SMA Research Platform

Evidence graph for Spinal Muscular Atrophy

Biology-first target discovery
Christian Fischer / Bryzant Labs
14,766Targets
453Trials
84Drugs
7Datasets
6,987Sources
64,683Claims
72,052Evidence
29,649Hypotheses

Hypothesis Prioritization

HYPOTHESIS

Phase 2: Multi-criteria ranked hypotheses scored across evidence depth, source convergence, therapeutic clarity, target strength, and novelty. Tier A = top 5 high-conviction, Tier B = medium priority, Tier C = needs more evidence.

How does Hypothesis Scoring work?

Hypotheses are generated by Claude Sonnet + Gemini from clusters of co-occurring claims, then scored across 5 dimensions:

  • Evidence Depth (25%) — number of independent PubMed sources supporting the core claim; weighted by study type (RCT > cohort > in-vitro)
  • Source Convergence (20%) — agreement across distinct research groups; single-lab replications score lower
  • Therapeutic Clarity (20%) — specificity of the proposed intervention: named target, mechanism, and disease stage
  • Target Strength (20%) — composite target score of the primary molecular target (see Target Scoring methodology)
  • Novelty (15%) — inverse frequency of the hypothesis pattern in the existing literature; penalizes well-known mechanisms

Final score = weighted sum. Hypotheses below 0.3 are suppressed from the default view. Generation runs nightly on newly ingested claims.

Loading hypotheses...
Login → Command Center