Journal of Cheminformatics最新文献

{"title":"Fast intermolecular interaction energy calculation with the OPLS-AA force field","authors":"Mirco Daniel,&nbsp;Hannah Kullik,&nbsp;Martin Urban,&nbsp;Christoph Steinbeck,&nbsp;Achim Zielesny","doi":"10.1186/s13321-026-01264-9","DOIUrl":"10.1186/s13321-026-01264-9","url":null,"abstract":"<div><p>A fast pipeline based on the OPLS-AA force field is presented that enables the automated calculation of non-bonding intermolecular (dimer) interaction energies derived from a set of small organic (monomer) molecules. To calculate the non-bonding contributions, optimized geometries of the monomer molecules as well as their OPLS-AA van der Waals and atomic partial charge parameters are required. The key advantage of the new pipeline lies in its fast, highly parallelized in-memory computations without slow I/O operations, which make it possible to thoroughly process comparatively large numbers of (more than a hundred) monomer molecules within acceptable time frames (hours and days): Compared to an analogous, more versatile, and comprehensive approach, the new computational scheme delivers comparable results while being more than two orders of magnitude faster. For locally estimating the required OPLS-AA force field parameters with the LigParGen and BOSS software packages, a user-friendly graphical user interface for the Windows operating system is provided.</p><p><b>Scientific contribution</b></p><p>Rapid calculation of mutual intermolecular energies for a set of monomer molecules based on the widely used OPLS-AA force field enables a considerable expansion of this type of calculation for practical purposes. The performance improvement can be used to achieve significant improvements of interaction energy averages as well as considerable expansions in the size of the monomer molecule set.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01264-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148927086","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":"A decoupled alignment kernel for peptide membrane permeability predictions","authors":"Ali Amirahmadi,&nbsp;Gökçe Geylan,&nbsp;Leonardo De Maria,&nbsp;Farzaneh Etminani,&nbsp;Mattias Ohlsson,&nbsp;Alessandro Tibo","doi":"10.1186/s13321-026-01276-5","DOIUrl":"10.1186/s13321-026-01276-5","url":null,"abstract":"<div><p>Cyclic peptides are promising modalities for targeting intracellular sites; however, cell-membrane permeability remains a key bottleneck, exacerbated by limited public data and the need for well-calibrated uncertainty. Instead of relying on data-eager complex deep learning architecture, we propose a monomer-aware decoupled global alignment kernel (MD-GAK), which couples chemically meaningful residue–residue similarity with sequence alignment while decoupling local matches from gap penalties. MD-GAK is a relatively simple kernel. To further demonstrate the robustness of our framework, we also introduce a variant, PMD-GAK, which incorporates a triangular positional prior. As we will show in the experimental section, PMD-GAK can offer additional advantages over MD-GAK, particularly in reducing calibration errors. Since our focus is on uncertainty estimation, we use Gaussian Processes as the predictive model, as both MD-GAK and PMD-GAK can be directly applied within this framework. We demonstrate the effectiveness of our methods through an extensive set of experiments, comparing our fully reproducible approach against state-of-the-art models, and show that it outperforms them across all metrics.</p><p><b>Scientific contribution</b></p><p>We introduce monomer-aware decoupled global alignment kernels for Gaussian processes (MD-GAK and position-aware PMD-GAK) that align cyclic peptides at the sequence level using chemically rich monomer fingerprints and explicit positional priors, yielding positive-definite similarity measures tailored to permeability modeling. Compared with order-agnostic fingerprint methods, standard global-alignment kernels and state-of-the-art graph and language-model baselines, our alignment-aware GPs provide improved discrimination, probabilistic calibration and scaffold-level robustness under stringent, leakage-controlled cyclic-peptide permeability benchmarks.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13439769/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148676683","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":"How well can off-the-shelf LLMs elucidate molecular structures from mass spectra using chain-of-thought reasoning?","authors":"Yufeng Wang,&nbsp;Lu Wei,&nbsp;Lin Liu,&nbsp;Hao Xu,&nbsp;Haibin Ling","doi":"10.1186/s13321-026-01234-1","DOIUrl":"10.1186/s13321-026-01234-1","url":null,"abstract":"<div><p>Mass spectrometry (MS) is a powerful analytical technique for identifying small molecules, yet determining complete molecular structures directly from tandem mass spectra (MS/MS) remains a long-standing challenge due to complex fragmentation patterns and the vast diversity of chemical space. Recent progress in large language models (LLMs) has shown promise for reasoning-intensive scientific tasks, but their capability for chemical interpretation is still unclear. We present a zero-shot chain-of-thought (CoT) benchmark for evaluating how well off-the-shelf general-purpose LLMs can infer molecular structure from text-serialized MS/MS peak lists and a known molecular formula, without fine-tuning, retrieval, external chemistry tools, or constrained search. Rather than proposing a new spectrum-trained model, our goal is diagnostic: to isolate what the evaluated off-the-shelf LLMs can and cannot do in a direct MS/MS-to-SMILES generation setting when only textualized spectral evidence and prompting are available. This distinction is important because our benchmark targets a deliberately constrained regime: direct structure generation from text-formatted spectral evidence alone, rather than multimodal reasoning with spectral images, candidate reranking over structures generated by specialized chemistry systems, or knowledge and search-augmented LLM workflows. We formalize expert chemists’ reasoning steps (such as double bond equivalent (DBE) analysis, neutral loss identification, and fragment assembly) into structured prompts and assess multiple state-of-the-art LLMs (Claude-3.5-Sonnet, GPT-4o-mini, and Llama-3 series) using the MassSpecGym dataset. Our evaluation across metrics of SMILES validity, formula consistency, and structural similarity reveals that while LLMs can produce syntactically valid and partially plausible structures, they fail to achieve chemical accuracy or link reasoning to correct molecular predictions. These findings highlight both the interpretive potential and the current limitations of LLM-based reasoning for molecular elucidation, providing a foundation for future work that combines domain knowledge and reinforcement learning to achieve chemically grounded AI reasoning.</p><p><b>Scientific contribution</b></p><p>We introduce a zero-shot chain-of-thought benchmark for direct MS/MS-to-SMILES prediction with off-the-shelf general-purpose LLMs, providing a controlled test of text-only, no-tools molecular structure elucidation. In contrast to prior approaches based on spectrum-trained models, multimodal reasoning, or tool-augmented candidate pipelines, our study isolates the capabilities and limitations of prompting alone. We show that fluent chain-of-thought reasoning does not translate into chemically grounded structure recovery, establishing a reproducible baseline and a clear target for future method development.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01234-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148783380","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":"Transformers for molecular property prediction: domain adaptation efficiently improves performance","authors":"Afnan Sultan,&nbsp;Max Rausch-Dupont,&nbsp;Shahrukh Khan,&nbsp;Olga Kalinina,&nbsp;Dietrich Klakow,&nbsp;Andrea Volkamer","doi":"10.1186/s13321-026-01252-z","DOIUrl":"10.1186/s13321-026-01252-z","url":null,"abstract":"&lt;div&gt;&lt;p&gt;Over the past six years, molecular transformer models have become a part of the computational toolbox for drug discovery. Most existing models are pre-trained on millions to billions of molecules from large-scale unlabeled datasets such as ZINC or ChEMBL. However, the extent to which such large-scale pre-training improves molecular property prediction remains unclear. This study investigates the potential of transformer models for molecular property prediction while addressing their current limitations. We explore strategies to enhance performance, including the influence of pre-training dataset size and the benefits of domain adaptation through chemically informed objectives. Our results show that increasing the pre-training dataset beyond approximately 400–800K molecules does not improve performance across seven datasets covering five ADME endpoints: lipophilicity, permeability, solubility (two datasets), microsomal stability (two datasets), and plasma protein binding. In contrast, applying domain adaptation on a small number of domain-relevant molecules (&lt;span&gt;(le 4K)&lt;/span&gt;) using multi-task regression of physicochemical properties significantly improves model performance across all datasets (&lt;i&gt;P&lt;/i&gt;-value &lt; 0.001). Furthermore, we find that a model pre-trained on &lt;span&gt;(sim)&lt;/span&gt;400K molecules and adapted on a small domain-specific dataset outperforms larger-scale transformer models like MolFormer and performs comparably to MolBERT. Benchmarking these models alongside baseline representations using RDKit descriptors and Morgan fingerprints reveals that incorporating chemically, physically, and topologically informed features consistently leads to superior performance, regardless of whether used with traditional or transformer-based architectures. While traditional practices such as a random forest model with RDKit descriptors remain strong baselines, this study identifies concrete practices that significantly enhance the performance of transformer models. In particular, aligning pre-training and adaptation with chemically meaningful tasks and domain-relevant data offers a promising path forward for future advancements in molecular property prediction. Our models are available on HuggingFace to allow for easy use and adaptation at https://huggingface.co/collections/UdS-LSV/domain-adaptation-molecular-transformers-6821e7189ada6b7d0a5b62d4.&lt;/p&gt;&lt;p&gt;&lt;b&gt;Scientific contribution&lt;/b&gt;&lt;/p&gt;&lt;p&gt;We introduce the first systematic evaluation of domain adaptation strategies for molecular transformer models in predicting key ADME properties, such as lipophilicity, solubility, clearance, etc. Our results demonstrate that combining pre-training with domain adaptation significantly improves predictive performance and generalization across diverse chemical datasets (P-value &lt;span&gt;(&lt; 1e^{-9})&lt;/span&gt;). This contribution advances cheminformatics by offering practical guidelines and open resources for developing more accurate and robust molecular tra","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13430829/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148667942","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":"Computational mapping of productive POI–E3 ligase conformations to guide de novo degrader design: application to WEE1 and PKMYT1 PROTACs","authors":"Husam Nassar,&nbsp;Matthias Schmidt,&nbsp;Hany S. Ibrahim,&nbsp;Dina Robaa,&nbsp;Wolfgang Sippl","doi":"10.1186/s13321-026-01268-5","DOIUrl":"10.1186/s13321-026-01268-5","url":null,"abstract":"<div><p>Targeted protein degradation has emerged as a promising therapeutic strategy, yet rational degrader design remains challenged by the dynamic nature of protein of interest (POI)–E3 ligase interactions. While X-ray crystallography and cryo-EM provide valuable structural snapshots, they are insufficient for capturing the conformational heterogeneity underpinning efficient ubiquitination and degradation. Here, we present a unified computational workflow to systematically generate and evaluate POI–E3 ligase conformational states for CRBN- and VHL-mediated proteolysis-targeting chimeras (PROTACs). The workflow integrates warhead connectivity analysis, conformational clustering, ubiquitination accessibility assessment and molecular dynamics simulations to identify productive POI–E3 ligase geometries. Analysis of experimental structures revealed that PROTAC linkers do not exceed 15 Å, providing a practical attachment-atom distance based filter for docking-derived models. Furthermore, POI–E3 ligase conformations differing by more than 7.5 Å Cα RMSD exhibited distinct ubiquitination profiles, offering quantitative guidance for defining structurally and functionally divergent states. Experimental ternary complexes consistently positioned one or more solvent-exposed POI lysine residues within 50 Å of the E2 catalytic Cys111, establishing a mechanistically grounded criterion for ubiquitination competence. Validation against 34 experimentally determined PROTAC ternary complexes achieved a 97% recovery rate and identified multiple ubiquitination competent conformations beyond experimental snapshots. The workflow was subsequently applied to model productive WEE1-CRBN and PKMYT1-CRBN conformations, for which no experimental structures are available. PROTAC induced-fit docking demonstrated that active PROTACs selectively engage productive POI–E3 ligase geometries with linker-compatible attachment atom distances. Overall, this study provides a quantitative, structure-based framework for guiding the rational design of ubiquitination-based degraders. The code and example data supporting this workflow are openly available at https://github.com/Husam-PSE/PROTACMap.</p><p><b>Scientific contribution</b></p><p>This study offers a generalizable computational framework for identifying productive POI–E3 ligase conformations. It demonstrates that effective degradation depends on the interplay between conformational diversity, feasible warhead connectivity and preserved ubiquitination competence, rather than solely on ternary complex stability or binding affinity. Our computational approach was applied on WEE1 and PKMYT1 PROTACs for which no experimental ternary structure is available.</p><h3>Graphical Abstract</h3>\u0000<div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13404913/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148597440","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":"AlphaDTA: integrating AlphaFold3 embeddings and 3D complex structures for drug-target binding affinity prediction.","authors":"Minjae Chung, Sejin Park, Hyunju Lee","doi":"10.1186/s13321-026-01259-6","DOIUrl":"10.1186/s13321-026-01259-6","url":null,"abstract":"<p><p>Accurate prediction of drug-target binding affinity plays an important role in structure-based drug discovery, yet existing approaches are constrained by their reliance on scarce experimentally determined protein-ligand complex structures. In this context, recent advances in biomolecular structure prediction models, such as AlphaFold3, have emerged as a promising approach to alleviate the scarcity of experimentally determined protein-ligand complex structures. In this study, we introduce AlphaDTA, a framework that integrates AlphaFold3-predicted structures and embeddings for drug-target binding affinity prediction. AlphaDTA processes two types of AlphaFold3 embeddings, single and pair embeddings. We utilized the single embeddings at both fine-grained and coarse-grained levels to capture local interaction patterns and global binding context, and used the pair embeddings to encode cross-molecular relational features. The AlphaFold3-predicted structures are further processed by a three-dimensional structure-based geometric encoder to produce corresponding structural embedding representations. The resulting single, pair, and structural embeddings are then integrated through adaptive fusion for affinity prediction. When we evaluated AlphaDTA using recently proposed PDBbind data splits designed to reduce train-test structural overlap, AlphaDTA achieved state-of-the-art or competitive performance across multiple independent benchmarks. In a case study on the cystic fibrosis transmembrane conductance regulator, AlphaDTA correctly identifies a clinically approved potentiator and suggests a potential repurposing candidate among FDA-approved drugs.Scientific contribution AlphaDTA enables accurate drug-target binding affinity prediction without relying on experimentally determined protein-ligand complex structures. By integrating AlphaFold3-derived single, pair, and structure-based embeddings through adaptive fusion, AlphaDTA improves generalization on structurally nonredundant benchmarks and demonstrates utility for target-specific drug repurposing.</p>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":" ","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148547121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing virtual screening of cystathionine β-synthase inhibitors: benchmarking target-specific machine-learning scoring functions against state-of-the-art AI docking and co-folding approaches","authors":"Cao-Minh Truong,&nbsp;Van-Thinh To,&nbsp;Nathalie Janel,&nbsp;Julien Dairou,&nbsp;Pedro J. Ballester,&nbsp;Olivier Taboureau,&nbsp;Viet-Khoa Tran-Nguyen","doi":"10.1186/s13321-026-01262-x","DOIUrl":"10.1186/s13321-026-01262-x","url":null,"abstract":"<div><p>Cystathionine β-synthase (CBS) has emerged as an important therapeutic target implicated in cancer and Down syndrome, yet the discovery of selective CBS inhibitors remains challenging due to limited structural diversity of known ligands and the scarcity of target-focused virtual screening (VS) benchmarks. In this study, we present the first comprehensive evaluation of CBS-specific artificial intelligence (AI) models for structure-based VS, supported by a carefully curated and up-to-date data set of experimentally validated CBS inhibitors, true inactives and decoys. Using this data set, we developed CBS-specific binary classification models trained on docking-derived features and evaluated them in a rigorous five-fold cross-validation framework that employed similarity-controlled splits, ensuring structural independence between training and test sets while minimizing intra-fold class bias. Predictive performance was assessed primarily using the normalized enrichment factor of true actives at 1% (NEF1%) alongside balanced accuracy. Across all folds, the CBS-specific AI models demonstrated consistently high screening power and robust classification performance. Importantly, we benchmarked their performance against a diverse panel of 16 established VS pipelines, including widely adopted docking-based scoring schemes, modern deep-learning (DL) docking tools, and recent co-folding approaches for protein–ligand binding prediction. The CBS-specific AI classifiers substantially outperformed these state-of-the-art (SOTA) methods in early enrichment (NEF1% = 0.764 ± 0.191), highlighting the advantage of target-focused training for VS tasks. Our results further reveal that generic DL docking and co-folding approaches struggle to achieve reliable screening performance when applied to targets under-represented in or entirely absent from their training data, as appears to be the case for CBS. This finding underscores a key limitation of broadly trained foundation-style models in prospective drug discovery campaigns involving less-studied proteins. Overall, this work reinforces the benefits of target-specific AI scoring models tailored to individual proteins, highlights the value of high-quality curated data sets for such efforts, and provides practical guidance for selecting VS strategies in case of data-limited targets. To promote transparency and reproducibility, all input and output files, curated data sets and source code are freely available via GitHub and Zenodo.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01262-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148497072","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":"Evaluation of deep learning architectures for predicting ligand interactions with neurologically relevant GPCRs","authors":"Souvik Dey,&nbsp;Pinyi Lu,&nbsp;Anders Wallqvist,&nbsp;Mohamed Diwan M. AbdulHameed","doi":"10.1186/s13321-026-01258-7","DOIUrl":"10.1186/s13321-026-01258-7","url":null,"abstract":"<div><p>G protein-coupled receptors (GPCRs) are therapeutic targets for over 30% of approved drugs, yet specific GPCR subtypes act as molecular initiating events in several neurotoxic adverse outcome pathways. Therefore, knowledge of GPCR-ligand interactions is critical for drug discovery and computational toxicology. However, accurate predictions of GPCR-ligand binding can be challenging due to receptor conformational flexibility, complex membrane environment, and lack of selectivity among ligands. Drug-target interaction (DTI) models that jointly encode protein and ligand representations offer a promising approach to predict these interactions. In this study, we identified 119 neurologically relevant GPCRs and evaluated three deep learning architectures for creating a unified GPCR-ligand DTI model: dual-projection cosine similarity networks and transformer encoders (both using pre-computed embeddings) as well as bidirectional cross-attention networks (with frozen or fine-tuned encoders). Unlike prior studies that rely primarily on random splits, we evaluated model performance across random-split, cluster-split, and novel protein scenarios to provide realistic estimates of generalization. All the models performed well, achieving area under the receiver operating characteristic curve (AUROC) values of 0.91 on random-split validation, 0.81 on cluster-split testing (structurally distinct ligands), and 0.64 on novel GPCR generalization (proteins unseen during training). However, in the unseen-proteins test set, predictions were less accurate for GPCRs from protein families not represented in the training data or those with contrasting ligand interactions. We also assessed the models’ ability to detect ligand selectivity, achieving an AUROC of 0.71 on ligands with at least five known GPCR interactions, although sensitivity remained low at 0.49. Our curated neurological GPCR dataset and rigorous evaluation framework provide realistic model assessment, reveal where current models succeed or fail, and provide practical guidance for deploying GPCR-ligand predictors in drug discovery and toxicity screening.</p><p><b>Scientific contribution</b></p><p>Our work connects computational toxicology and GPCR pharmacology by systematically evaluating transformers and similarity-based proteochemometric architectures for predicting CNS-relevant GPCR-ligand interactions under rigorous cold-start conditions. Our analysis reveals that while models achieve strong performance on structurally novel ligands, generalization to novel GPCRs remains challenging, with particularly poor prediction for out-of-family receptors. These results provide a rigorous evaluation framework for predicting ligand interactions against neurologically relevant GPCRs and highlight the need for improved protein representation learning in computational toxicology frameworks.</p></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01258-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148451629","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":"EvoDiffMol: evolutionary diffusion framework for 3D molecular design with optimized properties","authors":"Xiaobo Lin,&nbsp;Logan T. Kearney,&nbsp;Zhaoqian Su,&nbsp;Yunchao Liu,&nbsp;Amit K. Naskar,&nbsp;Debsindhu Bhowmik","doi":"10.1186/s13321-026-01237-y","DOIUrl":"10.1186/s13321-026-01237-y","url":null,"abstract":"<div><p>Designing molecules with specific target properties remains a fundamental challenge in computational chemistry. While existing approaches show promise, most rely on simplified representations like SMILES strings or 2D graphs that lack essential three-dimensional geometric information. We present EvoDiffMol, a computational framework that integrates evolutionary algorithms with three-dimensional diffusion models for property-driven molecular generation. The method operates through adaptive evolutionary optimization, where population-based selection guides the generation process toward desired property landscapes. EvoDiffMol supports both unconstrained molecular design and scaffold-constrained generation that preserves fixed substructures while optimizing complementary regions. Comprehensive evaluation demonstrates exceptional performance, achieving the highest drug-likeness score (0.94) among all compared state-of-the-art methods while maintaining excellent validity, uniqueness, and novelty. Beyond single property optimization, the framework demonstrates flexible multi-property optimization capabilities, simultaneously controlling multiple molecular descriptors including synthetic accessibility, lipophilicity, topological polar surface area, and clinically relevant ADMET properties such as cardiotoxicity (hERG) and intestinal permeability (Caco-2). This adaptability spans from simple descriptors to practical pharmaceutical endpoints without requiring complete model retraining. The framework achieves precise control over target property values, generating molecules with properties closely matching specified targets for both single and multiple descriptors. Scaffold-constrained experiments preserve fixed molecular cores while maintaining effective property optimization. The three-dimensional representation offers advantages in maintaining structural validity during iterative optimization, with potential for geometry-aware applications in materials science and drug discovery. </p><h3>Graphical abstract</h3>\u0000<div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01237-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148454230","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":"ScrambleBench: a workflow for comparative assessment of structure-based de novo generative models","authors":"Veincent Yap,&nbsp;Pan Xu,&nbsp;Frankie S. Mak,&nbsp;Klement Foo,&nbsp;Congbao Kang,&nbsp;Padmanabhan Anbazhagan,&nbsp;Weijun Xu","doi":"10.1186/s13321-026-01254-x","DOIUrl":"10.1186/s13321-026-01254-x","url":null,"abstract":"&lt;div&gt;&lt;p&gt;Generative artificial intelligence (AI) has rapidly advanced over the past decade in the field of drug discovery, particularly for the de novo design of small molecules based on target protein structures. While generative AI has the potential to complement traditional structure-based drug design (SBDD) to discover novel hits, their performance is often assessed using non-standardized evaluation criteria. As the number of generative AI models continue to grow, it becomes increasingly important to determine whether these tools are sufficiently robust and reliable for integration into medicinal chemistry workflow. Here, we propose ScrambleBench, a benchmarking workflow designed to evaluate structure-based generative AI models that align with medicinal chemists’ practical objectives to identify chemically diverse, drug-like hit candidates that adopt plausible binding conformations and exhibit favourable docking affinities. Using six representative models (Pocket2Mol, PocketFlow, Lingo3DMol, DiffSBDD, PMDM, and Chemistry42), we systematically assessed performance across diverse target classes, including two GPCRs, two kinases, and two hydrolases. While some generative models show superior performance for particular evaluation endpoints, none demonstrates overall dominance across all evaluated criteria. Notably, despite benchmarked proteins (e.g., CDK2, GSK3β) being present in the training datasets, the models still show limited generalization to target binding sites, which resulted in high redocking RMSD values and low virtual hit rates. Our results highlight the importance of evaluating chemical diversity explicitly and using the recently proposed metrics such as Hamiltonian Diversity (HamDiv) which assess both quantity and dissimilarity of a molecular set. Furthermore, as many generated ligands fail to meaningfully engage the target active site, we propose that future generative frameworks incorporate improved loss functions that place greater emphasis on drug-like physicochemical properties and correct pharmacophore recognition.&lt;/p&gt;&lt;p&gt;&lt;b&gt;Scientific contribution&lt;/b&gt;&lt;/p&gt;&lt;p&gt;While numerous de novo generative models have been proposed for structure-based molecular design, objective comparison between methods remains challenging due to inconsistent benchmarking practices and heterogeneous evaluation criteria. ScrambleBench introduces a unified and reproducible benchmarking workflow that integrates diversity analysis, conformational validity assessment, docking reproducibility, pharmacophore matching, and virtual hit rate evaluation within a single framework. By systematically comparing representative generative models using common datasets and standardized assessment criteria, this work advances the field by enabling transparent evaluation model performance and practical applicability. Overall, ScrambleBench provides a holistic medicinal chemistry-oriented framework that identifies methodological strengths, limitations, and opportunities for futu","PeriodicalId":617,"journal":{"name":"Journal of Cheminformatics","volume":"18 1","pages":""},"PeriodicalIF":7.9,"publicationDate":"2026-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1186/s13321-026-01254-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148393668","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}