Ontology pre-training improves machine learning-based predictions for metabolites

Deep learning has recently led to multiple breakthroughs in longstanding biological problems. Recent advances have shown that integration of expert knowledge can improve deep learning model predictive performance in complex domains such as biology. Bio-ontologies offer a rich source of curated biological knowledge that can be harnessed to this end. Here, we describe an intuitive and generalisable approach to embed the knowledge contained in a classification hierarchy derived from a bio-ontology into a deep learning model as an intermediate training step between general-purpose pre-training and task-specific fine-tuning: a process that we call'ontology pre-training'. We show that this approach leads to an improvement in predictive performance and a reduction in training time for a broad range of prediction tasks related to metabolite functions, activities and properties in living systems, using a range of datasets derived from MoleculeNet. We see the biggest improvement for regression tasks, e.g., prediction of lipophilicity and aqueous solubility of molecules, and a robust improvement for most classification tasks. Our approach can be adapted for a wide range of knowledge sources, models and prediction tasks.

Authors

Institutions

Publication Details

Journal
PLoS Computational Biology
Published
2026-11-17
DOI
https://doi.org/10.1371/journal.pcbi.1014925
Citations
1
Primary Topic
Computational Drug Discovery Methods
Type
article
Field-Weighted Citation Impact
1.31

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Ontology pre-training improves machine learning-based predictions for metabolites

Charlotte Tumescheit, Till Mossakowski, Simon Flügel, Janna Hastings et al.
1 citations
PLoS Computational Biology
Computational Drug Discovery Methods
1.31
article

Ontology pre-training improves machine learning-based predictions for metabolites

Charlotte Tumescheit, Till Mossakowski, Simon Flügel, Janna Hastings, Martin Larralde, Fabian Neuhaus, Martin Glauer
article en
1 citations

Abstract

Deep learning has recently led to multiple breakthroughs in longstanding biological problems. Recent advances have shown that integration of expert knowledge can improve deep learning model predictive performance in complex domains such as biology. Bio-ontologies offer a rich source of curated biological knowledge that can be harnessed to this end. Here, we describe an intuitive and generalisable approach to embed the knowledge contained in a classification hierarchy derived from a bio-ontology into a deep learning model as an intermediate training step between general-purpose pre-training and task-specific fine-tuning: a process that we call'ontology pre-training'. We show that this approach leads to an improvement in predictive performance and a reduction in training time for a broad range of prediction tasks related to metabolite functions, activities and properties in living systems, using a range of datasets derived from MoleculeNet. We see the biggest improvement for regression tasks, e.g., prediction of lipophilicity and aqueous solubility of molecules, and a robust improvement for most classification tasks. Our approach can be adapted for a wide range of knowledge sources, models and prediction tasks.

PLoS Computational BiologyVol. 22(11)
Osnabrück University (DE), University of Zurich (CH), Leiden University Medical Center (NL), Otto-von-Guericke-Universität Magdeburg (DE)
National Science Foundation, Deutsche Forschungsgemeinschaft, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
Openalex Percentile: Top 24%
Computational Drug Discovery Methods
1.31
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon