Brixo
Skip to main content
Back to Life Sciences Agents
Insilico Medicine logo

Insilico Medicine

Insilico Medicine, a clinical stage biotech company powered by generative AI, is connecting biology, chemistry, and clinical trials analysis using next-generation AI systems. The company has developed AI platforms that utilize deep generative models, reinforcement learning, transformers, and other modern machine learning techniques for novel target discovery and the generation of novel molecular structures with desired properties. Insilico Medicine is developing breakthrough solutions to discover and develop innovative drugs for cancer, fibrosis, immunity, central nervous system diseases, infectious diseases, autoimmune diseases, and aging-related diseases.

Visit Website

Founded

2014

Location

Boston, Massachusetts

Employees

282

Funding

~$123M+ equity; $100M debt

Insilico Medicine — AI-Driven, End-to-End Drug Discovery and Development

Insilico Medicine is a clinical-stage biotech using generative AI and automation to discover and develop novel therapeutics from target to clinic. Its integrated platform, Pharma.AI, spans target discovery, de novo small‑molecule and biologics design, and preclinical-to-clinical decision support. The company operates globally with headquarters in Boston and R&D hubs across North America and Asia. Leadership includes founder and CEO Alex Zhavoronkov and co‑CEO/CSO Feng Ren. Insilico also runs an AI‑enabled robotics lab to accelerate wet‑lab validation.

  • Company site: [Insilico Medicine](https://insilico.com/)
  • Leadership: [Team and bios](https://insilico.com/team)
  • Headquarters: Boston, MA, USA
  • Founded: 2014
  • Size: ~201–500 employees; 73k+ followers
  • Funding and history: [Crunchbase](https://www.crunchbase.com/organization/insilico-medicine)
  • What Insilico Offers

    Insilico’s software and wet‑lab capabilities are packaged as the Pharma.AI suite. These tools can be licensed, used in collaborations, or applied to Insilico’s internal pipeline.

  • PandaOmics (Target Discovery)
  • Finds and ranks novel therapeutic targets by integrating multi‑omics, literature, patents, and clinical data.
  • Learn more: [PandaOmics](https://insilico.com/pandaomics) and peer‑reviewed [methods paper](https://pubs.acs.org/doi/10.1021/acs.jcim.3c01619).
  • Chemistry42 (Small‑Molecule Design)
  • Generative de novo design and multi‑parameter optimization with ADME/Tox constraints for hit‑to‑lead and lead optimization.
  • See examples in Insilico’s case pages (e.g., [USP1](https://insilico.com/usp1)).
  • Biology42 (Generative Biologics)
  • Sequence and structure‑aware biologics design with predictive and physics‑based workflows.
  • Platform overview: [Biology42](https://insilico.com/generativebiologics).
  • AI‑Run Robotics Lab
  • Automates experimental validation to shorten design–make–test–analyze cycles.
  • Lab overview: [AI‑enabled robotics lab](https://insilico.com/roboticslab).
  • Clinical and Pipeline Highlights

  • Lead program: Rentosertib (formerly INS018_055) for idiopathic pulmonary fibrosis (IPF)
  • Among the first AI‑discovered and AI‑designed small molecules to reach Phase II.
  • Coverage: [MIT Technology Review](https://www.technologyreview.com/2024/03/20/1089939/a-wave-of-drugs-dreamed-up-by-ai-is-on-its-way/), [Drug Target Review](https://www.drugtargetreview.com/news/157365/first-ai-designed-drug-rentosertib-named-by-usan/), and [ACS C&EN](https://pubs.acs.org/doi/10.1021/cen-10208-buscon4).
  • Broader pipeline spans oncology and fibrosis, with assets advanced internally and via partnerships. An example of external validation is the Exelixis license for ISM3091, a small molecule discovered on Insilico’s platform: [Exelixis partnership announcement](https://ir.exelixis.com/news-releases/news-release-details/exelixis-and-insilico-medicine-enter-exclusive-global-license).
  • Supporting research: [Nature Biotechnology](https://www.nature.com/articles/s41587-024-02143-0) publication on a small‑molecule TNIK inhibitor linked to fibrosis biology.
  • How It Works: Data, Models, and Workflow

  • Data foundation: PandaOmics aggregates omics datasets, scientific publications, clinical trials, and broader biomedical corpora into a unified knowledge base for target ideation and prioritization .
  • Generative design: Chemistry42 and Biology42 combine generative models with physics‑based and simulation workflows for small molecules and biologics .
  • Automated validation: An AI‑enabled robotics lab closes the loop with rapid experimental testing and iteration .
  • Note: Public documentation does not list specific third‑party software integrations; engagements appear project‑specific and enterprise‑driven.
  • Commercial Model, Pricing, and Access

  • Engagements include:
  • Platform licensing (PandaOmics, Chemistry42, Biology42).
  • Asset‑level collaborations and co‑development.
  • Advancement of Insilico’s internal programs.
  • Pricing and trials:
  • No public self‑serve pricing or free trials are listed for core platforms.
  • Access typically via enterprise agreements or partnerships.
  • Insilico has promoted separate AI assistants in media with trial access, but these are distinct from the core drug discovery suite (see [FierceBiotech coverage](https://www.fiercebiotech.com/medtech/insilico-medicine-launches-ai-assistant-drafting-medical-research-papers)).
  • Who It’s For

  • Large pharma and mid‑size biopharma seeking AI‑accelerated target discovery and rapid hit‑to‑lead with de novo design.
  • Emerging biotechs aiming to expand early pipelines without building a full in‑house informatics stack.
  • Academic translational centers and consortia leveraging multi‑omics and literature mining for target ideation.
  • High‑Value Use Cases

  • Novel target identification and prioritization across multi‑omics, literature, patents, and clinical data .
  • De novo small‑molecule design with multi‑parameter optimization and ADME/Tox filtering for hit and lead series .
  • Generative biologics design and optimization with predictive and physics‑based toolchains .
  • Program advancement and validation through an AI‑run robotics lab to compress cycle times .
  • Market Perception: What Buyers Should Know

  • Pros
  • Tangible clinical progress: Rentosertib’s Phase II status is cited as evidence that AI‑generated molecules can advance in the clinic .
  • Speed and cost: Commentary highlights accelerated design‑to‑clinic timelines versus historical norms .
  • Clear platform narrative: Consistent coverage of PandaOmics and Chemistry42’s end‑to‑end workflow with published methods .
  • Considerations
  • Generalizability: Some skepticism that a single or few clinical programs prove platform‑wide superiority across indications .
  • Limited third‑party software reviews: Few independent user reviews on sites like G2 or Capterra for day‑to‑day platform experience .
  • Opaque pricing and access: Lack of public pricing can lengthen evaluation and procurement cycles.
  • Why It Matters

    Insilico exemplifies the shift from AI as a point solution to an integrated, lab‑connected discovery engine. The combination of target discovery, de novo design, and automated validation aims to reduce cycle times, de‑risk early decisions, and produce candidates that progress clinically. The Phase II advancement of Rentosertib and external deals like the [Exelixis license](https://ir.exelixis.com/news-releases/news-release-details/exelixis-and-insilico-medicine-enter-exclusive-global-license) strengthen the case for platform credibility while buyers assess scalability across diseases.

    Notable Coverage and Resources

  • Company: [Insilico Medicine](https://insilico.com/) | [Team](https://insilico.com/team) | [LinkedIn](https://www.linkedin.com/company/in-silico-medicine)
  • Platforms: [PandaOmics](https://insilico.com/pandaomics) | [Biology42](https://insilico.com/generativebiologics) | [Robotics lab](https://insilico.com/roboticslab)
  • Case studies and areas: [USP1](https://insilico.com/usp1) | [MAT2A](https://insilico.com/mat2a)
  • Clinical and media: [MIT Technology Review](https://www.technologyreview.com/2024/03/20/1089939/a-wave-of-drugs-dreamed-up-by-ai-is-on-its-way/) | [Drug Target Review](https://www.drugtargetreview.com/news/157365/first-ai-designed-drug-rentosertib-named-by-usan/) | [ACS C&EN](https://pubs.acs.org/doi/10.1021/cen-10208-buscon4)
  • Research: [Nature Biotechnology (TNIK inhibitor)](https://www.nature.com/articles/s41587-024-02143-0) | [PandaOmics methods](https://pubs.acs.org/doi/10.1021/acs.jcim.3c01619)
  • Partnerships: [Exelixis license for ISM3091](https://ir.exelixis.com/news-releases/news-release-details/exelixis-and-insilico-medicine-enter-exclusive-global-license)
  • Company background: [Wikipedia](https://en.wikipedia.org/wiki/Insilico_Medicine) | [Crunchbase](https://www.crunchbase.com/organization/insilico-medicine)
  • Getting Started

  • Engage via enterprise sales for platform licensing, pilot projects, or asset collaborations.
  • Prepare a data brief: therapeutic area(s), target classes, available omics/structural data, desired timelines/milestones.
  • Request a technical deep dive on PandaOmics/Chemistry42/Biology42 workflows and validation via the [Insilico Medicine website](https://insilico.com/).
  • Search keywords: Insilico Medicine, Pharma.AI, PandaOmics, Chemistry42, Biology42, AI drug discovery, generative AI for pharma, de novo molecule design, IPF Rentosertib, lab automation, robotics lab, fibrosis and oncology drug pipeline.

    Related Companies

    Atomwise logo

    Atomwise

    Atomwise is a preclinical pharma company revolutionizing how drugs are discovered with AI. Atomwise has strengthened its drug discovery and development expertise by expanding its Board of Directors and creating a Scientific Advisory Board (SAB). These appointments signal a critical milestone for Atomwise as the company focuses on its own internal pipeline. We invented the use of deep learning for structure-based drug discovery, today developing a pipeline of small-molecule drug candidates advancing into preclinical studies. Our AtomNet technology has been used to unlock more undruggable targets than any other AI drug discovery platform. We are tackling over 600 unique disease targets with more than 250 partners around the world, including leading pharmaceutical, agrochemical, and emerging biotechnology companies. Atomwise has raised over $174 million from leading venture capital firms to advance our mission to make better medicines, faster. We’re at a critical time in history where our need for new kinds of medicines is greater than any time in human memory. Fortunately, we can leverage advancing technology and scientific breakthroughs to accelerate discovery. New data, new algorithms, new compute platforms lift all of us, enable our work on the hardest of problems, empower us to invent and create, and ultimately save one billion lives. Join us: www.atomwise.com/careers

    Genesis Therapeutics logo

    Genesis Therapeutics

    Genesis Therapeutics – headquartered in Burlingame, CA, with a fully integrated laboratory in San Diego – is unifying AI and biotechnology to discover novel and breakthrough treatments for patients with severe and devastating conditions. We are using a proprietary state-of-the-art generative and predictive AI platform called GEMS (Genesis Exploration of Molecular Space), to accelerate and optimize small molecule drug discovery. The GEMS platform integrates deep learning-based predictive models, molecular simulations, and molecular generative AI. GEMS accelerates hit ID through lead optimization and candidate selection by generating promising molecules for synthesis and experimental testing, and iterating this process through multiple cycles of AI-enabled discovery and optimization. We have leveraged GEMS to build an internal pipeline with multiple programs against high-value targets, including data-poor and canonically undruggable targets where GEMS is uniquely advantaged. In addition, Genesis has two AI platform collaborations across a range of therapeutic areas: Eli Lilly (signed in 2022) and Genentech (signed in 2020). Genesis has raised over $280M in funding from top technology and biotech investors, including Andreessen Horowitz, Rock Springs Capital, T. Rowe Price, Fidelity, Radical Ventures, NVentures (NVIDIA's VC arm), BlackRock, and Menlo Ventures. We are rapidly growing our team with a variety of openings on our machine learning, computational chemistry, and software teams (primarily located in the Bay Area) and our chemistry, biology, and clinical teams (primarily located in San Diego). To learn more about Genesis Therapeutics, or current employment opportunities, please visit our website.

    Insitro logo

    Insitro

    insitro is a data-driven drug discovery and development company that leverages machine learning and high-throughput biology to transform the way medicines are created to help patients. At insitro, we are rethinking the entire drug discovery process, from the perspective of machine learning, human genetics, and high-throughput, quantitative biology. Over the past five decades, we have seen the development of new medicines becoming increasingly more difficult and expensive, leaving many patients with significant unmet need. We’re embarking on a new approach to drug development – one that leverages machine learning and unique in vitro strategies for modeling disease state and designing new therapeutic interventions. We aim to eliminate key bottlenecks in traditional drug discovery, so we can help more people sooner and at a much lower cost to the patient and the healthcare industry. We believe that by harnessing the power of technology to interrogate and measure human biology, we can have a major impact on many diseases. We invest heavily in cutting edge bioengineering technologies to enable the construction of large-scale, high-quality data sets that are designed specifically to drive machine learning methods. Our first application is to use human genetics, functional genomics, and machine learning to build a new generation of in vitro human cell-derived disease models whose response to perturbation is designed to be predictive of human clinical outcomes. This cannot be done without great people. We are bringing together an outstanding team of people whose expertise spans multiple disciplines - life sciences, machine learning, human genetics, engineering, and drug discovery - and building a unique culture where people from diverse backgrounds work as a single team towards a common goal. We offer opportunities to collaborative people with expertise in life science and computational science. Join us to help bring better health to more people, faster and cheaper.