Graph Neural Network Models for Chemical Compound Activeness Prediction For COVID-19 Drugs Discovery using Lipinski's Descriptors

In this study, we implemented graph neural network (GNN) methods to forecast in vitro inhibitory bioactivity or pharmacological concentration of chemical compounds against severe acute respiratory syndrome (SARS) coronaviruses from the graph representation amongst the compounds (i.e., nodes) and their respective features(i.e., node features) obtained by RDKit tool from their respectively SMILES (Simplified MolecularInput Line-Entry System), and we compared GNN models by experiments with our graph data of 375 nodes with 44,475 edges or links. This was done in response to the severe and significant consequences of the ongoing Coronavirus disease 2019 (COVID-19) disease. As a result, we discovered that implemented models, simple graph convolution (SGC), and graph convolution network (GCN) performed significantly well with comparable performance. © 2022 IEEE.

MOLECULES GENERATION TO INHIBIT COVID-19 DISEASE USING ENCODER-DECODER LSTM ARCHITECTURE AND PCA PROPERTIES

COVID-19 has become the world's worst pandemic and has claimed over six million lives as of March 2022. The virus is now in alongside cancer as one of the most common causes of death. Likewise, there is no definitive or unique treatment for COVID-19 outside of a selected few drugs approved by the Food and Drug Administration (FDA). While Artificial Intelligence (AI) can be used to generate molecules that target Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), the virus responsible for COVID-19, such molecules are novel and do not yet exist in the market. With the emergence and availability of several drug datasets related to COVID-19 (tests, images, graphs, and ChEMBLs), recent works based on Deep Learning (DL) techniques have been employed to generate molecules and check the effectiveness of existing molecules on COVID-19. In our study, we investigated the benefits of an Encoder–Decoder (ED) architecture based on Long Short-Term Memory (LSTM) cells. As a result, the molecules were converted into a vector during the encoding phase, which was then decoded back into SMILES molecules strings. We propose an approach to incorporate four features of Principal Components Analysis (PCA) with Encoder–Decoder Long Short-Term Memory (ED-LSTM) for regularization, which means that, instead of avoiding linear mapping, we assumed that the data could be linearly separable. We concluded that ED-LSTM with unit norm constraint has the best reconstruction accuracy in the context of generating molecules. The resulting dataset was used with the aid of virtual screening and convolutional neural networks to check the drugs that have the best binding affinity with SARS-CoV-2. We achieved an accuracy of 87.35% on the test set. [ FROM AUTHOR] Copyright of Journal of Mechanics in Medicine & Biology is the property of World Scientific Publishing Company and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Repurposing of drugs for combined treatment of COVID-19 cytokine storm using machine learning.

Severe acute respiratory syndrome coronavirus 2 (SARS­CoV­2) induced cytokine storm is the major cause of COVID­19 related deaths. Patients have been treated with drugs that work by inhibiting a specific protein partly responsible for the cytokines production. This approach provided very limited success, since there are multiple proteins involved in the complex cell signaling disease mechanisms. We targeted five proteins: Angiotensin II receptor type 1 (AT1R), A disintegrin and metalloprotease 17 (ADAM17), Nuclear Factor­Kappa B (NF­κB), Janus kinase 1 (JAK1) and Signal Transducer and Activator of Transcription 3 (STAT3), which are involved in the SARS­CoV­2 induced cytokine storm pathway. We developed machine learning (ML) models for these five proteins, using known active inhibitors. After developing the model for each of these proteins, FDA-approved drugs were screened to find novel therapeutics for COVID­19. We identified twenty drugs that are active for four proteins with predicted scores greater than 0.8 and eight drugs active for all five proteins with predicted scores over 0.85. Mitomycin C is the most active drug across all five proteins with an average prediction score of 0.886. For further validation of these results, we used the PyRx software to conduct protein-ligand docking experiments and calculated the binding affinity. The docking results support findings by the ML model. This research study predicted that several drugs can target multiple proteins simultaneously in cytokine storm-related pathway. These may be useful drugs to treat patients because these therapies can fight cytokine storm caused by the virus at multiple points of inhibition, leading to synergistically effective treatments.

Development of Machine Learning Regression Model for COVID-19 Drug Target Prediction

There is a perennial need to identify novel, effective therapeutic agents to combat rising infections. Recently, prediction of therapeutic targets to decrease the impact of COVID-19 has posed an urgent challenge requiring innovative solutions. Successful identification of novel drug-target combinations may greatly facilitate drug development. To meet this need, we developed a COVID-19 drug target prediction model using machine learning approaches to quickly identify drug candidates for 18 COVID-19 protein targets. Specifically, we analyzed the performance of three prediction models to predict drug-target docking scores, which represents the strength of interactions between ligands and proteins. Docking scores were predicted for 300,457 molecules on 18 different COVID-19 related protein docking targets. Our proposed approach achieved a competitive performance with mathrm{R}-{2}=0.69,MAE=0.285, MSE=0.627. In addition, we identify chemical structures associated with stronger binding affinities across target binding sites. We believe our work could potentially save pharmaceutical companies significant resources, especially during the early stages of drug development. © 2022 IEEE.

Multi-ligand molecular docking, simulation, free energy calculations and wavelet analysis of the synergistic effects between natural compounds baicalein and cubebin for the inhibition of the main protease of SARS-CoV-2.

Combination drugs have been used for several diseases for many years since they produce better therapeutic effects. However, it is still a challenge to discover candidates to form a combination drug. This study aimed to investigate whether using a comprehensive in silico approach to identify novel combination drugs from a Chinese herbal formula is an appropriate and creative strategy. We, therefore, used Toujie Quwen Granules for the main protease (Mpro) of SARS-CoV-2 as an example. We first used molecular docking to identify molecular components of the formula which may inhibit Mpro. Baicalein (HQA004) is the most favorable inhibitory ligand. We also identified a ligand from the other component, cubebin (CHA008), which may act to support the proposed HQA004 inhibitor. Molecular dynamics simulations were then performed to further elucidate the possible mechanism of inhibition by HQA004 and synergistic bioactivity conferred by CHA008. HQA004 bound strongly at the active site and that CHA008 enhanced the contacts between HQA004 and Mpro. However, CHA008 also dynamically interacted at multiple sites, and continued to enhance the stability of HQA004 despite diffusion to a distant site. We proposed that HQA004 acted as a possible inhibitor, and CHA008 served to enhance its effects via allosteric effects at two sites. Additionally, our novel wavelet analysis showed that as a result of CHA008 binding, the dynamics and structure of Mpro were observed to have more subtle changes, demonstrating that the inter-residue contacts within Mpro were disrupted by the synergistic ligand. This work highlighted the molecular mechanism of synergistic effects between different herbs as a result of allosteric crosstalk between two ligands at a protein target, as well as revealed that using the multi-ligand molecular docking, simulation, free energy calculations and wavelet analysis to discover novel combination drugs from a Chinese herbal remedy is an innovative pathway.

N-Containing α-Mangostin Analogs via Smiles Rearrangement as the Promising Cytotoxic, Antitrypanosomal, and SARS-CoV-2 Main Protease Inhibitory Agents.

New N-containing xanthone analogs of α-mangostin were synthesized via one-pot Smiles rearrangement. Using cesium carbonate in the presence of 2-chloroacetamide and catalytic potassium iodide, α-mangostin (1) was subsequently transformed in three steps to provide ether 2, amide 3, and amine 4 in good yields at an optimum ratio of 1:3:3, respectively. The evaluation of the biological activities of α-mangostin and analogs 2-4 was described. Amine 4 showed promising cytotoxicity against the non-small-cell lung cancer H460 cell line fourfold more potent than that of cisplatin. Both compounds 3 and 4 possessed antitrypanosomal properties against Trypanosoma brucei rhodesiense at a potency threefold stronger than that of α-mangostin. Furthermore, ether 2 gave potent SARS-CoV-2 main protease inhibition by suppressing 3-chymotrypsinlike protease (3CLpro) activity approximately threefold better than that of 1. Fragment molecular orbital method (FMO-RIMP2/PCM) indicated the improved binding interaction of 2 in the 3CLpro active site regarding an additional ether moiety. Thus, the series of N-containing α-mangostin analogs prospectively enhance druglike properties based on isosteric replacement and would be further studied as potential biotically active chemical entries, particularly for anti-lung-cancer, antitrypanosomal, and anti-SARS-CoV-2 main protease applications.

On Approximating the pIC50 Value of COVID-19 Medicines In Silico with Artificial Neural Networks.

In the case of pandemics such as COVID-19, the rapid development of medicines addressing the symptoms is necessary to alleviate the pressure on the medical system. One of the key steps in medicine evaluation is the determination of pIC50 factor, which is a negative logarithmic expression of the half maximal inhibitory concentration (IC50). Determining this value can be a lengthy and complicated process. A tool allowing for a quick approximation of pIC50 based on the molecular makeup of medicine could be valuable. In this paper, the creation of the artificial intelligence (AI)-based model is performed using a publicly available dataset of molecules and their pIC50 values. The modeling algorithms used are artificial and convolutional neural networks (ANN and CNN). Three approaches are tested-modeling using just molecular properties (MP), encoded SMILES representation of the molecule, and the combination of both input types. Models are evaluated using the coefficient of determination (R2) and mean absolute percentage error (MAPE) in a five-fold cross-validation scheme to assure the validity of the results. The obtained models show that the highest quality regression (R2¯=0.99, σR2¯=0.001; MAPE¯=0.009%, σMAPE¯=0.009), by a large margin, is obtained when using a hybrid neural network trained with both MP and SMILES.

Deep learning in drug discovery: a futuristic modality to materialize the large datasets for cheminformatics.

Artificial intelligence (AI) development imitates the workings of the human brain to comprehend modern problems. The traditional approaches such as high throughput screening (HTS) and combinatorial chemistry are lengthy and expensive to the pharmaceutical industry as they can only handle a smaller dataset. Deep learning (DL) is a sophisticated AI method that uses a thorough comprehension of particular systems. The pharmaceutical industry is now adopting DL techniques to enhance the research and development process. Multi-oriented algorithms play a crucial role in the processing of QSAR analysis, de novo drug design, ADME evaluation, physicochemical analysis, preclinical development, followed by clinical trial data precision. In this study, we investigated the performance of several algorithms, including deep neural networks (DNN), convolutional neural networks (CNN) and multi-task learning (MTL), with the aim of generating high-quality, interpretable big and diverse databases for drug design and development. Studies have demonstrated that CNN, recurrent neural network and deep belief network are compatible, accurate and effective for the molecular description of pharmacodynamic properties. In Covid-19, existing pharmacological compounds has also been repurposed using DL models. In the absence of the Covid-19 vaccine, remdesivir and oseltamivir have been widely employed to treat severe SARS-CoV-2 infections. In conclusion, the results indicate the potential benefits of employing the DL strategies in the drug discovery process.Communicated by Ramaswamy H. Sarma.

MOLECULES GENERATION TO INHIBIT COVID-19 DISEASE USING ENCODER-DECODER LSTM ARCHITECTURE AND PCA PROPERTIES

COVID-19 has become the world’s worst pandemic and has claimed over six million lives as of March 2022. The virus is now in alongside cancer as one of the most common causes of death. Likewise, there is no definitive or unique treatment for COVID-19 outside of a selected few drugs approved by the Food and Drug Administration (FDA). While Artificial Intelligence (AI) can be used to generate molecules that target Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), the virus responsible for COVID-19, such molecules are novel and do not yet exist in the market. With the emergence and availability of several drug datasets related to COVID-19 (tests, images, graphs, and ChEMBLs), recent works based on Deep Learning (DL) techniques have been employed to generate molecules and check the effectiveness of existing molecules on COVID-19. In our study, we investigated the benefits of an Encoder–Decoder (ED) architecture based on Long Short-Term Memory (LSTM) cells. As a result, the molecules were converted into a vector during the encoding phase, which was then decoded back into SMILES molecules strings. We propose an approach to incorporate four features of Principal Components Analysis (PCA) with Encoder–Decoder Long Short-Term Memory (ED-LSTM) for regularization, which means that, instead of avoiding linear mapping, we assumed that the data could be linearly separable. We concluded that ED-LSTM with unit norm constraint has the best reconstruction accuracy in the context of generating molecules. The resulting dataset was used with the aid of virtual screening and convolutional neural networks to check the drugs that have the best binding affinity with SARS-CoV-2. We achieved an accuracy of 87.35% on the test set. [ FROM AUTHOR] Copyright of Journal of Mechanics in Medicine & Biology is the property of World Scientific Publishing Company and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Unsymmetrical aromatic disulfides as SARS-CoV-2 Mpro inhibitors: Molecular docking, molecular dynamics, and ADME scoring investigations.

COVID-19 pandemic caused by very severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) agent is an ongoing major global health concern. The disease has caused more than 452 million affected cases and more than 6 million death worldwide. Hence, there is an urgency to search for possible medications and drug treatments. There are no approved drugs available to treat COVID-19 yet, although several vaccine candidates are already available and some of them are listed for emergency use by the world health organization (WHO). Identifying a potential drug candidate may make a significant contribution to control the expansion of COVID-19. The in vitro biological activity of asymmetric disulfides against coronavirus through the inhibition of SARS-CoV-2 main protease (Mpro) protein was reported. Due to the lack of convincing evidence those asymmetric disulfides have favorable pharmacological properties for the clinical treatment of Coronavirus, in silico evaluation should be performed to assess the potential of these compounds to inhibit the SARS-CoV-2 Mpro. In this context, we report herein the molecular docking for a series of 40 unsymmetrical aromatic disulfides as SARS-CoV-2 Mpro inhibitor. The optimal binding features of disulfides within the binding pocket of SARS-CoV-2 endoribonuclease protein (Protein Data Bank [PDB]: 6LU7) was described. Studied compounds were ranked for potential effectiveness, and those have shown high molecular docking scores were proposed as novel drug candidates against SARS-CoV-2. Moreover, the outcomes of drug similarity and ADME (Absorption, Distribution, Metabolism, and Excretion) analyses have may have the effectiveness of acting as medicines, and would be of interest as promising starting point for designing compounds against SARS-CoV-2. Finally, the stability of these three compounds in the complex with Mpro was validated through molecular dynamics (MD) simulation, in which they displayed stable trajectory and molecular properties with a consistent interaction profile.

Predicting Drug-Target Affinity Based on Recurrent Neural Networks and Graph Convolutional Neural Networks.

BACKGROUND: Drug development requires a lot of money and time, and the outcome of the challenge is unknown. So, there is an urgent need for researchers to find a new approach that can reduce costs. Therefore, the identification of drug-target interactions (DTIs) has been a critical step in the early stages of drug discovery. These computational methods aim to narrow the search space for novel DTIs and to elucidate the functional background of drugs. Most of the methods developed so far use binary classification to predict the presence or absence of interactions between the drug and the target. However, it is more informative but also more challenging to predict the strength of the binding between a drug and its target. If the strength is not strong enough, such a DTI may not be useful. Hence, the development of methods to predict drug-target affinity (DTA) is of significant importance Method: We have improved the GraphDTA model from a dual-channel model to a triple-channel model. We interpreted the target/protein sequences as time series and extracted their features using the LSTM network. For the drug, we considered both the molecular structure and the local chemical background, retaining the four variant networks used in GraphDTA to extract the topological features of the drug and capturing the local chemical background of the atoms in the drug by using BiGRU. Thus, we obtained the latent features of the target and two latent features of the drug. The connection of these three feature vectors is then inputted into a 2 layer FC network, and a valuable binding affinity is the output. RESULT: We used the Davis and Kiba datasets, using 80% of the data for training and 20% of the data for validation. Our model showed better performance when compared with the experimental results of GraphDTA Conclusion: In this paper, we altered the GraphDTA model to predict drug-target affinity. It represents the drug as a graph and extracts the two-dimensional drug information using a graph convolutional neural network. Simultaneously, the drug and protein targets are represented as a word vector, and the convolutional neural network is used to extract the time-series information of the drug and the target. We demonstrate that our improved method has better performance than the original method. In particular, our model has better performance in the evaluation of benchmark databases.

Wearing N95, Surgical, and Cloth Face Masks Compromises the Perception of Emotion.

According to the familiar axiom, the eyes are the window to the soul. However, wearing masks to prevent the spread of viruses such as COVID-19 involves obscuring a large portion of the face. Do the eyes carry sufficient information to allow for the accurate perception of emotions in dynamic expressions obscured by masks? What about the perception of the meanings of specific smiles? We addressed these questions in two studies. In the first, participants saw dynamic expressions of happiness, disgust, anger, and surprise that were covered by N95, surgical, or cloth masks or were uncovered and rated the extent to which the expressions conveyed each of the same four emotions. Across conditions, participants perceived significantly lower levels of the expressed (target) emotion in masked faces, and this was particularly true for expressions composed of more facial action in the lower part of the face. Higher levels of other (non-target) emotions were also perceived in masked expressions. In the second study, participants rated the extent to which three categories of smiles (reward, affiliation, and dominance) conveyed positive feelings, reassurance, and superiority, respectively. Masked smiles communicated less of the target signal than unmasked smiles, but not more of other possible signals. The present work extends recent studies of the effects of masked faces on the perception of emotion in its novel use of dynamic facial expressions (as opposed to still images) and the investigation of different types of smiles. Supplementary Information: The online version contains supplementary material available at 10.1007/s42761-021-00097-z.

Structure features of peptide-type SARS-CoV main protease inhibitors: Quantitative structure activity relationship study.

In the present work, an extensive QSAR (Quantitative Structure Activity Relationships) analysis of a series of peptide-type SARS-CoV main protease (MPro) inhibitors following the OECD guidelines has been accomplished. The analysis was aimed to identify salient and concealed structural features that govern the MPro inhibitory activity of peptide-type compounds. The QSAR analysis is based on a dataset of sixty-two peptide-type compounds which resulted in the generation of statistically robust and highly predictive multiple models. All the developed models were validated extensively and satisfy the threshold values for many statistical parameters (for e.g. R2 â€‹= â€‹0.80-0.82, Q2 loo â€‹= â€‹0.74-0.77, Q 2 LMO  â€‹= â€‹0.66-0.67). The developed QSAR models identified number of sp2 hybridized Oxygen atoms within seven bonds from aromatic Carbon atoms, the presence of Carbon and Nitrogen atoms at a topological distance of 3 and other interrelations of atom pairs as important pharmacophoric features. Hence, the present QSAR models have a good balance of Qualitative (Descriptive QSARs) and Quantitative (Predictive QSARs) approaches, therefore useful for future modifications of peptide-type compounds for anti- SARS-CoV activity.