Nature

Relationship between prediction accuracy and uncertainty in compound potency prediction using deep neural networks and control models

Predictions of most machine learning (ML) models including all deep learning models 1 cannot be rationalized via human reasoning, which is often referred to as the “black box” nature of such models 2.
Nasdaq

Predictive Oncology Develops Advanced Predictive Models for Natural Compounds in Cancer Drug Discovery

Predictive Oncology Inc. announced the successful development of predictive models for 21 unique compounds sourced from the University of Michigan's Natural Products Discovery Core, marking a ...
Medical Xpress

Experimental compounds show promise for Alzheimer's and pain treatment in animal models

A study published in the Journal of Medicinal Chemistry presents a new family of candidate compounds for the treatment of Alzheimer's disease and pain, which have shown promising effects in animal ...
Nature

Ligand-based machine learning models to classify active compounds for prostaglandin EP2 receptor

Prostaglandins exhibit remarkable chemical diversity owing to their unique structural features and multiple isomeric forms. They are lipid compounds derived from arachidonic acid, a polyunsaturated ...
PsyPost on MSN

Psychedelic compound reduces cocaine motivation and cravings in animal models

Recent laboratory research reveals that a chemical compound known for inducing psychedelic effects reduces the motivation to ...
News Medical

New AI models quickly find compounds that target Lyme bacteria

Based on these initial screenings, the researchers then developed AI models which could comb through a large swath of the estimated 1 X 10 60 compounds (that's 1 followed by 60 zeroes) in the ...