Journal of Cheminformatics最新文献

{"title":"Chemical classification program synthesis using generative artificial intelligence","authors":"Christopher J. Mungall,&nbsp;Adnan Malik,&nbsp;Daniel R. Korn,&nbsp;Justin T. Reese,&nbsp;Noel M. O’Boyle,&nbsp;Janna Hastings","doi":"10.1186/s13321-025-01092-3","DOIUrl":"10.1186/s13321-025-01092-3","url":null,"abstract":"<div><p>Accurately classifying chemical structures is essential for cheminformatics and bioinformatics, including tasks such as identifying bioactive compounds of interest, screening molecules for toxicity to humans, finding non-organic compounds with desirable material properties, or organizing large chemical libraries for drug discovery or environmental monitoring. However, manual classification is labor-intensive and difficult to scale to large chemical databases. Existing automated approaches either rely on manually constructed classification rules, or are deep learning methods that lack explainability. This work presents an approach that uses generative artificial intelligence to automatically write <i>chemical classifier programs</i> for classes in the Chemical Entities of Biological Interest (ChEBI) database. These programs can be used for efficient deterministic run-time classification of SMILES structures, with natural language explanations. The programs themselves constitute an explainable computable ontological model of chemical class nomenclature, which we call the ChEBI Chemical Class Program Ontology (C3PO). We validated our approach against the ChEBI database, and compared our results against deep learning models and a naive SMARTS pattern based classifier. C3PO outperforms the naive classifier, but does not reach the performance of state of the art deep learning methods. However, C3PO has a number of strengths that complement deep learning methods, including explainability and reduced data dependence. C3PO can be used alongside deep learning classifiers to provide an explanation of the classification, where both methods agree. The programs can be used as part of the ontology development process, and iteratively refined by expert human curators. </p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01092-3","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145203187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction: Retrosynthetic crosstalk between single-step reaction and multi-step planning","authors":"Junseok Choe,&nbsp;Hajung Kim,&nbsp;Yan Ting Chok,&nbsp;Mogan Gim,&nbsp;Jaewoo Kang","doi":"10.1186/s13321-025-01101-5","DOIUrl":"10.1186/s13321-025-01101-5","url":null,"abstract":"","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01101-5","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145195428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TraceMetrix: a traceable metabolomics interactive analysis platform","authors":"Wei Chen,&nbsp;Yanpeng An,&nbsp;Ziru Chen,&nbsp;Ruijin Luo,&nbsp;Qinwei Lu,&nbsp;Cong Li,&nbsp;Chenhan Zhang,&nbsp;Qingxia Huang,&nbsp;Qinsheng Chen,&nbsp;Lianglong Zhang,&nbsp;Xiaoxuan Yi,&nbsp;Yixue Li,&nbsp;Huiru Tang,&nbsp;Guoqing Zhang","doi":"10.1186/s13321-025-01095-0","DOIUrl":"10.1186/s13321-025-01095-0","url":null,"abstract":"<div><p>Metabolomics data analysis is a multifaceted process often constrained by limited data sharing and a lack of transparency, which hinders reproducibility of results. While existing bioinformatics tools address some of these challenges, achieving greater simplicity and operational clarity remains essential for fully leveraging the potential of metabolomics. Here, we introduce TraceMetrix, a web-based platform designed for interactive traceability in metabolomics data analysis. TraceMetrix provides a flexible management system for both raw and derived data, enabling comprehensive tracking of file origins and destinations throughout the whole analysis pipeline. The platform documents the software and parameters used across four key modules, from raw data preprocessing, data cleaning, statistical analysis to functional analysis, enabling users to easily track critical factors influencing result accuracy. By mapping upstream and downstream relationships for nearly 19 analytical functions, TraceMetrix ensures end-to-end traceability, viewable interactively online or exportable as detailed reports. To address the limitations of single-machine environments in processing large-scale datasets, TraceMetrix is deployed on a high-performance computing cluster for efficient batch processing. Using a non-targeted metabolomics dataset, we demonstrated its traceability function to optimize parameter selection, successfully reproducing the analysis process and validating the original study's findings. TraceMetrix integrates traceability across data, software, and processes, significantly enhancing reproducibility in metabolomics research. The platform supports diverse applications and is freely available at https://www.biosino.org/tracemetrix.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01095-0","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145182843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Subgrapher: visual fingerprinting of chemical structures","authors":"Lucas Morin,&nbsp;Gerhard Ingmar Meijer,&nbsp;Valéry Weber,&nbsp;Luc Van Gool,&nbsp;Peter W. J. Staar","doi":"10.1186/s13321-025-01091-4","DOIUrl":"10.1186/s13321-025-01091-4","url":null,"abstract":"<div><p>Automatic extraction of molecules from scientific literature plays a crucial role in accelerating research across fields ranging from drug discovery to materials science. Patent documents, in particular, contain molecular information in visual form, which is often inaccessible through traditional text-based searches. In this work, we introduce SubGrapher, a method for the visual fingerprinting of molecule and Markush structure images. Unlike conventional Optical Chemical Structure Recognition (OCSR) models that attempt to reconstruct full molecular graphs, SubGrapher focuses on extracting fingerprints directly from images. Using learning-based instance segmentation, SubGrapher identifies functional groups and carbon backbones, constructing a substructure-based fingerprint that enables the retrieval of molecules and Markush structures. Our approach is evaluated against state-of-the-art OCSR and fingerprinting methods, demonstrating superior retrieval performance and robustness across diverse molecule and Markush structure depictions. The benchmark datasets, models, and inference code are publicly available..</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01091-4","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145182842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MolPrice: assessing synthetic accessibility of molecules based on market value","authors":"Friedrich Hastedt,&nbsp;Klaus Hellgardt,&nbsp;Sophia Yaliraki,&nbsp;Dongda Zhang,&nbsp;Antonio del Rio Chanona","doi":"10.1186/s13321-025-01076-3","DOIUrl":"10.1186/s13321-025-01076-3","url":null,"abstract":"<div><p>Machine learning approaches for conceptualizing and designing in silico compounds have attracted significant attention. However, the applicability of these compounds is often challenged by synthetic viability and cost-effectiveness. Researchers introduced proxy-scores, known as synthethic accessiblity scoring, to quantify the ease of synthesis for virtual molecules. Despite their utility, existing synthetic accessibility tools have notable limitations: they overlook compound purchasability, lack physical interpretability, and often rely on imperfect computer-aided synthesis planning algorithms. We introduce <i>MolPrice</i>, an accurate and fast model for molecular price prediction. Utilizing self-supervised contrastive learning, <i>MolPrice</i> autonomously generates price labels for synthetically complex molecules, enabling the model to generalize to molecules beyond the training distribution. Our results show that <i>MolPrice</i> reliably assigns higher prices to synthetically complex molecules than to readily purchasable ones, effectively distinguishing different levels of synthetic accessibility. Furthermore, <i>MolPrice</i> achieves competitive performance on literature benchmarks for synthetic accessibility. To demonstrate its practical utility, we conduct a virtual screening case study, illustrating how <i>MolPrice</i> successfully identifies purchasable molecules from a large candidate library. <i>MolPrice</i> bridges the gap between generative molecular design and real-world feasibility by integrating cost-awareness into synthetic accessibility assessment, making it a powerful model to accelerate molecular discovery.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01076-3","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145188879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-modal contrastive drug synergy prediction model guided by single modality","authors":"Tong Luo,&nbsp;Zheng Zhang,&nbsp;Xian-gan Chen,&nbsp;Zhi Li","doi":"10.1186/s13321-025-01087-0","DOIUrl":"10.1186/s13321-025-01087-0","url":null,"abstract":"<div><p>Compared to monotherapy, drug combinations exhibit stronger efficacy, fewer side effects, and lower drug resistance in cancer treatment. However, traditional wet-lab methods for screening synergistic drug combinations are both costly and inefficient. Lately, the development of various drug synergy methods has been promoted by the emergence of multiple drug synergy databases. Many of these methods use multimodal data and achieve good results. However, if various modalities of data is given equal consideration without taking into account the differences in features between the two modalities, this may lead to less effective multi-modal learning. We propose a multi-modal contrastive learning method for drug synergy prediction, named MCDSP. Specifically, MCDSP extracts entity embedding features of drugs and cell lines from heterogeneous graphs, while leveraging molecular fingerprints and gene expression features as biomolecular features for drugs and cell lines. These two different types of features serve as two types of modality information. Under the guided of single modality prediction tasks, we evaluated the relevant information of each modality. Through contrastive learning, the prediction bias of the two modalities are reduced, which obtain improved quality of multi-modal feature. Experiments show that MCDSP outperforms baseline methods on large datasets, and it performs well in handling unknown drug combinations and cell lines. MCDSP has demonstrated significant effectiveness in predicting drug synergy.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01087-0","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PKSmart: an open-source computational model to predict intravenous pharmacokinetics of small molecules","authors":"Srijit Seal,&nbsp;Maria-Anna Trapotsi,&nbsp;Manas Mahale,&nbsp;Vigneshwari Subramanian,&nbsp;Nigel Greene,&nbsp;Ola Spjuth,&nbsp;Andreas Bender","doi":"10.1186/s13321-025-01066-5","DOIUrl":"10.1186/s13321-025-01066-5","url":null,"abstract":"<p>Drug exposure, a key determinant of drug safety and efficacy, is governed by pharmacokinetic (PK) parameters such as volume of distribution (VDss), clearance (CL), half-life (t½), fraction unbound in plasma (fu), and mean residence time (MRT). In this study, we developed machine learning models to predict human PK parameters for 1,283 unique compounds using molecular structure, physicochemical properties, and predicted animal PK data. Our approach involved a two-stage modeling pipeline. First, we trained models to predict rat, dog, and monkey PK parameters (VDss, CL, fu) from chemical structure and properties for 371 compounds. These models were used to predict animal PK values for 1,283 unique compounds with human PK data. These animal PK predictions were then integrated with molecular descriptors and fingerprints to build Random Forest models for human PK parameters. The models demonstrated consistent performance across nested cross-validation and external validation sets, with predictive accuracy for VDss comparable to proprietary models developed by AstraZeneca. Notably, human VDss and CL predictions achieved external R² values of 0.39 and 0.46, respectively. To support broad accessibility and integration into early drug discovery workflows such as Design-Make-Test-Analyze (DMTA), we developed PKSmart (https://broad.io/PKSmart), a freely available web application. All code and models are also open source, enabling local deployment. To our knowledge, this represents the first public suite of PK prediction models with performance on par with industry standard models.</p><p>This study introduces the first publicly available pharmacokinetic (PK) models that match industry-standard predictions, utilizing molecular structural fingerprints, physicochemical properties, and predicted animal PK data to model human pharmacokinetics. Our approach is validated through repeated nested cross-validation and an external test set, including comparing predictions to an industry standard model. The models are released via a web-hosted application (https://broad.io/PKSmart) for wider accessibility and utility in drug development processes.</p>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01066-5","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating ligand docking methods for drugging protein–protein interfaces: insights from AlphaFold2 and molecular dynamics refinement","authors":"Jordi Gómez Borrego,&nbsp;Marc Torrent Burgas","doi":"10.1186/s13321-025-01067-4","DOIUrl":"10.1186/s13321-025-01067-4","url":null,"abstract":"<p>Advances in docking protocols have significantly enhanced the field of protein–protein interaction (PPI) modulation, with AlphaFold2 (AF2) and molecular dynamics (MD) refinements playing pivotal roles. This study evaluates the performance of AF2 models against experimentally solved structures in docking protocols targeting PPIs. Using a dataset of 16 interactions with validated modulators, we benchmarked eight docking protocols, revealing similar performance between native and AF2 models. Local docking strategies outperformed blind docking, with TankBind_local and Glide providing the best results across the structural types tested. MD simulations and other ensemble generation algorithms such as AlphaFlow, refined both native and AF2 models, improving docking outcomes but showing significant variability across conformations. These results suggest that, while structural refinement can enhance docking in some cases, overall performance appears to be constrained by limitations in scoring functions and docking methodologies. Although protein ensembles can improve virtual screening, predicting the most effective conformations for docking remains a challenge. These findings support the use of AF2-generated structures in docking protocols targeting PPIs and highlight the need to improve current scoring methodologies.</p><p>This study provides a systematic benchmark of docking protocols applied to protein–proteininteractions (PPIs) using both experimentally solved structures and AlphaFold2 models. Byintegrating molecular dynamics ensembles and AlphaFlow-generated conformations, we showthat structural refinement improves docking outcomes in selected cases, but overallperformance remains constrained by docking scoring function limitations. Our analysis showsthat AlphaFold2 models perform comparably to native structures in PPI docking, validating theiruse when experimental data are unavailable. These results establish a reference framework forfuture PPI-focused virtual screening and underscore the need for improved scoring functionsand ensemble-based approaches to better exploit emerging structural prediction tools.</p>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01067-4","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145133533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cache: Utilizing ultra-large library screening in Rosetta to identify novel binders of the WD-repeat domain of Leucine-Rich Repeat Kinase 2","authors":"Fabian Liessmann,&nbsp;Paul Eisenhuth,&nbsp;Alexander Fürll,&nbsp;Oanh Vu,&nbsp;Rocco Moretti,&nbsp;Jens Meiler","doi":"10.1186/s13321-025-01084-3","DOIUrl":"10.1186/s13321-025-01084-3","url":null,"abstract":"<p>In this study, we present a pipeline for identifying novel ligands targeting the Tryptophan-Aspartate-Repeat domain 40 (WDR40) of Leucine-Rich Repeat Kinase 2 (LRRK2), a protein associated with Parkinson’s disease, as part of the first Critical Assessment of Computational Hit-finding Experiments (CACHE) challenge, a blind benchmark experiment for drug discovery. Mutations in this protein are the most common genetic cause of familial Parkinson’s disease, yet this target remains understudied. We conducted an ultra-large library screening (ULLS) of the Enamine REAL space using a newly developed evolutionary algorithm, RosettaEvolutionaryLigand (REvoLd), which allows for efficient screening of combinatorial compound libraries. The protocol involved refining the target structure with molecular dynamic simulations, identifying a binding site via blind-docking, and optimizing compounds through REvoLd, culminating in a manual selection amongst the top-scoring REvoLd hits. A single binder molecule was identified that derived from the combination of two Enamine building blocks. In the second round, derivatives of the hit compound were used as input for REvoLd to further sample within the Enamine REAL space. Ultimately, a total of five molecules were identified, from which three show a measurable dissociation constant K<span>(_D)</span> value better than 150 <span>(upmu)</span> μm, showcasing the effectiveness of this approach. However, it also highlighted shortcomings, such as the preference for nitrogen-rich rings in the RosettaLigand scoring function.</p><p>We introduce the first real-world application for REvoLd, an evolutionary docking algorithm enabling efficient ultra-large library screening for flexible protein targets. Our approach identified novel binders for the WDR40 domain of LRRK2 within the CACHE challenge #1, representing the first prospective validation of REvoLd. Here, we present a preparation pipeline to allow exploration of a large protein pocket with unspecific binding areas, and unlike prior brute-force docking efforts, our method integrates receptor flexibility and combinatorial chemistry optimization.</p>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01084-3","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145141368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Contrastive explanations for machine learning predictions in chemistry","authors":"Alec Lamens,&nbsp;Jürgen Bajorath","doi":"10.1186/s13321-025-01100-6","DOIUrl":"10.1186/s13321-025-01100-6","url":null,"abstract":"<div><p>The concept of contrastive explanations originating from human reasoning is used in explainable artificial intelligence. In machine learning, contrastive explanations relate alternative prediction outcomes to each other involving the identification of features leading to opposing model decisions. We introduce a methodological framework for deriving contrastive explanations for machine learning models in chemistry to systematically generate intuitive explanations of predictions in high-dimensional feature spaces. The molecular contrastive explanations (MolCE) methodology explores alternative model decisions by generating virtual analogues of test compounds through replacements of molecular building blocks and quantifies the degree of “contrastive shifts” resulting from changes in model probability distributions. In a proof-of-concept study, MolCE was applied to explain selectivity predictions of ligands of D2-like dopamine receptor isoforms.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"17 1","pages":""},"PeriodicalIF":5.7,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01100-6","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145110668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}