"My patient finally has a genetic diagnosis... but how do I treat it?"

~ Clinician caring for a rare disease patient

Too often, a genetic diagnosis is just the beginning of a long, uncertain search for therapies. The SAIL AI-Tx Challenge calls on innovators to build AI systems that turn diagnoses into actionable treatment options for rare disease patients.

Challenge Structure

Phase 0: Question Benchmark Curation

No Deadline: Open for Submissions

Overview

The question benchmark curation task will focus on soliciting questions from a community of experts that cover five major categories: (1) Established, Targeted Therapies, (2) Established, Supportive Therapies, (3) identification of and eligibility for Clinical Trials, (4) Drug Development and Repurposing, and (5) Variant Assessment, with an emphasis on information relevant to amenability for genetic therapies. Questions should be answerable using information in public databases and the scientific literature.

Submit your questions here - now open! We welcome contributions from clinical genetics and drug development experts, as well as from patients and families living with rare genetic conditions.

Phase 1: Question-Answering Task

Deadline: June 30, 2026 (submissions closed)

Overview

The question answering (QA) task will test AI models’ ability to answer the therapeutic questions about a patient’s genetic diagnosis that were curated in Phase 0.

Phase 1: Input Format

AI models will be provided with an input JSON object containing entries for hypothetical patients, including 1+ genetic variants, brief clinical context, and a question relevant to the individual/variant’s candidacy for therapeutics. Input tasks will be formatted as follows:

For example,

{
  "id": "AITX-00123",
  "patient": {
    "genotype": [
      {
        "gene": "CFTR",
        "transcript": "NM_000492.4",
        "variant_cdna": "c.1521_1523del",
        "variant_protein": "p.Phe508del",
        "zygosity": "homozygous"
      }
    ],
    "clinical_context": "A 15-year-old male with a diagnosis of cystic fibrosis presents with chronic sinopulmonary disease characterized by persistent respiratory symptoms and recurrent infections. He also has exocrine pancreatic insufficiency requiring enzyme replacement therapy and exhibits features of male infertility consistent with congenital bilateral absence of the vas deferens (CBAVD)."
  },
  "question": {
    "category": "Established_Targeted",
    "answer_format": "binary",    
    "prompt": "Is the c.1521_1523del (F508del) variant eligible for treatment with Trikafta (elexacaftor/tezacaftor/ivacaftor)? Respond with “Yes” or “No”.",
    "date_submitted": "2024-12-10"  
  }
}

Questions are being crowdsourced from a community of experts in clinical genetics and drug development. We would love your contributions!

Phase 1: Output Format & Evaluation

Models must output a JSON object with fields for response and evidence justification. Responses will be auto-scored against reference answers using exact match criteria, while evidence fields provide transparency and factual grounding and may be reviewed by judges. Example specifications are shown below.

For example,

{
  "id": "AITX-00123",
  "response": "Yes",
  "evidence": [
    {
      "source": "https://www.nature.com/articles/s41434-022-00347-0",
      "time_accessed": 1749151852,
      "justification": "Trikafta (elexacaftor/tezacaftor/ivacaftor) was approved by the FDA in 2019 for patients aged 12 and older with at least one copy of the p.Phe508del mutation. As this patient has two copies of the mutation and meets the age requirement, he is eligible for Trikafta therapy."
    },
    {
      "source": "https://www.accessdata.fda.gov/drugsatfda_docs/nda/2019/212273Orig1s000Approv.pdf",
      "time_accessed": 1749162712,
      "justification": "FDA approval letter for Trikafta states an indication for patients 12+ years old with at least one copy of the p.Phe508del mutation, which this patient meets."
    }
  ]
}

Phase 1 Model Submission through Hugging Face is now closed. We welcome your submissions for Phase 2!

Phase 2: Actionability Report Generation

Deadline: November 1, 2026

The Phase 2 Actionability Report Generation task is now open to the general public. (Previously, this task had been advertised as invite-only to top performers from Phase 1.) Hypothetical patients will be released on October 1, 2026.

Overview

The actionability report generation task tests an AI system’s ability to generate a comprehensive therapeutic report for a hypothetical patient. Unlike Phase 1’s short answers, this phase requires open-ended narrative synthesis covering established therapies, investigational options, and repurposing candidates, with optional inclusion of emerging targeted approaches (e.g., ASOs, gene therapies).

Phase 2: Input Format

See Phase 1: Question-Answering Task Input. The input format for Phase 2 is identical, except for the absence of the question fields.

Phase 2: Output Format

Submitted AI models must return a structured, markdown-formatted actionability report as a string within a JSON object. Details below.

Markdown Report Template

These requirements apply to every section of the report:

1. Cite a verifiable source for every claim. Not necessarily a paper! A database record (UniProt, ClinVar, OMIM), drug label, guideline, or trial registry entry is fine, given a URL or accession. Same as Phase 1’s evidence.source.
2. Where no prior report exists, show your reasoning instead. For instance, judging ASO amenability from variant position. Cite the underlying facts, and never cite a reference that doesn’t support the claim.
3. State conditional actions. If missing patient information would change a recommendation, say so: “If seizures occur more often than once every three days, then XXX. Otherwise, YYY.”
4. Don’t repeat across sections. Put each action in the single best-fitting section (an ASO approved for the patient’s specific variant and presentation belongs under Targeted Therapies, not again under Bespoke Therapies).
5. Markdown formatting is required. Subheadings, bullets, links, and references beyond the template are encouraged.

For example,

{
  "id": "AITX-30001",
  "report_markdown": "## Therapeutic Actionability Report for Patient AITX-30001\n\n### Summary..."
}

Phase 2: Evaluation

Particularly challenging patient cases and anticipated answer keys are being developed by a panel of experts in clinical genetics, translational research, and drug development. User model submissions will be evaluated by these same expert panels. Reports will be scored based on the following dimensions:

Tutorials: links to databases and video tutorials on utilizing compute resources.
Submit Questions: example input questions which are being crowdsourced from a community of experts in clinical genetics and drug development.
FAQ: responses to questions regarding challenge scope and requirements.