Message Passing Neural Networks Improve Prediction of Metabolite Authenticity

Flynn, Noah R.; Swamidass, S. Joshua

doi:10.1021/acs.jcim.2c01383

Cited by 3 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once the (likely) SoMs in a molecule are identified, medicinal chemists can often devise strategies for optimizing the metabolic properties while maintaining the compound’s bioactivity on the biomacromolecular target. Likewise, some metabolite structure predictors (including GLORYx, Meteor, − and XenoNet , ) use predicted SoMs to filter and rank predicted metabolites.…”

Section: Introductionmentioning

confidence: 99%

Active Learning Approach for Guiding Site-of-Metabolism Measurement and Annotation

Chen,

Seidel,

Jacob

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

The ability to determine and predict metabolically labile atom positions in a molecule (also called "sites of metabolism" or "SoMs") is of high interest to the design and optimization of bioactive compounds, such as drugs, agrochemicals, and cosmetics. In recent years, several in silico models for SoM prediction have become available, many of which include a machinelearning component. The bottleneck in advancing these approaches is the coverage of distinct atom environments and rare and complex biotransformation events with high-quality experimental data. Pharmaceutical companies typically have measured metabolism data available for several hundred to several thousand compounds. However, even for metabolism experts, interpreting these data and assigning SoMs are challenging and timeconsuming. Therefore, a significant proportion of the potential of the existing metabolism data, particularly in machine learning, remains dormant. Here, we report on the development and validation of an active learning approach that identifies the most informative atoms across molecular data sets for SoM annotation. The active learning approach, built on a highly efficient reimplementation of SoM predictor FAME 3, enables experts to prioritize their SoM experimental measurements and annotation efforts on the most rewarding atom environments. We show that this active learning approach yields competitive SoM predictors while requiring the annotation of only 20% of the atom positions required by FAME 3. The source code of the approach presented in this work is publicly available.

show abstract

Section: Introductionmentioning

confidence: 99%

Active Learning Approach for Guiding Site-of-Metabolism Measurement and Annotation

Chen,

Seidel,

Jacob

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Metabolite structure predictors making use of predicted SoMs include GLORYx, 12 Meteor, [13][14][15] and XenoNet. 16,17 https://doi.org/10.26434/chemrxiv-2023-4dnf1 ORCID: https://orcid.org/0000-0003-2667-5877 Content not peer-reviewed by ChemRxiv. License: CC BY 4.0 SoM predictors are generally found to perform well.…”

Section: Introductionmentioning

confidence: 99%

FAME.AL: Site-of-metabolism prediction with active learning

Chen,

Seidel,

Jacob

et al. 2023

Preprint

View full text Add to dashboard Cite

The ability to determine and predict metabolically labile atom positions in a molecule (also called “sites of metabolism” or “SoMs”) is of high interest to the design and optimization of bioactive compounds such as drugs, agrochemicals, and cosmetics. In recent years, several in silico models for SoM prediction have become available, many of which include a machine-learning component. The bottleneck in the further development of these approaches is the coverage of distinct atom environments and rare and complex biotransformation events with high-quality experimental data. In this context, active learning strategies could yield higher data efficiency and, in addition, provide guidance to experimentalists on which atom environments to investigate next for maximum information gain. Here we report on the development and validation of FAME.AL, an active learning approach for site-of-metabolism prediction that builds on the previously published FAst MEtabolizer (FAME 3). The active learning approach yielded competitive performance for phase 1 and phase 2 metabolism (Matthews correlation coefficients of approximately 0.50 on holdout data) while using only 20% of the training data used by classical modeling setups. Besides high performance and high data efficiency, the active learning approach is also characterized by high robustness and speed. The approach is largely invariant to starting conditions and parameters, and substantial speed-ups can be yielded by using small atom batches rather than individual atoms during the iterative model-building process. The source code of FAME.AL is publicly available.

show abstract