Lessons learned during the journey of data: from experiment to model for predicting kinase affinity, selectivity, polypharmacology, and resistance.

Recent advances in machine learning (ML) are reshaping drug discovery. Structure-based ML methods use physically-inspired models to predict binding affinities from protein:ligand complexes. These methods promise to enable the integration of data for many related targets, which addresses issues related to data scarcity for single targets and could enable generalizable predictions for a broad range of targets, including mutants.

Continuous Subcutaneous Foslevodopa/Foscarbidopa in Parkinson's Disease: Safety and Efficacy Results From a 12-Month, Single-Arm, Open-Label, Phase 3 Study.

Introduction: Foslevodopa/foscarbidopa, a soluble formulation of levodopa/carbidopa (LD/CD) prodrugs for the treatment of Parkinson's disease (PD), is administered as a 24-hour/day continuous subcutaneous infusion (CSCI) with a single infusion site. The efficacy and safety of foslevodopa/foscarbidopa versus oral immediate-release LD/CD was previously demonstrated in patients with PD in a 12-week, randomized, double-blind, phase 3 trial (NCT04380142). We report the results of a separate 52-week, open-label, phase 3 registrational trial (NCT03781167) that evaluated the safety/tolerability and efficacy of 24-hour/day foslevodopa/foscarbidopa CSCI in patients with advanced PD.

Safety and efficacy of continuous subcutaneous foslevodopa-foscarbidopa in patients with advanced Parkinson's disease: a randomised, double-blind, active-controlled, phase 3 trial.

Background: Levodopa is the most effective symptomatic therapy for Parkinson's disease, but patients with advanced Parkinson's disease develop motor fluctuations with chronic oral levodopa therapy. Foslevodopa-foscarbidopa is a soluble formulation of levodopa and carbidopa prodrugs that is delivered as a 24-h/day continuous subcutaneous infusion, and we aimed to assess the safety and efficacy of this formulation in patients with advanced Parkinson's disease.

Methods: A 12-week randomised, double-blind, double-dummy, active-controlled study was done at 65 academic and community study centres in the USA and Australia.

TeachOpenCADD 2022: open source and FAIR Python pipelines to assist in structural bioinformatics and cheminformatics research.

Computational pipelines have become a crucial part of modern drug discovery campaigns. Setting up and maintaining such pipelines, however, can be challenging and time-consuming-especially for novice scientists in this domain. TeachOpenCADD is a platform that aims to teach domain-specific skills and to provide pipeline templates as starting points for research projects.