What a pharma pipeline actually is, and what researching one involves

A pharma pipeline is the full set of drug candidates a company — or a biological target — has moving through development at any given time, spanning everything from early discovery to regulatory approval. “Researching a pipeline” isn’t one lookup; it’s a layered question: which candidates exist for this target, what stage has each reached, what evidence supports that stage, who’s developing it, and how the timeline unfolded to get there.

Answering that fully means pulling from several different kinds of records that don’t share a database: clinical trial registries show stage progress, milestone histories explain why a candidate advanced or stalled, patents and papers show the underlying science and IP position, and deal records show who’s funding or licensing it. A single target like EGFR can have well over a thousand associated candidates spread across every stage from preclinical to approved — which is why pipeline research is really assembling a multi-source timeline, not answering one query.

Why this needs Pharma Intelligence

Pharma Intelligence links drugs to targets, diseases, development phases, regulatory actions, and supporting evidence across more than 30 tools spanning trials, patents, papers, deals, labels, and translational medicine — so you can move from a target search to a specific drug’s profile to its milestone history without switching platforms. Every record returned is a structured entity — a drug identifier, a phase, a milestone date — not a document snippet, which is what makes chaining a target search into a milestone fetch possible in one conversation.

Prepare your query

Start with the biological target you want to explore — in this example, the gene symbol EGFR. No identifier or external database code needed; the server resolves common target names during the search. If you’re working within a specific therapeutic area, approval geography, or development stage, note those too — Pharma Intelligence filters by disease, organization, highest phase, and milestone date, so you can narrow to approved drugs, Phase III candidates, or a specific region. This tutorial’s query is simply “search for drugs targeting EGFR,” returning the full set of EGFR-directed candidates to select from.

1Connect Pharma Intelligence

1. Get a Patsnap Open Platform API key.
2. Copy the connection URL or JSON config from the Connect panel on the Pharma Intelligence page.
3. Add the server to your AI assistant or coding agent or another MCP-compatible client, then restart it.
4. Confirm the drug, target, and milestone tools are available before you ask.

2Run the example query

Search for drugs targeting EGFR, then show me details and milestones for one of the approved candidates.

Claude breaks this into three steps: calling ls_drug_search(target=["EGFR"]) to retrieve the list of EGFR-targeted drugs, selecting one identifier from the results and calling ls_drug_fetch for the full profile, then calling ls_drug_milestone_fetch with that identifier for the development timeline — a broad target search narrowing to a specific asset, then pulling the history that explains how it reached its current phase.

3What the result tells you

Each milestone record includes a date, event type, and geographic scope, so you can trace the candidate’s progression from preclinical work through registration. The result also includes the drug’s mechanism summary, target list, and organizational attribution — enough context to compare this asset against others in the same target class.

4Go further with follow-up questions

With the milestone history in hand, refine further:

• “Which milestones occurred in the last two years?” surfaces recent regulatory or clinical activity.
• “Show me trial-related milestones only” isolates efficacy and safety events from regulatory filings.
• “Which other drugs in the search results have reached Phase III or approval?” returns qualifying candidates with mechanisms and sponsors.
• “Fetch target details for EGFR and show me related papers” connects the drug evidence back to the underlying science — target profile, associated diseases, drug counts, and translational research.