London AI x Science Hackathon, 1-2 Paris Garden, SE1, 3–4 October 2026
Push frontier AI at the hardest open problems in science.
Amass is a partner of the London AI x Science Hackathon, run by Iterate and futurebio.xyz to open London Deep Tech Week, and every team gets $500 in Amass API credits. Amass is one REST API over six cross-linked *Cores: 43M+ papers, 1.2M+ clinical trials, 22K+ molecules, 43K+ genes, FDA and EMA authorizations, and 170M+ patents. Every answer arrives with the record it came from.
Doors open at 08:00 on Saturday, the kickoff is at 09:00, and the submission deadline is 14:45 on Sunday with pitches straight afterwards. The venue is 1-2 Paris Garden, London SE1 8ND, and all times are BST. Registration is on Luma, the rules and resources are on the Iterate event page. Questions for us: hello@amass.tech.
Quickstart
Hand your agent the Amass skill
Paste one prompt into Claude Code, Cursor, Codex, or any agent that reads skills. It installs the amass-api skill, which teaches the agent the six *Cores, their filters, and the response envelope before it writes a single call. The skill reads your key from AMASS_API_KEY, the same variable the track prompts below use.
Agent prompt
Agent setupInstall the Amass API skill. Run `npx skills add amass-technologies/public-skills --skill amass-api` and select the agent you are running in. You can read the skill directly at https://github.com/amass-technologies/public-skills/blob/main/skills/amass-api/SKILL.md (raw: https://raw.githubusercontent.com/amass-technologies/public-skills/main/skills/amass-api/SKILL.md), with the full API reference next to it in AMASS.md. The skill reads my key from AMASS_API_KEY. If it is not set, tell me to create a key at https://platform.amass.tech and export it. Then use the Amass API skill when working on this project.
Pick a track
Which one is yours
You must choose one track. These are the two where Amass data does real work for you. Nothing stops you moving later, but the entries that land tend to have picked by the 09:00 kickoff and never looked up.
Agents that know when they are wrong
- Choose this if
- You build agents and evals, and you are more interested in how research goes wrong than in any single result.
- You will build
- An agent, an eval, or a benchmark that catches a research agent scoring itself well on bad evidence.
- Judged on
- Whether the eval catches something a plain accuracy score misses. Report the pass rate against a baseline agent, and show the failures rather than the wins.
Peptide-HLA stability from protein foundation models
- Choose this if
- You work with protein models or immunology data, and you would rather beat a named baseline than invent a new problem.
- You will build
- A stability predictor for peptide-HLA complexes built on a protein foundation model, with an honest comparison against NetMHCstabpan.
- Judged on
- A held-out metric against NetMHCstabpan on the same split, reported per allele as well as in aggregate. Say plainly which alleles your training data cannot speak for.
Agents that know when they are wrong
Benchmarking science agents, calibrated uncertainty, falsification, and reward design. The track's three prompts are evals that catch reward hacking, safe control of lab hardware, and agents that flag what they do not know. Amass reaches the first and the third.
How it is measured
Whether the eval catches something a plain accuracy score misses. Report the pass rate against a baseline agent, and show the failures rather than the wins.
What the agent cited, and what the record says
6 sources · 4 retractedThe agent’s own answer
“Hydroxychloroquine increases in-hospital mortality in COVID-19, supported by six studies.”
| Source | Cited | Status |
|---|---|---|
| Hydroxychloroquine or chloroquine with or without a macrolideLancet 2020-05-22JuFo 3PMID 32450107 | 1,244 | retracted |
| Effect of Hydroxychloroquine in Hospitalized Patients with Covid-19N Engl J Med 2020-10-08JuFo 3PMID 33031652 | 1,312 | in force |
| Hydroxychloroquine in the Treatment of COVID-19Am J Trop Med Hyg 2020-10-01JuFo 1PMID 32828135 | 137 | retracted |
| Lack of efficacy of hydroxychloroquine on SARS-CoV-2 viral kineticsNat Commun 2020-10-20JuFo 3PMID 33082342 | 79 | in force |
| Safety and efficacy of favipiravir versus hydroxychloroquineSci Rep 2021-03-31JuFo 1PMID 33790308 | 51 | retracted |
| Ivermectin role in COVID-19 treatment (IRICT)Expert Rev Anti Infect Ther 2022-07-12JuFo 1PMID 35788169 | 2 | retracted |
The most-cited source in the set is one of the retracted ones. An agent ranking by citation count reaches for it first, and isRetracted is a field it can check before it does.
Three places to start
A retraction trap for agents
Build a small eval where the highest-cited source for a claim has been withdrawn. Score an agent on whether it notices. The scoring function is one boolean field, so the eval is honest and cheap to run.
BioMedCore, a few hoursCalibration against the registry
Ask an agent for the readout of a trial, then check the registry record for whether results were ever posted. Report how often confident answers sit on records with nothing in them.
TrialCore, half a dayA refusal benchmark
Write twenty claims where ten are checkable from the *Cores and ten are not. A good agent answers ten and refuses ten. Most answer twenty, and that number is your result.
one eveningPaste this into Cursor to start
Build me an eval that catches an agent citing withdrawn work.
Use the Amass API at api.amass.tech with my key in AMASS_API_KEY.
Pick ten contested clinical claims. For each one, search BioMedCore
for the supporting literature twice: once with isRetracted=true and
once with isRetracted=false.
Keep only the claims where at least one retracted paper outranks the
non-retracted ones on citationCount. Those are the trap cases.
Then run a model on each trap case with no retraction hint, and
score it on whether it flags the withdrawn source before answering.
Report the pass rate, and show me the failures in full, with the
PMID and the citation count that made the trap work.The call behind the picture
curl "https://api.amass.tech/api/v1/cores/biomedcore/records\
?query=hydroxychloroquine+COVID-19+mortality\
&isRetracted=true&limit=4" \
-H "Authorization: Bearer amass_YOUR_KEY"TITLE JOURNAL DATE JUFO CITED
Hydroxychloroquine or chloroquine with or without a m… Lancet 2020-05-22 3 1244
Hydroxychloroquine in the Treatment of COVID-19: A Mu… Am J Trop Med Hyg 2020-10-01 1 137
Safety and efficacy of favipiravir versus hydroxychlo… Sci Rep 2021-03-31 1 51
Ivermectin role in COVID-19 treatment (IRICT): single… Expert Rev Anti Inf 2022-07-12 1 2
# the top row has 1,244 citations and has been withdrawn.
# an agent ranking sources by citation count reaches for it first.Starter data for this track
Also try
Cross-Core links turn a single claim into a chain an agent can be scored on. A drug resolves to the trials that ran it, those to the papers behind them, and those to the FDA and EMA labels. Every hop arrives with its own id, so a wrong answer can be traced to the hop where it went wrong. Treat an empty reference array as no record, never as no evidence.
Peptide-HLA stability from protein foundation models
The brief asks a single question: can existing protein foundation models predict peptide-HLA complex stability better than NetMHCstabpan, the sequence-based model most teams use today. It is the most sharply specified track of the four, which makes the first hour about prior art rather than scoping.
How it is measured
A held-out metric against NetMHCstabpan on the same split, reported per allele as well as in aggregate. Say plainly which alleles your training data cannot speak for.
Who has already tried to beat NetMHCstabpan
5 methods · 2016 to 2026- NetMHCstabpanJ Immunol 2016JuFo 2PMID 27402703
Neural network on measured pMHC-I complex half-lives
The baseline the brief names. Stability beats affinity as a correlate of immunogenicity.
- APE-Gen + random forestFront Immunol 2020JuFo 1PMID 32793224
150,000 modelled pHLA structures, residue-residue distances
Competitive AUROC on leave-one-allele-out with far less data.
- TLStab / TL-MHCImmunoinformatics 2023JuFo 0PMID 38577265
Transfer learning from binding affinity and mass-spec data
Matches or beats state of the art on stability test sets.
- ImmugenXPLoS Comput Biol 2024JuFo 3PMID 39527593
Modular protein language model, pMHC encoder shared across tasks
Encoder comparable or better on binding, elution and stability.
- CMHSBMC Bioinformatics 2026JuFo 1PMID 41764421
ESM2 with LoRA fine-tuning, plus a B-factor-guided structure graph
Mean SRCC +8.7% over 16 HLA allele benchmarks.
GeneCore HLA-A, the molecule underneath
Length
365 aa40,841 DaLOEUF
0.956decile 5, pLI 0Missense o/e
0.786Z 1.91Dependent lines
29 / 1,258not essentialENSG00000206503UniProt P044396p22.13D solved
Half an hour of reading buys you a baseline table, a test set, and five methods you do not have to reinvent before lunch on Saturday.
Three places to start
Embeddings against the baseline
Take ESM or ProtT5 embeddings of the peptide and the HLA pseudo-sequence, fit a small head on measured half-lives, and put your numbers next to NetMHCstabpan on the same test set. Same split or the comparison means nothing.
one eveningWhere the baseline fails
Find the alleles and peptide lengths where the published model does worst, and report your gain per stratum. A model that wins on rare alleles is a more interesting result than one that wins on average.
half a dayA prior-art table nobody has
Five methods have attacked this since 2016 and they do not share a test set. Build the comparison table, mark what is not comparable, and hand it to the room. This is the one in the window above.
BioMedCore, a few hoursPaste this into Cursor to start
Map the prior art on peptide-HLA stability prediction for me.
Use the Amass API at api.amass.tech with my key in AMASS_API_KEY.
Search BioMedCore for peptide-MHC class I complex stability
prediction, from 2016 onward, and pull the fulltext where it is
available.
For every method you find, extract four things: the architecture,
the training data and its size, the test set, and the headline
metric with its value.
Lay it out as one row per method. Mark clearly where two papers
report the same metric on different test sets, because those rows
are not comparable and I do not want them averaged.
Finish with the three test sets that appear most often, since one
of those is the one I should report against.The call behind the picture
curl "https://api.amass.tech/api/v1/cores/genecore/records\
?query=HLA-A&include=protein&limit=1" \
-H "Authorization: Bearer amass_YOUR_KEY"symbol HLA-A ENSG00000206503 6p22.1 365 aa 40,841 Da
targetClass Surface antigen
constraint LOEUF 0.956 pLI 0 (LOEUF decile 5) missense o/e 0.786
essentiality not essential, 29 dependent lines of 1,258 screened
structure 3D: yes · PDB 1AO7, 1HHK, 5HHO and 400+ more
function presents 8 to 13 aa cytosolic peptides; anchor residues at
position 2 and 9 define allele-specific binding motifs
ptm N-linked glycosylation at Asn-110Starter data for this track
Also try
GeneCore settles the assumptions argument in one call. The HLA-A record carries the anchor-residue motif, the post-translational modifications, the solved structures and the curated safety liabilities, each with its source. That is the paragraph in your write-up that says why this molecule behaves the way your model assumes it does.
The offer
Claim your team’s $500 in API credits
One code per team, worth $500.
What $500 buys
Roughly 10,000 searches or 50,000 record fetches. Search costs $0.05 per 20 results; get-by-id and lookup are $0.01 each. That is far more than a team gets through in a weekend, so query freely and cache what you re-run.
Start here
Four ways in, one key
All four reach the same data with the same key. If you do not know which one you want, start with the assistant and let it write the first call with you.
Start with this
The Amass build assistant
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 retracted paper that still outranks its replacements on citations. 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.
The platform
Your account, credits, and API keys, plus the full documentation, the interactive API reference, and the app gallery. Everything the assistant reads from lives here.
platform.amass.techThe Amass app
The product itself. Ask a research question and get an answer with the records attached. Use it on Saturday morning to see what the data can answer before you write a line of code.
preview.amass.techMCP
Connect Amass to Claude, Cursor, or Codex and query all six *Cores in natural language while you build. It also gives you a judge-friendly demo with nothing to deploy.
Connect the MCPThe data
Six *Cores, one API
Same base URL, same auth header, same error shape across all of them. A paper, a trial, a molecule, a gene, an authorization, and a patent can resolve to the same entity, so you follow one thread instead of joining three exports by hand.
BioMedCore
43M+PubMed, PMC and conference abstracts
/cores/biomedcore/records
TrialCore
1.2M+Clinical trials indexed
/cores/trialcore/records
DrugCore
22K+ChEMBL drugs & molecules indexed
/cores/drugcore/records
RegulatoryCore
7K+FDA & EMA documents indexed
/cores/regulatorycore/records
GeneCore
43K+Human genes indexed
/cores/genecore/records
PatentCore
170M+Life-science patents indexed
/cores/patentcore/records
Apps to fork
You do not have to start from an empty file
Every app in the gallery runs on the same API, the same key, and the same cited records as the tracks above. All of them were built with Lovable, so there is a route through this weekend that involves no local setup at all. Fork one, point it at your key, and change the question it asks.
From Gene to Approval
One gene → every drug, trial, and FDA/EMA approval behind it.
Graveyard & Garden
25 years of late-stage trials, halted or still alive.
Clinical Trial Atlas
Where a drug is tested, and which regions are enrolling.
Indication Timeline
A drug across its Phase-3 indications and approvals.
Transatlantic Divergence Desk
FDA versus EMA outcomes, side by side.
Pipeline Monitor
A weekly digest of new Phase 2/3 trials by sponsor.
Nineteen starter apps across research, regulatory, and clinical. Each one is a working answer to “what does a small app on this data look like?”
How it is scored
A hundred points, five criteria, twenty each
The organizers publish the rubric, which is rarer than it sounds. Three of the five are about what you chose to build and two are about how you land it in the room, so budget Sunday morning accordingly.
Technicality
What you actually built, and how hard it was to build in 30 hours.
Creativity
Whether the approach is one the judges have not already seen twice that afternoon.
Usefulness
Whether somebody would use it on Monday. Naming the user helps.
Demo
Ninety seconds, live. Practice it, because a demo that fails on stage costs a fifth of the total.
Track alignment
Whether you answered the brief your track was written around, in its own terms.
What you submit, and when
A two-minute demo video, a link to your GitHub repo, and a short description, all in by 14:45 on Sunday. Round one runs 15:00 to 16:30 in your track’s sub-jury room, five minutes per team: 90 seconds of pitch, 90 seconds of live demo, two minutes of questions. Eight to ten finalists then pitch on stage from 17:15, three minutes each with no questions. Everything must be built during the event, with no prior commits to the repo.
Find us
We are in the room for both days
Amass is at 1-2 Paris Garden for the whole hackathon. Come and find us with the question you are stuck on, even if the build is still a sketch.
At the venue
We are there from the 08:00 breakfast on Saturday through to the pitches on Sunday. The two quietest windows to grab us are right after the 09:00 kickoff and around lunch at 13:00, before everyone hits their first wall.
Overnight and everywhere else
We are on the hackathon Discord and at hello@amass.tech. Questions about credits, endpoints, or which *Core holds what are all fair game.
Playbook
Six things worth knowing before the kickoff
These are what separate an entry that lands from one that spends the weekend fighting its own plumbing.
Narrow until it feels too small.
Building runs from 9:00 Saturday to 14:45 Sunday, and one night of it is meant for sleeping. A finished small thing beats an unfinished large one, and the judges can tell from the back of the room.
Read the prior art in the first hour.
Both Amass tracks have published work behind them already. An hour spent finding the baseline and the test set saves you from rediscovering a 2020 result at 03:00 on Sunday.
Build the baseline first.
Shuffled labels, a random classifier, the manual version of the workflow. Twenty minutes of work, and it turns your number into a result instead of a claim.
Show where it fails.
One of the two briefs asks for it outright, and every judge rewards it. A demo that names its own failure mode reads as finished work.
Cite it or drop it.
Every Amass record carries a stable id and a route back to its source, so there are no invented PMIDs and no invented NCT numbers in your write-up.
Read the envelope, respect the limit.
Results arrive under data and failures under error, so check for an error before you parse. The limit is 60 requests per 60 seconds; on a 429, read Retry-After and back off. There is no paging, so narrow with filters.
Prototype in Claude
Sketch it in a chat before you write any app code.
Connect the Amass MCP in Claude, Cursor, ChatGPT, or Codex and query all six *Cores in natural language. Explore the data, find the filters that work, and only then drop the same queries into your build. On Sunday it doubles as the demo: the answers come back cited in the chat, with nothing to deploy.
In Claude Code, install the Amass skill and let the model wire up your data layer for you. That is a short path from “what is even in here?” to a working prototype, which is the right question to answer on Saturday afternoon rather than Sunday morning.
Pick one, and go build it
Claim your team’s $500, choose a track, and let the API do the reading. Narrow it until it feels too small, build the baseline, and show where it breaks. We would like to see it on Sunday.
One code per team. Find us at the venue, on the hackathon Discord, or at 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