Closed Beta · Invite-Only · Shaping With Users

pharmasearch.tools

Drug intelligence for people who need the answer — not a subscription to a bloated terminal.

// full-stack US pharma data, one REST API, one sign-up

Every FDA dataset, every international regulator we can legally redistribute, every clinical trial registry, every major open scientific database — normalized into one instance with a documented Probability-of-Approval engine and a Claude-powered AI analyst that runs real SQL on top. Every data point commercially-free and traceable to its source row.

25+Data Sources
1Unified API
0Sales Cycles
100%Open Data
NDA 212102FinteplaAPPROVED2020-06-25 NDA 204275NuzyraAPPROVED2018-10-02 BLA 125557KanjintiAPPROVED2019-06-13 NDA 218347RezdiffraAPPROVED2024-03-14 NDA 217030WegovyEXPANDED2024-03-08 NDA 215206LeqembiAPPROVED2023-07-06 BLA 761300AqneursaAPPROVED2024-09-24 NDA 212102FinteplaAPPROVED2020-06-25 NDA 204275NuzyraAPPROVED2018-10-02 BLA 125557KanjintiAPPROVED2019-06-13 NDA 218347RezdiffraAPPROVED2024-03-14 NDA 217030WegovyEXPANDED2024-03-08 NDA 215206LeqembiAPPROVED2023-07-06 BLA 761300AqneursaAPPROVED2024-09-24 NDA 212102FinteplaAPPROVED2020-06-25 NDA 204275NuzyraAPPROVED2018-10-02 BLA 125557KanjintiAPPROVED2019-06-13 NDA 218347RezdiffraAPPROVED2024-03-14 NDA 217030WegovyEXPANDED2024-03-08 NDA 215206LeqembiAPPROVED2023-07-06 BLA 761300AqneursaAPPROVED2024-09-24
§ IThe problem

Enterprise pharma tools are built for enterprises.

The terminals are priced for investment banks and mega-pharma. The onboarding takes twelve months and a committee. Every feature is a separate SKU. Meanwhile, the people who actually need this data every day — clinical researchers, biotech analysts, medical-affairs teams, diligence consultants, IR — either get priced out or end up stuck with ten browser tabs and an FDA.gov bookmark.

pharmasearch.tools is the opposite bet. One self-serve sign-up. Full-stack US pharma intelligence. An API that covers every public data point we can legally redistribute, an engine that predicts approval probability with documented backtest accuracy, and an AI agent that does the analyst-intern work in seconds. Built entirely on commercially-free data — no paid subscriptions to scrape, no licensing landmines to inherit, every row attributable to its source.

§ IIWhat’s in the box

Four capabilities. One platform.

Each one alone would be a product. Together they’re the difference between “another database” and “the answer to the question you actually have.”

CAPABILITY 01

Search pharma data like one database — because it is.

Every FDA dataset, every international regulator we can legally redistribute, every clinical trial registry, every major open scientific database — normalized into one Postgres instance with a unified REST API in front. Write one query, get patent expiration dates. Write another, get every Phase 1/2/3/4 trial ever registered for a drug. A safety analyst traces one FAERS mention back through the label, the Drugs@FDA review, the CRL history, and the sponsor’s SEC filings — in one query.

CAPABILITY 02

The Probability of Approval engine.

The flagship. Give it a drug name, indication, and phase. It returns a probability the drug will win FDA approval, backed by a documented, testable methodology. Backtested on historical cases, accuracy, calibration, and ranking performance is comparable to or better than hand-curated expert consensus — while being fully reproducible and fully traceable to source rows. Every score emits a provenance record. Click through to the row in one tap.

CAPABILITY 03

REMS data correlation that actually works.

FDA’s REMS (Risk Evaluation and Mitigation Strategies) data is scattered across PDFs, change-log CSVs, and separate ETASU requirements documents. We ingested the whole thing and structured it — live program registry, Elements To Assure Safe Use (patient agreements, provider certifications, pharmacy registrations, lab monitoring), modification history, enforcement actions, patient-burden estimates, and ML-generated REMS predictions for pipeline drugs. Encoded into PoA scoring on both sides of the ledger.

CAPABILITY 04

The AI agent — not a chatbot, a working analyst.

The AI endpoints expose a Claude-powered analyst with full read access to the database. Not a RAG system over documents — an agent that runs real SQL, joins tables across sources, reads FDA Review PDFs, summarizes FAERS adverse-event patterns, compares trial protocols, and cites its sources with row IDs. Every call goes against fresh DB state. When it says “the FDA rejected this class in 2019 per CRL,” there’s a row ID.

§ II½The AI agent, in motion

Ask a question. Get a cited answer.

Real SQL against fresh DB state. Tool calls visible. Every claim grounded in a primary source. This is a live sample — what happens when you ask the agent a drug-safety question.

p AI Analyst CONNECTED
Thinking · calling tools
adverse_events_by_drug(fintepla)
get_drug_label(fintepla)
get_rems_program(fenfluramine)
p
Sources FDA Label REMS@FDA FAERS EMA EPAR
§ IIIThe corpus

Twenty-five authoritative sources. One schema.

Every source normalized into the same instance, queryable through one API, traceable back to its primary URL with a row ID. No paid subscriptions anywhere in this list.

FDA Drugs@FDAApplications, Summary Reviews, approval letters, labels
FDA Orange BookApproved products, patents, exclusivity data
FDA Complete Response LettersFull openFDA CRL transparency dataset
FDA Advisory CommitteeMeeting records, drug linkage, briefing docs
FDA PMRs / PMCsPost-market requirements and commitments
FDA REMS@FDAActive programs, ETASU, modification history
FDA drug recallsClass I/II/III, reason categorization
FDA NDC DirectoryEvery marketed product with NDC code
NIH DailyMedFull SPL label archive, revision history
ClinicalTrials.govProtocols, structured results, AE counts
CMS Open PaymentsPhysician-industry payments (KOL signals)
CMS Medicare Part B / DMulti-year market-size data
USPTO patentsMetadata keyed to Orange Book
EMA EPAREuropean regulatory review text
Health CanadaNotice of Compliance, recall history
IQWiG (German HTA)Added-benefit assessments
OrphanetRare-disease designations, drug-disease graph
PubMedClinical literature with drug/condition links
OpenTargetsFull drug × target × disease graph
ChEMBLStructures, bioactivities, ATC, indications
PharmGKBClinical pharmacogenomic annotations
IUPHAR / BPS PharmacologyTarget selectivity data
Wikidata pharmacologyCross-reference graph
RxNormBrand-to-generic normalization
DGIdbDrug-gene interactions
§ IVFlagship implementation

Probability of Approval — three phases, one score.

Every PoA score is the output of three documented scoring rules run in sequence, blended against historical class-failure multipliers, and emitted with a full provenance record. Here’s what runs under the hood — and what a live forecast looks like.

PHASE 01

Precedent Depth

Walks the OpenTargets knowledge graph (drug → target → indication → approved-analog cohort) and classifies evidence into five tiers. Each tier carries a tier-implied probability.

Level Asame drug, same indication, previously approved
Level Bsame target, same indication
Level Csame mechanism, same indication
Level Dsame therapeutic area
Level Enovel
PHASE 02

Cohort Outcome Rate

Computes historical success rates for the matched cohort from our ClinicalTrials.gov terminal-trial universe, blended with published Phase Transition Success Rate base rates using a documented cascade discount.

Rewards drugs whose analog cohort has a track record. Punishes drugs whose peers die in Phase 3.

PHASE 03

Benefit-Risk Framework

Scores four dimensions — severity of condition, unmet medical need, benefit, risk — across every relevant source: FAERS adverse events, boxed-warning history, EMA EPAR benefit-risk sections, FDA Review docs, Health Canada recalls, IQWiG HTA ratings.

Real sources. Real weights. No vibes.

NEGATIVE ADJUST

Class-failure multipliers

Negative-adjustment multipliers fire when historical evidence warrants: known class failures (Alzheimer’s amyloid graveyard, CETP inhibitors, ion-channel antiarrhythmics), CRLs for the same mechanism/indication, the subject drug’s own Phase 3 failure history, post-market boxed-warning additions in the analog cohort.

Bayesian Forecast HIGH
67%
80% credible interval
52% 81%
Analog Precedent
72
Target Validation
81
Safety Benchmark
54
Reg. Pathway
91
Endpoint History
68
Live forecast · sample prov-id 04A82

Every score is traceable

The engine emits a structured provenance record showing exactly which rule fired, which sources contributed, and which drugs in the analog cohort drove the probability. You can click through to the source row in one tap. No black box. No “trust us.”

Backtested on historical cases, accuracy, calibration, and ranking performance are comparable to or better than hand-curated expert consensus — while being fully reproducible and fully traceable to source rows.

§ VThe data integrity promise

Commercially-free. Fully attributable. Published.

We don’t ingest DrugBank’s commercial subscription content. We don’t scrape Citeline, BiomedTracker, DealForma, Evaluate Pharma, or any paid database. Every source is listed with its current license, commercial status, share-alike flags, and attribution requirements — published at /docs/DATA_LICENSING.md.

US Gov public domain
openFDA, FDA Drugs@FDA, Orange Book, REMS@FDA, ClinicalTrials.gov, NIH DailyMed, NDC Directory, CMS Open Payments, CMS Medicare, PubMed, USPTO PatentsView, RxNorm
CC0 / public-domain dedicated
OpenTargets, Wikidata, PubChem
CC-BY (attribution)
Orphanet, EMA EPAR, Health Canada
CC-BY-SA (share-alike)
ChEMBL, PharmGKB, IUPHAR / BPS Guide to Pharmacology
MIT / permissive
DGIdb
§ VIUnder the hood

Fast when the internet is on fire.

Every endpoint has a local answer. Live upstream calls only happen when someone explicitly asks for fresh data. The architecture is built to stay available when half the public data providers are not.

§ VIIVersus the incumbents

The comparison is not subtle.

We’re not trying to displace an enterprise RFP cycle. We’re giving solo consultants, small biotechs, research labs, and teams that can’t justify a six-figure seat the same answers — with receipts.

Feature
pharmasearch.tools
Enterprise incumbents
Deployment
Self-serve signup, free trial
Sales cycle, procurement, long onboarding
API access
Every endpoint in one plan
Often an additional enterprise tier
PoA prediction
Included, traceable, documented
Not standard, or gated behind enterprise pricing
Provenance / citations
Every score → source row
Varies — often opaque
Data licensing
Full audit at /docs/DATA_LICENSING.md
Opaque — baked into total-cost figure
AI analyst
Claude-powered, full DB access
Usually none
Update cadence
Continuous ingest from FDA / EMA / CT.gov
Quarterly publishing cadence
What’s in the box
Full schema is visible
Often not
§ VIIIWhat’s shipping

Beta means live. And actively sharpening.

The platform is already powering real queries. These are the next items landing — users see each improvement as it goes live.

Deeper FDA Review coverage

Scraping more Drugs@FDA Summary Review PDFs with on-demand Benefit-Risk Framework parsing.

FDA AdCom transcript ingestion

To extract actual vote tallies — the FDA’s strongest public predictor of approval.

Full EMA EPAR coverage

Rate-limited by EMA’s servers but climbing steadily.

Publications-landscape scoring

Wiring PubMed research velocity into PoA as a positive signal for active investigation.

More therapeutic-area priors

Expanding beyond the modeled class graveyards (Alzheimer’s amyloid, CETP, ion-channel antiarrhythmics) to cover more historical class failures.

DailyMed historical archive

The current archive is ingested; the retired pre-2015 setids are the next target.

Real-time FDA update webhooks

Polling today; push-based in the roadmap.

§ IXWho this is for

People who need the answer today.

Clinical researchers

Compare your trial design against every historical analog in seconds. Pull every terminal trial in your indication in one query.

Biotech diligence analysts

Validate a deal thesis with real FDA, CMS, EMA, and clinical data. Trace every asset back to its primary row.

Medical-affairs teams

Prepare scientific responses with citable primary sources. Every response grounded in a row ID you can reference.

Investor relations & equity research

Cover sponsor pipelines with PoA scores you can defend to the committee — not proprietary analyst opinions.

Small biotech leadership

Can’t justify a six-figure enterprise seat but still needs the answers. One sign-up, full corpus, one plan.

Regulatory consultants

Track FDA action patterns by committee, reviewer, or drug class. Query the whole CRL transparency dataset in one line.

Academic researchers

A commercially-licensed source of the same data you’d otherwise pull piecemeal from a dozen APIs and a scraper.

Due-diligence consultants

Want to know which of a sponsor’s portfolio carries ETASU burden? One query. When was a REMS modified and what changed? In modification history.

Built to serve the question. Not the contract.

If you spend any meaningful amount of time looking up drug labels, chasing down trial registrations, trying to reconstruct an FDA Review, or estimating the odds that a pipeline asset crosses the approval line — this is for you.