Explore the vast range of titles available.

This work introduces a method to tune a sequence-based generative model for molecular de novo design that through augmented episodic likelihood can learn to generate structures with certain specified desirable properties. We demonstrate how this model can execute a range of tasks such as generating analogues to a query structure and generating compounds predicted to be active against a biological target. As a proof of principle, the model is first trained to generate molecules that do not contain sulphur. As a second example, the model is trained to generate analogues to the drug Celecoxib, a technique that could be used for scaffold hopping or library expansion starting from a single molecule. Finally, when tuning the model towards generating compounds predicted to be active against the dopamine receptor type 2, the model generates structures of which more than 95% are predicted to be active, including experimentally confirmed actives that have not been included in either the generative model nor the activity prediction model. Graphical abstract .

The increase of publicly available bioactivity data in recent years has fueled and catalyzed research in chemogenomics, data mining, and modeling approaches. As a direct result, over the past few years a multitude of different methods have been reported and evaluated, such as target fishing, nearest neighbor similarity-based methods, and Quantitative Structure Activity Relationship (QSAR)-based protocols. However, such studies are typically conducted on different datasets, using different validation strategies, and different metrics. In this study, different methods were compared using one single standardized dataset obtained from ChEMBL, which is made available to the public, using standardized metrics (BEDROC and Matthews Correlation Coefficient). Specifically, the performance of Naïve Bayes, Random Forests, Support Vector Machines, Logistic Regression, and Deep Neural Networks was assessed using QSAR and proteochemometric (PCM) methods. All methods were validated using both a random split validation and a temporal validation, with the latter being a more realistic benchmark of expected prospective execution. Deep Neural Networks are the top performing classifiers, highlighting the added value of Deep Neural Networks over other more conventional methods. Moreover, the best method (‘DNN_PCM’) performed significantly better at almost one standard deviation higher than the mean performance. Furthermore, Multi-task and PCM implementations were shown to improve performance over single task Deep Neural Networks. Conversely, target prediction performed almost two standard deviations under the mean performance. Random Forests, Support Vector Machines, and Logistic Regression performed around mean performance. Finally, using an ensemble of DNNs, alongside additional tuning, enhanced the relative performance by another 27% (compared with unoptimized ‘DNN_PCM’). Here, a standardized set to test and evaluate different machine learning algorithms in the context of multi-task learning is offered by providing the data and the protocols. Graphical Abstract .

Background The logarithmic acid dissociation constant pKa reflects the ionization of a chemical, which affects lipophilicity, solubility, protein binding, and ability to pass through the plasma membrane. Thus, pKa affects chemical absorption, distribution, metabolism, excretion, and toxicity properties. Multiple proprietary software packages exist for the prediction of pKa, but to the best of our knowledge no free and open-source programs exist for this purpose. Using a freely available data set and three machine learning approaches, we developed open-source models for pKa prediction. Methods The experimental strongest acidic and strongest basic pKa values in water for 7912 chemicals were obtained from DataWarrior, a freely available software package. Chemical structures were curated and standardized for quantitative structure–activity relationship (QSAR) modeling using KNIME, and a subset comprising 79% of the initial set was used for modeling. To evaluate different approaches to modeling, several datasets were constructed based on different processing of chemical structures with acidic and/or basic pKas. Continuous molecular descriptors, binary fingerprints, and fragment counts were generated using PaDEL, and pKa prediction models were created using three machine learning methods, (1) support vector machines (SVM) combined with k-nearest neighbors (kNN), (2) extreme gradient boosting (XGB) and (3) deep neural networks (DNN). Results The three methods delivered comparable performances on the training and test sets with a root-mean-squared error (RMSE) around 1.5 and a coefficient of determination (R 2 ) around 0.80. Two commercial pKa predictors from ACD/Labs and ChemAxon were used to benchmark the three best models developed in this work, and performance of our models compared favorably to the commercial products. Conclusions This work provides multiple QSAR models to predict the strongest acidic and strongest basic pKas of chemicals, built using publicly available data, and provided as free and open-source software on GitHub.

Despite several decades of research, the beneficial effect of flavonoids on health is still enigmatic. Here, we focus on the antioxidant effect of flavonoids, which is elementary to their biological activity. A relatively new strategy for obtaining a more accurate understanding of this effect is to leverage computational chemistry. This review systematically presents various computational chemistry indicators employed over the past five years to investigate the antioxidant activity of flavonoids. We categorize these strategies into five aspects: electronic structure analysis, thermodynamic analysis, kinetic analysis, interaction analysis, and bioavailability analysis. The principles, characteristics, and limitations of these methods are discussed, along with current trends.

Chemogenomics data generally refers to the activity data of chemical compounds on an array of protein targets and represents an important source of information for building in silico target prediction models. The increasing volume of chemogenomics data offers exciting opportunities to build models based on Big Data. Preparing a high quality data set is a vital step in realizing this goal and this work aims to compile such a comprehensive chemogenomics dataset. This dataset comprises over 70 million SAR data points from publicly available databases (PubChem and ChEMBL) including structure, target information and activity annotations. Our aspiration is to create a useful chemogenomics resource reflecting industry-scale data not only for building predictive models of in silico polypharmacology and off-target effects but also for the validation of cheminformatics approaches in general.

The definition which is probably closer to what it is now assumed to be common practice in our field was given by Per-Olov Löwdin in 1967 [2], who pointed out a number of important (and still alive) specificities of any quantum-based field of study: (i) its interest in the determination of the electronic properties of atoms, more complex molecules and aggregates; (ii) the interaction of theory, experiments, mathematics, and computational algorithms in the construction of the core concepts and its methodology; and (iii) the convenient relationship with the subjects of mathematics and physics. In light of this precedent, it is hardly necessary to emphasize how I am grateful and honored to have been proposed to assume the role of Editor-in-Chief, and to have been given the opportunity to serve to the whole scientific community from this position. The collections scheduled along 2024–2025 will include not only emerging topics (e.g., machine learning meets quantum chemistry) but are also intended to cover fundamental yet challenging questions dealing with excited states dynamics and reactivity, many-body electronic structure methods, or charge transfer and electronic coupling, to name just a few of them, which we believe they constitute a hallmark for the theoretical and computational chemistry field.

The following review article attempts to compare the antioxidant activity of the compounds. For this purpose, density functional theory/Becke three-parameter Lee–Yang–Parr (DFT/B3LYP) methodology was carried out instead of using pharmacological methodologies because of economic benefits and high accuracy. This methodology filtrates the compounds with the lowest antioxidant activity. At first, the Koopmans’ theorem was carried out to calculate some descriptors to compare antioxidants. The energy of the highest occupied molecular orbitals (HOMO) was accepted as the best indicator, and then some studies confirmed that the highest occupied molecular orbital/lowest unoccupied molecular orbital (HOMO–LUMO) energy gap is the more precise descriptor. Although it would be better to compare spin density distribution (SDD) on the oxygen of the corresponding radical in the polarizable continuum model (PCM) to evaluate their capability to chain reaction inhibition. Next, it was mentioned that in the multi-target directed ligands (MTDLs), the antioxidant is connected to other moieties in para positions to create better antioxidants or novel hybrid compounds. Indeed, SDD was introduced as a descriptor for MTDL antioxidant effectiveness. Then, the relation between antioxidants and aromaticity was investigated. The more the aromaticity of an antioxidant, the more stable the corresponding radical is. Subsequently, in preferred antioxidant activity, it was defined that the hydrogen atom transfer (HAT) mechanism is more favored in metabolism phase I. It has been seen that the solvent model can change the antioxidant mechanism. Therefore, the solvent model is more important than the chemical structure of antioxidants, and an ideal antioxidant should be evaluated in PCM for pharmacological evaluations.

The ESPA (Electronic Structure, Principles and Applications) conference is organized every two years in Spain. It brings together international specialists in theoretical and computational chemistry to present and discuss the latest advances in this field. The first edition was held in Madrid in 1998, and then, subsequently, in San Sebastián, Sevilla, Valladolid, Santiago de Compostela, Palma de Mallorca, Oviedo, Barcelona, Badajoz, Castellón, and Toledo. The 12th edition of the conference could not be held in 2020 due to the covid epidemic, and it was held in Vigo from June 21 to 24, 2022. This special issue assembles a collection of articles from presentations given at the conference.

Drug repurposing offers a promising alternative to dramatically shorten the process of traditional de novo development of a drug. These efforts leverage the fact that a single molecule can act on multiple targets and could be beneficial to indications where the additional targets are relevant. Hence, extensive research efforts have been directed toward developing drug based computational approaches. However, many drug based approaches are known to incur low successful rates, due to incomplete modeling of drug-target interactions. There are also many technical limitations to transform theoretical computational models into practical use. Drug based approaches may, thus, still face challenges for drug repurposing task. Upon this challenge, we developed a consensus inverse docking (CID) workflow, which has a ~ 10% enhancement in success rate compared with current best method. Besides, an easily accessible web server named auto in silico consensus inverse docking (ACID) was designed based on this workflow ( http://chemyang.ccnu.edu.cn/ccb/server/ACID ).