I

Insilico Medicine

Insilico Medicine's AI-generated drug INS018_055 enters Phase II human clinical trials for idiopathic pulmonary fibrosis

Curated & reviewed by Peter Korpak, Founder & Chief Analyst, 100SignalsHow we verify
~3 years (2020 discovery to 2023 Phase II)Drug Development Timeline to Phase II
3 compoundsAI-generated drugs in clinical stage
40 sites (U.S. and China)Phase II trial sites planned

Vendor-reported figures — source: www.cnbc.com

The Challenge

Idiopathic pulmonary fibrosis (IPF) is a chronic, progressive lung disease affecting ~100,000 people in the U.S. with a prognosis of death within 2–5 years if untreated. Existing treatments only slow disease progression and cause uncomfortable side effects. Insilico sought a 'moonshot' molecule targeting a novel biological mechanism rather than incrementally improving existing therapies.

The Solution

Insilico Medicine applied its proprietary generative AI platform to simultaneously discover a novel disease target and design a novel small-molecule drug candidate (INS018_055) from scratch. The AI performed both target identification and molecular generation — making it the first drug with both an AI-discovered target and an AI-generated molecular design. Discovery work began in 2020 and the compound was advanced into a randomized, double-blind, placebo-controlled Phase II trial.

Results

INS018_055 became the first fully generative AI drug to reach Phase II human clinical trials, enrolling patients in China with plans to expand to 60 subjects across 40 sites in the U.S. and China. The Phase II readout is expected in 2024. Insilico also has two additional AI-assisted compounds in the clinical stage: a COVID-19 drug in Phase I and an FDA-cleared cancer drug (USP1 inhibitor for solid tumors).

Key Takeaways

  • End-to-end generative AI can compress the drug discovery timeline from target identification through clinical candidate nomination, bypassing years of traditional screening.
  • Validating an AI drug-discovery platform requires advancing compounds all the way into human trials — in-silico results alone are insufficient proof.
  • A single AI platform can be applied across multiple disease areas simultaneously, enabling a diversified clinical pipeline from one technology investment.

Share:

Details

Company Size
Startup
Quality
Curated
Last verified
Jul 28, 2026

Have a similar implementation?

Share your customer's AI results and link it to your vendor profile.

Submit a case study →