FDA Accepts In Silico DDT to Predict DILI
The FDA's Center for Drug Evaluation and Research (CDER) has accepted the first Letter of Intent for an in silico drug development tool (DDT) into its Innovative Science and Technology Approaches for New Drugs (ISTAND) qualification program, the agency announced June 3, 2026. The tool, an AI-Driven Digital Liver Model, aims to predict drug-induced liver injury (DILI) for small-molecule candidates by using AI to compare their chemical structures against historical reference drugs with known DILI risk. The FDA classifies it as a New Approach Methodology meant to complement other risk assessments in a weight-of-evidence approach and to reduce reliance on animal testing. Acting CDER Director Michael Davis said new technologies show incredible promise in helping improve and streamline drug development. The acceptance is the first of three qualification steps, and the FDA notes current modeling does not reliably identify human DILI risk.
What happened
The FDA's Center for Drug Evaluation and Research (CDER) has accepted the first Letter of Intent (LOI) for an in silico drug development tool (DDT) into the Innovative Science and Technology Approaches for New Drugs (ISTAND) DDT Qualification Program. The tool is an AI-Driven Digital Liver Model for predicting drug-induced liver injury (DILI) in small-molecule drug candidates. The FDA says this LOI acceptance is the first of three qualification steps; next the developer submits a Qualification Plan, then a full qualification package. Acting CDER Director Michael Davis said new technologies are "showing incredible promise in helping improve and streamline drug development," and Jeffrey Siegel, Director of the Office of Drug Evaluation Sciences, said the model "shows promise in assessing the risk of hepatotoxicity during preclinical phases of drug development."
How it works
Per the FDA, the model is a New Approach Methodology (NAM) that uses AI to compare the chemical structures of new drug candidates against historical reference drugs with known DILI risk. Predictions are meant to complement other DILI risk-assessment methods as part of a weight-of-evidence approach, supporting decisions before phase I trials. The agency notes current modeling does not accurately identify human DILI risk and that DILI is a leading cause of clinical-trial termination and drug attrition.
Why it matters
For computational toxicology and drug-development practitioners, acceptance into ISTAND creates a formal regulatory pathway for an AI structure-based liver-toxicity model. It also aligns with FDA's stated push to reduce animal testing through the 3Rs (replacement, reduction, and refinement). Qualification, if achieved, would let sponsors use the tool within a defined context of use.
What to watch
- •Progress through the remaining ISTAND qualification steps.
- •Published or independent benchmarking of the model's predictive performance.
- •Any context-of-use language the FDA issues if the DDT is qualified, and subsequent sponsor uptake.
Sourcing note
Details and quotes come from the FDA's announcement, with independent reporting from Reuters and background from the FDA's ISTAND program page. No qualification is final at the LOI stage.
Scoring Rationale
Regulatory acceptance of the first in silico DDT under ISTAND is notable for computational toxicology and AI-in-drug-development practitioners, creating a formal pathway and aligning with FDA's stated goal of reducing animal testing. Qualification is early-stage (the first of three steps) and requires further validation, keeping it notable rather than landmark.
Practice interview problems based on real data
1,500+ SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
