Journal of Chemical Information and Modeling 最新文献

{"title":"Ligand Many-Body Expansion as a General Approach for Accelerating Transition Metal Complex Discovery.","authors":"Daniel B K Chu, David A González-Narváez, Ralf Meyer, Aditya Nandy, Heather J Kulik","doi":"10.1021/acs.jcim.4c01728","DOIUrl":"10.1021/acs.jcim.4c01728","url":null,"abstract":"<p><p>Methods that accelerate the evaluation of molecular properties are essential for chemical discovery. While some degree of ligand additivity has been established for transition metal complexes, it is underutilized in asymmetric complexes, such as the square pyramidal coordination geometries highly relevant to catalysis. To develop predictive methods beyond simple additivity, we apply a many-body expansion to octahedral and square pyramidal complexes and introduce a correction based on adjacent ligands (i.e., the <i>cis</i> interaction model). We first test the <i>cis</i> interaction model on adiabatic spin-splitting energies of octahedral Fe(II) complexes, predicting DFT-calculated values of unseen binary complexes to within an average error of 1.4 kcal/mol. Uncertainty analysis reveals the optimal basis, comprising the homoleptic and <i>mer</i> symmetric complexes. We next show that the <i>cis</i> model (i.e., the <i>cis</i> interaction model solved for the optimal basis) infers both DFT- and CCSD(T)-calculated model catalytic reaction energies to within 1 kcal/mol on average. The <i>cis</i> model predicts low-symmetry complexes with reaction energies outside the range of binary complex reaction energies. We observe that <i>trans</i> interactions are unnecessary for most monodentate systems but can be important for some combinations of ligands, such as complexes containing a mixture of bidentate and monodentate ligands. Finally, we demonstrate that the <i>cis</i> model may be combined with Δ-learning to predict CCSD(T) reaction energies from exhaustively calculated DFT reaction energies and the same fraction of CCSD(T) reaction energies needed for the <i>cis</i> model, achieving around 30% of the error from using the CCSD(T) reaction energies in the <i>cis</i> model alone.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"9397-9412"},"PeriodicalIF":5.6,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142737775","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":"Improved and Interpretable Prediction of Cytochrome P450-Mediated Metabolism by Molecule-Level Graph Modeling and Subgraph Information Bottlenecks.","authors":"Yi Li, Qin-Wei Xu, Guo-Lei Jian, Xiao-Ling Zhang, Hua Wang","doi":"10.1021/acs.jcim.4c01632","DOIUrl":"10.1021/acs.jcim.4c01632","url":null,"abstract":"<p><p>Accurately identifying sites of metabolism (SoM) mediated by cytochrome P450 (CYP) enzymes, which are responsible for drug metabolism in the body, is critical in the early stage of drug discovery and development. Current computational methods for CYP-mediated SoM prediction face several challenges, including limitations to traditional machine learning models at the atomic level, heavy reliance on complex feature engineering, and the lack of interpretability relevant to medicinal chemistry. Here, we propose GraphCySoM, a novel molecule-level modeling approach based on graph neural networks, utilizing lightweight features and interpretable annotations on substructures, to effectively and interpretably predict CYP-mediated SoM. Unlike computationally expensive atomic descriptors derived from resource-intensive chemistry or even quantum chemistry calculations, we emphasize that graph-based molecular modeling initialized solely with lightweight features enables the adaptive learning of molecular topology through message-passing mechanisms combined with various aggregation kernels. Extensive ablation experiments demonstrate that GraphCySoM significantly outperforms baseline models and achieves superior performance compared with competing methods while exhibiting advantages in computational efficiency. Moreover, the attention mechanism and subgraph information bottlenecks are incorporated to analyze node importance and feature significance, resulting in mining substructures associated with the SoM. To the best of our knowledge, this is the first comprehensive study of CYP-mediated SoM using molecule-level modeling and interpretable technology. Our method achieves new state-of-the-art performance and provides potential insights into the molecular and pharmacological mechanisms underlying drug metabolism catalyzed by CYP enzymes. All source files and trained models are freely available at https://github.com/liyigerry/GraphCySoM.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"9487-9500"},"PeriodicalIF":5.6,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142737774","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":"Property Prediction for Complex Compounds Using Structure-Free Mendeleev Encoding and Machine Learning.","authors":"Zixin Zhuang, Amanda S Barnard","doi":"10.1021/acs.jcim.4c01343","DOIUrl":"10.1021/acs.jcim.4c01343","url":null,"abstract":"<p><p>Predicting the properties for unseen materials exclusively on the basis of the chemical formula before synthesis and characterization has advantages for research and resource planning. This can be achieved using suitable structure-free encoding and machine learning methods, but additional processing decisions are required. In this study, we compare a variety of structure-free materials encodings and machine learning algorithms to predict the structure/property relationships of battery materials. It was found that the physical units used to measure the property labels have an important impact on the predictive ability of the models, regardless of the computational approach. Property labels with respect to weight give excellent performance, but property labels with respect to volume cannot be predicted with confidence using only chemical information, even when the underlying physical characteristics are the same. These results contrast with previous studies of unsupervised learning and classification, where structure-free encoding excelled, and highlight how the structural features or property labels of materials are represented plays an important role in the predictive ability of machine learning models.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"9205-9214"},"PeriodicalIF":5.6,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142811442","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":"Influence of Data Curation and Confidence Levels on Compound Predictions Using Machine Learning Models.","authors":"Elena Xerxa, Martin Vogt, Jürgen Bajorath","doi":"10.1021/acs.jcim.4c01573","DOIUrl":"10.1021/acs.jcim.4c01573","url":null,"abstract":"<p><p>While data curation principles and practices are a major topic in data science, they are often not explicitly considered in machine learning (ML) applications in chemistry. We have been interested in evaluating the potential effects of data curation on the performance of molecular ML models. Therefore, a sequential curation scheme was developed for compounds and activity data, and different ML classification models were generated at increasing data confidence levels and evaluated. Sequential data curation was found to systematically increase classification performance in an incremental manner due to cumulative effects of individual data curation criteria. The analysis of chemical space distributions of compound subsets at different data confidence levels revealed that the separation of compounds with different class labels in chemical space generally increased during sequential activity data curation, which was mostly due to subsequent elimination of singletons rather than compounds from analogue series. These findings provided a rationale for increasing the classification performance of ML models as a consequence of increasingly stringent data curation. Taken together, the results reported herein suggest that further attention should be paid to varying data curation and confidence levels when deriving and assessing ML models for chemical applications.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"9341-9349"},"PeriodicalIF":5.6,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142826587","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":"Pred-AHCP: Robust Feature Selection-Enabled Sequence-Specific Prediction of Anti-Hepatitis C Peptides via Machine Learning.","authors":"Akash Saraswat, Utsav Sharma, Aryan Gandotra, Lakshit Wasan, Sainithin Artham, Arijit Maitra, Bipin Singh","doi":"10.1021/acs.jcim.4c00900","DOIUrl":"10.1021/acs.jcim.4c00900","url":null,"abstract":"<p><p>Every year, an estimated 1.5 million people worldwide contract Hepatitis C, a significant contributor to liver problems. Although many studies have explored machine learning's potential to predict antiviral peptides, very few have addressed the problem of predicting peptides against specific viruses such as Hepatitis C. In this study, we demonstrate the application and fine-tuning of machine learning (ML) algorithms to predict peptides that are effective against Hepatitis C virus (HCV). We developed a fine-tuned and explainable ML model that harnesses the amino acid sequence of a peptide to predict its anti-hepatitis C potential. Specifically, features were computed based on sequence and physicochemical properties. The feature selection was performed using a combined strategy of mutual information and variance inflation factor. This facilitated the removal of redundant and multicollinear features, enhancing the model's generalizability in predicting anti-hepatitis C peptides (AHCPs). The model using the random forest algorithm produced the best performance with an accuracy of about 92%. The feature analysis highlights that the distributions of hydrophobicity, polarizability, coil-forming residues, frequency of glycine residues and the existence of dipeptide motifs VL, LV, and CC emerged as the key predictors for identifying AHCPs targeting different components of HCV. The developed model can be accessed through the Pred-AHCP web server, provided at http://tinyurl.com/web-Pred-AHCP. This resource facilitates the prediction and re-engineering of AHCPs for designing peptide-based therapeutics while also proposing an exploration of similar strategies for designing peptide inhibitors effective against other viruses. The developed ML model can also be used for validating peptide sequences generated using generative artificial intelligence methods for further optimization.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"9111-9124"},"PeriodicalIF":5.6,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142589477","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":"Employing Machine Learning Models to Predict Potential α-Glucosidase Inhibitory Plant Secondary Metabolites Targeting Type-2 Diabetes and Their <i>In Vitro</i> Validation.","authors":"Lemnaro Jamir, Hariprasad P","doi":"10.1021/acs.jcim.4c00955","DOIUrl":"10.1021/acs.jcim.4c00955","url":null,"abstract":"<p><p>The need for new antidiabetic drugs is evident, considering the ongoing global burden of type-2 diabetes mellitus despite notable progress in drug discovery from laboratory research to clinical application. This study aimed to build machine learning (ML) models to predict potential α-glucosidase inhibitors based on the data set comprising over 537 reported plant secondary metabolite (PSM) α-glucosidase inhibitors. We assessed 35 ML models by using seven different fingerprints. The Random forest with the RDKit fingerprint was the best-performing model, with an accuracy (ACC) of 83.74% and an area under the ROC curve (AUC) of 0.803. The resulting robust ML model encompasses all reported α-glucosidase inhibitory PSMs. The model was employed to predict potential α-glucosidase inhibitors from an in-house 5810 PSM database. The model identified 965 PSMs with a prediction activity ≥0.90 for α-glucosidase inhibition. Twenty-four predicted PSMs were subjected to <i>in vitro</i> assay, and 13 were found to inhibit α-glucosidase with IC₅₀ ranging from 0.63 to 7 mg/mL. Among them, seven compounds recorded IC₅₀ values less than the standard drug acarbose and were investigated further to have optimal drug-likeness and medicinal chemistry characteristics. The ML model and <i>in vitro</i> experiments have identified nervonic acid as a promising α-glucosidase inhibitor. This compound should be further investigated for its potential integration into the diabetes treatment system.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"9150-9162"},"PeriodicalIF":5.6,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142337350","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":"Exploring the Potential of Adaptive, Local Machine Learning in Comparison to the Prediction Performance of Global Models: A Case Study from Bayer's Caco-2 Permeability Database.","authors":"Frank Filip Steinbauer, Thorsten Lehr, Andreas Reichel","doi":"10.1021/acs.jcim.4c01083","DOIUrl":"10.1021/acs.jcim.4c01083","url":null,"abstract":"<p><p>Machine learning (ML) techniques are being widely implemented to fill the gap in simple molecular design guidelines for newer therapeutic modalities in the extended and beyond rule of five chemical space (eRo5, bRo5). These ML techniques predict molecular properties directly from the structure, allowing for the prioritization of promising compounds. However, the performance of models varies greatly among ML use cases. A molecular property for which achieving sufficient performance in generalizing global models still remains difficult is Caco-2 permeability. Especially within the lower permeability ranges, which are specific for larger molecules belonging to the e/bRo5 space, accurate regression predictions have proven to be challenging. The present study, therefore, identifies a suitable combination of ML algorithm and descriptors, consisting of the LightGBM algorithm and RDKit molecular property descriptors, to predict Caco-2 permeability very efficiently by a simple global model. An additionally introduced local model uses the same algorithm and descriptors but selects its training data based on Tanimoto fingerprint similarity to match the individual test compound's structure. Evaluation of this adaptive model, by systematically varying the number of most similar structures for training, shows that, in comparison to the global model, there was only marginally improved performance with specific training data constellations. These random improvements indicate that deriving general rules for local model parametrization is not possible <i>a priori</i> for the chosen algorithm and descriptor combination, and preselecting training data does not seem advantageous over global ML based on all available data, while creation of more data-efficient models was generally proven to be possible.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"9163-9172"},"PeriodicalIF":5.6,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142674420","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":"DeepAIPs-Pred: Predicting Anti-Inflammatory Peptides Using Local Evolutionary Transformation Images and Structural Embedding-Based Optimal Descriptors with Self-Normalized BiTCNs.","authors":"Shahid Akbar, Matee Ullah, Ali Raza, Quan Zou, Wajdi Alghamdi","doi":"10.1021/acs.jcim.4c01758","DOIUrl":"10.1021/acs.jcim.4c01758","url":null,"abstract":"<p><p>Inflammation is a biological response to harmful stimuli, playing a crucial role in facilitating tissue repair by eradicating pathogenic microorganisms. However, when inflammation becomes chronic, it leads to numerous serious disorders, particularly in autoimmune diseases. Anti-inflammatory peptides (AIPs) have emerged as promising therapeutic agents due to their high specificity, potency, and low toxicity. However, identifying AIPs using traditional in vivo methods is time-consuming and expensive. Recent advancements in computational-based intelligent models for peptides have offered a cost-effective alternative for identifying various inflammatory diseases, owing to their selectivity toward targeted cells with low side effects. In this paper, we propose a novel computational model, namely, <b>DeepAIPs-Pred</b>, for the accurate prediction of AIP sequences. The training samples are represented using LBP-PSSM- and LBP-SMR-based evolutionary image transformation methods. Additionally, to capture contextual semantic features, we employed attention-based ProtBERT-BFD embedding and QLC for structural features. Furthermore, differential evolution (DE)-based weighted feature integration is utilized to produce a multiview feature vector. The SMOTE-Tomek Links are introduced to address the class imbalance problem, and a two-layer feature selection technique is proposed to reduce and select the optimal features. Finally, the novel self-normalized bidirectional temporal convolutional networks (SnBiTCN) are trained using optimal features, achieving a significant predictive accuracy of 94.92% and an AUC of 0.97. The generalization of our proposed model is validated using two independent datasets, demonstrating higher performance with the improvement of ∼2 and ∼10% of accuracies than the existing state-of-the-art model using Ind-I and Ind-II, respectively. The efficacy and reliability of <b>DeepAIPs-Pred</b> highlight its potential as a valuable and promising tool for drug development and research academia.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"9609-9625"},"PeriodicalIF":5.6,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142764647","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":"Correction to \"Exposing the Limitations of Molecular Machine Learning with Activity Cliffs\".","authors":"Derek van Tilborg, Alisa Alenicheva, Francesca Grisoni","doi":"10.1021/acs.jcim.3c01576","DOIUrl":"10.1021/acs.jcim.3c01576","url":null,"abstract":"","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"9643-9648"},"PeriodicalIF":5.6,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49671493","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":"UniBioPAN: A Novel Universal Classification Architecture for Bioactive Peptides Inspired by Video Action Recognition.","authors":"Ruihong Wang, Xiao Liang, Yi Zhao, Wenjun Xue, Guizhao Liang","doi":"10.1021/acs.jcim.4c01599","DOIUrl":"10.1021/acs.jcim.4c01599","url":null,"abstract":"<p><p>The classification of bioactive peptides is of great importance in protein biology, but there is still a lack of a universal and effective classifier. Inspired by video action recognition, we developed the UniBioPAN architecture to create a universal peptide classifier to solve this problem. The architecture treats the peptide sequence as a video sequence and the molecular image of each amino acid in the peptide sequence as a video frame, enabling feature extraction and classification using convolutional neural networks, bidirectional long short-term memory networks, and fully connected networks. As a novel peptide classification architecture, UniBioPAN significantly outperforms other universal architecture in ACC, AUC and MCC across 11 data sets, and F1 score in 9 data sets. UniBioPAN is available in three ways: python script, jupyter notebook script and web server (https://gzliang.cqu.edu.cn/software/UniBioPAN.html). In summary, UniBioPAN is a universal, convenient, and high-performance peptide classification architecture. UniBioPAN holds significant importance in the discovery of bioactive peptides and the advancement of peptide classifiers. All the codes and data sets are publicly available at https://github.com/sanwrh/UniBioPAN.</p>","PeriodicalId":44,"journal":{"name":"Journal of Chemical Information and Modeling ","volume":" ","pages":"9276-9285"},"PeriodicalIF":5.6,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142685419","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}