--- title: "Build on the Amass API at the DTU Skylab hackathon" description: "Amass hosts the AI in Life Sciences hackathon at DTU Skylab on 16 September 2026. Claim $50 in API credits, then build on one REST API across the six cross-linked Cores on the public API, covering literature, trials, drugs, genes, FDA and EMA regulatory, and patents. There are five project ideas inside, each sized for one evening." url: https://amass.tech/dtu-hackathon --- # Build on the Amass API at the DTU Skylab hackathon AI in Life Sciences · DTU Skylab · Wed 16 September 2026 # Turn life-science data into working software in one evening. Amass hosts this hackathon with [Cursor Copenhagen and DTU Skylab](https://luma.com/cursor-jwp4). One REST API covers the six cross-linked Cores on the public API: 40M+ papers, 1.2M+ trials, 22K+ molecules, 43K+ genes, FDA and EMA authorizations, and life-science patents. Records are typed, and every answer traces back to its source. Copy the credit code, then pick one of [five project ideas](#ideas) sized for the build block. The [build assistant](https://platform.amass.tech/assistant) writes the API calls with you. [Create your account →](https://platform.amass.tech)[Open the build assistant](https://platform.amass.tech/assistant) Doors open at 14:30 and the kickoff is at 15:00. Building runs from 15:30, demos start at 17:30, and prizes are announced at 18:00. The venue is the DTU Skylab Auditorium at Diplomvej 373D. Email [hello@amass.tech](mailto:hello@amass.tech) if you get stuck, or find us in the room. Your $50 credit code The code is worth $50 in Amass API credits. Create an account, redeem the code, then generate a key. It takes about two minutes. Then your first call bash ``` # every DTU paper on the topic, this year curl "https://api.amass.tech/api/v1/cores/biomedcore/records\ ?query=metabolic+engineering+yeast+cell+factory\ &institutionRors=04qtj9h94&minPublicationDate=2026-01-01" \ -H "Authorization: Bearer amass_YOUR_KEY" ``` response · 200 OK ``` Enzyme-constrained genome-scale model of Yarrowia lipolytica… Appl Microbiol Biotechnol Engineering and characterization of small-molecule transporters Trends Biotechnol Reusable and modular combinatorial libraries for S. cerevisiae Metab Eng pAo: a consensus genome-scale metabolic model for A. oryzae Comput Struct Biotechnol J Kinetic sampling shows the effect of medium composition… Microb Cell Fact # 04qtj9h94 is DTU's ROR id. Swap in your own ORCID with authorOrcids. ``` Start here ## Four ways in All four give you the same data with the same key. If you are not sure which one you want, start with the assistant. Start with this ### The Amass build assistant This is a chat grounded in the Amass documentation, built to help you write against the API. Describe what you are trying to do, such as finding every Danish Phase 2 trial in atopic dermatitis and the papers behind them. It answers with the endpoint, the filters, and the field names, so you are not guessing at parameter names from a schema you have not read yet. [Open the assistant →](https://platform.amass.tech/assistant) [ ### The platform This is where your account, credits, and API keys live, alongside the full documentation, the interactive API reference, and a gallery of apps you can fork. Everything the assistant reads from is here. platform.amass.tech](https://platform.amass.tech)[ ### The Amass app This is the product itself. Ask a research question and get an answer with the records attached. Use it to scope an idea and see what the data can answer before you write a line of code. preview.amass.tech](https://preview.amass.tech)[ ### MCP Connect Amass to Claude, Cursor, or Codex and query all six Cores in natural language while you build. Use it to find the filters that work before you hard-code them. Connect the MCP](https://amass.tech/mcp) The data ## Six Cores on the public API These six are the Cores the REST API and the MCP serve today. Every one of them takes the same base URL and the same auth header, and returns the same error format. A paper, a trial, a molecule, a gene, an authorization, and a patent all resolve to the same entity, so you can follow one thread instead of joining three exports by hand. ### BiomedCore 40M+ PubMed & PMC papers indexed /cores/biomedcore/records ### TrialCore 1.2M+ Clinical trials indexed /cores/trialcore/records ### DrugCore 22K+ ChEMBL drugs & molecules indexed /cores/drugcore/records ### RegulatoryCore FDA + EMA FDA & EMA documents indexed /cores/regulatorycore/records ### GeneCore 43K+ Human genes indexed /cores/genecore/records ### PatentCore 16M+ Life-science patents indexed Preview /cores/patentcore/records Project ideas ## Five things you could ship tonight These are five different kinds of build across five different parts of the API. Pick one and make it yours. Every response below is a real record from the live API, trimmed to fit the column. [01 Literature radar](#radar)[02 Method scout](#methods)[03 Gene dossier](#dossier)[04 Dataset builder](#dataset)[05 Prior-art check](#priorart) 01 ### A literature radar for your niche This is an agent that runs your topic against everything published since you last looked, keeps only the journals you would actually cite, and writes a short digest with a PMID on every line. The version worth building is the one that runs on Monday morning without you. BiomedCore bash ``` curl "https://api.amass.tech/api/v1/cores/biomedcore/records\ ?query=engineered+probiotic+living+therapeutic+gut+microbiome\ &minPublicationDate=2026-05-01&minJournalQualityJufo=2&limit=5" \ -H "Authorization: Bearer amass_YOUR_KEY" ``` response · 200 OK · 5 records ``` TITLE JOURNAL DATE JUFO Harnessing the microbiome for cancer therapy Nat Rev Microbiol 2026-06-01 3 Living drug carriers: microbial and bioengineered platf… J Control Release 2026-08-24 3 The gut microbiome and allograft outcomes J Clin Invest 2026-08-17 3 Targeted and quantitatively modeled biologic delivery… J Control Release 2026-06-10 3 Developing spore-forming gut bacteria as model organisms Trends Microbiol 2026-08-01 2 ``` Also try Point it at yourself instead of a topic. authorOrcids returns your own papers, and minCreateDate tells you what entered the index since your last run, which is the difference between a digest and a diff. 02 ### A method scout for the technique you are learning This one answers how something was measured rather than what was found. Give it a technique and it returns the papers that establish the method. It then reads their full text and pulls out the parameters you have to choose anyway, including tracer, organism, instrument, controls, and reported precision. BiomedCoreinclude=fulltext bash ``` curl "https://api.amass.tech/api/v1/cores/biomedcore/records\ ?query=13C+metabolic+flux+analysis+Escherichia+coli+method\ &minJournalQualityJufo=2&limit=5" \ -H "Authorization: Bearer amass_YOUR_KEY" ``` response · 200 OK · ranked by relevance ``` TITLE JOURNAL YR CITED 13C-MFA of co-cultures: a novel approach Metab Eng 2015 89 Metabolism of the fast-growing bacterium V. natriegens… Metab Eng 2017 89 Quantifying biomass composition by GC/MS Anal Chem 2014 83 Optimal tracers for parallel labeling experiments… Metab Eng 2016 72 FreeFlux: a Python package for time-efficient INST-MFA ACS Synth Biol 2023 10 ``` Also try Fetch the top hits one at a time with include=fulltext and have the model fill a comparison table. Keep fulltext off the search itself, because it multiplies the response size for rows you are about to discard. 03 ### A one-page dossier for the gene you work on This gets you from gene to clinic in four calls. GeneCore gives you druggability, curated safety liabilities, population constraint, and CRISPR essentiality. The cross-links then hand you the drugs that hit the target, the trials that ran them, and the FDA and EMA authorizations that came out the far end. Every hop carries its record id. GeneCoreDrugCoreTrialCoreRegulatoryCore bash ``` curl "https://api.amass.tech/api/v1/cores/genecore/records\ ?query=GLP1R&include=protein&limit=1" \ -H "Authorization: Bearer amass_YOUR_KEY" ``` response · 200 OK · GeneCore GLP1R ``` symbol GLP1R ENSG00000112164 6p21.2 463 aa targetClass Membrane receptor › Family B GPCR › Glucagon-like peptide receptor tractability small molecule: Advanced Clinical · other clinical: Approved Drug constraint LOEUF 0.494 pLI 0.986 (LOEUF decile 1) essentiality not essential, 2 dependent lines of 1,233 screened structure 3D: yes · 70 PDB entries · Pfam PF00002, PF02793 ``` Also try include=referencesDrugCore returns the DrugCore ids for the molecules that target it, including semaglutide, liraglutide, dulaglutide, and the oral small molecule danuglipron. Each of those carries its own trial, literature, and authorization links. 04 ### The dataset your model is missing Most hackathon models fail on data, not architecture. The API returns rows that already carry features and a label. Genes come with constraint, essentiality, tractability, and target class. Molecules come with canonical SMILES, an InChIKey, and a clinical-stage label. Terminated trials come with a free-text reason in whyStopped. Filter to the slice you want and start training. GeneCoreDrugCoreTrialCore bash ``` curl "https://api.amass.tech/api/v1/cores/genecore/records\ ?query=transporter&isDruggable=true&isEssential=true\ &maxConstraintLoeuf=0.5&limit=20" \ -H "Authorization: Bearer amass_YOUR_KEY" ``` response · 200 OK · 3 records ``` SYMBOL NAME LOEUF DEPENDENT/TESTED SM TRACTABILITY VCP valosin containing protein 0.134 1258 / 1258 predictive only ATP1A1 Na+/K+ ATPase subunit alpha 1 0.188 1056 / 1258 Approved Drug RHOQ ras homolog family member Q 0.476 1125 / 1258 predictive only # four filters, three rows. isDruggable counts predictive buckets too, # so add tractabilityStage=APPROVED_DRUG for clinical precedent only. ``` Also try There is no pagination, and a search returns at most 300 rows, so build a set by splitting or widening the filters rather than paging. Cache responses locally too, because the same query returns the same rows and re-running it spends the credits again. 05 ### A prior-art check before the idea becomes a company Skylab is full of projects that could be spun out, and the first honest question is what somebody has already claimed. Full-text search runs over title, abstract, claims, and description, and it collapses each patent family to one publication. A landscape comes back as five inventions instead of twenty filings of the same one. PatentCoreDrugCoreBiomedCore bash ``` curl "https://api.amass.tech/api/v1/cores/patentcore/records\ ?query=precision+fermentation+recombinant+milk+protein\ &countryCode=US&limit=5" \ -H "Authorization: Bearer amass_YOUR_KEY" ``` response · 200 OK · family-collapsed ``` PUBLICATION ASSIGNEE PRIORITY CITED-BY US-10988521-B1 ALPINE ROADS INC 2020-09-30 16 US-2023106635-A1 PERFECT DAY INC 2020-02-19 9 US-2024215599-A1 RE MILK LTD 2021-05-12 1 US-2024294589-A1 FONTERRA COOPERATIVE GROUP 2021-06-24 0 US-12458039-B2 PERFECT DAY INC 2019-04-22 0 # one row per family. priorityDate is the prior-art cutoff. ``` Also try include=claims on a hit shows what is actually claimed rather than what the abstract implies, and referencesBiomedCore walks back to the papers behind the filing. PatentCore is in preview, so the schema can still move. Playbook ## Five things worth knowing before 15:30 These are the things that separate a demo that lands from one that spends the evening fighting its own plumbing. 01 ### Two hours is the real constraint. Pick one endpoint and one output somebody can see on a projector. A literature radar that runs beats a platform that almost does. 02 ### Let the build assistant write the calls. Describe the thing you want in plain language. It answers from the documentation and hands back the request, the filters, and the field names, which is most of the fiddly part. 03 ### Ground every claim in a record. Each result carries a stable Amass id and a route back to its source. There are no invented PMIDs and no invented NCT numbers, which is the whole reason to query rather than ask a model from memory. 04 ### Narrow with filters, because there is no paging. A search returns at most 300 rows. Reach for minJournalQualityJufo, phase, maxConstraintLoeuf, assignee, and date windows. A tighter query is higher signal and costs fewer credits. 05 ### Read the envelope and respect the limit. Results arrive under data and failures arrive under error, so check for error before you parse. The limit is 60 requests per 60 seconds. On a 429, read Retry-After and back off. ## Go build something tonight Redeem the code, open the assistant, and let the API do the reading. We would like to see it at 17:30. $50 in API credits Redeem it at platform.amass.tech once you have created your account. If it does not apply, find us in the room or email hello@amass.tech. [Create your account →](https://platform.amass.tech)[Build assistant](https://platform.amass.tech/assistant)[Try the app](https://preview.amass.tech)[Connect the MCP](https://amass.tech/mcp)