Insitro

What Insitro does

Insitro is an AI-driven drug discovery and development company founded in 2018 by Daphne Koller (co-founder of Coursera, former Stanford professor, former Chief Computing Officer at Calico) and headquartered in South San Francisco. The company operates a full-stack, modality-agnostic drug discovery platform anchored by the Virtual Human Platform, a genetically grounded causal AI engine that integrates multimodal human and cellular data to identify therapeutically validated targets. Platform components include ChemML for small molecule design, ClinML for clinical data phenotyping, CellML for cell-based screening, and POSH (Pooled Optical Screening in Human cells), which combines pooled CRISPR screening with self-supervised Vision Transformers to map gene function at scale. The January 2026 acquisition of CombinAbleAI added physics-informed biologics design capabilities, launching the TherML integrated therapeutic design engine spanning small molecules, oligonucleotides, antibodies, and complex biologics.

The business model is partnership-driven rather than product-driven. Insitro generates revenue primarily through upfront payments, R&D/development/regulatory/commercial milestones, and royalties from co-development agreements with large pharmaceutical and biotechnology partners, supplemented by equity capital from top-tier life sciences and growth investors (a16z, ARCH, BlackRock, Casdin, CPP Investments, Foresite, GV, SoftBank, Temasek, Third Rock, T. Rowe Price). Flagship partnerships include Bristol Myers Squibb (initial $50M upfront and potential $2.1B+ in ALS milestones, plus subsequent $25M, $10M, and $20M payments), Eli Lilly (metabolic diseases and TuneLab ADMET data partnership), and Gilead Sciences (NASH). Active offices span South San Francisco, Tel Aviv (post-CombinAbleAI acquisition), Warsaw, and Kuala Lumpur, with research collaboration in the UK through Moorfields Eye Hospital.

Complementing the partner-funded model is an emerging wholly-owned pipeline: CTRO-1013, an siRNA MASH candidate with anti-fibrotic preclinical data presented in 2026, and the BAT-01 obesity program derived from an AI-enabled brown adipose tissue GWAS. Approximately 200-500 employees support R&D, ML, and partnership operations; the company conducted a 22% workforce reduction in May 2025 to extend cash runway into 2027, reflecting both pre-commercial cost discipline and broader biotech market pressure.

Name

Insitro

Legal name

Insitro, Inc.

Website

https://insitro.com

Company type

Private

Founded year

2018

Operating status

Operating

Headcount range

251–500 employees

Short description

Insitro is an AI-driven drug discovery company that uses machine learning, human genetics, and high-throughput experimentation to identify therapeutic targets and design small molecules, oligonucleotides, and biologics for pharmaceutical partners and a wholly-owned pipeline in metabolic and CNS diseases.

Ownership category

akta.pro rank

Product category

AI-driven drug discovery

NAICS

Research and Development in Biotechnology (except Nanobiotechnology) (541714), Biological Product (except Diagnostic) Manufacturing (325414)

SIC

Services-Commercial Physical & Biological Research (8731), Pharmaceutical Preparations (2834)

akta.pro primary industry

AI/ML Platforms for Drug Discovery & Experiment Optimization (HLAGAJAO)

akta.pro secondary industries

AI/ML-Enabled Biologic Discovery Platforms (computational design, in silico screening) (HLAAAIAE), Target Identification & Validation Platforms (omics-driven, chemoproteomics, genetic validation) (HLAAAIAI), In Silico / Computational Toxicology & PK/PD Modeling (HLAGAFAM)

Keywords

• AI drug discovery
• Machine learning therapeutics
• Computational biology platform
• Human genetics research
• Pharmaceutical partnership licensing

Headquarters

HQ city

South San Francisco

HQ country

United States

HQ region

North America

Offices4 records

Markets served

GTM type

B2B

Offering type

Services

Cost components

Personnel, Technology or R&D, Operations, Marketing or Sales, Infrastructure

Revenue model

1. Pharmaceutical Partnerships and Licensing: Insitro generates revenue through strategic partnerships with pharmaceutical companies involving upfront payments, milestone payments (research, development, regulatory, and commercial), and royalties on successful products. Partnerships include BMS for ALS (up to $2.1B+ deal value), Eli Lilly for metabolic diseases, and Gilead for NASH therapies.
2. Milestone Payments: Non-dilutive funding from pharmaceutical partnerships through research and development milestone achievements. Estimated $150M from non-dilutive partnerships as of recent funding rounds.
3. Equity Funding: Capital raised through equity financing rounds from institutional investors including a16z, ARCH, BlackRock, Casdin, CPP Investments, Foresite Capital, GV, SoftBank, Temasek, Third Rock Ventures, and T. Rowe Price. Total approximately $800M raised.

Go-to-market motion2 records

Distribution channels2 records

Marketing channels5 records

Core offering

Insitro operates an AI-driven, full-stack modality-agnostic drug discovery platform that combines machine learning, human genetics, and high-throughput in vitro experimentation to identify disease targets and design therapeutic candidates across small molecules, oligonucleotides, antibodies, and complex biologics. The company monetizes the platform through strategic co-development partnerships with pharmaceutical companies (BMS, Eli Lilly, Gilead) and Moorfields Eye Hospital, generating revenue from upfront payments, R&D/regulatory/commercial milestones, and royalties. Insitro also advances a wholly-owned pipeline of therapeutic candidates (e.g., CTRO-1013 for MASH, BAT-01 for obesity).

Product overview

Insitro is an AI therapeutics company offering a unified, full-stack modality-agnostic drug discovery platform. The core offering centers on the Virtual Human™ Platform—a genetically anchored causal AI engine—that integrates multi-modal human and cellular data to discover disease mechanisms. Built upon this foundation are specialized capability modules: TherML™ serves as the integrated therapeutic design engine spanning all modalities (small molecules, oligonucleotides, antibodies, biologics); ChemML™ handles small molecule discovery with ADMET prediction and AI-driven design loops; CellML™ enables cell-based phenotypic screening; and ClinML™ processes clinical data for phenotype generation. The POSH platform provides pooled optical screening capabilities. The January 2026 acquisition of CombinAbleAI extended the platform to include advanced biologics design with physics-informed AI optimization. Pipeline includes therapeutic candidates such as CTRO-1013 for MASH and BAT-01 for obesity.

Differentiator

Problem solved

Functional benefit

Brands

• TherML: Therapeutic Machine Learning platform for AI-driven drug design across small molecules, oligonucleotides, antibodies, and complex biologics
• Virtual Human
• ChemML
• CellML
• ClinML
• POSH

Products and services

• Virtual Human Platform Genetically anchored causal AI engine that reveals how disease begins, progresses, and can be resolved by integrating the world's largest integrated multimodal corpus of human and cellular data to support target identification across therapeutic areas. Targeted at pharmaceutical R&D partners via strategic co-development agreements.
• TherML (Therapeutic Machine Learning) Platform Integrated therapeutic design engine spanning small molecules, oligonucleotides, antibodies, and complex biologics in a single platform, enabling simultaneous in silico optimization of potency and developability before committing to experimental work. Available through co-development partnerships with pharmaceutical companies.
• ChemML Platform End-to-end small molecule discovery and optimization platform integrating proprietary Quantitative Adaptive Libraries, predictive ADMET modeling, AI-driven design loops, and a large compute cluster of 192 H100 GPUs. Used to discover molecules for partners such as Bristol Myers Squibb.
• CellML Platform Cell model platform for screening genetically supported targets in primary human cells using high-content imaging, transcriptomics, and functional assays to assess cellular phenotypes. Provides the wet-lab foundation for Insitro's ML-driven target validation work.
• ClinML Platform Clinical machine learning platform that analyzes multimodal clinical data including MRI scans, DXA imaging, and biomarker streams to generate high-quality phenotypes for genetic discovery. Used in human cohort analytics and clinical trial design.
• POSH (Pooled Optical Screening in Human cells) Platform Scalable experimental and computational platform integrating pooled CRISPR screening, high-content CellPaint imaging, and self-supervised Vision Transformers to map gene function at scale without relying on predefined biomarkers. Used in-house and through partner programs to identify therapeutic targets.
• CTRO-1013 (MASH therapeutic candidate) Liver-targeted IRS1 silencing siRNA therapeutic for MASH (metabolic dysfunction-associated steatohepatitis), demonstrating anti-fibrotic signals in preclinical models with effects partially independent of liver fat reduction, advancing toward first-in-human trials. Wholly-owned internal pipeline candidate.
• BAT-01 Program (Obesity target) Obesity therapeutic target identified through the first AI-enabled GWAS of brown adipose tissue using machine learning-derived phenotypes. In preclinical models, BAT-01 knockdown drives 15% body-weight reduction via peripheral adipose beiging. Internal pipeline program.

Quantifiable outcome

• De-risks drug discovery through human genetics validation at scale
• +2 more outcomes

Named customers4 records

Segments4 records

Ideal customer profiles3 records

Technology focussed Yes

API detail

Has API

No

API docs

API detail

Core technology

AI maturity

App detail

AI capability10 records

Feature7 records

Partnerships

Five partnerships are on record, tiered flagship and core.

• CombinAbleAI (Roche/Genentech)flagshipStrategic or Co-development Partner · 1 June 2024Acquisition of CombinAbleAI platform from Roche/Genentech. The platform provides in silico biology capabilities and multi-omics data integration. Includes engineering team in Israel and computational biology expertise. Represents Insitro's largest strategic acquisition to date.
• Bristol Myers SquibbflagshipStrategic or Co-development Partner · 1 January 2023Strategic collaboration for ALS (amyotrophic lateral sclerosis) drug discovery using Insitro's Virtual Human platform and machine learning capabilities. The partnership includes $50M upfront payment with potential milestone and royalty payments totaling over $2.1B. BMS and Insitro will co-develop targets identified through Insitro's platform.
• Moorfields Eye Hospital / INSIGHTcoreStrategic or Co-development Partner · 1 January 2021AI foundation model collaboration for ophthalmic image analysis and disease detection. INSIGHT project develops AI models using eye scan data for early disease detection and predictive analytics. Partnership provides access to large-scale clinical imaging data.
• Eli LillyflagshipStrategic or Co-development Partner · 1 January 2019Strategic agreement for metabolic diseases including MASLD (metabolic dysfunction-associated steatotic liver disease), MASH (metabolic dysfunction-associated steatohepatitis), and obesity. The partnership leverages Insitro's human genetics platform for target identification and validation in metabolic indications.
• Gilead SciencescoreStrategic or Co-development Partner · 1 January 2018Partnership for NASH (non-alcoholic steatohepatitis) therapies using Insitro's machine learning-driven drug discovery platform. Collaboration focuses on target identification and validation for liver diseases with unmet medical need.

Scale indicators5 records

Recent moves7 records

Expansion highlights6 records

Direct peers

• Recursion Pharmaceuticals: Public AI-driven drug discovery company combining high-throughput biology, automation, and ML to build a wholly-owned and partnered therapeutic pipeline — the closest publicly traded analog to Insitro's platform-plus-pipeline model.
• Exscientia: AI-native pharma with a generative chemistry platform producing small-molecule drug candidates for partners like BMS and Sanofi; competes head-to-head with Insitro's ChemML and partnership-driven GTM.
• Schrödinger: Computational chemistry and physics-based simulation platform serving pharma partners and advancing a wholly-owned pipeline; overlaps with Insitro on physics-informed molecular design (especially post-CombinAbleAI) and platform licensing.
• BenevolentAI: AI drug discovery company using knowledge graphs and ML for target identification and clinical development; comparable to Insitro in the target-ID and repurposing segments and competes for similar pharma partnerships.
• Atomwise: Pioneer in structure-based small-molecule AI design (AtomNet) with pharma partnerships across multiple therapeutic areas; overlaps with Insitro's ChemML and virtual screening capabilities.

Emerging players

• Isomorphic Labs: Alphabet/DeepMind-backed AI drug discovery company applying AlphaFold-derived models to partnered drug design; competes for the same large-pharma ML-discovery mandates and benefits from Alphabet's compute scale.
• Genesis Therapeutics: AI-driven small-molecule design company combining graph neural networks with physics; competes with Insitro's ChemML for partnership-driven discovery programs and on generative chemistry quality.
• XtalPi: China-based AI + robotics drug discovery company with significant pharma partnerships and a public listing; relevant regional and platform peer to Insitro's modality-agnostic design ambitions.
• Iambic Therapeutics: AI-driven drug discovery company using physics-informed neural networks for small-molecule design; comparable to Insitro's ChemML and broader ML-platform thesis with overlapping partnership-driven GTM.

Broad incumbents

• Verily (Alphabet): Alphabet-owned life sciences platform leveraging large-scale clinical and biological data, including former Daphne Koller involvement as chief computing officer; adjacent incumbent in the same ML-meets-biology space, and a potential partner or competitor.

Market position

Strengths5 records

Weaknesses5 records

Competitive moat5 records

Key risks7 records

Key highlights7 records

Customer concentration

• Xx.com/insitro
• LinkedInlinkedin.com/company/insitro

Revenue estimate

Valuation estimate

Number of profiles

Profiles11 records

Subsidiaries1 record

Funding overview

Funding rounds3 records

Investors18 records

Funding detail is available on the Subscription and Enterprise plan.Contact sales →

M&A2 records

Investments

M&A and investment is available on the Subscription and Enterprise plan.Contact sales →

Frequently asked questions about Insitro