Syntensor

Syntensor is a pioneering company that develops new methods to model complex metabolic interactions within every cell and across all tissues. By generating mechanistic, causal hypotheses for drug efficacy and systemic toxicity, Syntensor aims to transform how medicines are developed and prescribed. The company uses machine learning methods coupled with first-principles thinking in biology to assist drug developers, clinicians, and physicians. Syntensor addresses the complexity and scale of the human biological system by applying machine learning methods to model biological processes dynamically at a systemic scale. As a leader in the field of dynamical systems modeling for biology, Syntensor is the first to apply these methods commercially at scale. Its platform is generalizable across diseases, therapeutic modalities, and patient genotype/phenotype, allowing scientists and doctors to simulate the effects of a drug on a patient to evaluate efficacy and potential toxicity. Syntensor advances fundamental methods in Geometric Deep Learning and Neural Graph Differential Equations, capturing the dynamics and state-space of a large-scale representation of the human biological system with 2,000,000 components per cell for around 2,000 cell types. The company is also a contributor and supporter of DiffeqML/Torchdyn, the leading open-source library in the Neural Graph Differential Equations space. Syntensor’s platform couples mechanistic, causal inference with an apps and services layer, enabling drug developers, clinicians, and physicians to self-serve hypotheses and predict the dynamics of individual components of the system and the systemic effects of perturbation. The company operates as a distributed-first team working asynchronously across timezones in East and West Coast US, Canada, and Europe, and offers competitive salary, stock options, and 401K for all open roles.