Abstract: Accurate predictions of acid dissociation constants are essential to rational molecular design in the pharmaceutical industry and elsewhere. There has been much interest in developing new machine learning methods that can produce fast and accurate pKa predictions for arbitrary species, as well as estimates of prediction uncertainty. Previously, as part of the SAMPL6 community-wide blind challenge, Bannan et al. approached the problem of predicting [Formula: see text]s by using a Gaussian process regression to predict microscopic [Formula: see text]s, from which macroscopic [Formula: see text] values can be analytically computed (Bannan et al. in J Comput-Aided Mol Des 32:1165-1177). While this method can make reasonably quick and accurate predictions using a small training set, accuracy was limited by the lack of a sufficiently broad range of chemical space in the training set (e.g., the inclusion of polyprotic acids). Here, to address this issue, we construct a deep Gaussian Process (GP) model that can include more features without invoking the curse of dimensionality. We trained both a standard GP and a deep GP model using a database of approximately 3500 small molecules curated from public sources, filtered by similarity to targets. We tested the model on both the SAMPL6 and more recent SAMPL7 challenge, which introduced a similar lack of ionizable sites and/or environments found between the test set and the previous training set. The results show that while the deep GP model made only minor improvements over the standard GP model for SAMPL6 predictions, it made significant improvements over the standard GP model in SAMPL7 macroscopic predictions, achieving a MAE of 1.5 [Formula: see text].

Abstract: Metal binding sites, antigen epitopes and drug binding sites are the hotspots in viral proteins that control how viruses interact with their hosts. virusMED (virus Metal binding sites, Epitopes and Drug binding sites) is a rich internet application based on a database of atomic interactions around hotspots in 7041 experimentally determined viral protein structures. 25306 hotspots from 805 virus strains from 75 virus families were characterized, including influenza, HIV-1 and SARS-CoV-2 viruses. Just as Google Maps organizes and annotates points of interest, virusMED presents the positions of individual hotspots on each viral protein and creates an atlas upon which newly characterized functional sites can be placed as they are being discovered. virusMED contains an extensive set of annotation tags about the virus species and strains, viral hosts, viral proteins, metal ions, specific antibodies and FDA-approved drugs, which permits rapid screening of hotspots on viral proteins tailored to a particular research problem. The virusMED portal (https://virusmed.biocloud.top) can serve as a window to a valuable resource for many areas of virus research and play a critical role in the rational design of new preventative and therapeutic agents targeting viral infections.

Abstract: BACKGROUND: The Gouqi-wentang formula (GQWTF) is a herbal formula used by Academician Xiao-lin Tong for the clinical treatment of T2DM. GQWTF is beneficial to qi, nourishes Yin, clears heat, and promotes fluid production, but the effective components and their mechanism of action remain unclear. METHODS: The main components of GQWTF were detected by LC-MS, and the multi-target mechanisms of GQWTF in T2DM were elucidated using network pharmacology analysis, including target prediction, protein-protein interaction network construction and analysis, Gene Ontology (GO) terms, Kyoto Encyclopaedia of Genes and Genomes (KEGG) pathway annotation, and other network construction. Finally, the efficacy of the GQWTF was verified using biological experiments. RESULTS: First, the "herb-channel tropism" network suggested that GQWTF focuses more on treating diseases by recuperating the liver, which is considered as an important insulin-sensitive organ. Subsequently, a total of 16 active ingredients in GQWTF were detected and screened, and their biological targets were predicted. Then, "compound-target" network was constructed, where enrichment analysis of GQWTF targets reflected its potential pharmacological activities. After T2DM-related target identification, 39 cross targets of GQWTF and T2DM were obtained, and 30 key targets highly responsible for the beneficial effect of GQWTF on T2DM were identified by PPI analysis. GO analysis of these key targets showed that many biological processes of GQWTF in treating T2DM are key in the occurrence and development of T2DM, including components related to inflammatory/immune response, insulin, and metabolism. KEGG analysis revealed the regulation of multiple signalling pathways, such as insulin resistance, PPAR signalling pathway, FoxO signalling pathway, Fc epsilon RI signalling pathway, and pathways that influence diabetes primarily by regulating metabolism as well as other T2DM directly related pathways. Furthermore, a "formula-compound-pathway-symptom" network was constructed to represent a global view of GQWTF in the treatment of T2DM. CONCLUSIONS: This study explored the mechanism of action of GQWTF in T2DM by multi-component and multi-target multi pathways, which could provide a theoretical basis for the development and clinical application of GQWTF.

Abstract: Many contemporary cheminformatics methods, including computer-aided de novo drug design, hold promise to significantly accelerate and reduce the cost of drug discovery. Thanks to this attractive outlook, the field has thrived and in the past few years has seen an especially significant growth, mainly due to the emergence of novel methods based on deep neural networks. This growth is also apparent in the development of novel de novo drug design methods with many new generative algorithms now available. However, widespread adoption of new generative techniques in the fields like medicinal chemistry or chemical biology is still lagging behind the most recent developments. Upon taking a closer look, this fact is not surprising since in order to successfully integrate the most recent de novo drug design methods in existing processes and pipelines, a close collaboration between diverse groups of experimental and theoretical scientists needs to be established. Therefore, to accelerate the adoption of both modern and traditional de novo molecular generators, we developed Generator User Interface (GenUI), a software platform that makes it possible to integrate molecular generators within a feature-rich graphical user interface that is easy to use by experts of diverse backgrounds. GenUI is implemented as a web service and its interfaces offer access to cheminformatics tools for data preprocessing, model building, molecule generation, and interactive chemical space visualization. Moreover, the platform is easy to extend with customizable frontend React.js components and backend Python extensions. GenUI is open source and a recently developed de novo molecular generator, DrugEx, was integrated as a proof of principle. In this work, we present the architecture and implementation details of GenUI and discuss how it can facilitate collaboration in the disparate communities interested in de novo molecular generation and computer-aided drug discovery.

Abstract: [Figure: see text].

Abstract: The MEDication-Indication (MEDI) knowledgebase has been utilized in research with electronic health records (EHRs) since its publication in 2013. To account for new drugs and terminology updates, we rebuilt MEDI to overhaul the knowledgebase for modern EHRs. Indications for prescribable medications were extracted using natural language processing and ontology relationships from six publicly available resources: RxNorm, Side Effect Resource 4.1, Mayo Clinic, WebMD, MedlinePlus, and Wikipedia. We compared the estimated precision and recall between the previous MEDI (MEDI-1) and the updated version (MEDI-2) with manual review. MEDI-2 contains 3031 medications and 186,064 indications. The MEDI-2 high precision subset (HPS) includes indications found within RxNorm or at least three other resources. MEDI-2 and MEDI-2 HPS contain 13% more medications and over triple the indications compared to MEDI-1 and MEDI-1 HPS, respectively. Manual review showed MEDI-2 achieves the same precision (0.60) with better recall (0.89 vs. 0.79) compared to MEDI-1. Likewise, MEDI-2 HPS had the same precision (0.92) and improved recall (0.65 vs. 0.55) than MEDI-1 HPS. The combination of MEDI-1 and MEDI-2 achieved a recall of 0.95. In updating MEDI, we present a more comprehensive medication-indication knowledgebase that can continue to facilitate applications and research with EHRs.

Abstract: Traditional drug discovery effectively contributes to the treatment of many diseases but is limited by high costs and long cycles. Quantitative structure-activity relationship (QSAR) methods were introduced to evaluate the activity of compounds virtually, which saves the significant cost of determining the activities of the compounds experimentally. Over the past two decades, many web tools for QSAR modeling with various features have been developed to facilitate the usage of QSAR methods. These web tools significantly reduce the difficulty of using QSAR and indirectly promote drug discovery. However, there are few comprehensive summaries of these QSAR tools, and researchers may have difficulty determining which tool to use. Hence, we systematically surveyed the mainstream web tools for QSAR modeling. This work may guide researchers in choosing appropriate web tools for developing QSAR models, and may also help develop more bioinformatics tools based on these existing resources. For nonprofessionals, we also hope to make more people aware of QSAR methods and expand their use.

Abstract: Some effective drugs have been approved or issued an Emergency Use Authorization for the treatment of COVID-19 in hospitalized patients, but post-market surveillance is warranted to monitor adverse events. We reviewed clinical trials and case reports in patients with moderate-to-severe COVID-19 infection who received remdesivir, baricitinib, tocilizumab, or sarilumab. The drug-specific pharmacokinetics, toxicity, and drug interactions are summarized in this study. Remdesivir and baricitinib are small-molecule drugs that are mainly metabolized by the kidneys, while tocilizumab and sarilumab are monoclonal antibody drugs with metabolic pathways that are currently not fully understood. The most common adverse events of these drugs are alterations in liver function, but serious adverse events have rarely been attributed to them. Only a few studies have reported that remdesivir might be cardiotoxic and that baricitinib might cause thromboembolism. Biological agents such as baricitinib, tocilizumab, and sarilumab could inhibit the pathway of inflammatory processes, leading to immune dysregulation, so the risk of secondary infection should be assessed before prescribing. Further recognition of the pathogenic mechanism and risk factors of adverse events is essential for optimizing treatment strategies.

Abstract: The COVID-19 pandemic is raging. It revealed the importance of rapid scientific advancement towards understanding and treating new diseases. To address this challenge, we adapt an explainable artificial intelligence algorithm for data fusion and utilize it on new omics data on viral-host interactions, human protein interactions, and drugs to better understand SARS-CoV-2 infection mechanisms and predict new drug-target interactions for COVID-19. We discover that in the human interactome, the human proteins targeted by SARS-CoV-2 proteins and the genes that are differentially expressed after the infection have common neighbors central in the interactome that may be key to the disease mechanisms. We uncover 185 new drug-target interactions targeting 49 of these key genes and suggest re-purposing of 149 FDA-approved drugs, including drugs targeting VEGF and nitric oxide signaling, whose pathways coincide with the observed COVID-19 symptoms. Our integrative methodology is universal and can enable insight into this and other serious diseases.

Abstract: Drug-target interaction (DTI) prediction is a crucial step in drug discovery and repositioning as it reduces experimental validation costs if done right. Thus, developing in-silico methods to predict potential DTI has become a competitive research niche, with one of its main focuses being improving the prediction accuracy. Using machine learning (ML) models for this task, specifically network-based approaches, is effective and has shown great advantages over the other computational methods. However, ML model development involves upstream hand-crafted feature extraction and other processes that impact prediction accuracy. Thus, network-based representation learning techniques that provide automated feature extraction combined with traditional ML classifiers dealing with downstream link prediction tasks may be better-suited paradigms. Here, we present such a method, DTi2Vec, which identifies DTIs using network representation learning and ensemble learning techniques. DTi2Vec constructs the heterogeneous network, and then it automatically generates features for each drug and target using the nodes embedding technique. DTi2Vec demonstrated its ability in drug-target link prediction compared to several state-of-the-art network-based methods, using four benchmark datasets and large-scale data compiled from DrugBank. DTi2Vec showed a statistically significant increase in the prediction performances in terms of AUPR. We verified the "novel" predicted DTIs using several databases and scientific literature. DTi2Vec is a simple yet effective method that provides high DTI prediction performance while being scalable and efficient in computation, translating into a powerful drug repositioning tool.