Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases

AI in drug discovery and its clinical relevance

The COVID-19 pandemic has emphasized the need for novel drug discovery process. However, the journey from conceptualizing a drug to its eventual implementation in clinical settings is a long, complex, and expensive process, with many potential points of failure. Over the past decade, a vast growth in medical information has coincided with advances in computational hardware (cloud computing, GPUs, and TPUs) and the rise of deep learning. Medical data generated from large molecular screening profiles, personal health or pathology records, and public health organizations could benefit from analysis by Artificial Intelligence (AI) approaches to speed up and prevent failures in the drug discovery pipeline. We present applications of AI at various stages of drug discovery pipelines, including the inherently computational approaches of de novo design and prediction of a drug's likely properties. Open-source databases and AI-based software tools that facilitate drug design are discussed along with their associated problems of molecule representation, data collection, complexity, labeling, and disparities among labels. How contemporary AI methods, such as graph neural networks, reinforcement learning, and generated models, along with structure-based methods, (i.e., molecular dynamics simulations and molecular docking) can contribute to drug discovery applications and analysis of drug responses is also explored. Finally, recent developments and investments in AI-based start-up companies for biotechnology, drug design and their current progress, hopes and promotions are discussed in this article.

Transfer learning for drug-target interaction prediction

MOTIVATION

Utilizing AI-driven approaches for drug-target interaction (DTI) prediction require large volumes of training data which are not available for the majority of target proteins. In this study, we investigate the use of deep transfer learning for the prediction of interactions between drug candidate compounds and understudied target proteins with scarce training data. The idea here is to first train a deep neural network classifier with a generalized source training dataset of large size and then to reuse this pre-trained neural network as an initial configuration for re-training/fine-tuning purposes with a small-sized specialized target training dataset. To explore this idea, we selected six protein families that have critical importance in biomedicine: kinases, G-protein-coupled receptors (GPCRs), ion channels, nuclear receptors, proteases, and transporters. In two independent experiments, the protein families of transporters and nuclear receptors were individually set as the target datasets, while the remaining five families were used as the source datasets. Several size-based target family training datasets were formed in a controlled manner to assess the benefit provided by the transfer learning approach.

RESULTS

Here, we present a systematic evaluation of our approach by pre-training a feed-forward neural network with source training datasets and applying different modes of transfer learning from the pre-trained source network to a target dataset. The performance of deep transfer learning is evaluated and compared with that of training the same deep neural network from scratch. We found that when the training dataset contains fewer than 100 compounds, transfer learning outperforms the conventional strategy of training the system from scratch, suggesting that transfer learning is advantageous for predicting binders to under-studied targets.

AVAILABILITY AND IMPLEMENTATION

The source code and datasets are available at https://github.com/cansyl/TransferLearning4DTI. Our web-based service containing the ready-to-use pre-trained models is accessible at https://tl4dti.kansil.org.

Novel Essential Oils Blend as a Repellent and Toxic Agent against Disease-Transmitting Mosquitoes

Bio-insecticidal research has focused on long-term vector control using essential oils (EOs). This study examined the larvicidal, oviposition-deterrent, and repellent properties of five medicinal herb-based EO formulations (EOFs) on mosquitoes that are vectors of dengue, filariasis, and malaria. EOFs were significantly more toxic to the larvae and pupae of Culex quinquefasciatus, Anopheles stephensi, and Aedes aegypti with LC₅₀ = 9.23, 12.85, and 14.46 ppm, as well with 10.22, 11.39, and 12.81 ppm, with oviposition active indexes of -0.84, -0.95, and -0.92, respectively. Oviposition-deterrent repellence was found in 91.39%, 94.83%, and 96.09%. EOs and N, N-Diethyl-3-methylbenzamide (DEET) were prepared at various concentrations for time duration repellent bioassays (6.25-100 ppm). Ae. aegypti, An. stephensi, and Cx. quinquefasciatus were monitored for 300, 270, and 180 min, respectively. At 100 ppm, EOs and DEET had comparable repellence in terms of test durations. EOF's primary components d-limonene (12.9%), 2,6-octadienal, 3,7-dimethyl, (Z) (12.2%), acetic acid, phenylmethyl ester (19.6%), verbenol (7.6%), and benzyl benzoate (17.4%) may be combined to make a mosquito larvicidal and repellant equivalent to synthetic repellent lotions. In the molecular dynamics simulations, limonene (-6.1 kcal/mol) and benzyl benzoate (-7.5 kcal/mol) had a positive chemical association with DEET (-6.3 kcal/mol) and interacted with the OBP binding pocket with high affinity and stability. This research will help local herbal product manufacturers and the cosmetics industry in developing 100% herbal insect repellent products to combat mosquito-borne diseases, including dengue, malaria, and filariasis.

Transcriptomics, metabolomics, and in-silico drug predictions for liver damage in young and aged burn victims

Burn induces a systemic response affecting multiple organs, including the liver. Since the liver plays a critical role in metabolic, inflammatory, and immune events, a patient with impaired liver often exhibits poor outcomes. The mortality rate after burns in the elderly population is higher than in any other age group, and studies show that the liver of aged animals is more susceptible to injury after burns. Understanding the aged-specific liver response to burns is fundamental to improving health care. Furthermore, no liver-specific therapy exists to treat burn-induced liver damage highlighting a critical gap in burn injury therapeutics. In this study, we analyzed transcriptomics and metabolomics data from the liver of young and aged mice to identify mechanistic pathways and in-silico predict therapeutic targets to prevent or reverse burn-induced liver damage. Our study highlights pathway interactions and master regulators that underlie the differential liver response to burn injury in young and aged animals.

Virtual Screening of Nrf2 Dietary-Derived Agonists and Safety by a New Deep-Learning Model and Verified In Vitro and In Vivo

Nuclear factor (erythroid-derived 2)-like 2 (Nrf2) is an essential regulatory target of antioxidants, but the lack of Nrf2 active site information has hindered discovery of new Nrf2 agonists from food-derived compounds by large-scale virtual screening. Two deep-learning models were separately trained to screen for Nrf2-agonists and safety. The trained models screened potentially active chemicals from approximately 70,000 dietary compounds within 5 min. Of the 169 potential Nrf2 agonists identified via deep-learning screening, 137 had not been reported before. Six compounds selected from the new Nrf2 agonists significantly increased (p < 0.05) the activity of Nrf2 on carbon tetrachloride (CCl₄)-intoxicated HepG2 cells (nicotiflorin (99.44 ± 18.5%), artemetin (97.91 ± 8.22%), daidzin (87.73 ± 3.77%), linonin (74.27 ± 5.73%), sinensetin (72.74 ± 10.41%), and tectoridin (77.78 ± 4.80%)), and their safety were demonstrated by an MTT assay. The safety and Nrf2 agonistic activity of nicotiflorin, artemetin, and daidzin were also reconfirm by a single-dose acute oral toxicity study and CCl₄-intoxicated rat assay.

In-Silico Approaches for the Screening and Discovery of Broad-Spectrum Marine Natural Product Antiviral Agents Against Coronaviruses

The urgent need for SARS-CoV-2 controls has led to a reassessment of approaches to identify and develop natural product inhibitors of zoonotic, highly virulent, and rapidly emerging viruses. There are yet no clinically approved broad-spectrum antivirals available for beta-coronaviruses. Discovery pipelines for pan-virus medications against a broad range of betacoronaviruses are therefore a priority. A variety of marine natural product (MNP) small molecules have shown inhibitory activity against viral species. Access to large data caches of small molecule structural information is vital to finding new pharmaceuticals. Increasingly, molecular docking simulations are being used to narrow the space of possibilities and generate drug leads. Combining in-silico methods, augmented by metaheuristic optimization and machine learning (ML) allows the generation of hits from within a virtual MNP library to narrow screens for novel targets against coronaviruses. In this review article, we explore current insights and techniques that can be leveraged to generate broad-spectrum antivirals against betacoronaviruses using in-silico optimization and ML. ML approaches are capable of simultaneously evaluating different features for predicting inhibitory activity. Many also provide a semi-quantitative measure of feature relevance and can guide in selecting a subset of features relevant for inhibition of SARS-CoV-2.

Artificial Intelligence in Drug Metabolism and Excretion Prediction: Recent Advances, Challenges, and Future Perspectives

Drug metabolism and excretion play crucial roles in determining the efficacy and safety of drug candidates, and predicting these processes is an essential part of drug discovery and development. In recent years, artificial intelligence (AI) has emerged as a powerful tool for predicting drug metabolism and excretion, offering the potential to speed up drug development and improve clinical success rates. This review highlights recent advances in AI-based drug metabolism and excretion prediction, including deep learning and machine learning algorithms. We provide a list of public data sources and free prediction tools for the research community. We also discuss the challenges associated with the development of AI models for drug metabolism and excretion prediction and explore future perspectives in the field. We hope this will be a helpful resource for anyone who is researching in silico drug metabolism, excretion, and pharmacokinetic properties.

In Silico Evaluation of Quercetin Methylated Derivatives on the Interaction with Secretory Phospholipases A2 from Crotalus durissus terrificus and Bothrops jararacussu

Quercetin derivatives have already shown their anti-inflammatory potential, inhibiting essential enzymes involved in this process. Among diverse pro-inflammatory toxins from snake venoms, phospholipase A2 is one of the most abundant in some species, such as Crotalus durissus terrificus and Bothrops jararacussu from the Viperidae family. These enzymes can induce the inflammatory process through hydrolysis at the sn-2 position of glycerophospholipids. Hence, elucidating the main residues involved in the biological effects of these macromolecules can help to identify potential compounds with inhibitory activity. In silico tools were used in this study to evaluate the potential of quercetin methylated derivatives in the inhibition of bothropstoxin I (BthTX-I) and II (BthTX-II) from Bothrops jararacussu and phospholipase A2 from Crotalus durissus terrificus. The use of a transitional analogous and two classical inhibitors of phospholipase A2 guided this work to find the role of residues involved in the phospholipid anchoring and the subsequent development of the inflammatory process. First, main cavities were studied, revealing the best regions to be inhibited by a compound. Focusing on these regions, molecular docking assays were made to show main interactions between each compound. Results reveal that analogue and inhibitors, Varespladib (Var) and p-bromophenacyl bromide (BPB), guided quercetins derivatives analysis, revealing that Leu2, Phe5, Tyr28, glycine in the calcium-binding loop, His48, Asp49 of BthTX-II and Cdtspla2 were the main residues to be inhibited. 3MQ exhibited great interaction with the active site, similar to Var results, while Q anchored better in the BthTX-II active site. However, strong interactions in the C-terminal region, highlighting His120, seem to be crucial to decreasing contacts with phospholipid and BthTX-II. Hence, quercetin derivatives anchor differently with each toxin and further in vitro and in vivo studies are essential to elucidate these data.

Deep Learning Methods Applied to Drug Concentration Prediction of Olanzapine

Pharmacometrics and the utilization of population pharmacokinetics play an integral role in model-informed drug discovery and development (MIDD). Recently, there has been a growth in the application of deep learning approaches to aid in areas within MIDD. In this study, a deep learning model, LSTM-ANN, was developed to predict olanzapine drug concentrations from the CATIE study. A total of 1527 olanzapine drug concentrations from 523 individuals along with 11 patient-specific covariates were used in model development. The hyperparameters of the LSTM-ANN model were optimized through a Bayesian optimization algorithm. A population pharmacokinetic model using the NONMEM model was constructed as a reference to compare to the performance of the LSTM-ANN model. The RMSE of the LSTM-ANN model was 29.566 in the validation set, while the RMSE of the NONMEM model was 31.129. Permutation importance revealed that age, sex, and smoking were highly influential covariates in the LSTM-ANN model. The LSTM-ANN model showed potential in the application of drug concentration predictions as it was able to capture the relationships within a sparsely sampled pharmacokinetic dataset and perform comparably to the NONMEM model.

An efficient method for qualitation and quantitation of multi-components of the herbal medicine Qingjin Yiqi Granules

Qingjin Yiqi Granules (QJYQ) is a Traditional Chinese Medicines (TCMs) prescription for the patients with post-COVID-19 condition. It is essential to carry out the quality evaluation of QJYQ. A comprehensive investigation was conducted by establishing deep-learning assisted mass defect filter (deep-learning MDF) mode for qualitative analysis, ultra-high performance liquid chromatography and scheduled multiple reaction monitoring method (UHPLC-sMRM) for precise quantitation to evaluate the quality of QJYQ. Firstly, a deep-learning MDF was used to classify and characterize the whole phytochemical components of QJYQ based on the mass spectrum (MS) data of ultra-high performance liquid chromatography quadrupole time of flight tandem mass spectrometry (UHPLC-Q-TOF/MS). Secondly, the highly sensitive UHPLC-sMRM data-acquisition method was established to quantify the multi-ingredients of QJYQ. Totally, nine major types of phytochemical compounds in QJYQ were intelligently classified and 163 phytochemicals were initially identified. Furthermore, fifty components were rapidly quantified. The comprehensive evaluation strategy established in this study would provide an effective tool for accurately evaluating the quality of QJYQ as a whole.

Drug-target interaction prediction based on protein features, using wrapper feature selection

Drug-target interaction prediction is a vital stage in drug development, involving lots of methods. Experimental methods that identify these relationships on the basis of clinical remedies are time-taking, costly, laborious, and complex introducing a lot of challenges. One group of new methods is called computational methods. The development of new computational methods which are more accurate can be preferable to experimental methods, in terms of total cost and time. In this paper, a new computational model to predict drug-target interaction (DTI), consisting of three phases, including feature extraction, feature selection, and classification is proposed. In feature extraction phase, different features such as EAAC, PSSM and etc. would be extracted from sequence of proteins and fingerprint features from drugs. These extracted features would then be combined. In the next step, one of the wrapper feature selection methods named IWSSR, due to the large amount of extracted data, is applied. The selected features are then given to rotation forest classification, to have a more efficient prediction. Actually, the innovation of our work is that we extract different features; and then select features by the use of IWSSR. The accuracy of the rotation forest classifier based on tenfold on the golden standard datasets (enzyme, ion channels, G-protein-coupled receptors, nuclear receptors) is as follows: 98.12, 98.07, 96.82, and 95.64. The results of experiments indicate that the proposed model has an acceptable rate in DTI prediction and is compatible with the proposed methods in other papers.

AttentionDTA: Drug-Target Binding Affinity Prediction by Sequence-Based Deep Learning With Attention Mechanism

The identification of drug-target relations (DTRs) is substantial in drug development. A large number of methods treat DTRs as drug-target interactions (DTIs), a binary classification problem. The main drawback of these methods are the lack of reliable negative samples and the absence of many important aspects of DTR, including their dose dependence and quantitative affinities. With increasing number of publications of drug-protein binding affinity data recently, DTRs prediction can be viewed as a regression problem of drug-target affinities (DTAs) which reflects how tightly the drug binds to the target and can present more detailed and specific information than DTIs. The growth of affinity data enables the use of deep learning architectures, which have been shown to be among the state-of-the-art methods in binding affinity prediction. Although relatively effective, due to the black-box nature of deep learning, these models are less biologically interpretable. In this study, we proposed a deep learning-based model, named AttentionDTA, which uses attention mechanism to predict DTAs. Different from the models using 3D structures of drug-target complexes or graph representation of drugs and proteins, the novelty of our work is to use attention mechanism to focus on key subsequences which are important in drug and protein sequences when predicting its affinity. We use two separate one-dimensional Convolution Neural Networks (1D-CNNs) to extract the semantic information of drug's SMILES string and protein's amino acid sequence. Furthermore, a two-side multi-head attention mechanism is developed and embedded to our model to explore the relationship between drug features and protein features. We evaluate our model on three established DTA benchmark datasets, Davis, Metz, and KIBA. AttentionDTA outperforms the state-of-the-art deep learning methods under different evaluation metrics. The results show that the attention-based model can effectively extract protein features related to drug information and drug features related to protein information to better predict drug target affinities. It is worth mentioning that we test our model on IC50 dataset, which provides the binding sites between drugs and proteins, to evaluate the ability of our model to locate binding sites. Finally, we visualize the attention weight to demonstrate the biological significance of the model. The source code of AttentionDTA can be downloaded from https://github.com/zhaoqichang/AttentionDTA_TCBB.

Molecular docking and dynamics simulation analysis of the human FXIIa with compounds from the Mcule database

The human factor XIIa is a serine protease enzyme that is implicated in the pathological thrombosis. This coagulation factor represents an interesting molecular target to design safer antithrombotic agents without adversely influencing physiological hemostasis. Therefore, it is of interest to virtually screen the human factor XIIa crystal with millions of compounds in Mcule database in order to identify potential inhibitors. For this purpose, both molecular docking and dynamics simulation were employed to identify potential hits. Also, various predictive approaches were utilized to estimate chemical, pharmacokinetics and toxicological features for the top hits. As such, we report here that compound 4 (1-(4-benzylpiperazin-1-yl)-2-[5-(3,5-dimethylpyrazol-1-yl)-1,2,3, 4-tetrazol-2-yl]ethanone) may be a potential ligand against the human factor XIIa for further consideration in the design and development of novel antithrombotic agents.

Comparative Studies on Resampling Techniques in Machine Learning and Deep Learning Models for Drug-Target Interaction Prediction

The prediction of drug-target interactions (DTIs) is a vital step in drug discovery. The success of machine learning and deep learning methods in accurately predicting DTIs plays a huge role in drug discovery. However, when dealing with learning algorithms, the datasets used are usually highly dimensional and extremely imbalanced. To solve this issue, the dataset must be resampled accordingly. In this paper, we have compared several data resampling techniques to overcome class imbalance in machine learning methods as well as to study the effectiveness of deep learning methods in overcoming class imbalance in DTI prediction in terms of binary classification using ten (10) cancer-related activity classes from BindingDB. It is found that the use of Random Undersampling (RUS) in predicting DTIs severely affects the performance of a model, especially when the dataset is highly imbalanced, thus, rendering RUS unreliable. It is also found that SVM-SMOTE can be used as a go-to resampling method when paired with the Random Forest and Gaussian Naïve Bayes classifiers, whereby a high F1 score is recorded for all activity classes that are severely and moderately imbalanced. Additionally, the deep learning method called Multilayer Perceptron recorded high F1 scores for all activity classes even when no resampling method was applied.

How to approach machine learning-based prediction of drug/compound-target interactions

The identification of drug/compound-target interactions (DTIs) constitutes the basis of drug discovery, for which computational predictive approaches have been developed. As a relatively new data-driven paradigm, proteochemometric (PCM) modeling utilizes both protein and compound properties as a pair at the input level and processes them via statistical/machine learning. The representation of input samples (i.e., proteins and their ligands) in the form of quantitative feature vectors is crucial for the extraction of interaction-related properties during the artificial learning and subsequent prediction of DTIs. Lately, the representation learning approach, in which input samples are automatically featurized via training and applying a machine/deep learning model, has been utilized in biomedical sciences. In this study, we performed a comprehensive investigation of different computational approaches/techniques for protein featurization (including both conventional approaches and the novel learned embeddings), data preparation and exploration, machine learning-based modeling, and performance evaluation with the aim of achieving better data representations and more successful learning in DTI prediction. For this, we first constructed realistic and challenging benchmark datasets on small, medium, and large scales to be used as reliable gold standards for specific DTI modeling tasks. We developed and applied a network analysis-based splitting strategy to divide datasets into structurally different training and test folds. Using these datasets together with various featurization methods, we trained and tested DTI prediction models and evaluated their performance from different angles. Our main findings can be summarized under 3 items: (i) random splitting of datasets into train and test folds leads to near-complete data memorization and produce highly over-optimistic results, as a result, should be avoided, (ii) learned protein sequence embeddings work well in DTI prediction and offer high potential, despite interaction-related properties (e.g., structures) of proteins are unused during their self-supervised model training, and (iii) during the learning process, PCM models tend to rely heavily on compound features while partially ignoring protein features, primarily due to the inherent bias in DTI data, indicating the requirement for new and unbiased datasets. We hope this study will aid researchers in designing robust and high-performing data-driven DTI prediction systems that have real-world translational value in drug discovery.

SSELM-neg: spherical search-based extreme learning machine for drug-target interaction prediction

BACKGROUND

The experimental verification of a drug discovery process is expensive and time-consuming. Therefore, efficiently and effectively identifying drug-target interactions (DTIs) has been the focus of research. At present, many machine learning algorithms are used for predicting DTIs. The key idea is to train the classifier using an existing DTI to predict a new or unknown DTI. However, there are various challenges, such as class imbalance and the parameter optimization of many classifiers, that need to be solved before an optimal DTI model is developed.

METHODS

In this study, we propose a framework called SSELM-neg for DTI prediction, in which we use a screening approach to choose high-quality negative samples and a spherical search approach to optimize the parameters of the extreme learning machine.

RESULTS

The results demonstrated that the proposed technique outperformed other state-of-the-art methods in 10-fold cross-validation experiments in terms of the area under the receiver operating characteristic curve (0.986, 0.993, 0.988, and 0.969) and AUPR (0.982, 0.991, 0.982, and 0.946) for the enzyme dataset, G-protein coupled receptor dataset, ion channel dataset, and nuclear receptor dataset, respectively.

CONCLUSION

The screening approach produced high-quality negative samples with the same number of positive samples, which solved the class imbalance problem. We optimized an extreme learning machine using a spherical search approach to identify DTIs. Therefore, our models performed better than other state-of-the-art methods.

Opportunities and challenges in application of artificial intelligence in pharmacology

Artificial intelligence (AI) is a machine science that can mimic human behaviour like intelligent analysis of data. AI functions with specialized algorithms and integrates with deep and machine learning. Living in the digital world can generate a huge amount of medical data every day. Therefore, we need an automated and reliable evaluation tool that can make decisions more accurately and faster. Machine learning has the potential to learn, understand and analyse the data used in healthcare systems. In the last few years, AI is known to be employed in various fields in pharmaceutical science especially in pharmacological research. It helps in the analysis of preclinical (laboratory animals) and clinical (in human) trial data. AI also plays important role in various processes such as drug discovery/manufacturing, diagnosis of big data for disease identification, personalized treatment, clinical trial research, radiotherapy, surgical robotics, smart electronic health records, and epidemic outbreak prediction. Moreover, AI has been used in the evaluation of biomarkers and diseases. In this review, we explain various models and general processes of machine learning and their role in pharmacological science. Therefore, AI with deep learning and machine learning could be relevant in pharmacological research.

Artificial Intelligence and Machine Learning for Lead-to-Candidate Decision-Making and Beyond

The use of artificial intelligence (AI) and machine learning (ML) in pharmaceutical research and development has to date focused on research: target identification; docking-, fragment-, and motif-based generation of compound libraries; modeling of synthesis feasibility; rank-ordering likely hits according to structural and chemometric similarity to compounds having known activity and affinity to the target(s); optimizing a smaller library for synthesis and high-throughput screening; and combining evidence from screening to support hit-to-lead decisions. Applying AI/ML methods to lead optimization and lead-to-candidate (L2C) decision-making has shown slower progress, especially regarding predicting absorption, distribution, metabolism, excretion, and toxicology properties. The present review surveys reasons why this is so, reports progress that has occurred in recent years, and summarizes some of the issues that remain. Effective AI/ML tools to derisk L2C and later phases of development are important to accelerate the pharmaceutical development process, ameliorate escalating development costs, and achieve greater success rates.

BloodNet: An attention-based deep network for accurate, efficient, and costless bloodstain time since deposition inference

The time since deposition (TSD) of a bloodstain, i.e., the time of a bloodstain formation is an essential piece of biological evidence in crime scene investigation. The practical usage of some existing microscopic methods (e.g., spectroscopy or RNA analysis technology) is limited, as their performance strongly relies on high-end instrumentation and/or rigorous laboratory conditions. This paper presents a practically applicable deep learning-based method (i.e., BloodNet) for efficient, accurate, and costless TSD inference from a macroscopic view, i.e., by using easily accessible bloodstain photos. To this end, we established a benchmark database containing around 50,000 photos of bloodstains with varying TSDs. Capitalizing on such a large-scale database, BloodNet adopted attention mechanisms to learn from relatively high-resolution input images the localized fine-grained feature representations that were highly discriminative between different TSD periods. Also, the visual analysis of the learned deep networks based on the Smooth Grad-CAM tool demonstrated that our BloodNet can stably capture the unique local patterns of bloodstains with specific TSDs, suggesting the efficacy of the utilized attention mechanism in learning fine-grained representations for TSD inference. As a paired study for BloodNet, we further conducted a microscopic analysis using Raman spectroscopic data and a machine learning method based on Bayesian optimization. Although the experimental results show that such a new microscopic-level approach outperformed the state-of-the-art by a large margin, its inference accuracy is significantly lower than BloodNet, which further justifies the efficacy of deep learning techniques in the challenging task of bloodstain TSD inference. Our code is publically accessible via https://github.com/shenxiaochenn/BloodNet. Our datasets and pre-trained models can be freely accessed via https://figshare.com/articles/dataset/21291825.

Recent Studies of Artificial Intelligence on In Silico Drug Distribution Prediction

Drug distribution is an important process in pharmacokinetics because it has the potential to influence both the amount of medicine reaching the active sites and the effectiveness as well as safety of the drug. The main causes of 90% of drug failures in clinical development are lack of efficacy and uncontrolled toxicity. In recent years, several advances and promising developments in drug distribution property prediction have been achieved, especially in silico, which helped to drastically reduce the time and expense of screening undesired drug candidates. In this study, we provide comprehensive knowledge of drug distribution background, influencing factors, and artificial intelligence-based distribution property prediction models from 2019 to the present. Additionally, we gathered and analyzed public databases and datasets commonly utilized by the scientific community for distribution prediction. The distribution property prediction performance of five large ADMET prediction tools is mentioned as a benchmark for future research. On this basis, we also offer future challenges in drug distribution prediction and research directions. We hope that this review will provide researchers with helpful insight into distribution prediction, thus facilitating the development of innovative approaches for drug discovery.

Structural Analysis and Prediction of Hematotoxicity Using Deep Learning Approaches

Hematotoxicity has been becoming a serious but overlooked toxicity in drug discovery. However, only a few in silico models have been reported for the prediction of hematotoxicity. In this study, we constructed a high-quality dataset comprising 759 hematotoxic compounds and 1623 nonhematotoxic compounds and then established a series of classification models based on a combination of seven machine learning (ML) algorithms and nine molecular representations. The results based on two data partitioning strategies and applicability domain (AD) analysis illustrate that the best prediction model based on Attentive FP yielded a balanced accuracy (BA) of 72.6%, an area under the receiver operating characteristic curve (AUC) value of 76.8% for the validation set, and a BA of 69.2%, an AUC of 75.9% for the test set. In addition, compared with existing filtering rules and models, our model achieved the highest BA value of 67.5% for the external validation set. Additionally, the shapley additive explanation (SHAP) and atom heatmap approaches were utilized to discover the important features and structural fragments related to hematotoxicity, which could offer helpful tips to detect undesired positive substances. Furthermore, matched molecular pair analysis (MMPA) and representative substructure derivation technique were employed to further characterize and investigate the transformation principles and distinctive structural features of hematotoxic chemicals. We believe that the novel graph-based deep learning algorithms and insightful interpretation presented in this study can be used as a trustworthy and effective tool to assess hematotoxicity in the development of new drugs.

Predicting the Likelihood of Molecules to Act as Modulators of Protein-Protein Interactions

Targeting protein-protein interactions (PPIs) by small molecule modulators (iPPIs) is an attractive strategy for drug therapy, and some iPPIs have already been introduced into the clinic. Blocking PPIs is however considered to be a more difficult task than inhibiting enzymes or antagonizing receptor activity. In this paper, we examine whether it is possible to predict the likelihood of molecules to act as iPPIs. Using our in-house iterative stochastic elimination (ISE) algorithm, we constructed two classification models that successfully distinguish between iPPIs from the iPPI-DB database and decoy molecules from either the Enamine HTS collection (ISE 1) or the ZINC database (ISE 2). External test sets of iPPIs taken from the TIMBAL database and decoys from Enamine HTS or ZINC were screened by the models: the area under the curve for the receiver operating characteristic curve was 0.85-0.89, and the Enrichment Factor increased from an initial 1 to as much as 66 for ISE 1 and 57 for ISE 2. Screening of the Enamine HTS and ZINC data sets through both models results in a library of ∼1.3 million molecules that pass either one of the models. This library is enriched with iPPI candidates that are structurally different from known iPPIs, and thus, it is useful for target-specific screenings and should accelerate the discovery of iPPI drug candidates. The entire library is available in Table S6.

Vaxi-DL: An Artificial Intelligence-Enabled Platform for Vaccine Development

Vaccine development is a complex and long process. It involves several steps, including computational studies, experimental analyses, animal model system studies, and clinical trials. This process can be accelerated by using in silico antigen screening to identify potential vaccine candidates. In this chapter, we describe a deep learning-based technique which utilizes 18 biological and 9154 physicochemical properties of proteins for finding potential vaccine candidates. Using this technique, a new web-based system, named Vaxi-DL, was developed which helped in finding new vaccine candidates from bacteria, protozoa, viruses, and fungi. Vaxi-DL is available at: https://vac.kamalrawal.in/vaxidl/ .

A systematic review on the state-of-the-art strategies for protein representation

The study of drug-target protein interaction is a key step in drug research. In recent years, machine learning techniques have become attractive for research, including drug research, due to their automated nature, predictive power, and expected efficiency. Protein representation is a key step in the study of drug-target protein interaction by machine learning, which plays a fundamental role in the ultimate accomplishment of accurate research. With the progress of machine learning, protein representation methods have gradually attracted attention and have consequently developed rapidly. Therefore, in this review, we systematically classify current protein representation methods, comprehensively review them, and discuss the latest advances of interest. According to the information extraction methods and information sources, these representation methods are generally divided into structure and sequence-based representation methods. Each primary class can be further divided into specific subcategories. As for the particular representation methods involve both traditional and the latest approaches. This review contains a comprehensive assessment of the various methods which researchers can use as a reference for their specific protein-related research requirements, including drug research.

In silico structure-based designers of therapeutic targets for diabetes mellitus or obesity: A protocol for systematic review

Obesity is a significant risk factor for several chronic non-communicable diseases, being closely related to Diabetes Mellitus. Computer modeling techniques favor the understanding of interaction mechanisms between specific targets and substances of interest, optimizing drug development. In this article, the protocol of two protocols of systematic reviews are described for identifying therapeutic targets and models for treating obesity or diabetes mellitus investigated in silico. The protocol is by the guidelines from the Preferred Reporting Items for Systematic Reviews and Meta-Analyzes Protocols (PRISMA-P) and was published in the International Prospective Register of Systematic Reviews database (PROSPERO: CRD42022353808). Search strategies will be developed based on the combination of descriptors and executed in the following databases: PubMed; ScienceDirect; Scopus; Web of Science; Virtual Health Library; EMBASE. Only original in silico studies with molecular dynamics, molecular docking, or both will be inserted. Two trained researchers will independently select the articles, extract the data, and assess the risk of bias. The quality will be assessed through an adapted version of the Strengthening the Reporting of Empirical Simulation Studies (STRESS) and the risk of bias using a checklist obtained from separate literature sources. The implementation of this protocol will result in the elaboration of two systematic reviews identifying the therapeutic targets for treating obesity (review 1) or diabetes mellitus (review 2) used in computer simulation studies and their models. The systematization of knowledge about these treatment targets and their in silico structures is fundamental, primarily because computer simulation contributes to more accurate planning of future either in vitro or in vivo studies. Therefore, the reviews developed from this protocol will guide decision-making regarding the choice of targets/models in future research focused on therapeutics of obesity or Diabetes Mellitus contributing to mitigate of factors such as costs, time, and necessity of in vitro and/or in vivo assays.

Machine learning-based prediction of drug approvals using molecular, physicochemical, clinical trial, and patent-related features

BACKGROUND

Drug development productivity has been declining lately due to elevated costs and reduced discovery rates. Therefore, pharmaceutical companies have been seeking alternative ways to determine and evaluate drug candidates.

RESEARCH DESIGN AND METHODS

In this work, we proposed a new computational approach to directly predict the regulatory approval of drug candidates, and implemented it as a method called 'DrugApp.' To accomplish this task, we employed multiple types of features including molecular and physicochemical properties of drug candidates, together with clinical trial and patent-related features, which are then processed by random forest classifiers to train our disease group-specific approval prediction models.

RESULTS

Our evaluations indicated DrugApp has a high and robust prediction performance. Within a use-case study, we showed our method can predict phase IV trial drugs that are later withdrawn from the market due to severe side effects. Finally, we used DrugApp models to forecast the approval of drug candidates that are currently in phases I/II/III of clinical trials.

CONCLUSIONS

We hope that our study will aid the research community in terms of evaluating and improving the process of drug development. The datasets, source code, results, and pre-trained models of DrugApp are freely available at https://github.com/HUBioDataLab/DrugApp.

Machine intelligence-driven framework for optimized hit selection in virtual screening

Virtual screening (VS) aids in prioritizing unknown bio-interactions between compounds and protein targets for empirical drug discovery. In standard VS exercise, roughly 10% of top-ranked molecules exhibit activity when examined in biochemical assays, which accounts for many false positive hits, making it an arduous task. Attempts for conquering false-hit rates were developed through either ligand-based or structure-based VS separately; however, nonetheless performed remarkably well. Here, we present an advanced VS framework—automated hit identification and optimization tool (A-HIOT)—comprises chemical space-driven stacked ensemble for identification and protein space-driven deep learning architectures for optimization of an array of specific hits for fixed protein receptors. A-HIOT implements numerous open-source algorithms intending to integrate chemical and protein space leading to a high-quality prediction. The optimized hits are the selective molecules which we retrieve after extreme refinement implying chemical space and protein space modules of A-HIOT. Using CXC chemokine receptor 4, we demonstrated the superior performance of A-HIOT for hit molecule identification and optimization with tenfold cross-validation accuracies of 94.8% and 81.9%, respectively. In comparison with other machine learning algorithms, A-HIOT achieved higher accuracies of 96.2% for hit identification and 89.9% for hit optimization on independent benchmark datasets for CXCR4 and 86.8% for hit identification and 90.2% for hit optimization on independent test dataset for androgen receptor (AR), thus, shows its generalizability and robustness. In conclusion, advantageous features impeded in A-HIOT is making a reliable approach for bridging the long-standing gap between ligand-based and structure-based VS in finding the optimized hits for the desired receptor. The complete resource (framework) code is available at https://gitlab.com/neeraj-24/A-HIOT.

Graphical Abstract

Predicting drug-target binding affinity through molecule representation block based on multi-head attention and skip connection

Exiting computational models for drug-target binding affinity prediction have much room for improvement in prediction accuracy, robustness and generalization ability. Most deep learning models lack interpretability analysis and few studies provide application examples. Based on these observations, we presented a novel model named Molecule Representation Block-based Drug-Target binding Affinity prediction (MRBDTA). MRBDTA is composed of embedding and positional encoding, molecule representation block and interaction learning module. The advantages of MRBDTA are reflected in three aspects: (i) developing Trans block to extract molecule features through improving the encoder of transformer, (ii) introducing skip connection at encoder level in Trans block and (iii) enhancing the ability to capture interaction sites between proteins and drugs. The test results on two benchmark datasets manifest that MRBDTA achieves the best performance compared with 11 state-of-the-art models. Besides, through replacing Trans block with single Trans encoder and removing skip connection in Trans block, we verified that Trans block and skip connection could effectively improve the prediction accuracy and reliability of MRBDTA. Then, relying on multi-head attention mechanism, we performed interpretability analysis to illustrate that MRBDTA can correctly capture part of interaction sites between proteins and drugs. In case studies, we firstly employed MRBDTA to predict binding affinities between Food and Drug Administration-approved drugs and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) replication-related proteins. Secondly, we compared true binding affinities between 3C-like proteinase and 185 drugs with those predicted by MRBDTA. The final results of case studies reveal reliable performance of MRBDTA in drug design for SARS-CoV-2.

Deep learning in drug discovery: an integrative review and future challenges

Recently, using artificial intelligence (AI) in drug discovery has received much attention since it significantly shortens the time and cost of developing new drugs. Deep learning (DL)-based approaches are increasingly being used in all stages of drug development as DL technology advances, and drug-related data grows. Therefore, this paper presents a systematic Literature review (SLR) that integrates the recent DL technologies and applications in drug discovery Including, drug-target interactions (DTIs), drug-drug similarity interactions (DDIs), drug sensitivity and responsiveness, and drug-side effect predictions. We present a review of more than 300 articles between 2000 and 2022. The benchmark data sets, the databases, and the evaluation measures are also presented. In addition, this paper provides an overview of how explainable AI (XAI) supports drug discovery problems. The drug dosing optimization and success stories are discussed as well. Finally, digital twining (DT) and open issues are suggested as future research challenges for drug discovery problems. Challenges to be addressed, future research directions are identified, and an extensive bibliography is also included.

New Cholesteryl Ester Transfer Protein from Indonesian Herbal Plants as Candidate Treatment of Cardiovascular Disease

BACKGROUND: There is a strong negative relationship between high-density lipoprotein cholesterol (HDL-C) and the risk of cardiovascular disease (CVD). Cholesterol ester transfer protein (CETP) is a glycoprotein transporter that transfers cholesterol esters to very low-density lipoprotein and low-density lipoprotein cholesterol (LDL-C). The CETP inhibitor is a new strategy against CVD because of its ability to increase HDL-C. Various Indonesian plants have not been optimally used, and in silico phytochemical screening of these plants showing potential as CETP inhibitors is still limited. AIM: This study for exploring Indonesian phytochemicals as CETP inhibitors for new CVD treatments. METHODS: We screened 457 phytochemicals registered in the herbal database and met Lipinski’s rule of five. Their molecular structures were downloaded from the PubChem database. The three-dimensional structures of CETP and dalcetrapib (the CETP inhibitor standard) were obtained from a protein data bank (http://www.rcsb.org/pdb/) with the 4EWS code and ZINC database with the ZINC03976476 code, respectively. CETP–dalcetrapib binding complexes were validated 5 times using AutoDock Vina 1.1.2 software. Interactions between CETP and phytochemicals were molecularly docked with the same software and visualized using Pymol 1.8× software. RESULTS: Dalcetrapib had a docking score of −9.22 kcal/mol and bound to CETP at Ser230 and His232 residues. The 11 phytochemicals had lower binding scores than dalcetrapib, but only L-(+)-tartaric acid, chitranone, and oxoxylopine could interact with CETP at the Ser230 residue. These are commonly found in Tamarindus indica, Plumbago zeylanica, and Annona reticulata, respectively. CONCLUSION: L-(+)-Tartaric acid, chitranone, and oxoxylopine show potential as CETP inhibitors in silico.

Effect analysis of a virtual simulation experimental platform in teaching pulpotomy

BACKGROUND

The experimental teaching of pediatric dentistry is a bridge between theoretical study and clinical practice, and virtual simulation technology provides a new method of instruction.

METHODS

We built an experimental teaching platform using virtual simulation technology for vital pulpotomy that includes learning and examination modes. A total of 199 students majoring in stomatology in the fourth year at Sun Yat-Sen University were randomly divided into a control group (conventional teaching mode) and an experimental group (virtual simulation experimental teaching model). The teaching effect was evaluated by theoretical and experimental examination.

RESULTS

We found that both the theoretical and experimental scores of the experimental group were higher than those of the control group, and the theoretical scores of the experimental group after exposure to the virtual simulation experimental teaching platform were also higher than those before the class, with significant differences (P < 0.05). Feedback from the experimental group after the class indicated that the platform reinforced their theoretical knowledge and greatly improved their mastery of operational skills.

CONCLUSIONS

The application of a virtual simulation experimental teaching platform can effectively improve the teaching of pulpotomy.

Application of Computational Biology and Artificial Intelligence in Drug Design

Traditional drug design requires a great amount of research time and developmental expense. Booming computational approaches, including computational biology, computer-aided drug design, and artificial intelligence, have the potential to expedite the efficiency of drug discovery by minimizing the time and financial cost. In recent years, computational approaches are being widely used to improve the efficacy and effectiveness of drug discovery and pipeline, leading to the approval of plenty of new drugs for marketing. The present review emphasizes on the applications of these indispensable computational approaches in aiding target identification, lead discovery, and lead optimization. Some challenges of using these approaches for drug design are also discussed. Moreover, we propose a methodology for integrating various computational techniques into new drug discovery and design.

In vitro models for investigating itch

Itch (pruritus) is a sensation that drives a desire to scratch, a behavior observed in many animals. Although generally short-lasting and not causing harm, there are several pathological conditions where chronic itch is a hallmark symptom and in which prolonged scratching can induce damage. Finding medications to counteract the sensation of chronic itch has proven difficult due to the molecular complexity that involves a multitude of triggers, receptors and signaling pathways between skin, immune and nerve cells. While much has been learned about pruritus from in vivo animal models, they have limitations that corroborate the necessity for a transition to more human disease-like models. Also, reducing animal use should be encouraged in research. However, conducting human in vivo experiments can also be ethically challenging. Thus, there is a clear need for surrogate models to be used in pre-clinical investigation of the mechanisms of itch. Most in vitro models used for itch research focus on the use of known pruritogens. For this, sensory neurons and different types of skin and/or immune cells are stimulated in 2D or 3D co-culture, and factors such as neurotransmitter or cytokine release can be measured. There are however limitations of such simplistic in vitro models. For example, not all naturally occurring cell types are present and there is also no connection to the itch-sensing organ, the central nervous system (CNS). Nevertheless, in vitro models offer a chance to investigate otherwise inaccessible specific cell–cell interactions and molecular pathways. In recent years, stem cell-based approaches and human primary cells have emerged as viable alternatives to standard cell lines or animal tissue. As in vitro models have increased in their complexity, further opportunities for more elaborated means of investigating itch have been developed. In this review, we introduce the latest concepts of itch and discuss the advantages and limitations of current in vitro models, which provide valuable contributions to pruritus research and might help to meet the unmet clinical need for more refined anti-pruritic substances.

Glycoinformatics in the Artificial Intelligence Era

Artificial intelligence (AI) methods have been and are now being increasingly integrated in prediction software implemented in bioinformatics and its glycoscience branch known as glycoinformatics. AI techniques have evolved in the past decades, and their applications in glycoscience are not yet widespread. This limited use is partly explained by the peculiarities of glyco-data that are notoriously hard to produce and analyze. Nonetheless, as time goes, the accumulation of glycomics, glycoproteomics, and glycan-binding data has reached a point where even the most recent deep learning methods can provide predictors with good performance. We discuss the historical development of the application of various AI methods in the broader field of glycoinformatics. A particular focus is placed on shining a light on challenges in glyco-data handling, contextualized by lessons learnt from related disciplines. Ending on the discussion of state-of-the-art deep learning approaches in glycoinformatics, we also envision the future of glycoinformatics, including development that need to occur in order to truly unleash the capabilities of glycoscience in the systems biology era.

In-silico investigation of a novel inhibitors against the antibiotic-resistant Neisseria gonorrhoeae bacteria

Antibiotics are drugs that are used to treat or prevent bacterial infections. They work by either killing or stopping bacteria from spreading. Nevertheless, it appeared in the last decade, Antibiotic-resistant bacteria are bacteria resistant to antibiotics and cannot be controlled or killed by them. In the presence of an antibiotic, they can live and even reproduce. The Neisseria gonorrhoeae bacteria is appearing to be a multidrug-resistant pathogen. Many factors contribute to antibiotic resistance, including unfettered access to antimicrobials, incorrect drug selection, misuse, and low-quality antibiotics. Here, we investigated in-silico docking screening and analysis for ten natural marine fungus extracted compounds. The resulted data were examined for the best binding affinity, toxicity, and chemical interactions. The most superior compound was elipyrone A with six hydrogen bonds, −8.5 of binding affinity, and preferable results in the SWISS-ADME examination. It is well known that “Declining corporate investment and a lack of innovation in the development of new antibiotics are weakening efforts to battle drug-resistant illnesses,” according to the World Health Organization (WHO). So, we extended our effort to predict a new natural compound to overcome the resistance of this bacteria.

Combining structure-based pharmacophore modeling and machine learning for the identification of novel BTK inhibitors

Bruton's tyrosine kinase (BTK) is a critical enzyme which is involved in multiple signaling pathways that regulate cellular survival, activation, and proliferation, making it a major cancer therapeutic target. We applied the novel integrated structure-based pharmacophore modeling, machine learning, and other in silico studies to screen the Korean chemical database (KCB) to identify the potential BTK inhibitors (BTKi). Further evaluation of these inhibitors on three different human cancer cell lines showed significant cell growth inhibitory activity. Among the 13 compounds shortlisted, four demonstrated consistent cell inhibition activity among breast, gastric, and lung cancer cells (IC50 below 3 μM). The selected compounds also showed significant kinase inhibition activity (IC50 below 5 μM). The current study suggests the potential of these inhibitors for targeting BTK malignant tumors.

Deep learning and machine intelligence: New computational modeling techniques for discovery of the combination rules and pharmacodynamic characteristics of Traditional Chinese Medicine

It has been increasingly accepted that Multi-Ingredient-Based interventions provide advantages over single-target therapy for complex diseases. With the growing development of Traditional Chinese Medicine (TCM) and continually being refined of a holistic view, "multi-target" and "multi-pathway" integration characteristics of which are being accepted. However, its effector substances, efficacy targets, especially the combination rules and mechanisms remain unclear, and more powerful strategies to interpret the synergy are urgently needed. Artificial intelligence (AI) and computer vision lead to a rapidly expanding in many fields, including diagnosis and treatment of TCM. AI technology significantly improves the reliability and accuracy of diagnostics, target screening, and new drug research. While all AI techniques are capable of matching models to biological big data, the specific methods are complex and varied. Retrieves literature by the keywords such as "artificial intelligence", "machine learning", "deep learning", "traditional Chinese medicine" and "Chinese medicine". Search the application of computer algorithms of TCM between 2000 and 2021 in PubMed, Web of Science, China National Knowledge Infrastructure (CNKI), Elsevier and Springer. This review concentrates on the application of computational in herb quality evaluation, drug target discovery, optimized compatibility and medical diagnoses of TCM. We describe the characteristics of biological data for which different AI techniques are applicable, and discuss some of the best data mining methods and the problems faced by deep learning and machine learning methods applied to Chinese medicine.

Protein Function Analysis through Machine Learning

Machine learning (ML) has been an important arsenal in computational biology used to elucidate protein function for decades. With the recent burgeoning of novel ML methods and applications, new ML approaches have been incorporated into many areas of computational biology dealing with protein function. We examine how ML has been integrated into a wide range of computational models to improve prediction accuracy and gain a better understanding of protein function. The applications discussed are protein structure prediction, protein engineering using sequence modifications to achieve stability and druggability characteristics, molecular docking in terms of protein–ligand binding, including allosteric effects, protein–protein interactions and protein-centric drug discovery. To quantify the mechanisms underlying protein function, a holistic approach that takes structure, flexibility, stability, and dynamics into account is required, as these aspects become inseparable through their interdependence. Another key component of protein function is conformational dynamics, which often manifest as protein kinetics. Computational methods that use ML to generate representative conformational ensembles and quantify differences in conformational ensembles important for function are included in this review. Future opportunities are highlighted for each of these topics.

PLA-MoRe: A Protein-Ligand Binding Affinity Prediction Model via Comprehensive Molecular Representations

Accurately predicting the binding affinity of protein-ligand pairs is an essential part of drug discovery. Since wet laboratory experiments to determine the binding affinity are expensive and time-consuming, several computational methods for binding affinity prediction have been proposed. In the representation of compounds, most methods only focus on the structural properties such as SMILES and ignore the bioactive properties. In this study, we proposed a novel model named PLA-MoRe to predict protein-ligand binding affinity, which represents compounds based on both structural and bioactive properties and mainly contains three feature extractors. First, a structure feature extractor based on the graph isomorphism network was constructed to learn the representations of the molecular graphs. Second, we designed an Autoencoder-based bioactive feature extractor to integrate the multisource bioactive information including chemical, target, network, cellular, and clinical. The above two parts aimed to learn representations of compounds in terms of structures and bioactivities, respectively. Then, we constructed a sequence feature extractor to learn embeddings for protein sequences. The output of the three extractors was concatenated and fed into a fully connected network for affinity prediction. We compared PLA-MoRe with three state-of-the-art methods, and an ablation study was conducted to test the role of each part of the model. Further attention visualization showed that our model had the potential to locate the binding sites, which might help explain the mechanism of interaction. These results prove that PLA-MoRe is competitive and reliable. The resource codes are freely available at the GitHub repository https://github.com/QingyuLiaib/PLA-MoRe.

Structures of the SARS-CoV-2 spike glycoprotein and applications for novel drug development

COVID-19 caused by SARS-CoV-2 has raised a health crisis worldwide. The high morbidity and mortality associated with COVID-19 and the lack of effective drugs or vaccines for SARS-CoV-2 emphasize the urgent need for standard treatment and prophylaxis of COVID-19. The receptor-binding domain (RBD) of the glycosylated spike protein (S protein) is capable of binding to human angiotensin-converting enzyme 2 (hACE2) and initiating membrane fusion and virus entry. Hence, it is rational to inhibit the RBD activity of the S protein by blocking the RBD interaction with hACE2, which makes the glycosylated S protein a potential target for designing and developing antiviral agents. In this study, the molecular features of the S protein of SARS-CoV-2 are highlighted, such as the structures, functions, and interactions of the S protein and ACE2. Additionally, computational tools developed for the treatment of COVID-19 are provided, for example, algorithms, databases, and relevant programs. Finally, recent advances in the novel development of antivirals against the S protein are summarized, including screening of natural products, drug repurposing and rational design. This study is expected to provide novel insights for the efficient discovery of promising drug candidates against the S protein and contribute to the development of broad-spectrum anti-coronavirus drugs to fight against SARS-CoV-2.

A two-layer mono-objective algorithm based on guided optimization to reduce the computational cost in virtual screening

Virtual screening methods focus on searching molecules with similar properties to a given compound. Molecule databases are made up of large numbers of compounds and are constantly increasing. Therefore, fast and efficient methodologies and tools have to be designed to explore them quickly. In this context, ligand-based virtual screening methods are a well-known and helpful tool. These methods focus on searching for the most similar molecules in a database to a reference one. In this work, we propose a new tool called 2L-GO-Pharm, which requires less computational effort than OptiPharm, an efficient and robust piece of software recently proposed in the literature. The new-implemented tool maintains or improves the quality of the solutions found by OptiPharm, and achieves it by considerably reducing the number of evaluations needed. Some of the strengths that help 2L-GO-Pharm enhance searchability are the reduction of the search space dimension and the introduction of some circular limits for the angular variables. Furthermore, to ensure a trade-off between exploration and exploitation of the search space, it implements a two-layer strategy and a guided search procedure combined with a convergence test on the rotation axis. The performance of 2L-GO-Pharm has been tested by considering two different descriptors, i.e. shape similarity and electrostatic potential. The results show that it saves up to 87.5 million evaluations per query molecule.

Biomedical Data and Deep Learning Computational Models for Predicting Compound-Protein Relations

The identification of compound-protein relations (CPRs), which includes compound-protein interactions (CPIs) and compound-protein affinities (CPAs), is critical to drug development. A common method for compound-protein relation identification is the use of in vitro screening experiments. However, the number of compounds and proteins is massive, and in vitro screening experiments are labor-intensive, expensive, and time-consuming with high failure rates. Researchers have developed a computational field called virtual screening (VS) to aid experimental drug development. These methods utilize experimentally validated biological interaction information to generate datasets and use the physicochemical and structural properties of compounds and target proteins as input information to train computational prediction models. At present, deep learning has been widely used in computer vision and natural language processing and has experienced epoch-making progress. At the same time, deep learning has also been used in the field of biomedicine widely, and the prediction of CPRs based on deep learning has developed rapidly and has achieved good results. The purpose of this study is to investigate and discuss the latest applications of deep learning techniques in CPR prediction. First, we describe the datasets and feature engineering (i.e., compound and protein representations and descriptors) commonly used in CPR prediction methods. Then, we review and classify recent deep learning approaches in CPR prediction. Next, a comprehensive comparison is performed to demonstrate the prediction performance of representative methods on classical datasets. Finally, we discuss the current state of the field, including the existing challenges and our proposed future directions. We believe that this investigation will provide sufficient references and insight for researchers to understand and develop new deep learning methods to enhance CPR predictions.

Investigating SARS-CoV-2 Susceptibility in Animal Species: A Scoping Review

In the early stages of response to the SARS-CoV-2 pandemic, it was imperative for researchers to rapidly determine what animal species may be susceptible to the virus, under low knowledge and high uncertainty conditions. In this scoping review, the animal species being evaluated for SARS-CoV-2 susceptibility, the methods used to evaluate susceptibility, and comparing the evaluations between different studies were conducted. Using the PRISMA-ScR methodology, publications and reports from peer-reviewed and gray literature sources were collected from databases, Google Scholar, the World Organization for Animal Health (OIE), snowballing, and recommendations from experts. Inclusion and relevance criteria were applied, and information was subsequently extracted, categorized, summarized, and analyzed. Ninety seven sources (publications and reports) were identified which investigated 649 animal species from eight different classes: Mammalia, Aves, Actinopterygii, Reptilia, Amphibia, Insecta, Chondrichthyes, and Coelacanthimorpha. Sources used four different methods to evaluate susceptibility, in silico, in vitro, in vivo, and epidemiological analysis. Along with the different methods, how each source described "susceptibility" and evaluated the susceptibility of different animal species to SARS-CoV-2 varied, with conflicting susceptibility evaluations evident between different sources. Early in the pandemic, in silico methods were used the most to predict animal species susceptibility to SARS-CoV-2 and helped guide more costly and intensive studies using in vivo or epidemiological analyses. However, the limitations of all methods must be recognized, and evaluations made by in silico and in vitro should be re-evaluated when more information becomes available, such as demonstrated susceptibility through in vivo and epidemiological analysis.

Deep Learning and Structure-Based Virtual Screening for Drug Discovery against NEK7: A Novel Target for the Treatment of Cancer

NIMA-related kinase7 (NEK7) plays a multifunctional role in cell division and NLRP3 inflammasone activation. A typical expression or any mutation in the genetic makeup of NEK7 leads to the development of cancer malignancies and fatal inflammatory disease, i.e., breast cancer, non-small cell lung cancer, gout, rheumatoid arthritis, and liver cirrhosis. Therefore, NEK7 is a promising target for drug development against various cancer malignancies. The combination of drug repurposing and structure-based virtual screening of large libraries of compounds has dramatically improved the development of anticancer drugs. The current study focused on the virtual screening of 1200 benzene sulphonamide derivatives retrieved from the PubChem database by selecting and docking validation of the crystal structure of NEK7 protein (PDB ID: 2WQN). The compounds library was subjected to virtual screening using Auto Dock Vina. The binding energies of screened compounds were compared to standard Dabrafenib. In particular, compound 762 exhibited excellent binding energy of −42.67 kJ/mol, better than Dabrafenib (−33.89 kJ/mol). Selected drug candidates showed a reactive profile that was comparable to standard Dabrafenib. To characterize the stability of protein–ligand complexes, molecular dynamic simulations were performed, providing insight into the molecular interactions. The NEK7–Dabrafenib complex showed stability throughout the simulated trajectory. In addition, binding affinities, pIC50, and ADMET profiles of drug candidates were predicted using deep learning models. Deep learning models predicted the binding affinity of compound 762 best among all derivatives, which supports the findings of virtual screening. These findings suggest that top hits can serve as potential inhibitors of NEK7. Moreover, it is recommended to explore the inhibitory potential of identified hits compounds through in-vitro and in-vivo approaches.