Skip to content

Novel applications of machine learning in cheminformatics

New Content ItemThere has been a renewed interest in novel machine learning techniques in cheminformatics during the last years. This has been driven both by new methods, access to larger and imbalanced datasets as well as progress in high-performance and cloud computing. For example, methods such as conformal prediction, deep learning and matrix factorization have already made a significant impact and are part of making the drug discovery process more data-driven and efficient.

The 6th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2017) was held at Karolinska Institutet, Stockholm, Sweden on June 14-16, 2017. Authors whose papers were accepted to this conference (see Proceedings of Machine Learning Research, Volume 60) in the special section on Cheminformatics were invited to submit an extended version of their work to this special article collection. In addition the wider research community was invited to submit cheminformatics-related research involving applications or methods of machine learning with a novel direction.

Guest Edited by Ola Spjuth

  1. Content type: Methodology

    Docking and scoring large libraries of ligands against target proteins forms the basis of structure-based virtual screening. The problem is trivially parallelizable, and calculations are generally carried out ...

    Authors: Laeeq Ahmed, Valentin Georgiev, Marco Capuccini, Salman Toor, Wesley Schaal, Erwin Laure and Ola Spjuth

    Citation: Journal of Cheminformatics 2018 10:8

    Published on:

  2. Content type: Research article

    Iterative screening has emerged as a promising approach to increase the efficiency of screening campaigns compared to traditional high throughput approaches. By learning from a subset of the compound library, ...

    Authors: Fredrik Svensson, Avid M. Afzal, Ulf Norinder and Andreas Bender

    Citation: Journal of Cheminformatics 2018 10:7

    Published on: