Purpose: Variability in patient treatment responses can be a barrier to effective care. Utilization of available patient databases may improve the prediction of treatment responses. We evaluated machine learning methods to predict novel, individual patient responses to pregabalin for painful diabetic peripheral neuropathy, utilizing an agent-based modeling and simulation platform that integrates real-world observational study (OS) data and randomized clinical trial (RCT) data. Patients and methods: The best supervised machine learning methods were selected (through literature review) and combined in a novel way for aligning patients with relevant subgroups that best enable prediction of pregabalin responses. Data were derived from a German OS of pregabalin (N 2642) and nine international RCTs (N 1320).

Natural products are organic biomolecules produced by nature and, particularly those produced by microbiota, represent a rich source of evolutionarily optimized biologically active molecules. The Adapsyn platform combines genomic and metabolomic data with artificial intelligence and machine-learning to identify novel, mechanistically diverse evolved small molecules from human and environmental microbiomes. The financing will support the company's internal drug development programs. "We are excited to apply our platform to unlock the unique targeting capacity of these evolved compounds and realize new therapeutics," commented Nathan Magarvey, PhD, Founder and Chief Scientific Officer of Adapsyn. "Recent technological advances in machine learning, artificial intelligence, and large-scale genomic and metabolomic analysis are reenergizing the field of natural product drug development, and Adapsyn is excited to be at the forefront of this work."