v5.14.0

Natural language GraphRAG conversation memory and Graph model pathway enrichment

Natural Language GraphRAG Conversation Memory

Converse with the data in your custom data graph. Ask follow up questions leveraging the data returned in previous questions.

The conversation retains memory which allows you to ask follow up questions. A conversation with context can include questions such as

• Which genes are upregulated in bulk RNAseq tumor samples pathologically confirmed to be endometrium adenocarcinoma?

• Which of those genes are upregulated in fibroblast cells compared to epithelial cells of tumor samples pathologically confirmed to be endometrium adenocarcinoma?

• Of the genes unregulated are any of the associated proteins upregulated in tumor samples pathologically confirmed to be endometrium adenocarcinoma?

• Which biological processes are those genes involved in?

• Are there any approved drugs targeting the proteins identified to be upregulated?

Graph Model Pathway Enrichment

Launch a pathway enrichment analysis directly within your graph model. Identify the pathways enriched across the genes returned in your custom gene ranking and prioritization graph model. Let's say you build a graph model to prioritize gene targets based off of the scientific criteria you care about. The graph model will rank and prioritize genes on the basis of this criteria using quantitative data you have in the graph. Pathway enrichment can be launched within the platform utilizing the genes returned in the report.