Cover Image for Agents for Precision Health: a ClawBio Hackathon in Doha
Cover Image for Agents for Precision Health: a ClawBio Hackathon in Doha
Avatar for ClawBio
Presented by
ClawBio
ClawBio events and hackathons
34 Going

Agents for Precision Health: a ClawBio Hackathon in Doha

Registration
Approval Required
Your registration is subject to host approval.
Welcome! To join the event, please register below.
About Event

​The first agentic AI for health hackathon in the Middle East.

​Two days at Sidra Medicine. Real precision health questions. You build AI agents that do actual scientific work, and show a jury what they found.

  • ​When: Saturday 5 and Sunday 6 December 2026, 09:00 to 17:00

  • ​Where: Sidra Medicine, Education City, Doha

  • ​Cost: free, with lunch and coffee

  • ​Then: the 12th PMFG Summit, 7 to 9 December, Qatar National Convention Centre

​Why come

​AI agents can now plan an analysis, run the tools, check the result and write it up.

​In genomics and medicine that only counts if someone else can inspect what the agent did, rerun it and get the same answer.

​In two days you will:

  • ​learn to work with a coding agent, from people who build these systems

  • ​solve a real question in a team of up to five

  • ​present your result to a jury from science, industry and venture capital

  • ​meet the investigators in Qatar who are hiring

​We use ClawBio, an open-source project in which agents work through written, versioned skills, so every step is on the record.

​Speakers

  • ​Dr Khalid Fakhro, Chief Research Officer, Sidra Medicine. Opens the event.

  • ​Dr Manuel Corpas, Principal Investigator, Sidra Medicine, and founder of ClawBio. Agentic genomics, and whether we can trust it.

  • ​Cameron Lloyd, co-maintainer of ClawBio. A live worked example with a coding agent.

​More speakers will be added as they confirm.

​Programme

​Saturday 5 December

  • ​09:00 Opening, Dr Khalid Fakhro

  • ​09:15 Agentic genomics: can we trust it? Dr Manuel Corpas

  • ​09:40 Invited talks

  • ​10:45 Live worked example: one small analysis, from input data to a checked result, with a coding agent. Cameron Lloyd

  • ​12:00 The three tracks, their starter questions, and teams

  • ​12:30 Lunch

  • ​13:30 Build, with mentors on the floor

  • ​16:00 Careers panel: working in computational genomics and AI in Qatar, with investigators who are hiring

  • ​16:45 Social

​Sunday 6 December

  • ​09:00 Build, with mentors on hand

  • ​12:30 Lunch

  • ​13:30 Submissions close

  • ​14:00 Demos, five minutes per team

  • ​15:30 Jury deliberation

  • ​16:00 Awards and close

​Three tracks

​You do not need to arrive with an idea. Pick a track and start on a prepared question in the first hour.

​Track 1. Rare and paediatric disease

  • ​Rank candidate variants from a child's phenotype, show the evidence, and say when the agent cannot decide

  • ​Turn messy phenotype sheets into a clean, coded pedigree, with every change logged

  • ​Write a variant evidence summary in which every claim points to its source

​Track 2. Women's and newborn health

  • ​Run a microbiome analysis from raw data to result, with the full record of what was run

  • ​Triage a newborn screening gene panel, and state what cannot be concluded

  • ​Gather and grade the published evidence for a drug and gene pair in pregnancy

​Track 3. Omics in under-represented populations

  • ​Measure how a polygenic score transfers across ancestries, and report where it fails

  • ​Match pharmacogene results to dosing guidance, and find where an agent is confident without support

  • ​Produce an association report another team can rerun and get the same numbers

​Every question comes with

  • ​a short brief

  • ​example data (public or synthetic; no patient data)

  • ​a ClawBio skill to start from

  • ​a clear definition of done

​A mentor agrees the scope with each team before it starts, so you finish what you begin. You can also bring your own question.

​An agent that confidently invents an answer is worse than one that says it does not know. You are building for the second behaviour.

​The jury

​On Sunday afternoon every team presents to a jury from science, industry and venture capital. They ask two things:

  • ​Can the agent's work be inspected and trusted?

  • ​Could it become something real?

​Ajiri Omafokpe, co-founder of Builders Tribe, is the first confirmed member. More will be announced.

​Who should come

  • ​Bioinformaticians and computational biologists

  • ​Genomics researchers and clinicians

  • ​Students and postdocs

  • ​Software engineers and machine learning people

​From Qatar, the region and further afield.

​You do not need to have used ClawBio or an AI coding agent before. You do need to be comfortable reading and running code.

​Before the day

​Once you are registered we invite you to the ClawBio Slack. There you:

  • ​pick a track

  • ​find teammates, up to five per team

  • ​get your laptop set up before Saturday

  • ​ask for help during the build, and carry on afterwards

​Practical details

  • ​Bring: a laptop

  • ​Food: lunch and coffee are provided

  • ​Compute: GPU credits for teams that need them, supported by NVIDIA

  • ​Places: limited. Registration is reviewed; you will hear from us within 48 hours

  • ​Code: ClawBio is open source at ClawBio/ClawBio

  • ​PMFG Summit: 7 to 9 December, Qatar National Convention Centre, sidraweb.sidra.org/events/research/pmfg/2026

Location
Sidra Medicine, Education City, Doha, Qatar
Avatar for ClawBio
Presented by
ClawBio
ClawBio events and hackathons
34 Going