Foundation models of life, for life.
We build models of life beyond human understanding. Our models extrapolate from data to design breakthrough biological medicines. When the data is insufficient, we build experiments to create it, at unprecedented scale.
We are AI and biochemistry pioneers from
We work on the beach, where wet and dry meet to produce the best models for drug discovery.
Foundation models for better medicines
We build end-to-end foundation models that learn to design molecules directly from diverse observations of life. We specialize in sequence-based medicines like mRNA, siRNA, ASOs, and peptides where sequence is instrumental to function.
Deep learning from life
Others take a narrow, structure-based approach. We train models on massive amounts of heterogeneous data spanning sequence, function and structure. This enables our models to understand the phenomenon of life empirically. They thus generalize across programs and problems to unlock new therapies. Where training data is lacking, we build tools to generate it experimentally at unprecedented scale.
Our models train on heterogenous, multi-scale data, including public datasets, data generated by our lab, and partner data.
This enables them to synthesize an empirical understanding of the phenomenon of life and generalize across programs and problems.
Rapid wet + dry validation
We score novel data and designs in silico to continually improve our models and assays. But in silico validation is insufficient.
Our in-house wet lab ranks models and validates designs in vitro and in vivo at a high frequency. Iterative cycles reduce time and cost from design to drug candidate.
We score novel data and designs in silico to continually improve our models and assays. But in silico validation is insufficient.
Our in-house wet lab is also continually ranking models and validating designs in vitro and in vivo. Iterative cycles reduce time and cost from design to drug candidate.
Breakthrough drugs, beyond the data
Our proprietary algorithms are engineered to extrapolate beyond the best molecules in the data. Instead of merely learning what the best molecules in the data look like, they learn to iteratively improve therapeutic molecules, yielding designs superior to any seen before.
Models train on the best existing designs and extrapolate further, discerning how to improve molecules to ultimately make better designs than anything they’ve seen in the data.
We wield this process to enable you to design novel drug candidates that outperform current options across numerous properties.
Building custom models together
We partner with leading drugmakers to customize foundation models for their discovery programs. Then we co-design novel medicines and empower our partners to take them to the clinic.
We view partnerships as strategic alliances, working together over time to tune models, utilize data, and transfer knowledge. Let’s discuss how our team and technology can optimize your AI investment and pipeline.
Inside Inceptive
Our antedisciplinary team of scientists, AI researchers, and engineers works together on “the beach” where wet and dry meet and new ideas come to life.
Founded by AI and biochemistry pioneers in 2021, Inceptive now has offices in Palo Alto, Berlin and Zurich.
Backed by
.svg)
Models and molecules with maximum impact
Our mission
We believe AI models can do the greatest good for humanity by learning the mechanisms of life and designing novel therapies. We’re hiring scientists and engineers across AI and bio with the drive to optimize black box models for medicine.
Beginners only
We are leaders in our fields, but we bring a humble beginner’s mindset to our work. To explore the frontiers of life and design better medicines, we have to abandon what we thought we knew. We continuously start from scratch, ask new questions together, and follow the data.
