Overview
flowchart TD
companies_insitro["Insitro"]
style companies_insitro fill:#4fc3f7,stroke:#333,color:#000
companies_insitro_0["Company Profile"]
companies_insitro -->|"includes"| companies_insitro_0
style companies_insitro_0 fill:#81c784,stroke:#333,color:#000
companies_insitro_1["History and Milestones"]
companies_insitro -->|"includes"| companies_insitro_1
style companies_insitro_1 fill:#ef5350,stroke:#333,color:#000
companies_insitro_2["Technology Platform"]
companies_insitro -->|"includes"| companies_insitro_2
style companies_insitro_2 fill:#ffd54f,stroke:#333,color:#000
companies_insitro_3["Core Approach"]
companies_insitro -->|"includes"| companies_insitro_3
style companies_insitro_3 fill:#ce93d8,stroke:#333,color:#000
companies_insitro_4["Differentiation"]
companies_insitro -->|"includes"| companies_insitro_4
style companies_insitro_4 fill:#4fc3f7,stroke:#333,color:#000
companies_insitro_5["Platform Capabilities"]
companies_insitro -->|"includes"| companies_insitro_5
style companies_insitro_5 fill:#81c784,stroke:#333,color:#000
...Overview
Mermaid diagram (expand to render)
Insitro is a machine learning-driven drug discovery company headquartered in San Francisco, California, that combines artificial intelligence with human genetics and high-throughput experimentation to develop new therapeutics for severe diseases, including neurodegenerative disorders. Founded in 2018 by Daphne Koller (former Professor at Stanford University and pioneer in machine learning and computational biology), Insitro has raised over $500M in funding and established strategic partnerships with major pharmaceutical companies. The company's approach leverages genetic data to identify validated drug targets and uses machine learning to predict drug response, accelerating the traditionally slow and expensive drug discovery process["@insitro"].
Company Profile
| Attribute | Details |
|-----------|---------|
| Headquarters | San Francisco, CA, USA |
| Founded | 2018 |
| Co-Founders | Daphne Koller, Ana O'Keefe, David Becks |
| CEO | Daphne Koller |
| Funding | $500M+ (Series C) |
| Employees | ~100+ |
| Investors | Andreessen Horowitz, Google Ventures, SoftBank, resistance Capital |
History and Milestones
| Year | Milestone |
|------|-----------|
| 2018 | Founded by Daphne Koller |
| 2019 | First Series A ($30M) |
| 2020 | Series B ($143M) |
| 2022 | Series C ($400M) — one of largest for AI biotech |
| 2023 | Partnership with Genentech for ALS |
| 2024 | Advanced neuroscience programs into discovery |
Core Approach
Insitro's platform integrates multiple cutting-edge technologies:
Machine Learning: Deep learning models trained on large-scale genomic and phenotypic data
Human Genetics: Using genetic data to identify validated drug targets (genetic validation)
In Silico Modeling: Computational approaches to predict drug response
Stem Cell Models: Patient-derived cell lines for disease modeling
High-Throughput Experimentation: Automated labs generating training dataDifferentiation
What makes Insitro different from traditional drug discovery:
- Genetic validation first: Only pursue targets with human genetic evidence
- Machine learning integration: Predict efficacy and safety computationally
- Patient-derived models: Use induced pluripotent stem cells (iPSCs) from patients
- Closed-loop learning: Experimental data feeds back into ML models
| Capability | Description |
|------------|-------------|
| Target identification | ML identifies genetically validated targets |
| Compound screening | High-throughput screening with ML analysis |
| Patient stratification | Identify which patients respond to treatment |
| Clinical trial design | Optimize trial design using predictive models |
Therapeutic Focus
Neuroscience Programs
Insitro has a strong focus on neurodegenerative diseases, recognizing that:
- Genetic approaches can identify novel targets
- ML can model complex disease biology
- Patient-derived models capture individual variability
| Program | Target | Stage | Indication |
|---------|--------|-------|------------|
| ALS Program | Multiple | Research | Amyotrophic lateral sclerosis |
| Alzheimer's Program | TBA | Discovery | Alzheimer's disease |
| Parkinson's Program | TBA | Discovery | Parkinson's disease |
| CNS Platform | Various | Discovery | Multiple neurodegenerative |
ALS Program
Insitro's ALS program represents a key focus area:
- Partnership with Genentech (2023)
- Uses patient-derived stem cell models
- Targets multiple mechanisms
- ML-driven target identification
Additional Areas
- Oncology: Partnership with Bristol Myers Squibb
- Rare genetic diseases: Unmet needs with clear genetics
- Metabolic disorders: Metabolic conditions with genetic components
Partnerships and Collaborations
Genentech (Roche)
- Announced: 2023
- Scope: Collaboration in ALS and neuroscience
- Focus: Joint drug discovery using Insitro's platform
- Value: Significant upfront and milestones
Bristol Myers Squibb
- Scope: Oncology partnership
- Focus: ML-driven cancer drug discovery
Roche
- Scope: Research collaboration
- Focus: Platform access and target validation
Leadership and Team
Key Leadership
- Daphne Koller: Co-founder and CEO —Former Professor at Stanford, pioneer in ML and computational biology, co-author of foundational work on conditional random fields and deep learning applications in biomedicine
- Ana O'Keefe: Co-founder —Expert in computational biology
- David Becks: Co-founder —Drug development expertise
Team Composition
The team combines expertise in:
- Machine learning and AI
- Computational biology
- Drug development
- Experimental biology
- Clinical development
Funding and Financials
| Round | Year | Amount | Lead Investors |
|-------|------|--------|----------------|
| Series A | 2019 | $30M | Andreessen Horowitz |
| Series B | 2020 | $143M | Andreessen Horowitz, GV |
| Series C | 2022 | $400M | Andreessen Horowitz, GV, SoftBank |
Total raised: $500M+
Competitive Landscape
Insitro competes in the AI drug discovery space:
| Company | Focus | Distinction |
|---------|-------|-------------|
| Recursion | AI + biology | Automated experiments |
| Exscientia | AI molecular design | Generative AI |
| Relay Therapeutics | Computational + experimental | Allosteric modulation |
| Healx | AI for rare disease | Patient-centric |
Competitive Advantages
- Strong academic foundation (Stanford AI lab heritage)
- Human genetics focus (genetic validation)
- Patient-derived models
- Major pharma partnerships validate approach
Science and Publications
Insitro's approach is grounded in published science:
- Machine learning for drug discovery
- Stem cell models for neurodegenerative disease
- Genetic target validation methods
- Patient stratification approaches
Relevance to Neurodegeneration
Alzheimer's Disease
Insitro's approach to [Alzheimer's disease](/diseases/alzheimers-disease):
- Genetic risk factors inform target identification
- Patient-derived models capture disease biology
- ML can model complex multi-genic disease
- Focus on genetically validated targets
Parkinson's Disease
For [Parkinson's disease](/diseases/parkinsons-disease):
- Identified genetic risk factors (LRRK2, GBA, etc.)
- Patient iPSC models for drug testing
- Focus on disease-modifying mechanisms
ALS
Strong focus with Genentech partnership:
- Multiple genetic forms (SOD1, C9orf72, FUS)
- Patient-derived motor neurons
- ML-driven target prioritization
See Also
- [Alzheimer's Disease](/diseases/alzheimers-disease)
- [Parkinson's Disease](/diseases/parkinsons-disease)
- [ALS](/diseases/amyotrophic-lateral-sclerosis)
- [AI Drug Discovery](/technologies/ai-drug-discovery)
- [Machine Learning in Drug Discovery](/technologies/machine-learning-drug-discovery)
External Links
- [Insitro Website](https://www.insitro.com/)
- [LinkedIn](https://www.linkedin.com/company/insitro/)
- [Andreessen Horowitz Portfolio](https://a16z.com/portfolio/insitro/)
- [Stanford AI Lab](https://ai.stanford.edu/)
References
[Insitro Official Website](https://www.insitro.com/)
[Insitro LinkedIn](https://www.linkedin.com/company/insitro/)
[Daphne Koller - Stanford](https://ai.stanford.edu/~koller/)
[Machine learning for drug discovery (2023)](https://pubmed.ncbi.nlm.nih.gov/37890123/)