Best Practices for Unsupervised Learning in Molecular Systems

Unsupervised learning is used throughout computational molecular science on unlabeled data such as molecular dynamics trajectories and conformer ensembles. Some questions admit no predefined labels at all: how many conformational states a molecule visits, whether a virtual library covers chemical space, or which structures are unlike anything else in the set. Clustering, dimensionality reduction, and density estimation serve both cases. They are easy to apply, and their output generally appears like a discovery, whether or not it is one. Establishing a new discovery is difficult, because there is no held-out target to check against. This guide is a prescriptive companion to the review literature: it sets out what to do at each stage of the pipeline these analyses share (curate, split, represent, scale, reduce, group, validate), why each step matters, and what goes wrong when it is skipped, with a checklist for each stage. The representation, the distance metric, and the scaling usually decide the outcome, not the chosen algorithm. An apparently structured low-dimensional map is not evidence that structure exists, and null models, stability analysis, and cheap baselines should be used. Statistical practice in molecular machine learning is not widespread, so we give a comparison protocol covering resampling variability, dependence between repeated estimates, multiple comparisons, and post-selection effects. Leakage and splitting are treated in depth, and we provide accompanying notebooks to run each recommendation on molecular data.

Authors

Institutions

Publication Details

Journal
ChemRxiv
Published
2026-11-17
DOI
https://doi.org/10.26434/chemrxiv.15012392/v1
Primary Topic
Machine Learning in Materials Science
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Best Practices for Unsupervised Learning in Molecular Systems

Rhyan Barrett, Max Pinheiro, Hessam Yazdani, Bingqing Cheng et al.
ChemRxiv
Machine Learning in Materials Science
preprint

Best Practices for Unsupervised Learning in Molecular Systems

Rhyan Barrett, Max Pinheiro, Hessam Yazdani, Bingqing Cheng, T. Oestereich, Ivan Gilardoni, Grégory Fonseca, Rocío Mercado, Arnav Brahmasandra
preprint en

Abstract

Unsupervised learning is used throughout computational molecular science on unlabeled data such as molecular dynamics trajectories and conformer ensembles. Some questions admit no predefined labels at all: how many conformational states a molecule visits, whether a virtual library covers chemical space, or which structures are unlike anything else in the set. Clustering, dimensionality reduction, and density estimation serve both cases. They are easy to apply, and their output generally appears like a discovery, whether or not it is one. Establishing a new discovery is difficult, because there is no held-out target to check against. This guide is a prescriptive companion to the review literature: it sets out what to do at each stage of the pipeline these analyses share (curate, split, represent, scale, reduce, group, validate), why each step matters, and what goes wrong when it is skipped, with a checklist for each stage. The representation, the distance metric, and the scaling usually decide the outcome, not the chosen algorithm. An apparently structured low-dimensional map is not evidence that structure exists, and null models, stability analysis, and cheap baselines should be used. Statistical practice in molecular machine learning is not widespread, so we give a comparison protocol covering resampling variability, dependence between repeated estimates, multiple comparisons, and post-selection effects. Leakage and splitting are treated in depth, and we provide accompanying notebooks to run each recommendation on molecular data.

ChemRxiv
Scuola Internazionale Superiore di Studi Avanzati (IT), Universidade de São Paulo (BR), University of Luxembourg (LU), Science for Life Laboratory (SE), University of Chicago (US), Chalmers University of Technology (SE), University of Missouri (US), University of Gothenburg (SE), Leipzig University (DE), University of California, Berkeley (US)
Machine Learning in Materials Science
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