IND preparation for a rare genetic disease requires a clear picture of two things: who the patients are and which variants your eligibility criteria need to capture. Standard registries and structured databases often hold only a fraction of that evidence. The gaps that remain become risks at every stage: trial design, enrollment projections, and regulatory review.
You cannot make confident development decisions with an incomplete patient picture.
This case study documents how a clinical development team preparing for IND in a rare genetic cardiac disease used Genomenon to build a comprehensive patient and variant landscape from published biomedical literature. The team used AI-powered full-text search and expert curation to identify substantially more patient records and pathogenic variants than ClinVar held, uncovering a cohort with longitudinal clinical detail that no registry could provide. A consulting report translated the findings into strategic guidance for IND preparation and trial design.
The result: a regulatory-ready evidence base built before the gaps could become costly, with patient-level data supporting endpoint selection, enrollment criteria, and surrogate endpoint justification.
