AI in Biotechnology

Insilico Medicine's Rentosertib — the first antifibrotic small-molecule TNIK inhibitor, with both target and structure generated by generative AI — showed +98.4 mL mean change in forced vital capacity versus -20.3 mL on placebo at 12 weeks in the GENESIS-IPF Phase IIa trial (n=71), published in Nature Medicine. Patients on 60 mg QD not on concomitant antifibrotic therapy showed +187.8 mL. The first randomized clinical proof-of-concept that an AI-discovered target and AI-designed compound can deliver clinical efficacy in IPF.

Insilico Medicine used Chemistry42, its generative AI platform, to design ISM2286 — a first-in-class bifunctional PKMYT1 PROTAC degrader. The end-to-end AI workflow yielded 76% fewer off-target kinases (46→11) versus the RP-6306 reference inhibitor, validated in Nature Communications 2025.

Insitro combines automated laboratories generating multi-modal phenotypic cellular data with machine learning and generative AI to build phenotypic disease models, identify causal intervention points through human genetics, and deliver targeted therapies for the right patients.

Recursion operates BioHive-2, one of pharma's most powerful supercomputers built with NVIDIA, ingesting more than 50 petabytes of high-quality multimodal phenomics, transcriptomics, and proteomics data to power AI-enabled drug discovery across oncology and rare diseases.

Helio Genomics developed HelioLiver, an AI-powered blood test that uses machine learning to integrate cfDNA methylation patterns, protein tumor markers (AFP, AFP-L3%, DCP), and patient demographics for early detection of hepatocellular carcinoma. In the 1,968-patient CLiMB prospective study it achieved roughly 4x greater sensitivity for Stage I liver cancer than ultrasound, with early-stage sensitivity of 75-85% versus ultrasound's ~47%. HelioLiver is now commercially available nationwide in the U.S. through Quest Diagnostics' 7,700+ patient service centers (Medicare-covered at $662/test, CPT 0333U) and a 2026 commercial partnership with Syneos Health is scaling adoption via the AI-driven Kinetic platform and hybrid human/AI MSL field force. Cross-reference: deployed via Syneos Health's Kinetic + AI MSLs (use case c0b22088…).

Genentech partnered with AWS to develop the gRED Research Agent, an autonomous AI system built using Anthropic Claude Sonnet 3.5 in Amazon Bedrock Agents. The agent transforms how scientists interact with vast scientific datasets by processing complex biological queries, simultaneously searching through 38 million PubMed publications and internal repositories, synthesizing findings with cited summaries. This is expected to automate over 43,000 hours of manual biomarker validation effort and reduce time-to-target identification from weeks to minutes for Genentech's research teams.

Pfizer launched the Pfizer-Amazon Collaboration Team (PACT) initiative with AWS to drive innovation in digital drug development. PACT has deployed 14 AI and machine learning projects, including generative AI search saving scientists up to 16,000 hours of search time annually, a 55% reduction in infrastructure costs, and an anomaly detection system for Pfizer's Portable Continuous Miniature and Modular (PCMM) continuous manufacturing process. Prototypes move to MVP in 6 weeks instead of 3 months, and successful projects have expanded to multiple Pfizer business groups.

Amgen undertook a deliberate multi-phase deployment of generative AI tools, scaling from 300 Microsoft Copilot users in late 2023 to all 20,000 employees by mid-2024, then expanding to ChatGPT Enterprise in 2024.