PubChem (https://pubchem.ncbi.nlm.nih.gov) is a popular chemical information resource that serves the scientific community as well as the general public, with millions of unique users per month. In the past two years, PubChem made substantial improvements. Data from more than 100 new data sources were added to PubChem, including chemical-literature links from Thieme Chemistry, chemical and physical property links from SpringerMaterials, and patent links from the World Intellectual Properties Organization (WIPO). PubChem's homepage and individual record pages were updated to help users find desired information faster. This update involved a data model change for the data objects used by these pages as well as by programmatic users. Several new services were introduced, including the PubChem Periodic Table and Element pages, Pathway pages, and Knowledge panels. Additionally, in response to the coronavirus disease 2019 (COVID-19) outbreak, PubChem created a special data collection that contains PubChem data related to COVID-19 and the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

/pdf/pubchem-in-2021-new-data-content-and-improved-web-interfaces-1cbjezc4wh.pdf

PubChem in 2021: new data content and improved web interfaces.

Identification of B-cell epitopes (BCEs) is necessary for epitope-based vaccine development, antibody production, and disease prevention and diagnosis. Computational prediction of BCEs, which is necessary before classical wet lab validation, has gained tremendous interest recently. Although several computational methods have been developed, their accuracy is unreliable. Thus, developing a reliable model with significant prediction improvements is highly desirable. In this study, we first constructed a non-redundant dataset of 5,550 experimentally validated BCEs and 6,893 non-BCEs from the Immune Epitope Database. We then developed a novel ensemble learning framework for improved linear BCE predictor called iBCE-EL, a fusion of three independent predictors, namely, random forest, extremely randomised tree, and gradient boosting classifiers, which uses either dipeptide composition or a combination of dipeptide and physicochemical properties as input features. Cross-validation analysis on a benchmarking dataset showed that iBCE-EL performed better than individual classifiers, with an accuracy of 72.4%. Furthermore, iBCE-EL significantly outperformed the state-of-the-art method and six other machine learning-based methods developed in this study, with an accuracy of 71.8%, when objectively evaluated using an independent dataset. To the best of our knowledge, iBCE-EL is the first ensemble method for linear BCE prediction. It will facilitate the design of peptide-based vaccine adjuvants. iBCE-EL was implemented in a web-based platform, which is available at http://thegleelab.org/iBCE-EL.

/pdf/ibce-el-a-new-ensemble-learning-framework-for-improved-3wpv88vprt.pdf

iBCE-EL: A New Ensemble Learning Framework for Improved Linear B-Cell Epitope Prediction.

The primary goal of rational drug discovery is the identification of selective ligands which act on single or multiple drug targets to achieve the desired clinical outcome through the exploration of total chemical space. To identify such desired compounds, computational approaches are necessary in predicting their drug-like properties. G Protein-Coupled Receptors (GPCRs) represent one of the largest and most important integral membrane protein families. These receptors serve as increasingly attractive drug targets due to their relevance in the treatment of various diseases, such as inflammatory disorders, metabolic imbalances, cardiac disorders, cancer, monogenic disorders, etc. In the last decade, multitudes of three-dimensional (3D) structures were solved for diverse GPCRs, thus referring to this period as the "golden age for GPCR structural biology." Moreover, accumulation of data about the chemical properties of GPCR ligands has garnered much interest toward the exploration of GPCR chemical space. Due to the steady increase in the structural, ligand, and functional data of GPCRs, several cheminformatics approaches have been implemented in its drug discovery pipeline. In this review, we mainly focus on the cheminformatics-based paradigms in GPCR drug discovery. We provide a comprehensive view on the ligand- and structure-based cheminformatics approaches which are best illustrated via GPCR case studies. Furthermore, an appropriate combination of ligand-based knowledge with structure-based ones, i.e., integrated approach, which is emerging as a promising strategy for cheminformatics-based GPCR drug design is also discussed.

Exploring G protein-coupled receptors (GPCRs) ligand space via cheminformatics approaches: Impact on rational drug design

Cytochrome P450 enzymes (CYPs)-mediated drug metabolism influences drug pharmacokinetics and results in adverse outcomes in patients through drug-drug interactions (DDIs). Absorption, distribution, metabolism, excretion and toxicity (ADMET) issues are the leading causes for the failure of a drug in the clinical trials. As details on their metabolism are known for just half of the approved drugs, a tool for reliable prediction of CYPs specificity is needed. The SuperCYPsPred web server is currently focused on five major CYPs isoenzymes, which includes CYP1A2, CYP2C19, CYP2D6, CYP2C9 and CYP3A4 that are responsible for more than 80% of the metabolism of clinical drugs. The prediction models for classification of the CYPs inhibition are based on well-established machine learning methods. The models were validated both on cross-validation and external validation sets and achieved good performance. The web server takes a 2D chemical structure as input and reports the CYP inhibition profile of the chemical for 10 models using different molecular fingerprints, along with confidence scores, similar compounds, known CYPs information of drugs-published in literature, detailed interaction profile of individual cytochromes including a DDIs table and an overall CYPs prediction radar chart (http://insilico-cyp.charite.de/SuperCYPsPred/). The web server does not require log in or registration and is free to use.

SuperCYPsPred-a web server for the prediction of cytochrome activity

Computational prediction of cytochrome P450 inhibition and induction

The cytochrome P450 (CYP) enzyme superfamily is involved in phase I metabolism which chemically modifies a variety of substrates via oxidative reactions to make them more water-soluble and easier to eliminate. Inhibition of these enzymes leads to undesirable effects, including toxic drug accumulations and adverse drug-drug interactions. Hence, it is necessary to develop in silico models that can predict the inhibition potential of compounds for different CYP isoforms. This study focused on five major CYP isoforms, including CYP1A2, 2C9, 2C19, 2D6 and 3A4, that are responsible for more than 90% of the metabolism of clinical drugs. The main aim of this study is to develop a multiple-category classification model (MCM) for the major CYP isoforms using a Laplacian-modified naive Bayesian method. The dataset composed of more than 4500 compounds was collected from the PubChem Bioassay database. VolSurf+ descriptors and FCFP_8 fingerprint were used as input features to build classification models. The results demonstrated that the developed MCM using Laplacian-modified naive Bayesian method was successful in classifying inhibitors and non-inhibitors for each CYP isoform. Moreover, the accuracy, sensitivity and specificity values for both training and test sets were above 80% and also yielded satisfactory area under the receiver operating characteristic curve and Matthews correlation coefficient values.

In silico prediction of multiple-category classification model for cytochrome P450 inhibitors and non-inhibitors using machine-learning method.

In order to explore the consequences of spin–orbit coupling on spin–phonon interactions in a set of chemically similar mixed metal oxides, we measured the infrared vibrational properties of Co4B2O9 (B = Nb, Ta) as a function of temperature and compared our findings with lattice dynamics calculations and several different models of spin–phonon coupling. Frequency vs temperature trends for the Co2+ shearing mode near 150 cm−1 reveal significant shifts across the magnetic ordering temperature that are especially large in relative terms. Bringing these results together and accounting for noncollinearity, we obtain spin–phonon coupling constants of −3.4 and −4.3 cm−1 for Co4Nb2O9 and the Ta analog, respectively. Analysis reveals that these coupling constants are derived from interlayer (rather than intralayer) exchange interactions and that the interlayer interactions contain competing antiferromagnetic and ferromagnetic contributions. At the same time, beyond-Heisenberg terms are minimized due to fortuitous symmetry considerations, different from most other 4d- and 5d-containing oxides. Comparison with other contemporary oxides shows that spin–phonon coupling in this family of materials is among the strongest ever reported, suggesting an origin for magnetoelectric coupling.

J. H. Lee

Papers

In silico prediction of multiple-category classification model for cytochrome P450 inhibitors and non-inhibitors using machine-learning method.

Spin–phonon interactions and magnetoelectric coupling in Co4B2O9 (B = Nb, Ta)