A machine learning platform to estimate anti-SARS-CoV-2 activities

Integrated Transfer Learning and Multitask Learning Strategies to Construct Graph Neural Network Models for Predicting Bioaccumulation Parameters of Chemicals

Accurate prediction of parameters related to the environmental exposure of chemicals is crucial for the sound management of chemicals. However, the lack of large data sets for training models may result in poor prediction accuracy and robustness. Herein, integrated transfer learning (TL) and multitask learning (MTL) was proposed for constructing a graph neural network (GNN) model (abbreviated as TL-MTL-GNN model) using n-octanol/water partition coefficients as a source domain. The TL-MTL-GNN model was trained to predict three bioaccumulation parameters based on enlarged data sets that cover 2496 compounds with at least one bioaccumulation parameter. Results show that the TL-MTL-GNN model outperformed single-task GNN models with and without the TL, as well as conventional machine learning models trained with molecular descriptors or fingerprints. Applicability domains were characterized by a state-of-the-art structure-activity landscape-based (abbreviated as ADSAL) methodology. The TL-MTL-GNN model coupled with the optimal ADSAL was employed to predict bioaccumulation parameters for around 60,000 chemicals, with more than 13,000 compounds identified as bioaccumulative chemicals. The high predictive accuracy and robustness of the TL-MTL-GNN model demonstrate the feasibility of integrating the TL and MTL strategy in modeling small-sized data sets. The strategy holds significant potential for addressing small data challenges in modeling environmental chemicals.

Large-scale comparison of machine learning methods for profiling prediction of kinase inhibitors

Conventional machine learning (ML) and deep learning (DL) play a key role in the selectivity prediction of kinase inhibitors. A number of models based on available datasets can be used to predict the kinase profile of compounds, but there is still controversy about the advantages and disadvantages of ML and DL for such tasks. In this study, we constructed a comprehensive benchmark dataset of kinase inhibitors, involving in 141,086 unique compounds and 216,823 well-defined bioassay data points for 354 kinases. We then systematically compared the performance of 12 ML and DL methods on the kinase profiling prediction task. Extensive experimental results reveal that (1) Descriptor-based ML models generally slightly outperform fingerprint-based ML models in terms of predictive performance. RF as an ensemble learning approach displays the overall best predictive performance. (2) Single-task graph-based DL models are generally inferior to conventional descriptor- and fingerprint-based ML models, however, the corresponding multi-task models generally improves the average accuracy of kinase profile prediction. For example, the multi-task FP-GNN model outperforms the conventional descriptor- and fingerprint-based ML models with an average AUC of 0.807. (3) Fusion models based on voting and stacking methods can further improve the performance of the kinase profiling prediction task, specifically, RF::AtomPairs + FP2 + RDKitDes fusion model performs best with the highest average AUC value of 0.825 on the test sets. These findings provide useful information for guiding choices of the ML and DL methods for the kinase profiling prediction tasks. Finally, an online platform called KIPP ( https://kipp.idruglab.cn ) and python software are developed based on the best models to support the kinase profiling prediction, as well as various kinase inhibitor identification tasks including virtual screening, compound repositioning and target fishing.

Artificial Intelligence for Drug Discovery: Are We There Yet?

Drug discovery is adapting to novel technologies such as data science, informatics, and artificial intelligence (AI) to accelerate effective treatment development while reducing costs and animal experiments. AI is transforming drug discovery, as indicated by increasing interest from investors, industrial and academic scientists, and legislators. Successful drug discovery requires optimizing properties related to pharmacodynamics, pharmacokinetics, and clinical outcomes. This review discusses the use of AI in the three pillars of drug discovery: diseases, targets, and therapeutic modalities, with a focus on small-molecule drugs. AI technologies, such as generative chemistry, machine learning, and multiproperty optimization, have enabled several compounds to enter clinical trials. The scientific community must carefully vet known information to address the reproducibility crisis. The full potential of AI in drug discovery can only be realized with sufficient ground truth and appropriate human intervention at later pipeline stages.

Exploring DrugCentral: from molecular structures to clinical effects

DrugCentral, accessible at https://drugcentral.org , is an open-access online drug information repository. It covers over 4950 drugs, incorporating structural, physicochemical, and pharmacological details to support drug discovery, development, and repositioning. With around 20,000 bioactivity data points, manual curation enhances information from several major digital sources. Approximately 724 mechanism-of-action (MoA) targets offer updated drug target insights. The platform captures clinical data: over 14,300 on- and off-label uses, 27,000 contraindications, and around 340,000 adverse drug events from pharmacovigilance reports. DrugCentral encompasses information from molecular structures to marketed formulations, providing a comprehensive pharmaceutical reference. Users can easily navigate basic drug information and key features, making DrugCentral a versatile, unique resource. Furthermore, we present a use-case example where we utilize experimentally determined data from DrugCentral to support drug repurposing. A minimum activity threshold t should be considered against novel targets to repurpose a drug. Analyzing 1156 bioactivities for human MoA targets suggests a general threshold of 1 µM: t = 6 when expressed as - log[Activity(M)]). This applies to 87% of the drugs. Moreover, t can be refined empirically based on water solubility (S): t = 3 - logS, for logS < - 3. Alongside the drug repurposing classification scheme, which considers intellectual property rights, market exclusivity protections, and market accessibility, DrugCentral provides valuable data to prioritize candidates for drug repurposing programs efficiently.

Applying the digital data and the bioinformatics tools in SARS-CoV-2 research

Bioinformatics has been playing a crucial role in the scientific progress to fight against the pandemic of the coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The advances in novel algorithms, mega data technology, artificial intelligence and deep learning assisted the development of novel bioinformatics tools to analyze daily increasing SARS-CoV-2 data in the past years. These tools were applied in genomic analyses, evolutionary tracking, epidemiological analyses, protein structure interpretation, studies in virus-host interaction and clinical performance. To promote the in-silico analysis in the future, we conducted a review which summarized the databases, web services and software applied in SARS-CoV-2 research. Those digital resources applied in SARS-CoV-2 research may also potentially contribute to the research in other coronavirus and non-coronavirus viruses.

Discovering the Active Ingredients of Medicine and Food Homologous Substances for Inhibiting the Cyclooxygenase-2 Metabolic Pathway by Machine Learning Algorithms

Cyclooxygenase-2 (COX-2) and microsomal prostaglandin E2 synthase (mPGES-1) are two key targets in anti-inflammatory therapy. Medicine and food homology (MFH) substances have both edible and medicinal properties, providing a valuable resource for the development of novel, safe, and efficient COX-2 and mPGES-1 inhibitors. In this study, we collected active ingredients from 503 MFH substances and constructed the first comprehensive MFH database containing 27,319 molecules. Subsequently, we performed Murcko scaffold analysis and K-means clustering to deeply analyze the composition of the constructed database and evaluate its structural diversity. Furthermore, we employed four supervised machine learning algorithms, including support vector machine (SVM), random forest (RF), deep neural networks (DNNs), and eXtreme Gradient Boosting (XGBoost), as well as ensemble learning, to establish 640 classification models and 160 regression models for COX-2 and mPGES-1 inhibitors. Among them, ModelA_ensemble_RF_1 emerged as the optimal classification model for COX-2 inhibitors, achieving predicted Matthews correlation coefficient (MCC) values of 0.802 and 0.603 on the test set and external validation set, respectively. ModelC_RDKIT_SVM_2 was identified as the best regression model based on COX-2 inhibitors, with root mean squared error (RMSE) values of 0.419 and 0.513 on the test set and external validation set, respectively. ModelD_ECFP_SVM_4 stood out as the top classification model for mPGES-1 inhibitors, attaining MCC values of 0.832 and 0.584 on the test set and external validation set, respectively. The optimal regression model for mPGES-1 inhibitors, ModelF_3D_SVM_1, exhibited predictive RMSE values of 0.253 and 0.35 on the test set and external validation set, respectively. Finally, we proposed a ligand-based cascade virtual screening strategy, which integrated the well-performing supervised machine learning models with unsupervised learning: the self-organized map (SOM) and molecular scaffold analysis. Using this virtual screening workflow, we discovered 10 potential COX-2 inhibitors and 15 potential mPGES-1 inhibitors from the MFH database. We further verified candidates by molecular docking, investigated the interaction of the candidate molecules upon binding to COX-2 or mPGES-1. The constructed comprehensive MFH database has laid a solid foundation for the further research and utilization of the MFH substances. The series of well-performing machine learning models can be employed to predict the COX-2 and mPGES-1 inhibitory capabilities of unknown compounds, thereby aiding in the discovery of anti-inflammatory medications. The COX-2 and mPGES-1 potential inhibitor molecules identified through the cascade virtual screening approach provide insights and references for the design of highly effective and safe novel anti-inflammatory drugs.

Quantum chemical studies on the binding domain of SARS-CoV-2 S-protein: human ACE2 interface complex

A two-layer ONIOM(B3LYP/6-31G*:PM7) method is used to model the binding of several drug/drug-like molecules (L) at the SARS-CoV-2 S-protein: human ACE2 protein interface cavity. The selected molecules include a set of thirty-five ligands from the study of Smith and Smith which showed a high docking score in the range of -7.0 to -7.7 kcal/mol and another set of seven repurposing drugs, viz. favipiravir, remdesivir, EIDD, galidesivir, triazavirin, ruxolitinib, and baricitinib. The ONIOM model of the cavity (M) showed a highly polarized electron distribution along its top-to-bottom direction while Ls with lengths in the range 1.0 - 1.5 nm fitted well inside the cavity in a head-to-tail fashion to yield ML complexes. The ligands showed a large variation in the ONIOM-level binding energy (Eb), in the range -2.7 to -85.4 kcal/mol. The Eb of ML complexes better than -40.0 kcal/mol is observed for myricetin, fidarestat, protirelin, m-digallic acid, glucogallin, benserazide hydrochlorideseradie, remdesivir, tazobactum, sapropterin, nitrofurantoin, quinonoid, pyruvic acid calcium isoniazid, and aspartame, and among them the highest Eb -85.4 kcal/mol is observed for myricetin. A hydroxy substitution is suggested for the phenyl ring of aspartame to improve its binding behavior at the cavity, and the resulting ligand 43 showed the best Eb -84.5 kcal/mol. The ONIOM-level study is found to be effective for the interpretation of the noncovalent interactions resulting from residues such as arginine, histidine, tyrosine, lysine, carboxylate, and amide moieties in the active site and suggests rational design strategies for COVID-19 drug development.Communicated by Ramaswamy H. Sarma.

Bird's Eye View feature selection for high-dimensional data

In machine learning, an informative dataset is crucial for accurate predictions. However, high dimensional data often contains irrelevant features, outliers, and noise, which can negatively impact model performance and consume computational resources. To tackle this challenge, the Bird's Eye View (BEV) feature selection technique is introduced. This approach is inspired by the natural world, where a bird searches for important features in a sparse dataset, similar to how a bird search for sustenance in a sprawling jungle. BEV incorporates elements of Evolutionary Algorithms with a Genetic Algorithm to maintain a population of top-performing agents, Dynamic Markov Chain to steer the movement of agents in the search space, and Reinforcement Learning to reward and penalize agents based on their progress. The proposed strategy in this paper leads to improved classification performance and a reduced number of features compared to conventional methods, as demonstrated by outperforming state-of-the-art feature selection techniques across multiple benchmark datasets.

Evaluation of Mutual Information and Feature Selection for SARS-CoV-2 Respiratory Infection

This study aims to develop a predictive model for SARS-CoV-2 using machine-learning techniques and to explore various feature selection methods to enhance the accuracy of predictions. A precise forecast of the SARS-CoV-2 respiratory infections spread can help with efficient planning and resource allocation. The proposed model utilizes stochastic regression to capture the virus transmission's stochastic nature, considering data uncertainties. Feature selection techniques are employed to identify the most relevant and informative features contributing to prediction accuracy. Furthermore, the study explores the use of neighbor embedding and Sammon mapping algorithms to visualize high-dimensional SARS-CoV-2 respiratory infection data in a lower-dimensional space, enabling better interpretation and understanding of the underlying patterns. The application of machine-learning techniques for predicting SARS-CoV-2 respiratory infections, the use of statistical measures in healthcare, including confirmed cases, deaths, and recoveries, and an analysis of country-wise dynamics of the pandemic using machine-learning models are used. Our analysis involves the performance of various algorithms, including neural networks (NN), decision trees (DT), random forests (RF), the Adam optimizer (AD), hyperparameters (HP), stochastic regression (SR), neighbor embedding (NE), and Sammon mapping (SM). A pre-processed and feature-extracted SARS-CoV-2 respiratory infection dataset is combined with ADHPSRNESM to form a new orchestration in the proposed model for a perfect prediction to increase the precision of accuracy. The findings of this research can contribute to public health efforts by enabling policymakers and healthcare professionals to make informed decisions based on accurate predictions, ultimately aiding in managing and controlling the SARS-CoV-2 pandemic.

Interactome-Based Machine Learning Predicts Potential Therapeutics for COVID-19

COVID-19, the disease caused by SARS-CoV-2, has been disrupting our lives for more than two years now. SARS-CoV-2 interacts with human proteins to pave its way into the human body, thereby wreaking havoc. Moreover, the mutating variants of the virus that take place in the SARS-CoV-2 genome are also a cause of concern among the masses. Thus, it is very important to understand human-spike protein-protein interactions (PPIs) in order to predict new PPIs and consequently propose drugs for the human proteins in order to fight the virus and its different mutated variants, with the mutations occurring in the spike protein. This fact motivated us to develop a complete pipeline where PPIs and drug-protein interactions can be predicted for human-SARS-CoV-2 interactions. In this regard, initially interacting data sets are collected from the literature, and noninteracting data sets are subsequently created for human-SARS-CoV-2 by considering only spike glycoprotein. On the other hand, for drug-protein interactions both interacting and noninteracting data sets are considered from DrugBank and ChEMBL databases. Thereafter, a model based on a sequence-based feature is used to code the protein sequences of human and spike proteins using the well-known Moran autocorrelation technique, while the drugs are coded using another well-known technique, viz., PaDEL descriptors, to predict new human-spike PPIs and eventually new drug-protein interactions for the top 20 predicted human proteins interacting with the original spike protein and its different mutated variants like Alpha, Beta, Delta, Gamma, and Omicron. Such predictions are carried out by random forest as it is found to perform better than other predictors, providing an accuracy of 90.53% for human-spike PPI and 96.15% for drug-protein interactions. Finally, 40 unique drugs like eicosapentaenoic acid, doxercalciferol, ciclesonide, dexamethasone, methylprednisolone, etc. are identified that target 32 human proteins like ACACA, DST, DYNC1H1, etc.

Surely you are joking, Mr Docking!

In the wake of recent COVID-19 pandemics scientists around the world rushed to deliver numerous CADD (Computer-Aided Drug Discovery) methods and tools that could be reliably used to discover novel drug candidates against the SARS-CoV-2 virus. With that, there emerged a trend of a significant democratization of CADD that contributed to the rapid development of various COVID-19 drug candidates currently undergoing different stages of validation. On the other hand, this democratization also inadvertently led to the surge rapidly performed molecular docking studies to nominate multiple scores of novel drug candidates supported by computational arguments only. Albeit driven by best intentions, most of such studies also did not follow best practices in the field that require experience and expertise learned through multiple rigorously designed benchmarking studies and rigorous experimental validation. In this Viewpoint we reflect on recent disbalance between small number of rigorous and comprehensive studies and the proliferation of purely computational studies enabled by the ease of docking software availability. We further elaborate on the hyped oversale of CADD methods' ability to rapidly yield viable drug candidates and reiterate the critical importance of rigor and adherence to the best practices of CADD in view of recent emergence of AI and Big Data in the field.

Plant Extracts and SARS-CoV-2: Research and Applications

The recent pandemic of COVID-19 caused by the SARS-CoV-2 virus has brought upon the world an unprecedented challenge. During its acute dissemination, a rush for vaccines started, making the scientific community come together and contribute to the development of efficient therapeutic agents and vaccines. Natural products have been used as sources of individual molecules and extracts capable of inhibiting/neutralizing several microorganisms, including viruses. Natural extracts have shown effective results against the coronavirus family, when first tested in the outbreak of SARS-CoV-1, back in 2002. In this review, the relationship between natural extracts and SARS-CoV is discussed, while also providing insight into misinformation regarding the use of plants as possible therapeutic agents. Studies with plant extracts on coronaviruses are presented, as well as the main inhibition assays and trends for the future regarding the yet unknown long-lasting effects post-infection with SARS-CoV-2.

High-Throughput Screening for the Potential Inhibitors of SARS-CoV-2 with Essential Dynamic Behavior

Global health security has been challenged by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) pandemic. Due to the lengthy process of generating vaccinations, it is vital to reposition currently available drugs in order to relieve anti-epidemic tensions and accelerate the development of therapies for Coronavirus Disease 2019 (COVID-19), the public threat caused by SARS-CoV-2. High throughput screening techniques have established their roles in the evaluation of already available medications and the search for novel potential agents with desirable chemical space and more cost-effectiveness. Here, we present the architectural aspects of highthroughput screening for SARS-CoV-2 inhibitors, especially three generations of virtual screening methodologies with structural dynamics: ligand-based screening, receptor-based screening, and machine learning (ML)-based scoring functions (SFs). By outlining the benefits and drawbacks, we hope that researchers will be motivated to adopt these methods in the development of novel anti- SARS-CoV-2 agents.

Supervised Machine Learning Models to Identify Early-Stage Symptoms of SARS-CoV-2

The coronavirus disease (COVID-19) pandemic was caused by the SARS-CoV-2 virus and began in December 2019. The virus was first reported in the Wuhan region of China. It is a new strain of coronavirus that until then had not been isolated in humans. In severe cases, pneumonia, acute respiratory distress syndrome, multiple organ failure or even death may occur. Now, the existence of vaccines, antiviral drugs and the appropriate treatment are allies in the confrontation of the disease. In the present research work, we utilized supervised Machine Learning (ML) models to determine early-stage symptoms of SARS-CoV-2 occurrence. For this purpose, we experimented with several ML models, and the results showed that the ensemble model, namely Stacking, outperformed the others, achieving an Accuracy, Precision, Recall and F-Measure equal to 90.9% and an Area Under Curve (AUC) of 96.4%.

Prediction of Recurrent Mutations in SARS-CoV-2 Using Artificial Neural Networks

Predicting SARS-CoV-2 mutations is difficult, but predicting recurrent mutations driven by the host, such as those caused by host deaminases, is feasible. We used machine learning to predict which positions from the SARS-CoV-2 genome will hold a recurrent mutation and which mutations will be the most recurrent. We used data from April 2021 that we separated into three sets: a training set, a validation set, and an independent test set. For the test set, we obtained a specificity value of 0.69, a sensitivity value of 0.79, and an Area Under the Curve (AUC) of 0.8, showing that the prediction of recurrent SARS-CoV-2 mutations is feasible. Subsequently, we compared our predictions with updated data from January 2022, showing that some of the false positives in our prediction model become true positives later on. The most important variables detected by the model's Shapley Additive exPlanation (SHAP) are the nucleotide that mutates and RNA reactivity. This is consistent with the SARS-CoV-2 mutational bias pattern and the preference of some host deaminases for specific sequences and RNA secondary structures. We extend our investigation by analyzing the mutations from the variants of concern Alpha, Beta, Delta, Gamma, and Omicron. Finally, we analyzed amino acid changes by looking at the predicted recurrent mutations in the M-pro and spike proteins.

Antiviral Potential of Plants against COVID-19 during Outbreaks-An Update

Several human diseases are caused by viruses, including cancer, Type I diabetes, Alzheimer's disease, and hepatocellular carcinoma. In the past, people have suffered greatly from viral diseases such as polio, mumps, measles, dengue fever, SARS, MERS, AIDS, chikungunya fever, encephalitis, and influenza. Recently, COVID-19 has become a pandemic in most parts of the world. Although vaccines are available to fight the infection, their safety and clinical trial data are still questionable. Social distancing, isolation, the use of sanitizer, and personal productive strategies have been implemented to prevent the spread of the virus. Moreover, the search for a potential therapeutic molecule is ongoing. Based on experiences with outbreaks of SARS and MERS, many research studies reveal the potential of medicinal herbs/plants or chemical compounds extracted from them to counteract the effects of these viral diseases. COVID-19's current status includes a decrease in infection rates as a result of large-scale vaccination program implementation by several countries. But it is still very close and needs to boost people's natural immunity in a cost-effective way through phytomedicines because many underdeveloped countries do not have their own vaccination facilities. In this article, phytomedicines as plant parts or plant-derived metabolites that can affect the entry of a virus or its infectiousness inside hosts are described. Finally, it is concluded that the therapeutic potential of medicinal plants must be analyzed and evaluated entirely in the control of COVID-19 in cases of uncontrollable SARS infection.

Transcriptomics and RNA-Based Therapeutics as Potential Approaches to Manage SARS-CoV-2 Infection

SARS-CoV-2 is a coronavirus family member that appeared in China in December 2019 and caused the disease called COVID-19, which was declared a pandemic in 2020 by the World Health Organization. In recent months, great efforts have been made in the field of basic and clinical research to understand the biology and infection processes of SARS-CoV-2. In particular, transcriptome analysis has contributed to generating new knowledge of the viral sequences and intracellular signaling pathways that regulate the infection and pathogenesis of SARS-CoV-2, generating new information about its biology. Furthermore, transcriptomics approaches including spatial transcriptomics, single-cell transcriptomics and direct RNA sequencing have been used for clinical applications in monitoring, detection, diagnosis, and treatment to generate new clinical predictive models for SARS-CoV-2. Consequently, RNA-based therapeutics and their relationship with SARS-CoV-2 have emerged as promising strategies to battle the SARS-CoV-2 pandemic with the assistance of novel approaches such as CRISPR-CAS, ASOs, and siRNA systems. Lastly, we discuss the importance of precision public health in the management of patients infected with SARS-CoV-2 and establish that the fusion of transcriptomics, RNA-based therapeutics, and precision public health will allow a linkage for developing health systems that facilitate the acquisition of relevant clinical strategies for rapid decision making to assist in the management and treatment of the SARS-CoV-2-infected population to combat this global public health problem.

New Halogenated Compounds from Halimeda macroloba Seaweed with Potential Inhibitory Activity against Malaria

Malaria is one of the most important infectious diseases worldwide. The causative of the most severe forms of malaria, Plasmodium falciparum, has developed resistances against all the available antimalarial drugs. In the present study, the phytochemical investigation of the green seaweed Halimeda macroloba has afforded two new compounds 1–2, along with 4 known ones 3–6. The structures of the compounds had been confirmed using 1& 2D-NMR and HRESIMS analyses. Extensive machine-learning-supported virtual-screening suggested cytochrome-C enzyme as a potential target for compound 2. Docking, absolute-binding-free-energy (ΔG_binding) and molecular-dynamics-simulation (MDS) of compound 2 revealed the strong binding interaction of this compound with cytochrome-C. In vitro testing for crude extract and isolated compounds revealed the potential in vitro inhibitory activity of both extract and compound 2 against P. falciparum. The crude extract was able to inhibit the parasite growth with an IC₅₀ value of 1.8 ± 0.35 µg/mL. Compound 2 also showed good inhibitory activity with an IC₅₀ value of 3.2 ± 0.23 µg/mL. Meanwhile, compound 6 showed moderate inhibitory activity with an IC₅₀ value of 19.3 ± 0.51 µg/mL. Accordingly, the scaffold of compound 2 can be considered as a good lead compound for the future development of new antimalarial agents.

MolSearch

Leveraging computational methods to generate small molecules with desired properties has been an active research area in the drug discovery field. Towards real-world applications, however, efficient generation of molecules that satisfy multiple property requirements simultaneously remains a key challenge. In this paper, we tackle this challenge using a search-based approach and propose a simple yet effective framework called MolSearch for multi-objective molecular generation (optimization). We show that given proper design and sufficient information, search-based methods can achieve performance comparable or even better than deep learning methods while being computationally efficient. Such efficiency enables massive exploration of chemical space given constrained computational resources. In particular, MolSearch starts with existing molecules and uses a two-stage search strategy to gradually modify them into new ones, based on transformation rules derived systematically and exhaustively from large compound libraries. We evaluate MolSearch in multiple benchmark generation settings and demonstrate its effectiveness and efficiency.

Methodology-Centered Review of Molecular Modeling, Simulation, and Prediction of SARS-CoV-2

Despite tremendous efforts in the past two years, our understanding of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), virus-host interactions, immune response, virulence, transmission, and evolution is still very limited. This limitation calls for further in-depth investigation. Computational studies have become an indispensable component in combating coronavirus disease 2019 (COVID-19) due to their low cost, their efficiency, and the fact that they are free from safety and ethical constraints. Additionally, the mechanism that governs the global evolution and transmission of SARS-CoV-2 cannot be revealed from individual experiments and was discovered by integrating genotyping of massive viral sequences, biophysical modeling of protein-protein interactions, deep mutational data, deep learning, and advanced mathematics. There exists a tsunami of literature on the molecular modeling, simulations, and predictions of SARS-CoV-2 and related developments of drugs, vaccines, antibodies, and diagnostics. To provide readers with a quick update about this literature, we present a comprehensive and systematic methodology-centered review. Aspects such as molecular biophysics, bioinformatics, cheminformatics, machine learning, and mathematics are discussed. This review will be beneficial to researchers who are looking for ways to contribute to SARS-CoV-2 studies and those who are interested in the status of the field.

D3AI-CoV: a deep learning platform for predicting drug targets and for virtual screening against COVID-19

Target prediction and virtual screening are two powerful tools of computer-aided drug design. Target identification is of great significance for hit discovery, lead optimization, drug repurposing and elucidation of the mechanism. Virtual screening can improve the hit rate of drug screening to shorten the cycle of drug discovery and development. Therefore, target prediction and virtual screening are of great importance for developing highly effective drugs against COVID-19. Here we present D3AI-CoV, a platform for target prediction and virtual screening for the discovery of anti-COVID-19 drugs. The platform is composed of three newly developed deep learning-based models i.e., MultiDTI, MPNNs-CNN and MPNNs-CNN-R models. To compare the predictive performance of D3AI-CoV with other methods, an external test set, named Test-78, was prepared, which consists of 39 newly published independent active compounds and 39 inactive compounds from DrugBank. For target prediction, the areas under the receiver operating characteristic curves (AUCs) of MultiDTI and MPNNs-CNN models are 0.93 and 0.91, respectively, whereas the AUCs of the other reported approaches range from 0.51 to 0.74. For virtual screening, the hit rate of D3AI-CoV is also better than other methods. D3AI-CoV is available for free as a web application at http://www.d3pharma.com/D3Targets-2019-nCoV/D3AI-CoV/index.php, which can serve as a rapid online tool for predicting potential targets for active compounds and for identifying active molecules against a specific target protein for COVID-19 treatment.

Efficient Identification of Anti-SARS-CoV-2 Compounds Using Chemical Structure- and Biological Activity-Based Modeling

Identification of anti-SARS-CoV-2 compounds through traditional high-throughput screening (HTS) assays is limited by high costs and low hit rates. To address these challenges, we developed machine learning models to identify compounds acting via inhibition of the entry of SARS-CoV-2 into human host cells or the SARS-CoV-2 3-chymotrypsin-like (3CL) protease. The optimal classification models achieved good performance with area under the receiver operating characteristic curve (AUC-ROC) values of >0.78. Experimental validation showed that the best performing models increased the assay hit rate by 2.1-fold for viral entry inhibitors and 10.4-fold for 3CL protease inhibitors compared to those of the original drug repurposing screens. Twenty-two compounds showed potent (<5 μM) antiviral activities in a SARS-CoV-2 live virus assay. In conclusion, machine learning models can be developed and used as a complementary approach to HTS to expand compound screening capacities and improve the speed and efficiency of anti-SARS-CoV-2 drug discovery.

ELECTRA-DTA: a new compound-protein binding affinity prediction model based on the contextualized sequence encoding

Motivation

Drug-target binding affinity (DTA) reflects the strength of the drug-target interaction; therefore, predicting the DTA can considerably benefit drug discovery by narrowing the search space and pruning drug-target (DT) pairs with low binding affinity scores. Representation learning using deep neural networks has achieved promising performance compared with traditional machine learning methods; hence, extensive research efforts have been made in learning the feature representation of proteins and compounds. However, such feature representation learning relies on a large-scale labelled dataset, which is not always available.

Results

We present an end-to-end deep learning framework, ELECTRA-DTA, to predict the binding affinity of drug-target pairs. This framework incorporates an unsupervised learning mechanism to train two ELECTRA-based contextual embedding models, one for protein amino acids and the other for compound SMILES string encoding. In addition, ELECTRA-DTA leverages a squeeze-and-excitation (SE) convolutional neural network block stacked over three fully connected layers to further capture the sequential and spatial features of the protein sequence and SMILES for the DTA regression task. Experimental evaluations show that ELECTRA-DTA outperforms various state-of-the-art DTA prediction models, especially with the challenging, interaction-sparse BindingDB dataset. In target selection and drug repurposing for COVID-19, ELECTRA-DTA also offers competitive performance, suggesting its potential in speeding drug discovery and generalizability for other compound- or protein-related computational tasks.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13321-022-00591-x.

The Petasites hybridus CO2 Extract (Ze 339) Blocks SARS-CoV-2 Replication In Vitro

The coronavirus disease 2019 (COVID-19), caused by a novel coronavirus (SARS-CoV-2), has spread worldwide, affecting over 250 million people and resulting in over five million deaths. Antivirals that are effective are still limited. The antiviral activities of the Petasites hybdridus CO₂ extract Ze 339 were previously reported. Thus, to assess the anti-SARS-CoV-2 activity of Ze 339 as well as isopetasin and neopetasin as major active compounds, a CPE and plaque reduction assay in Vero E6 cells was used for viral output. Antiviral effects were tested using the original virus (Wuhan) and the Delta variant of SARS-CoV-2. The antiviral drug remdesivir was used as control. Pre-treatment with Ze 339 in SARS-CoV-2-infected Vero E6 cells with either virus variant significantly inhibited virus replication with IC₅₀ values of 0.10 and 0.40 μg/mL, respectively. The IC₅₀ values obtained for isopetasin ranged between 0.37 and 0.88 μM for both virus variants, and that of remdesivir ranged between 1.53 and 2.37 μM. In conclusion, Ze 339 as well as the petasins potently inhibited SARS-CoV-2 replication in vitro of the Wuhan and Delta variants. Since time is of essence in finding effective treatments, clinical studies will have to demonstrate if Ze339 can become a therapeutic option to treat SARS-CoV-2 infections.

Machine Learning Enables Accurate and Rapid Prediction of Active Molecules Against Breast Cancer Cells

Breast cancer (BC) has surpassed lung cancer as the most frequently occurring cancer, and it is the leading cause of cancer-related death in women. Therefore, there is an urgent need to discover or design new drug candidates for BC treatment. In this study, we first collected a series of structurally diverse datasets consisting of 33,757 active and 21,152 inactive compounds for 13 breast cancer cell lines and one normal breast cell line commonly used in in vitro antiproliferative assays. Predictive models were then developed using five conventional machine learning algorithms, including naïve Bayesian, support vector machine, k-Nearest Neighbors, random forest, and extreme gradient boosting, as well as five deep learning algorithms, including deep neural networks, graph convolutional networks, graph attention network, message passing neural networks, and Attentive FP. A total of 476 single models and 112 fusion models were constructed based on three types of molecular representations including molecular descriptors, fingerprints, and graphs. The evaluation results demonstrate that the best model for each BC cell subtype can achieve high predictive accuracy for the test sets with AUC values of 0.689–0.993. Moreover, important structural fragments related to BC cell inhibition were identified and interpreted. To facilitate the use of the model, an online webserver called ChemBC (http://chembc.idruglab.cn/) and its local version software (https://github.com/idruglab/ChemBC) were developed to predict whether compounds have potential inhibitory activity against BC cells.

Getting Started with the IDG KMC Datasets and Tools

The Illuminating the Druggable Genome (IDG) consortium is a National Institutes of Health (NIH) Common Fund program designed to enhance our knowledge of under-studied proteins, more specifically, proteins unannotated within the three most commonly drug-targeted protein families: G-protein coupled receptors, ion channels, and protein kinases. Since 2014, the IDG Knowledge Management Center (IDG-KMC) has generated several open-access datasets and resources that jointly serve as a highly translational machine-learning-ready knowledgebase focused on human protein-coding genes and their products. The goal of the IDG-KMC is to develop comprehensive integrated knowledge for the druggable genome to illuminate the uncharacterized or poorly annotated portion of the druggable genome. The tools derived from the IDG-KMC provide either user-friendly visualizations or ways to impute the knowledge about potential targets using machine learning strategies. In the following protocols, we describe how to use each web-based tool to accelerate illumination in under-studied proteins. © 2022 The Authors. Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: Interacting with the Pharos user interface Basic Protocol 2: Accessing the data in Harmonizome Basic Protocol 3: The ARCHS4 resource Basic Protocol 4: Making predictions about gene function with PrismExp Basic Protocol 5: Using Geneshot to illuminate knowledge about under-studied targets Basic Protocol 6: Exploring under-studied targets with TIN-X Basic Protocol 7: Interacting with the DrugCentral user interface Basic Protocol 8: Estimating Anti-SARS-CoV-2 activities with DrugCentral REDIAL-2020 Basic Protocol 9: Drug Set Enrichment Analysis using Drugmonizome Basic Protocol 10: The Drugmonizome-ML Appyter Basic Protocol 11: The Harmonizome-ML Appyter Basic Protocol 12: GWAS target illumination with TIGA Basic Protocol 13: Prioritizing kinases for lists of proteins and phosphoproteins with KEA3 Basic Protocol 14: Converting PubMed searches to drug sets with the DrugShot Appyter.

Application of Artificial Intelligence in COVID-19 Diagnosis and Therapeutics

The coronavirus disease 2019 (COVID-19) pandemic began at the end of December 2019, giving rise to a high rate of infections and causing COVID-19-associated deaths worldwide. It was first reported in Wuhan, China, and since then, not only global leaders, organizations, and pharmaceutical/biotech companies, but also researchers, have directed their efforts toward overcoming this threat. The use of artificial intelligence (AI) has recently surged internationally and has been applied to diverse aspects of many problems. The benefits of using AI are now widely accepted, and many studies have shown great success in medical research on tasks, such as the classification, detection, and prediction of disease, or even patient outcome. In fact, AI technology has been actively employed in various ways in COVID-19 research, and several clinical applications of AI-equipped medical devices for the diagnosis of COVID-19 have already been reported. Hence, in this review, we summarize the latest studies that focus on medical imaging analysis, drug discovery, and therapeutics such as vaccine development and public health decision-making using AI. This survey clarifies the advantages of using AI in the fight against COVID-19 and provides future directions for tackling the COVID-19 pandemic using AI techniques.

Comprehensive Consensus Analysis of SARS-CoV-2 Drug Repurposing Campaigns

The current COVID-19 pandemic has elicited extensive repurposing efforts (both small and large scale) to rapidly identify COVID-19 treatments among approved drugs. Herein, we provide a literature review of large-scale SARS-CoV-2 antiviral drug repurposing efforts and highlight a marked lack of consistent potency reporting. This variability indicates the importance of standardizing best practices-including the use of relevant cell lines, viral isolates, and validated screening protocols. We further surveyed available biochemical and virtual screening studies against SARS-CoV-2 targets (Spike, ACE2, RdRp, PLpro, and Mpro) and discuss repurposing candidates exhibiting consistent activity across diverse, triaging assays and predictive models. Moreover, we examine repurposed drugs and their efficacy against COVID-19 and the outcomes of representative repurposed drugs in clinical trials. Finally, we propose a drug repurposing pipeline to encourage the implementation of standard methods to fast-track the discovery of candidates and to ensure reproducible results.

A critical overview of computational approaches employed for COVID-19 drug discovery

COVID-19 has resulted in huge numbers of infections and deaths worldwide and brought the most severe disruptions to societies and economies since the Great Depression. Massive experimental and computational research effort to understand and characterize the disease and rapidly develop diagnostics, vaccines, and drugs has emerged in response to this devastating pandemic and more than 130 000 COVID-19-related research papers have been published in peer-reviewed journals or deposited in preprint servers. Much of the research effort has focused on the discovery of novel drug candidates or repurposing of existing drugs against COVID-19, and many such projects have been either exclusively computational or computer-aided experimental studies. Herein, we provide an expert overview of the key computational methods and their applications for the discovery of COVID-19 small-molecule therapeutics that have been reported in the research literature. We further outline that, after the first year the COVID-19 pandemic, it appears that drug repurposing has not produced rapid and global solutions. However, several known drugs have been used in the clinic to cure COVID-19 patients, and a few repurposed drugs continue to be considered in clinical trials, along with several novel clinical candidates. We posit that truly impactful computational tools must deliver actionable, experimentally testable hypotheses enabling the discovery of novel drugs and drug combinations, and that open science and rapid sharing of research results are critical to accelerate the development of novel, much needed therapeutics for COVID-19.

Disrupting 3D printing of medicines with machine learning

3D printing (3DP) is a progressive technology capable of transforming pharmaceutical development. However, despite its promising advantages, its transition into clinical settings remains slow. To make the vital leap to mainstream clinical practice and improve patient care, 3DP must harness modern technologies. Machine learning (ML), an influential branch of artificial intelligence, may be a key partner for 3DP. Together, 3DP and ML can utilise intelligence based on human learning to accelerate drug product development, ensure stringent quality control (QC), and inspire innovative dosage-form design. With ML's capabilities, streamlined 3DP drug delivery could mark the next era of personalised medicine. This review details how ML can be applied to elevate the 3DP of pharmaceuticals and importantly, how it can expedite 3DP's integration into mainstream healthcare.

Machine learning-based prediction of survival prognosis in cervical cancer

BACKGROUND

Accurately forecasting the prognosis could improve cervical cancer management, however, the currently used clinical features are difficult to provide enough information. The aim of this study is to improve forecasting capability by developing a miRNAs-based machine learning survival prediction model.

RESULTS

The expression characteristics of miRNAs were chosen as features for model development. The cervical cancer miRNA expression data was obtained from The Cancer Genome Atlas database. Preprocessing, including unquantified data removal, missing value imputation, samples normalization, log transformation, and feature scaling, was performed. In total, 42 survival-related miRNAs were identified by Cox Proportional-Hazards analysis. The patients were optimally clustered into four groups with three different 5-years survival outcome (≥ 90%, ≈ 65%, ≤ 40%) by K-means clustering algorithm base on top 10 survival-related miRNAs. According to the K-means clustering result, a prediction model with high performance was established. The pathways analysis indicated that the miRNAs used play roles involved in the regulation of cancer stem cells.

CONCLUSION

A miRNAs-based machine learning cervical cancer survival prediction model was developed that robustly stratifies cervical cancer patients into high survival rate (5-years survival rate ≥ 90%), moderate survival rate (5-years survival rate ≈ 65%), and low survival rate (5-years survival rate ≤ 40%).