Jmol SMILES and Jmol SMARTS: specifications and applications

Accurate Prediction of 1H NMR Chemical Shifts of Small Molecules Using Machine Learning

NMR is widely considered the gold standard for organic compound structure determination. As such, NMR is routinely used in organic compound identification, drug metabolite characterization, natural product discovery, and the deconvolution of metabolite mixtures in biofluids (metabolomics and exposomics). In many cases, compound identification by NMR is achieved by matching measured NMR spectra to experimentally collected NMR spectral reference libraries. Unfortunately, the number of available experimental NMR reference spectra, especially for metabolomics, medical diagnostics, or drug-related studies, is quite small. This experimental gap could be filled by predicting NMR chemical shifts for known compounds using computational methods such as machine learning (ML). Here, we describe how a deep learning algorithm that is trained on a high-quality, "solvent-aware" experimental dataset can be used to predict 1H chemical shifts more accurately than any other known method. The new program, called PROSPRE (PROton Shift PREdictor) can accurately (mean absolute error of <0.10 ppm) predict 1H chemical shifts in water (at neutral pH), chloroform, dimethyl sulfoxide, and methanol from a user-submitted chemical structure. PROSPRE (pronounced "prosper") has also been used to predict 1H chemical shifts for >600,000 molecules in many popular metabolomic, drug, and natural product databases.

Deep Generative Models in De Novo Drug Molecule Generation

The discovery of new drugs has important implications for human health. Traditional methods for drug discovery rely on experiments to optimize the structure of lead molecules, which are time-consuming and high-cost. Recently, artificial intelligence has exhibited promising and efficient performance for drug-like molecule generation. In particular, deep generative models achieve great success in de novo generation of drug-like molecules with desired properties, showing massive potential for novel drug discovery. In this study, we review the recent progress of molecule generation using deep generative models, mainly focusing on molecule representations, public databases, data processing tools, and advanced artificial intelligence based molecule generation frameworks. In particular, we present a comprehensive comparison of state-of-the-art deep generative models for molecule generation and a summary of commonly used molecular design strategies. We identify research gaps and challenges of molecule generation such as the need for better databases, missing 3D information in molecular representation, and the lack of high-precision evaluation metrics. We suggest future directions for molecular generation and drug discovery.

Machine Learning for Sequence and Structure-Based Protein-Ligand Interaction Prediction

Developing new drugs is too expensive and time -consuming. Accurately predicting the interaction between drugs and targets will likely change how the drug is discovered. Machine learning-based protein-ligand interaction prediction has demonstrated significant potential. In this paper, computational methods, focusing on sequence and structure to study protein-ligand interactions, are examined. Therefore, this paper starts by presenting an overview of the data sets applied in this area, as well as the various approaches applied for representing proteins and ligands. Then, sequence-based and structure-based classification criteria are subsequently utilized to categorize and summarize both the classical machine learning models and deep learning models employed in protein-ligand interaction studies. Moreover, the evaluation methods and interpretability of these models are proposed. Furthermore, delving into the diverse applications of protein-ligand interaction models in drug research is presented. Lastly, the current challenges and future directions in this field are addressed.

Decrypting orphan GPCR drug discovery via multitask learning

The drug discovery of G protein-coupled receptors (GPCRs) superfamily using computational models is often limited by the availability of protein three-dimensional (3D) structures and chemicals with experimentally measured bioactivities. Orphan GPCRs without known ligands further complicate the process. To enable drug discovery for human orphan GPCRs, multitask models were proposed for predicting half maximal effective concentrations (EC50) of the pairs of chemicals and GPCRs. Protein multiple sequence alignment features, and physicochemical properties and fingerprints of chemicals were utilized to encode the protein and chemical information, respectively. The protein features enabled the transfer of data-rich GPCRs to orphan receptors and the transferability based on the similarity of protein features. The final model was trained using both agonist and antagonist data from 200 GPCRs and showed an excellent mean squared error (MSE) of 0.24 in the validation dataset. An independent test using the orphan dataset consisting of 16 receptors associated with less than 8 bioactivities showed a reasonably good MSE of 1.51 that can be further improved to 0.53 by considering the transferability based on protein features. The informative features were identified and mapped to corresponding 3D structures to gain insights into the mechanism of GPCR-ligand interactions across the GPCR family. The proposed method provides a novel perspective on learning ligand bioactivity within the diverse human GPCR superfamily and can potentially accelerate the discovery of therapeutic agents for orphan GPCRs.

Design and Diversity Analysis of Chemical Libraries in Drug Discovery

Chemical libraries and compound data sets are among the main inputs to start the drug discovery process at universities, research institutes, and the pharmaceutical industry. The approach used in the design of compound libraries, the chemical information they possess, and the representation of structures, play a fundamental role in the development of studies: chemoinformatics, food informatics, in silico pharmacokinetics, computational toxicology, bioinformatics, and molecular modeling to generate computational hits that will continue the optimization process of drug candidates. The prospects for growth in drug discovery and development processes in chemical, biotechnological, and pharmaceutical companies began a few years ago by integrating computational tools with artificial intelligence methodologies. It is anticipated that it will increase the number of drugs approved by regulatory agencies shortly.

Review of techniques and models used in optical chemical structure recognition in images and scanned documents

Extraction of chemical formulas from images was not in the top priority of Computer Vision tasks for a while. The complexity both on the input and prediction sides has made this task challenging for the conventional Artificial Intelligence and Machine Learning problems. A binary input image which might seem trivial for convolutional analysis was not easy to classify, since the provided sample was not representative of the given molecule: to describe the same formula, a variety of graphical representations which do not resemble each other can be used. Considering the variety of molecules, the problem shifted from classification to that of formula generation, which makes Natural Language Processing (NLP) a good candidate for an effective solution. This paper describes the evolution of approaches from rule-based structure analyses to complex statistical models, and compares the efficiency of models and methodologies used in the recent years. Although the latest achievements deliver ideal results on particular datasets, the authors mention possible problems for various scenarios and provide suggestions for further development.

SApredictor: An Expert System for Screening Chemicals Against Structural Alerts

The rapid and accurate evaluation of chemical toxicity is of great significance for estimation of chemical safety. In the past decades, a great number of excellent computational models have been developed for chemical toxicity prediction. But most machine learning models tend to be “black box”, which bring about poor interpretability. In the present study, we focused on the identification and collection of structural alerts (SAs) responsible for a series of important toxicity endpoints. Then, we carried out effective storage of these structural alerts and developed a web-server named SApredictor (www.sapredictor.cn) for screening chemicals against structural alerts. People can quickly estimate the toxicity of chemicals with SApredictor, and the specific key substructures which cause the chemical toxicity will be intuitively displayed to provide valuable information for the structural optimization by medicinal chemists.

A Deep Learning-Based Quantitative Structure-Activity Relationship System Construct Prediction Model of Agonist and Antagonist with High Performance

Molecular design and evaluation for drug development and chemical safety assessment have been advanced by quantitative structure–activity relationship (QSAR) using artificial intelligence techniques, such as deep learning (DL). Previously, we have reported the high performance of prediction models molecular initiation events (MIEs) on the adverse toxicological outcome using a DL-based QSAR method, called DeepSnap-DL. This method can extract feature values from images generated on a three-dimensional (3D)-chemical structure as a novel QSAR analytical system. However, there is room for improvement of this system’s time-consumption. Therefore, in this study, we constructed an improved DeepSnap-DL system by combining the processes of generating an image from a 3D-chemical structure, DL using the image as input data, and statistical calculation of prediction-performance. Consequently, we obtained that the three prediction models of agonists or antagonists of MIEs achieved high prediction-performance by optimizing the parameters of DeepSnap, such as the angle used in the depiction of the image of a 3D-chemical structure, data-split, and hyperparameters in DL. The improved DeepSnap-DL system will be a powerful tool for computer-aided molecular design as a novel QSAR system.

Synthesis, molecular docking, and in silico ADMET studies of 4-benzyl-1-(2,4,6-trimethyl-benzyl)-piperidine: Potential Inhibitor of SARS-CoV2

Nowadays, over 200 countries face a wellbeing emergency because of epidemiological disease COVID-19 caused by the SARS-CoV-2 virus. It will cause a very high effect on the world's economy and the worldwide health sector. The present work is an investigation of the newly synthesized 4-benzyl-1-(2,4,6-trimethyl-benzyl)-piperidine (M1BZP) molecule's inhibitory potential against important protein targets of SARS-CoV-2 using computational approaches. M1BZP crystallizes in monoclinic type with P1211 space group. For the title compound M1BZP, spectroscopic characterization like ¹H NMR, ¹³C NMR, FTIR, were carried out. The geometry of the compound had been optimized by the DFT method and its results were compared with the X-ray diffraction data. The calculated energies for the Highest Occupied Molecular Orbital (HOMO) and the Lowest Unoccupied Molecular Orbital (LUMO) showed the stability and reactivity of the title compound. Intermolecular interactions in the crystal network were determined using Hirshfeld surface analyses. The molecular electrostatic potential (MEP) picture was drawn using the same level of theory to visualize the chemical reactivity and charge distribution on the molecule. Molecular docking study performed for the synthesized compound revealed an efficient interaction with the COVID-19 protease and resulted in good activities. We hope the present study would help workers in the field to develop potential vaccines and therapeutics against the novel coronavirus. Virtual ADME studies were carried out as well and a relationship between biological, electronic, and physicochemical qualifications of the target compound was determined. Toxicity prediction by computational technique for the title compound was also carried out.

Machine Learning in a Molecular Modeling Course for Chemistry, Biochemistry, and Biophysics Students

Recent advances in computer hardware and software, particularly the availability of machine learning libraries, allow the introduction of data-based topics such as machine learning into the Biophysical curriculum for undergraduate and/or graduate levels. However, there are many practical challenges of teaching machine learning to advanced-level students in the biophysics majors, who often do not have a rich computational background. Aiming to overcome such challenges, we present an educational study, including the design of course topics, pedagogical tools, and assessments of student learning, to develop the new methodology to incorporate the basis of machine learning in an existing Biophysical elective course, and engage students in exercises to solve problems in an interdisciplinary field. In general, we observed that students had ample curiosity to learn and apply machine learning algorithms to predict molecular properties. Notably, feedback from the students suggests that care must be taken to ensure student preparations for understanding the data-driven concepts and fundamental coding aspects required for using machine learning algorithms. This work establishes a framework for future teaching approaches that unite machine learning and any existing course in the biophysical curriculum, while also pinpointing the critical challenges that educators and students will likely face.

The effective volumes of waters of crystallization: general organic solids

Using a list of compatible hydrate/anhydrate pairs prepared by van de Streek and Motherwell [CrystEngComm (2007), 9, 55-64], we have examined the effective volume per water of crystallization for 179 pairs of organic solids using current data from the Cambridge Crystallographic Structural Database (CSD). The effective volume is the difference per water molecule between the asymmetric unit volumes of the hydrate and parent anhydrate, and has the mean value 24 ų. The conformational changes in the reference molecule between the hydrate and its anhydrate are shown in two figures: one for a relatively rigid standard organic molecule and (in the supplementary file) one for a more flexible linear molecule. Using data from Nyman and Day [Phys. Chem. Chem. Phys. (2016), 18, 31132-31143], we have also established a generic volumetric coefficient of thermal expansion of organic solids with a value of 147 ± 56 × 10^-6 K^-1. There is a significant number of outliers to the data, negative, near zero, and large and positive. Some explanation for the existence of these outliers is attempted.

DeepSnap-Deep Learning Approach Predicts Progesterone Receptor Antagonist Activity With High Performance

The progesterone receptor (PR) is important therapeutic target for many malignancies and endocrine disorders due to its role in controlling ovulation and pregnancy via the reproductive cycle. Therefore, the modulation of PR activity using its agonists and antagonists is receiving increasing interest as novel treatment strategy. However, clinical trials using the PR modulators have not yet been found conclusive evidences. Recently, increasing evidence from several fields shows that the classification of chemical compounds, including agonists and antagonists, can be done with recent improvements in deep learning (DL) using deep neural network. Therefore, we recently proposed a novel DL-based quantitative structure-activity relationship (QSAR) strategy using transfer learning to build prediction models for agonists and antagonists. By employing this novel approach, referred as DeepSnap-DL method, which uses images captured from 3-dimension (3D) chemical structure with multiple angles as input data into the DL classification, we constructed prediction models of the PR antagonists in this study. Here, the DeepSnap-DL method showed a high performance prediction of the PR antagonists by optimization of some parameters and image adjustment from 3D-structures. Furthermore, comparison of the prediction models from this approach with conventional machine learnings (MLs) indicated the DeepSnap-DL method outperformed these MLs. Therefore, the models predicted by DeepSnap-DL would be powerful tool for not only QSAR field in predicting physiological and agonist/antagonist activities, toxicity, and molecular bindings; but also for identifying biological or pathological phenomena.

LARMD: integration of bioinformatic resources to profile ligand-driven protein dynamics with a case on the activation of estrogen receptor

Protein dynamics is central to all biological processes, including signal transduction, cellular regulation and biological catalysis. Among them, in-depth exploration of ligand-driven protein dynamics contributes to an optimal understanding of protein function, which is particularly relevant to drug discovery. Hence, a wide range of computational tools have been designed to investigate the important dynamic information in proteins. However, performing and analyzing protein dynamics is still challenging due to the complicated operation steps, giving rise to great difficulty, especially for nonexperts. Moreover, there is a lack of web protocol to provide online facility to investigate and visualize ligand-driven protein dynamics. To this end, in this study, we integrated several bioinformatic tools to develop a protocol, named Ligand and Receptor Molecular Dynamics (LARMD, http://chemyang.ccnu.edu.cn/ccb/server/LARMD/ and http://agroda.gzu.edu.cn:9999/ccb/server/LARMD/), for profiling ligand-driven protein dynamics. To be specific, estrogen receptor (ER) was used as a case to reveal ERβ-selective mechanism, which plays a vital role in the treatment of inflammatory diseases and many types of cancers in clinical practice. Two different residues (Ile373/Met421 and Met336/Leu384) in the pocket of ERβ/ERα were the significant determinants for selectivity, especially Met336 of ERβ. The helix H8, helix H11 and H7-H8 loop influenced the migration of selective agonist (WAY-244). These computational results were consistent with the experimental results. Therefore, LARMD provides a user-friendly online protocol to study the dynamic property of protein and to design new ligand or site-directed mutagenesis.

Prediction Model with High-Performance Constitutive Androstane Receptor (CAR) Using DeepSnap-Deep Learning Approach from the Tox21 10K Compound Library

The constitutive androstane receptor (CAR) plays pivotal roles in drug-induced liver injury through the transcriptional regulation of drug-metabolizing enzymes and transporters. Thus, identifying regulatory factors for CAR activation is important for understanding its mechanisms. Numerous studies conducted previously on CAR activation and its toxicity focused on in vivo or in vitro analyses, which are expensive, time consuming, and require many animals. We developed a computational model that predicts agonists for the CAR using the Toxicology in the 21st Century 10k library. Additionally, we evaluate the prediction performance of novel deep learning (DL)-based quantitative structure-activity relationship analysis called the DeepSnap-DL approach, which is a procedure of generating an omnidirectional snapshot portraying three-dimensional (3D) structures of chemical compounds. The CAR prediction model, which applies a 3D structure generator tool, called CORINA-generated and -optimized chemical structures, in the DeepSnap-DL demonstrated better performance than the existing methods using molecular descriptors. These results indicate that high performance in the prediction model using the DeepSnap-DL approach may be important to prepare suitable 3D chemical structures as input data and to enable the identification of modulators of the CAR.

Optimization of a Deep-Learning Method Based on the Classification of Images Generated by Parameterized Deep Snap a Novel Molecular-Image-Input Technique for Quantitative Structure-Activity Relationship (QSAR) Analysis

Numerous chemical compounds are distributed around the world and may affect the homeostasis of the endocrine system by disrupting the normal functions of hormone receptors. Although the risks associated with these compounds have been evaluated by acute toxicity testing in mammalian models, the chronic toxicity of many chemicals remains due to high cost of the compounds and the testing, etc. However, computational approaches may be promising alternatives and reduce these evaluations. Recently, deep learning (DL) has been shown to be promising prediction models with high accuracy for recognition of images, speech, signals, and videos since it greatly benefits from large datasets. Recently, a novel DL-based technique called DeepSnap was developed to conduct QSAR analysis using three-dimensional images of chemical structures. It can be used to predict the potential toxicity of many different chemicals to various receptors without extraction of descriptors. DeepSnap has been shown to have a very high capacity in tests using Tox21 quantitative qHTP datasets. Numerous parameters must be adjusted to use the DeepSnap method but they have not been optimized. In this study, the effects of these parameters on the performance of the DL prediction model were evaluated in terms of the loss in validation as an indicator for evaluating the performance of the DL using the toxicity information in the Tox21 qHTP database. The relations of the parameters of DeepSnap such as (1) number of molecules per SDF split into (2) zoom factor percentage, (3) atom size for van der waals percentage, (4) bond radius, (5) minimum bond distance, and (6) bond tolerance, with the validation loss following quadratic function curves, which suggests that optimal thresholds exist to attain the best performance with these prediction models. Using the parameter values set with the best performance, the prediction model of chemical compounds for CAR agonist was built using 64 images, at 105° angle, with AUC of 0.791. Thus, based on these parameters, the proposed DeepSnap-DL approach will be highly reliable and beneficial to establish models to assess the risk associated with various chemicals.

A-H…σ Hydrogen Bonds: Dihydrogen and Cycloalkanes as Proton Acceptors

ωB97XD/aug-cc-pVTZ calculations were performed for complexes of dihydrogen, cyclopropane, cyclobutane and cyclopentane, with simple proton donating species such as hydrogen fluoride, hydrogen chloride, water, hydrogen cyanide and acetylene. Numerous dependencies between geometrical, energetic and topological parameters of complexes considered were found, since various theoretical approaches were applied: Quantum Theory of 'Atoms in Molecules' (QTAIM), Natural Bond Orbital (NBO) method and energy decomposition analysis (EDA). It was confirmed that complexes of dihydrogen and cyclopropane are linked through the A-H…σ interactions that may be classified as hydrogen bonds. In the case of complexes of cyclobutane such hydrogen bonds are rather weak. Other type and also weak A-H…C hydrogen bonds are formed for complexes with cyclopentane.

AIMMS suite: a web server dedicated for prediction of drug resistance on protein mutation

Drug resistance is one of the most intractable issues for successful treatment in current clinical practice. Although many mutations contributing to drug resistance have been identified, the relationship between the mutations and the related pharmacological profile of drug candidates has yet to be fully elucidated, which is valuable both for the molecular dissection of drug resistance mechanisms and for suggestion of promising treatment strategies to counter resistant. Hence, effective prediction approach for estimating the sensitivity of mutations to agents is a new opportunity that counters drug resistance and creates a high interest in pharmaceutical research. However, this task is always hampered by limited known resistance training samples and accurately estimation of binding affinity. Upon this challenge, we successfully developed Auto In Silico Macromolecular Mutation Scanning (AIMMS), a web server for computer-aided de novo drug resistance prediction for any ligand-protein systems. AIMMS can qualitatively estimate the free energy consequences of any mutations through a fast mutagenesis scanning calculation based on a single molecular dynamics trajectory, which is differentiated with other web services by a statistical learning system. AIMMS suite is available at http://chemyang.ccnu.edu.cn/ccb/server/AIMMS/.

Coordination of Be and Mg Centres by HCN Ligands - Be…N and Mg…N Interactions

ωB97XD/aug-cc-pVTZ calculations were performed for clusters of Z2+ cations (Z=Be and Mg) and HCN molecules (up to six molecules). The clusters of Be(CH3 )2 and Mg(CH3 )2 with HCN species were also calculated to analyse the influence of the Be/Mg-C formally covalent bonds on interactions of Be or Mg centre with ligands. The beryllium and magnesium centres possess different areas of a positive electrostatic potential that depend on a number of HCN ligands in the cluster considered. Numerous correlations between geometrical, energetic and topological parameters of the clusters considered are discussed since various theoretical approaches are applied; Quantum Theory of 'Atoms in Molecules', Natural Bond Orbital method and decomposition of the energy of interaction. The Be/Mg…N interactions classified as beryllium and magnesium bonds possess numerous characteristics which are known for the hydrogen bonds. Different types of coordination of Be and Mg centres analysed here exist also in crystal structures.

Challenges in the local delivery of peptides and proteins for oral mucositis management

Oral mucositis, a common inflammatory side effect of oncological treatments, is a disorder of the oral mucosa that can cause painful ulcerations, local motor disabilities, and an increased risk of infections. Due to the discomfort it produces and the associated health risks, it can lead to cancer treatment restrains, such as the need for dose reduction, cycle delays or abandonment. Current mucositis management has low efficiency in prevention and treatment. A topical drug application for a local action can be a more effective approach than systemic routes when addressing oral cavity pathologies. Local delivery of growth factors, antibodies, and anti-inflammatory cytokines have shown promising results. However, due to the peptide and protein nature of these novel agents, and the several anatomic, physiological and environmental challenges of the oral cavity, their local action might be limited when using traditional delivering systems. This review is an awareness of the issues and strategies in the local delivery of macromolecules for the management of oral mucositis.