Using Jupyter Notebooks for re-training machine learning models

Author(s)
Aljosa Smajic, Melanie Grandits, Gerhard F. Ecker
Abstract

Machine learning (ML) models require an extensive, user-driven selection of molecular descriptors in order to learn from chemical structures to predict actives and inactives with a high reliability. In addition, privacy concerns often restrict the access to sufficient data, leading to models with a narrow chemical space. Therefore, we propose a framework of re-trainable models that can be transferred from one local instance to another, and further allow a less extensive descriptor selection. The models are shared via a Jupyter Notebook, allowing the evaluation and implementation of a broader chemical space by keeping most of the tunable parameters pre-defined. This enables the models to be updated in a decentralized, facile, and fast manner. Herein, the method was evaluated with six transporter datasets (BCRP, BSEP, OATP1B1, OATP1B3, MRP3, P-gp), which revealed the general applicability of this approach.

Organisation(s)
Department of Pharmaceutical Sciences
Journal
Journal of Cheminformatics
Volume
14
No. of pages
9
ISSN
1758-2946
DOI
https://doi.org/10.1186/s13321-022-00635-2
Publication date
08-2022
Peer reviewed
Yes
Austrian Fields of Science 2012
301207 Pharmaceutical chemistry
Keywords
ASJC Scopus subject areas
Library and Information Sciences, Computer Science Applications, Physical and Theoretical Chemistry, Computer Graphics and Computer-Aided Design
Portal url
https://ucrisportal.univie.ac.at/en/publications/using-jupyter-notebooks-for-retraining-machine-learning-models(07a1579d-7acd-44b8-abed-43b566a482f0).html