ArticleNature communications2025
Data splitting to avoid information leakage with DataSAIL.
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 32 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
32 citing papers in PubMed.
- ChemLint: Conversational Cheminformatics with Large Language Models.Journal of chemical information and modeling · 2026Article
- Information leakage in enzyme-substrate prediction.Bioinformatics (Oxford, England) · 2026Article
- µORScreen: a lightweight consensus modeling framework for µ-opioid receptor ligand prediction and virtual screening.RSC advances · 2026Article
- Formation Energy Prediction and Feature Analysis of Lead-Free Double Perovskites Based on Deep Learning.Molecules (Basel, Switzerland) · 2026Article
- MetaTIS: a tool to predict cognate and near-cognate translation initiation sites in human.NAR genomics and bioinformatics · 2026Article
- Construction of a Comprehensive Contribution Ranking Model for Baijiu Aroma Compounds Based on Multi-Source Molecular Feature Fusion and Validation by Aroma Recombination.Foods (Basel, Switzerland) · 2026Article
- ALPAR: automated learning pipeline for antimicrobial resistance.Bioinformatics (Oxford, England) · 2026Article
- The emerging synergy of experimental and computational approaches for therapeutic modulation of biomolecular condensates.SLAS discovery : advancing life sciences R & D · 2026Review
- GPCR-GO: Relation-aware graph learning for predicting Gene Ontology terms of G protein-coupled receptors.PLoS computational biology · 2026Article
- QMAP: a benchmark for standardized evaluation of antimicrobial peptide MIC and hemolytic activity regression.Scientific reports · 2026Article
- Pocket-Surface Discrete Differential Geometry as a Leakage-Robust Feature Class for Protein-Ligand Binding Affinity Prediction.Molecules (Basel, Switzerland) · 2026Article
- Leakage-Safe ITS1 Identification of Fasciola hepatica and Fasciola gigantica with Reverse-Complement-Invariant CNN Inference.Acta parasitologica · 2026Article
- FAIR4prep: FAIR clinical informatics data preprocessing in artificial intelligence applications.Scientific data · 2026Article
- Multimodal Cross-Attentive Graph-Based Framework for Predicting In Vivo Endocrine Disruptors.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- AI-driven drug-target interaction prediction: current progress, challenges, and future roadmap for precision medicine.Journal of computer-aided molecular design · 2026Review
- Defining the Data set Defines the QSAR Claim.Journal of chemical information and modeling · 2026Article
- De Novo Structure Prediction from Tandem Mass Spectra: Algorithms, Benchmarks, and Limitations.Molecules (Basel, Switzerland) · 2026Review
- Review
- Protein Language Models: Applications and Perspectives.Journal of proteome research · 2026Review
- Leak Proof PDBBind: A Reorganized Data Set of Protein-Ligand Complexes for More Generalizable Binding Affinity Prediction.The journal of physical chemistry. B · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Information leakage is an increasingly important topic in machine learning research for biomedical applications. When information leakage happens during a model's training, it risks memorizing the training data instead of learning generalizable properties. This can lead to inflated performance metrics that do not reflect the actual performance at inference time. We present DataSAIL, a versatile Python package to facilitate leakage-reduced data splitting to enable realistic evaluation of machine learning models for biological data that are intended to be applied in out-of-distribution scenarios. DataSAIL is based on formulating the problem to find leakage-reduced data splits as a combinatorial optimization problem. We prove that this problem is NP-hard and provide a scalable heuristic based on clustering and integer linear programming. Finally, we empirically demonstrate DataSAIL's impact on evaluating biomedical machine learning models.
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.