We are so excited about this case study, as we strongly believe in Clinical Trials Transformation Initiative (CTTI)’s mission to develop and drive adoption of practices that will increase the quality and efficiency of clinical trials.

Think clinicaltrials.gov, but with all structured information in a database. This is AACT and it is an immensely valuable resource for intelligence in clinical trials. Before AI entered this space, you still needed to be a data scientist to access this resource.

Use MCP to interrogate clinicaltrials.cov. Back in December, as @anthropic.com released MCP, we directly linked it to AACT. Happy to share our case study with the Clinical Trials Transformation Initiative (CTTI) connects.ctti-clinicaltrials.org/show/57

Here's a peek at what it can do - an analysis of bispecific antibody patents: claude.site/artifacts/d9...

Want to try it yourself? Check out our GitHub repo for source code and setup instructions: github.com/navisbio/mcp...

⚡️ Quick note: While public BigQuery databases may be a bit dated, we're developing proprietary databases and tools for AI-powered translational research. Need access to current patent data, clinical trials, and more? Let's connect!

Happy to release the latest version of our MCP server for biomedical data in BigQuery. This update enables interaction with comprehensive biomedical data sources using Claude AI or any MCP-compatible LLM client. We're reducing hallucinations by letting LLMs interact directly with the databases.

Thank you! Yes, exactly. It’s really fun to explore the database this way.

The numbers comprise industry-sponsor-led interventional trials assessing drugs, biologics &
genetic therapies and were retrieved from AACT/clinicaltrials.gov using our AI agent workflow.

We often hear biopharma would be a super small market with only a couple of hundred biotech companies. But no one could really give us a number. So we had a look at biopharma companies with clinical stage activities:

4431 unique biopharma companies initiated trials in the last 5 years!

𝐄𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐜𝐲 𝐯𝐬. 𝐦𝐚𝐧𝐚𝐠𝐢𝐧𝐠 𝐜𝐨𝐦𝐩𝐥𝐞𝐱𝐢𝐭𝐲 𝐯𝐬. 𝐝𝐞 𝐧𝐨𝐯𝐨 𝐢𝐧𝐬𝐢𝐠𝐡𝐭𝐬

However, value propositions beyond efficiency were sought - managing complexity, improving decisions, generating novel insights. Challenge: benefits take years to manifest and are hard to disentangle from other variables.

𝐅𝐢𝐧𝐝𝐢𝐧𝐠 𝐭𝐡𝐞 𝐫𝐢𝐠𝐡𝐭 𝐀𝐈 𝐯𝐚𝐥𝐮𝐞 𝐩𝐫𝐨𝐩𝐨𝐬𝐢𝐭𝐢𝐨𝐧 𝐢𝐧 𝐛𝐢𝐨𝐩𝐡𝐚𝐫𝐦𝐚 𝐢𝐬 𝐜𝐡𝐚𝐥𝐥𝐞𝐧𝐠𝐢𝐧𝐠

Opinions varied on efficiency and cost savings, with skepticism about pure efficiency gains. Many said incremental gains were too small vs technical and cultural change required.

What's the right value proposition for gen AI in biopharma? Here's what we were told in numerous conversations with biopharma decision makers.
What is your experience?

Of note, maximum message length can become a limitation when assessing several targets at once and integrating many metrics in the analysis. For more complex workflows we envision separate agent workflows orchestrated from one main conversation.

Assess therapeutic targets in @opentargets.org in natural language and have Claude create dashboards on the fly.

We just built another integration for @anthropic.com 's Model Context Protocol (MCP) to enable Claude to get insights from the OpenTargets platform.

github.com/navisbio/mcp...

Claude for translational medical research. We built an interface to AACT/clinicaltrials.gov with the MCP protocol by @anthropic.com
Ask Claude to analyze trial design, biomarkers, outcomes, etc. and give you insights on the trial landscape.

navis-bio.com#MCP-ctgov
github.com/navisbio/ctg...