ArticleNature communications2025
Coverage bias in small molecule machine learning.
Article in Nature communications, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 23 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
23 citing papers in PubMed.
- Annotating Tandem Mass Spectra in Metabolomics with DreaMS and MassSpecGym.Methods in molecular biology (Clifton, N.J.) · 2027Article
- Predicting Functional Diversity Within Enzyme Families: A Practical Perspective.Chembiochem : a European journal of chemical biology · 2026Review
- Times are changing but order matters: transferable prediction of small-molecule liquid chromatography retention times.Nature methods · 2026Article
- Candidate Structure Prioritization in Non-Target Screening with Predicted Collision Cross-Sections and Uncertainty Quantification.Journal of chemical information and modeling · 2026Article
- ScrambleBench: a workflow for comparative assessment of structure-based de novo generative models.Journal of cheminformatics · 2026Article
- Improving Generalizability in Whole-Cell Antibiotic Discovery Through Active Learning.bioRxiv : the preprint server for biology · 2026Article
- Count your bits: fingerprint benchmarking to assess broad chemical space representation.Journal of cheminformatics · 2026Article
- Why machine learning fails at mass spectrometry for small molecules.Nature metabolism · 2026Article
- XGBPred-ACSM: A Hybrid Descriptor-Driven XGBoost Framework for Anticancer Small Molecule Prediction.Pharmaceuticals (Basel, Switzerland) · 2026Article
- Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS.Nature biotechnology · 2026Article
- Defining the Data set Defines the QSAR Claim.Journal of chemical information and modeling · 2026Article
- Article
- Navigating the conjugated metabolome.bioRxiv : the preprint server for biology · 2026Article
- Cross ionization mode chemical similarity prediction between tandem mass spectra in metabolomics.Nature communications · 2026Article
- FLARE: Fine-grained Learning for Alignment of spectra-molecule REpresentation Enhances Metabolite Annotation.bioRxiv : the preprint server for biology · 2026Article
- Cross-Species Multitask Learning with Molecular and ADME Descriptors for Liver Microsomal Metabolic Stability.Computational and structural biotechnology journal · 2026Article
- Refining EI-MS library search results through atomic-level insights.Communications chemistry · 2025Article
- MSNature methods · 2025Article
- Integrating AI/ML and multi-omics approaches to investigate the role of TNFRSF10A/TRAILR1 and its potential targets in pancreatic cancer.Computers in biology and medicine · 2025Article
- Effective data visualization strategies in untargeted metabolomics.Natural product reports · 2025Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
5 authors.
Funding
Abstract
Small molecule machine learning aims to predict chemical, biochemical, or biological properties from molecular structures, with applications such as toxicity prediction, ligand binding, and pharmacokinetics. A recent trend is developing end-to-end models that avoid explicit domain knowledge. These models assume no coverage bias in training and evaluation data, meaning the data are representative of the true distribution. However, the domain of applicability is rarely considered in such models. Here, we investigate how well large-scale datasets cover the space of known biomolecular structures. For doing so, we propose a distance measure based on solving the Maximum Common Edge Subgraph (MCES) problem, which aligns well with chemical similarity. Although this method is computationally hard, we introduce an efficient approach combining Integer Linear Programming and heuristic bounds. Our findings reveal that many widely-used datasets lack uniform coverage of biomolecular structures, limiting the predictive power of models trained on them. We propose two additional methods to assess whether training datasets diverge from known molecular distributions, potentially guiding future dataset creation to improve model performance.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.