM autonomously decides which tools to call and in what order — enabling multi-step analyses without manual workflow configuration.

1

You type a question

Natural language query with no required syntax — gene name, cancer type, and analysis type are inferred from context.

2

LangGraph plans the steps

A LangGraph agent decides which tools to call, in what order, and with what parameters — including multi-step chains.

3

MCP tools query real APIs

Each tool calls the relevant live endpoint or service layer, including LinkedOmics-hosted APIs, FunMap, WebGestalt, PubMed, and MyGene.info.

4

LLM synthesizes the answer

Results are formatted into a cited markdown response with visualizations, tables, and literature references.

Tech stack

FastAPILangGraphModel Context Protocol (MCP)Next.jsFastMCPLangChain

FAQ

Common questions

Do I need an account to use LinkedOmicsChat?

No. You can try the platform as a guest — click any chip on the welcome page or use the 'Try as guest' button. Create an account to save session history and export results.

What cancer types are supported?

TCGA survival analysis supports 35 cohort codes, including aggregate cohorts such as COADREAD, GBMLGG, KIPAN, and STES. CPTAC-integrated expression, survival, and correlation analyses currently cover 10 cohorts: BRCA, COAD, CCRCC, GBM, HNSCC, LSCC, LUAD, OV, PDAC, and UCEC.

Can it run multi-step analyses automatically?

Yes. The LangGraph agent can chain tools without you specifying the steps. For example: 'Find BRCA1 neighbors and run enrichment' automatically calls FunMap, collects the gene list, then calls WebGestalt with those genes.

What if my question is ambiguous?

The assistant will ask a focused clarification question rather than guessing. For finite choices (like analysis type), it shows quick-select option chips. For open-ended inputs like gene names, it asks directly.

Is the data real or simulated?

Production responses use live API calls to LinkedOmics-hosted services, FunMap, WebGestalt, PubMed, and MyGene.info as needed.


Ready to start exploring your research questions?

Built by Zhang Lab · Data and services from LinkedOmics, TCGA, CPTAC, PubMed, and related research resources