AI in Drug Discovery: 2026 Pipeline Analysis
How AI is accelerating drug discovery from target identification to clinical trials. Analysis of the 70+ AI-discovered drugs in clinical trials and the emerging AI-first pharma companies.
Key Data
Analysis
AI-discovered drug candidates in clinical trials exceeded 70 in 2025, up from fewer than 10 in 2020. The average time from target identification to preclinical candidate dropped from 4.5 years to 1.5 years for AI-assisted programs, representing a 3x acceleration.
The economics are transformative. Traditional drug discovery costs average $2.6B per approved drug with a 90% failure rate. AI-assisted discovery is showing early signs of both cost reduction (estimated 30-40% savings in preclinical phases) and improved success rates (AI-selected candidates show 15-20% higher Phase I success rates).
Three approaches are competing: AI-designed molecules (generating novel chemical structures), AI-repurposed drugs (finding new uses for existing approved drugs), and AI-optimized biologics (designing proteins and antibodies with desired properties). The first AI-designed drug to complete Phase II trials successfully — Insilico Medicine's INS018_055 for IPF — represents a proof of concept that the entire industry is watching.
Ehsan's Analysis
Insilico's IPF drug completing Phase II is the Wright Brothers moment for AI drug discovery. It proves the concept works. The 3x time reduction is significant, but the success rate improvement is the real game-changer. If AI can improve the 10% clinical success rate to even 15%, the economic impact across pharma is measured in hundreds of billions. The question is no longer whether AI will transform drug discovery — it is which AI approaches will dominate.
Ehsan Jahandarpour
AI Growth Strategist & Fractional CMO
Forbes Top 20 Growth Hacker · TEDx Speaker · 716 Academic Citations · Ex-Microsoft · CMO at FirstWave (ASX:FCT) · Forbes Communications Council