> ## Content Index
> Fetch the complete content index at: https://nexi.fund/llms.txt
> Use this file to discover other available public pages before exploring further.

# Insitro TherML: The AI-Native Drug Discovery Platform Reshaping Pharma R&D
- URL: https://nexi.fund/insitro-ai-drug-discovery-2026/
- Published: 2026-07-01T15:26:16.000Z
- Updated: 2026-07-01T15:26:16.000Z
- Description: Insitro has raised 100M to build TherML, a modality-agnostic AI engine for drug discovery. Early pharma validation from Lilly and BMS.
- Author: Nexi.fund Labs
- Tags: AI & Infrastructure, Biotech & Health, #mode-1, #hook-number, #track-F, #social-linkedin, #nosmm

The company has raised roughly $800 million to build a single machine-learning engine that designs small molecules, antibodies, oligonucleotides, and complex biologics. In January 2026, Insitro launched TherML, a platform that unifies four drug modalities under one AI architecture, trained on data its own automated labs generate at scale.

🎯

TherML treats potency and manufacturability as interdependent design criteria — not sequential trade-offs.  
  
The CombinAbleAI acquisition adds physics-informed, AI-driven design for complex biologic therapeutics, completing a full-stack system spanning every major drug modality.  
  
Early validation from Eli Lilly and Bristol Myers Squibb suggests large pharma sees the platform as infrastructure, not just another point-solution tool. 

Bringing a single drug to market now exceeds $2 billion. Nine of ten clinical candidates fail, most during Phase 2, after the expensive part has started. The industry has tried to make R&D cheaper through AI, but most AI-native drug discovery companies operate inside one modality: small molecules (Atomwise, Exscientia) or antibodies (Absci, BigHat).

Integration across modalities is the hard part. Each class has its own rules for binding, stability, delivery, and manufacturability. Building a platform that handles all four requires not just separate models for each, but a unified training pipeline that can transfer insights between them.

That is what TherML attempts. As we wrote in June, the convergence of AI and biology is reshaping drug discovery. Few companies are trying to build the infrastructure layer rather than a single therapy. [ai-drug-discovery-platforms-2026](https://eclibra.com/ai-drug-discovery-platforms-2026?ref=nexi.fund)

$800M total funding raised ↑ 2.3× since 2023 

#### Insitro capital raised to date

Includes $150M from non-dilutive pharma partnerships. Latest valuation: $7B. · *Insitro press releases, 2026*

## The TherML Architecture

TherML is not a single model. It is a stack of specialized engines connected by a shared training infrastructure, each responsible for one modality but feeding into a common representation space. The small-molecule engine uses Insitro's Quantitative Adaptive Libraries, algorithmically designed chemical libraries that map local regions of chemical space and generate training data on demand. The oligonucleotide engine industrializes siRNA candidate design across targets using AI and automation. The biologics engine, inherited from CombinAbleAI, applies physics-informed optimization pre-trained on more than 100,000 molecular dynamics surrogates to predict protein structure and flexibility. The antibody engine designs multi-specifics and T-cell engagers.

The key architectural choice: potency and developability are optimized simultaneously, not sequentially. Traditional drug design optimizes for binding affinity first, then checks whether the molecule can be manufactured. TherML generates designs that are already manufacturable. The platform estimates stability, solubility, and synthesis complexity alongside target engagement predictions.

> "Drug discovery has traditionally optimized molecules for potency before assessing developability — often discovering that highly potent candidates face manufacturing constraints. By integrating CombinAbleAI's physics-informed, AI-driven design with our causal biology platform, we treat potency and manufacturability as interdependent design criteria from the outset."— Philip Tagari, Chief Scientific Officer, Insitro

#### How TherML differs from other AI drug discovery platforms

Most AI drug discovery companies build for one modality. Atomwise runs structure-based small-molecule screens. Absci designs proteins. Recursion runs phenotypic imaging at scale. Insitro is the only company that builds small-molecule, antibody, oligonucleotide, and biologic models inside a shared platform, and the only one that combines its own wet-lab data generation (automated cell biology labs in South San Francisco) with its ML training pipeline in a continuous feedback loop.  
  
The closest competitor is Isomorphic Labs, but DeepMind's spinout focuses on AlphaFold-derived protein structure prediction, not end-to-end drug design. Recursion operates at scale on the phenotypic imaging side but outsources chemistry. Insitro's bet is that owning the entire stack (data generation, model training, and modality design) produces better candidates than any single layer alone. 

## Pharma Validation

The thesis is not theoretical. Eli Lilly signed three separate agreements in 2024-2025, including a September 2025 collaboration to build first-in-kind ML models predicting key pharmacological properties of small molecules. Bristol Myers Squibb extended its collaboration in 2025 after an earlier option exercise in 2022, leveraging the ChemML platform to discover molecules for ALS, a target where traditional approaches have produced few viable candidates.

The partnership structure is unusual. The company retains full global rights to its research programs; the pharma partner receives milestone payments and royalties on approved products. It is positioning itself as a platform owner rather than a contract research organization. The $150 million in non-dilutive partnership revenue already on the books supports that framing.

## Market Position

The AI drug discovery market has fragmented into roughly 200 startups globally. Most will fail because drug discovery's failure rate is structural, not because their models are wrong. TherML addresses the most common cause of clinical failure: developability issues that were predictable before trials began. If the platform reduces Phase 2 attrition by even 10 percentage points, the economic impact across a partnered pipeline would be measured in billions.

The risk is execution. The CEO (Daphne Koller, Stanford professor, Coursera co-founder, MacArthur fellow) has the credibility to attract talent and capital, but the company has not yet advanced a wholly-owned candidate to clinical trials. All pipeline assets are at discovery or preclinical stage. TherML is broad in scope. The question is whether it produces molecules that survive Phase 3.

### What happens to AI drug discovery by 2028?

🔮

**Platform-driven drug discovery will account for 15-20% of new clinical candidates entering Phase 1, up from roughly 5% today.**  
  
Probability: 65%. Three platform companies (Insitro, Recursion, Isomorphic Labs) will have generated at least one Phase 2 readout each by end of 2027, creating a feedback loop between real clinical data and model training. 

#### ✅ Arguments for

Both partners are reinvesting. Both extended collaborations in 2025, signalling confidence in the platform approach.  
  
The multi-modality bet is defensible: if the platform works across drug classes, it captures more of the pharma value chain than any single-modality competitor.  
  
**Confirmation criteria:** The company or a peer platform-company advances a wholly-owned candidate to Phase 1 within 12 months. 

#### ❌ Arguments against

No wholly-owned clinical candidate yet. The TherML platform has generated preclinical data but nothing in humans. The gap between preclinical promise and Phase 2 survival is the industry's steepest.  
  
Multi-modality increases scope, but also complexity. A platform that does everything well may turn out to do nothing exceptionally, especially against narrow specialists who optimize for one chemistry class.  
  
**Disconfirmation criteria:** No Insitro candidate enters the clinic by end of 2027, or an early-phase trial fails on safety. This is the most common developability failure TherML is designed to prevent. 

## Key signals to track

📊

**Key signals to track**  
  
IND filing for a wholly-owned candidate (pipeline progress)  
Partner option exercise on a TherML-designed molecule (external validation)  
TherML-designed molecule enters Phase 2 without major safety revision (developability claim test)  
A competitor launches a comparable multi-modality platform (competitive signal) 

## Development scenarios

#### 🟢 Optimistic scenario (25%)

TherML produces a clinical candidate within 18 months that shows a clean safety profile in Phase 1\. Both partners exercise options on platform-designed molecules. The multi-modality thesis is validated, and the company raises a Series D at a valuation exceeding $12B.  
  
**Implications:** Platform-based drug discovery becomes the default model for pharma R&D partnerships, and the company is positioned as the infrastructure layer. 

#### 🟡 Base-case scenario (50%)

TherML generates preclinical candidates, but the first wholly-owned IND filing is delayed to 2028\. Partnership revenue grows to $250M+ as existing partners expand collaborations. The platform gains credibility through partnered programs while in-house assets remain in discovery.  
  
**Implications:** Insitro becomes the preferred AI partner for pharma, profitable on partnership revenue but years away from an approved drug. 

#### 🔴 Pessimistic scenario (25%)

A partnered program fails in Phase 2, raising questions about platform-predicted developability. The partner does not exercise its option. Without external validation, the $7B valuation compresses in the next funding round.  
  
**Implications:** TherML's multi-modality scope is seen as a liability. Too broad to excel at any single modality. Capital shifts toward focused platforms with clearer paths to market. 

## Sources

[ insitro to Acquire CombinAbleAI to Complete its Full Stack, Modality-Agnostic AI Platform for Drug Discovery and Design Official press release detailing the TherML platform launch and CombinAbleAI acquisition — the primary source for all platform architecture claims. Insitro / BusinessWire ](https://www.insitro.com/news/combinabletherml?ref=nexi.fund) 

Primary source: platform announcement, January 2026

[ insitro partners with Lilly to build first-in-kind machine learning models Details of the September 2025 Eli Lilly collaboration on ML models for small-molecule drug discovery — the most significant pharma partnership validation. Insitro press release ](https://www.insitro.com/news/insitro-partners-with-lilly-to-build-first-in-kind-machine-learning-models-to-advance-small-molecule-drug-discovery?ref=nexi.fund) 

Key partnership — Lilly collaboration, September 2025

[ insitro Extends Research Collaboration with Bristol Myers Squibb BMS extended its Insitro collaboration in 2025 to discover molecules for ALS, leveraging the ChemML platform — second major pharma validation. Insitro press release ](https://www.insitro.com/news/insitro-extends-research-collaboration-with-bristol-myers-squibb-leveraging-insitros-chemml-discovery-platform?ref=nexi.fund) 

BMS collaboration extension, 2025