The thesis
The Problem
$2B
Cost per drug
Average cost to bring a single new drug to market.
90%
Never approved
Of candidates that enter Phase I, the share that never reach approval.
2
Root causes
Lack of efficacy and unforeseen safety — both failures of prediction.
Approach
ARCHITECTURE
Mechanism meets machine learning
A causal backbone grounds the model in biology; a data-driven layer learns what the rules can't yet describe; and calibrated uncertainty makes every prediction interpretable — down to the individual patient.
Mechanism
Grounded in the biology of how injury actually occurs.
Learning
Learns the patterns mechanism alone can't capture.
Precision
Calibrated uncertainty, tuned to person and context.
Applications
When will the liver be injured?
Safety intelligence, modernized.
FDA ISTAND
Regulatory milestone
Accepted into the FDA's ISTAND program to help predict drug-induced liver injury — the first in-silico tool of its kind that regulators and drug developers can rely on during development.
AI-Driven Digital Heart (Absentia DICT) to help predict drug-induced cardiac injury
AI-Driven Digital Kidney (Absentia DIRI) to help predict drug-induced renal injury
Impact
Catch toxicity liabilities in silico, before they end a program.
Prioritize molecules that are better medicines and reach patients faster.
Reduce reliance on animal studies and prevent unnecessary ones.
Fine-tune on your data to sharpen predictive power for your application.
Talk to our Team
Speak with our expert team to discover how AI-driven innovations are revolutionising biotechnology and accelerating breakthroughs in drug discovery and development.
