The new Amass app is live. Ask in plain language, check every claim. Try it free

Building an AI Scientist, London, July 3–5, 2026

Build your AI scientist on cited life-science data.

Amass sponsors the hackathon, and every participant gets $500 in Amass API credits. The credits buy calls to one REST API over six cross-linked *Cores: biomedical literature, clinical trials, drugs, genes, patents, and FDA and EMA regulatory records.

Each record comes back as typed JSON with a stable Amass ID and its source identifiers. Below: how to claim the credits, a gallery of apps to fork, and an API recipe for each track.

Claim $500 in credits →Jump to your track ↓

Credits go to the account you create with your hackathon email. Valid until July 12, 2026. Questions: hello@amass.tech.

The offer

Claim your $500 in API credits

Sign up with the email you registered for the hackathon with, and we add the $500 to that account.

01

Sign up with your hackathon email

Create an account at platform.amass.tech using the email you signed up for the hackathon with.

02

$500 added to your account

Your org is credited $500, matched on your registration email. Valid until July 12, 2026; check the balance with GET /v1/credits/api-credits.

03

Create a key and build

Open API Keys, click Create API Key (starts with amass_, shown once), and make your first call.

Credits not showing yet?

If your credits have not appeared, check that you used your registration email, then email hello@amass.tech or find Alex on-site.

What $500 buys

≈ 10,000 searches or 50,000 record fetches. Search is $0.05 per 20 results; get-by-id and lookup are $0.01 each.

Get started

From key to first response

Keys, docs and credits live at platform.amass.tech. One base URL, one auth header, JSON back.

bash
# base: https://api.amass.tech/api/v1
# auth: Authorization: Bearer amass_YOUR_KEY  (every request)
curl "https://api.amass.tech/api/v1/cores/trialcore/records\
?query=cancer+immunotherapy&phase=PHASE3\
&overallStatus=RECRUITING&limit=5" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK
{
  "data": [
    {
      "amassId": "AMTC_…",
      "briefTitle": "…",
      "phase": "PHASE3",
      "overallStatus": "RECRUITING",
      "sponsorName": "…",
      "enrollment": 900
    }
  ]
}

Platform and keys

Sign up, create API keys, check your credit balance.

Open

API reference

Interactive docs for all six *Cores, with every parameter and field.

Open

Quickstart

From API key to first response, step by step.

Open

LLM quick reference

Self-contained; paste it into your agent’s system prompt.

Open

Starter agent: Python

A runnable natural-language agent with the API loop built in.

Open

Starter agent: TypeScript

The same agent loop in TypeScript, for a Node or web app.

Open

OpenAPI spec

Machine-readable, for code generation, Postman and type inference.

Open

Agents or apps

The same API runs apps

The tracks below are agent recipes. The same key and records also power small interactive apps: a trial atlas, an indication timeline, a gene-to-approval explorer. All 19 in the gallery were built with Lovable. Fork one and point it at your key.

Browse the app gallery →No-code recipes
platform.amass.tech/app-gallery
Research

From Gene to Approval

One gene → every drug, trial, and FDA/EMA approval behind it.

Research

Graveyard & Garden

25 years of late-stage trials, halted or still alive.

Research

Clinical Trial Atlas

Where a drug is tested, and which regions are enrolling.

Research

Indication Timeline

A drug across its Phase-3 indications and approvals.

Regulatory

Transatlantic Divergence Desk

FDA versus EMA outcomes, side by side.

Clinical

Pipeline Monitor

A weekly digest of new Phase 2/3 trials by sponsor.

Nineteen starter apps across research, regulatory and clinical work. Fork one and run it on your credits.

The data

Six cross-linked *Cores

One auth header, one error format and one rate limit across all six. Records link across *Cores, so a paper, trial, drug, gene, patent and approval resolve to the same entity.

BioMedCore

43M+

/cores/biomedcore/records

Peer-reviewed biomedical literature from PubMed and PubMed Central. Every record includes MeSH terms and IDs, publication types (RCT, meta-analysis, systematic review), JuFo 0–3 journal quality tier, citation count, DOI, PMID, and PMCID. Optional: full text for PMC articles, ORCID-disambiguated authors with ROR-mapped affiliations, and links to the trials each paper describes in TrialCore. Conference abstracts sit in the same index and carry the Amass-assigned value Conference in publicationTypes.

TrialCore

1.2M+

/cores/trialcore/records

Clinical trial records from ClinicalTrials.gov and international registries. Includes protocol data, eligibility criteria, primary and secondary endpoints, sponsor details, arm groups, recruitment status, NCT ID, and the full lifecycle: start, completion, results posting, and why stopped. Outcome measurements are available as structured values per arm. Records link back to the publications that describe them in BioMedCore.

DrugCore

22K+

/cores/drugcore/records

ChEMBL-derived drugs and molecules, harmonized. Names, trade names, and synonyms; chemical structures with InChIKey and SMILES; modality classification; and highest clinical stage from preclinical through approval. Each drug cross-links to the trials, papers, and regulatory authorizations it appears in.

RegulatoryCore

7K+

/cores/regulatorycore/records

FDA and EMA regulatory data on one unified schema. FDA application records, drug labels, review documents, and approval letters; EMA EPARs, assessment reports, and SmPCs. Each record carries a unified authorization status, designations (Breakthrough Therapy, PRIME, Accelerated Approval), and orphan status, and cross-links to the drug it covers in DrugCore.

GeneCore

43K+

/cores/genecore/records

43,000+ harmonized human gene records from HGNC, NCBI, UniProt, and Ensembl. Druggability and tractability assessments, target safety data, genetic constraint via gnomAD v4.0 (pLI, LOEUF), and cellular essentiality from CRISPR dependency screens. Each gene cross-links to the drugs that target it in DrugCore; follow those links to their trials, papers and approvals.

PatentCore

170M+

/cores/patentcore/records

Patent publications with English-preferred full text (title, abstract, claims, and description) plus bibliographic metadata (publication and application numbers, jurisdiction, kind code, family id), CPC/IPC classifications, inventors and assignees, four separate dates, and citation lineage. Search returns one publication per family, the most relevant member, and every record cross-links to the drugs it mentions in DrugCore and the papers it cites in BioMedCore.

Tracks

An API recipe for every track

A starting point per track. Each command ran against the live API; the responses are real, trimmed for width. Jump to your track:

Experimental dataSafetyPre-clinical strategyIPTarget identificationStructure-based designLigand modelsOpen stream
Track

Experimental data

Proteomics / MS ingestion and visualization; curve copilot (GraphPad ↔ Claude); transform IC50/EC50 → Ki/Kd, then train a QSAR model on old vs. corrected values.

BioMedCoreDrugCore

Ground an IC50→Ki agent in the methods papers, filtered by journal quality, with citation counts.

bash
curl "https://api.amass.tech/api/v1/cores/biomedcore/records\
?query=Cheng-Prusoff+IC50+Ki+inhibition+constant\
&minJournalQualityJufo=1&limit=4" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · 4 records
TITLE                                                   JOURNAL                       YR   CITED
The power issue: determination of KB or Ki from IC50…   J Pharmacol Toxicol Methods   2002   171
An exact correction to the "Cheng-Prusoff" correction   Journal of Receptor Research  1988   109
Development of a Quantum Chemical Method for IC50        Molecular Informatics         2016    18
Binding Curve Viewer: equilibrium & kinetics of…        J Chem Inf Model              2024     4

Also try

For the QSAR half: DrugCore returns canonicalSmiles + mechanismsOfAction per ChEMBL compound, a ready feature set to compare models trained on raw vs. Ki/Kd-corrected labels.

Track

Safety

Evidence-backed toxicity report (e.g. “CRBN in atopic dermatitis”); zero-shot hERG de-risking: predict cardiac liability from structure and design an optimization loop that drops hERG binding while preserving potency.

GeneCoreRegulatoryCoreTrialCoreBioMedCore

hERG in one call: curated cardiac liabilities, channel class and loss-of-function constraint, the start of a de-risking loop.

bash
curl "https://api.amass.tech/api/v1/cores/genecore/records\
?query=KCNH2&limit=1" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · GeneCore KCNH2 (hERG)
symbol            KCNH2  (hERG)
location          7q36.1          LOEUF  0.568
targetClass       Ion channel › Voltage-gated potassium channel
safetyLiabilities
  • Torsades de Pointes              ClinPGx
  • Prolongation of QT interval      Bowes et al. (2012)
  • Increased mortality              AOP-Wiki
  • Receptor binding (in vitro)      ToxCast

Search the full text of FDA labels and EMA SmPCs for a safety phrase. Matched sections come back with the excerpt and an addressable ID.

bash
curl "https://api.amass.tech/api/v1/cores/regulatorycore/records\
?query=torsades+de+pointes&limit=4" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · full-text label sweep
Apokyn   (FDA)  →  §5.11  QTc Prolongation and Potential for Proarrhythmic Effects
Geodon   (FDA)  →  label: "…greater capacity to prolong the QT/QTc interval…"
Floxin   (FDA)  →  review: Precautions · Animal Pharmacology
Dacogen  (EMA)  →  matched on active substance

Also try

For the CRBN report: GeneCore returns CRBN with small-molecule “Approved Drug” tractability and PROTAC predictive buckets (the classic molecular-glue hub, LOEUF 1.15, LoF-tolerant). Cross-link to atopic-dermatitis trials with TrialCore and the literature with BioMedCore.

Track

Pre-clinical strategy

Assay optimization (clever DoE / Bayesian); protein and antibody finder built on literature use cases; disease-model planner; cross-species translational alignment.

TrialCoreBioMedCoreGeneCore

Benchmark a study design before you run it: allocation, masking, model, and sample size across completed trials in your indication.

bash
curl "https://api.amass.tech/api/v1/cores/trialcore/records\
?query=atopic+dermatitis&phase=PHASE2\
&overallStatus=COMPLETED&limit=5" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · completed Phase 2
TRIAL                                   N     ALLOCATION   MASKING   MODEL
Secukinumab for Atopic Dermatitis       41    RANDOMIZED   TRIPLE    PARALLEL
ILV-094 (anti-IL-22) proof-of-concept   60    RANDOMIZED   TRIPLE    PARALLEL
S-777469 dose-finding                  209    RANDOMIZED   DOUBLE    PARALLEL
Apremilast, moderate-to-severe AD      191    RANDOMIZED   TRIPLE    PARALLEL
CM310 open-label                       127    NA           NONE      SINGLE_GROUP

Also try

For the protein/antibody finder and disease-model planner: run BioMedCore with include=authorsMetadata to pull use cases, institutions (ROR) and ORCIDs from the literature, the in-domain evidence a datasheet leaves out.

Track

IP

Float the hidden “key compound” in a 500-molecule patent; Markush infringement testing; claims drafting with WIPO feedback loops; automated freedom-to-operate (FTO) search.

PatentCoreDrugCore

Map prior art in one call. Full-text search covers title, abstract, claims and description, and returns one publication per family, so an invention filed in several jurisdictions shows up once.

bash
curl "https://api.amass.tech/api/v1/cores/patentcore/records\
?query=lipid+nanoparticle+mRNA+delivery&limit=5" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · family-collapsed
PUBLICATION        ASSIGNEE                  PRIORITY     CITED-BY
US-2023398082-A1   NANOVATION THERAPEUTICS   2022-04-01   4
US-2024374754-A1   UNIV BRITISH COLUMBIA     2021-06-01   1
US-11338044-B2     TRANSLATE BIO             2011-06-08   5
US-2025073351-A1   TRANSLATE BIO             2021-04-19   0
US-2023181483-A1   TRANSLATE BIO             2019-07-08   1
# one row per family · priorityDate = prior-art cutoff · citedBy = impact

Go from a patent publication to the compounds it references. Each linked DrugCore record carries canonicalSmiles and an InChIKey for a Markush or freedom-to-operate check.

bash
curl "https://api.amass.tech/api/v1/cores/patentcore/records/\
AMPC_QxTI13VmBYdFPsMjGnj8svd02M2?include=referencesDrugCore" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · PatentCore → DrugCore
publicationNumber   US-10266485-B2   (MODERNATX INC)
title               Compounds and compositions for intracellular
                    delivery of therapeutic agents
priorityDate        2015-09-17        citedBy  49
referencesDrugCore  [ AMDC_IWZoNcLj…, AMDC_MV9bzvnP…, AMDC_Y9Bvjb… ]
                    each AMDC_ → a DrugCore structure
                    (canonicalSmiles + InChIKey) for RDKit / Tanimoto

Or start from the target. Pull canonical structures (SMILES and InChIKey) from DrugCore into RDKit for Tanimoto similarity, Markush membership or an FTO risk score.

bash
curl "https://api.amass.tech/api/v1/cores/drugcore/records\
?query=EGFR&drugType=SMALL_MOLECULE&limit=4" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · structures + stage + MoA
NAME            CHEMBL          STAGE     INCHIKEY
Erlotinib HCl   CHEMBL1079742   APPROVAL  GTTBEUCJPZQMDZ-UHFFFAOYSA-N
Aumolertinib    CHEMBL4761468   APPROVAL  DOEOECWDNSEFDN-UHFFFAOYSA-N
Icotinib        CHEMBL2087361   APPROVAL  QQLKULDARVNMAL-UHFFFAOYSA-N
Mavelertinib    CHEMBL3989970   PHASE1    JYIUNVOCEFIUIU-GHMZBOCLSA-N
# each record also carries canonicalSmiles + mechanismsOfAction (INHIBITOR → EGFR)

Also try

PatentCore searches the full text of patent publications (title, abstract, claims and description) across US, EP, WO and other jurisdictions, with family collapsing, forward and backward citations, and links into DrugCore. A filter note from live testing: assignee matches the normalized organization name exactly, so filter with assignee=MODERNATX INC, not assignee=Moderna. Pair it with DrugCore’s ChEMBL-derived structures and mechanisms for FTO and Markush work.

Track

Target identification

Predict clinical-trial attrition and classify it (toxicity vs. lack of efficacy); the “undruggable” protein classifier: spot hidden cryptic pockets from sequence / structure.

GeneCoreTrialCoreBioMedCore

Prioritize targets in one query: druggable, essential and loss-of-function constrained, each with the numbers behind it.

bash
curl "https://api.amass.tech/api/v1/cores/genecore/records\
?query=kinase&isDruggable=true&isEssential=true\
&targetClass=ENZYME&maxConstraintLoeuf=0.6&limit=5" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · target intelligence
SYMBOL  NAME                        LOEUF  DEPMAP dep/tested  SM TRACTABILITY
WEE1    WEE1 G2 checkpoint kinase   0.41   1183 / 1183        Advanced Clinical
CDK2    cyclin dependent kinase 2   0.39    770 / 1183        Advanced Clinical
PLK1    polo like kinase 1          0.21   1183 / 1183        Advanced Clinical
SMG1    SMG1 (PI3K-related)         0.10    340 /  351        —
PI4KA   PI4K alpha                  0.55    767 / 1183        —

Learn why programs die: filter TrialCore to terminated trials and read whyStopped, labeled training data for an attrition model.

bash
curl "https://api.amass.tech/api/v1/cores/trialcore/records\
?query=amyloid+Alzheimer&overallStatus=TERMINATED&limit=6" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · attrition signal
SPONSOR             PHASE   N      WHY STOPPED
Hoffmann-La Roche   PHASE3  1382   "…terminate development of gantenerumab following a
                                    pre-planned safety & efficacy analysis (GRADUATE I & II)…"
Hoffmann-La Roche   PHASE3  1053    (same program, prodromal / mild AD)
Inst. Neurodeg.     PHASE1     3   "…tracer did not evidence as a marker of disease"
Track

Structure-based design

Assess co-folding training-set similarity (how novel is my prediction?); target deconvolution for compounds with unknown targets; visualize selectivity differences between targets.

GeneCore (protein)DrugCore

Structural context for a target: 3D availability, PDB IDs and Pfam domains, as a novelty prior for co-folding predictions.

bash
curl "https://api.amass.tech/api/v1/cores/genecore/records\
?query=EGFR&include=protein&limit=1" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · EGFR protein block
symbol           EGFR    ENSG00000146648
has3dStructure   true    ·    354 PDB structures
pdbIds           1IVO, 1M14, 1M17, 1MOX, 1NQL, 1XKK, …
pfam             PF00757 · PF07714 (PK_Tyr_Ser-Thr) · PF01030 · PF14843 · PF21314
sequence         1210 aa    ·    134,277 Da

Also try

Use the PDB count as a training-set coverage prior, and DrugCore’s canonicalSmiles for the ligand side of a co-fold. The Boltz team is also offering API credits at this event.

Track

Ligand models

Few-shot bioactivity from a handful of actives; activity cliffs (predict them, do not smooth them); multi-objective generative design against 3–4 conflicting properties.

DrugCoreGeneCore

Assemble a few-shot actives set for a target: SMILES plus clinical stage as a weak relevance label.

bash
curl "https://api.amass.tech/api/v1/cores/drugcore/records\
?query=EGFR&drugType=SMALL_MOLECULE&limit=4" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · canonicalSmiles + stage
Erlotinib HCl  APPROVAL  C#Cc1cccc(Nc2ncnc3cc(OCCOC)c(OCCOC)cc23)c1.Cl
Icotinib       APPROVAL  C#Cc1cccc(Nc2ncnc3cc4c(cc23)OCCOCCOCCO4)c1
Aumolertinib   APPROVAL  C=CC(=O)Nc1cc(Nc2nccc(-c3cn(C4CC4)c4ccccc34)n2)c(OC)cc1N(C)CCN(C)C
Mavelertinib   PHASE1    C=CC(=O)N[C@@H]1CN(c2nc(Nc3cn(C)nc3OC)c3ncn(C)c3n2)C[C@H]1F

Also try

GeneCore EGFR → include=referencesDrugCore returns 87 targeting drugs in one hop, a ready-made labeled set. Contrast approved vs. Phase 1 scaffolds to mine activity cliffs.

Track

Open stream

Bring your own problem. All six *Cores and the links between them are open to you.

All six *CoresCross-*Core links

Cross-*Core links resolve one entity across six *Cores; each hop is a record with its own Amass ID.

bash
curl "https://api.amass.tech/api/v1/cores/genecore/records\
?query=EGFR&include=referencesDrugCore&limit=1" \
  -H "Authorization: Bearer amass_YOUR_KEY"
response · 200 OK · one gene → 87 drugs → …
EGFR  →  referencesDrugCore: 87 drugs
             │
             ├─ each drug → referencesTrialCore       (the trials that ran it)
             ├─ each drug → referencesBiomedCore      (the papers behind it)
             └─ each drug → referencesRegulatoryCore  (FDA / EMA labels)

gene → drug → trial → paper → approval, in one thread. all cited.

Playbook

Nine notes from building on the API

What tends to separate a demo that lands from one that fights its own plumbing.

01

Build an agent loop.

Let the model call the API in a loop: search broadly, filter, drill into a record, repeat. The open-source starter agents (Python and TypeScript) implement this loop; fork one.

02

Ground every claim in a record.

Each result carries a stable Amass ID that resolves to its source record, plus the original identifiers (PMID, NCT ID, ChEMBL ID). Have your agent cite only those.

03

Follow the cross-*Core links.

A gene resolves to the drugs that target it, the trials that ran them, the papers behind them, and the FDA and EMA labels that cover them, one call at a time. Treat an empty reference array as “none recorded,” not “no evidence.”

04

Query, do not scrape.

PubMed, ClinicalTrials.gov, ChEMBL, HGNC, UniProt, FDA and EMA data are already normalized and cross-linked. The ETL is done; spend the weekend on the idea.

05

Narrow with filters.

journalQualityJufo, phase, maxConstraintLoeuf, tractability, agency: tighter queries return more relevant records and spend fewer credits. Skip include=fulltext unless you need it.

06

Be nice to the rate limit.

60 requests / 60s, keyed by user + org. On a 429, read Retry-After and back off exponentially. Every response carries X-RateLimit-Remaining and X-Amass-Credit-Cost.

07

Read the data envelope.

Every response is wrapped in { "data": … }; errors come back in a different shape under "error". Check for error before you parse; a batch lookup can fail item by item.

08

Convert external IDs first.

Get-by-id endpoints take Amass IDs only (AMBC_, AMTC_, AMDC_, AMRC_, AMGC_). Batch PMIDs, DOIs, NCT IDs, ChEMBL IDs or gene IDs through the /lookup endpoints first, then fetch.

09

Cache, and mind pagination.

Same query, same result: memoize locally so iterating does not re-spend credits. There is no pagination; a search returns at most 300 results, so narrow with filters instead.

Prototype in Claude

Sketch the agent in Claude first.

Connect the Amass MCP in Claude, Claude Code, Cursor, ChatGPT or Codex and query the six *Cores in plain language. Find the filters that work, then move the same queries to the REST API.

In Claude Code, install the Amass SKILL.md and let the model wire up the data layer, from “what data is even in here?” to a working prototype.

Connect the MCPStarter agent:PythonTypeScript

Go further

More ways to put the credits to work

Routes for teams without a coder, or short on time.

Fork an app from the gallery

Nineteen starter apps on the same API, including a trial atlas, an indication timeline and a gene-to-approval explorer. Fork one and run it with your key.

Browse the gallery

No-code builds

Paste your key into Lovable, Streamlit or an n8n HTTP node to build a filterable trial tracker or a literature app.

See examples

Claude Code with SKILL.md

Install the Amass skill and let Claude Code write your API client, then spend the time on the science.

Get the skill

Demo it live in Claude

With the MCP connected, answers come back in the chat with their source identifiers: a demo for the judges with nothing to deploy.

How it works

Chain the *Cores

Fan out from one entity: gene → drug → trial → paper → label. Follow the reference fields and cite each hop.

See open stream

Share on Discord

Show your build to other life-science AI builders and tag the Amass team.

Join now
Alex Junge, Amass co-founder and CTO

On the ground

Meet the Amass team on-site

Alex Junge, Amass co-founder and CTO, is on-site Friday and Saturday until 14:00. Find him for credit problems, API help or a second opinion on your build. Meet the full Amass team →

LinkedInGitHubXEmail

Go build your AI scientist

Claim your $500 in credits, connect a *Core and let an agent do the reading.

Claim $500 in credits →API referenceConnect the MCP

Credits are valid until July 12, 2026. Questions: hello@amass.tech

Data
No training on your data
Hosting
EU-hosted, enterprise
Isolation
Tenant-isolated by architecture
Certification
ISO 27001, SOC 2, NIS2: in motion