DendroX: multi-level multi-cluster selection in dendrograms.

BACKGROUND: Cluster heatmaps are widely used in biology and other fields to uncover clustering patterns in data matrices. Most cluster heatmap packages provide utility functions to divide the dendrograms at a certain level to obtain clusters, but it is often difficult to locate the appropriate cut in the dendrogram to obtain the clusters seen in the heatmap or computed by a statistical method. Multiple cuts are required if the clusters locate at different levels in the dendrogram. RESULTS: We developed DendroX, a web app that provides interactive visualization of a dendrogram where users can divide the dendrogram at any level and in any number of clusters and pass the labels of the identified clusters for functional analysis. Helper functions are provided to extract linkage matrices from cluster heatmap objects in R or Python to serve as input to the app. A graphic user interface was also developed to help prepare input files for DendroX from data matrices stored in delimited text files. The app is scalable and has been tested on dendrograms with tens of thousands of leaf nodes. As a case study, we clustered the gene expression signatures of 297 bioactive chemical compounds in the LINCS L1000 dataset and visualized them in DendroX. Seventeen biologically meaningful clusters were identified based on the structure of the dendrogram and the expression patterns in the heatmap. We found that one of the clusters consisting of mostly naturally occurring compounds is not previously reported and has its members sharing broad anticancer, anti-inflammatory and antioxidant activities. CONCLUSIONS: DendroX solves the problem of matching visually and computationally determined clusters in a cluster heatmap and helps users navigate among different parts of a dendrogram. The identification of a cluster of naturally occurring compounds with shared bioactivities implicates a convergence of biological effects through divergent mechanisms.

Single-cell transcriptional signature-based drug repurposing and in vitro evaluation in colorectal cancer.

BACKGROUND: The need for intelligent and effective treatment of diseases and the increase in drug design costs have raised drug repurposing as one of the effective strategies in biomedicine. There are various computational methods for drug repurposing, one of which is using transcription signatures, especially single-cell RNA sequencing (scRNA-seq) data, which show us a clear and comprehensive view of the inside of the cell to compare the state of disease and health. METHODS: In this study, we used 91,103 scRNA-seq samples from 29 patients with colorectal cancer (GSE144735 and GSE132465). First, differential gene expression (DGE) analysis was done using the ASAP website. Then we reached a list of drugs that can reverse the gene signature pattern from cancer to normal using the iLINCS website. Further, by searching various databases and articles, we found 12 drugs that have FDA approval, and so far, no one has reported them as a drug in the treatment of any cancer. Then, to evaluate the cytotoxicity and performance of these drugs, the MTT assay and real-time PCR were performed on two colorectal cancer cell lines (HT29 and HCT116). RESULTS: According to our approach, 12 drugs were suggested for the treatment of colorectal cancer. Four drugs were selected for biological evaluation. The results of the cytotoxicity analysis of these drugs are as follows: tezacaftor (IC10 = 19 µM for HCT-116 and IC10 = 2 µM for HT-29), fenticonazole (IC10 = 17 µM for HCT-116 and IC10 = 7 µM for HT-29), bempedoic acid (IC10 = 78 µM for HCT-116 and IC10 = 65 µM for HT-29), and famciclovir (IC10 = 422 µM for HCT-116 and IC10 = 959 µM for HT-29). CONCLUSIONS: Cost, time, and effectiveness are the main challenges in finding new drugs for diseases. Computational approaches such as transcriptional signature-based drug repurposing methods open new horizons to solve these challenges. In this study, tezacaftor, fenticonazole, and bempedoic acid can be introduced as promising drug candidates for the treatment of colorectal cancer. These drugs were evaluated in silico and in vitro, but it is necessary to evaluate them in vivo.

Prioritized polycystic kidney disease drug targets and repurposing candidates from pre-cystic and cystic mouse Pkd2 model gene expression reversion.

BACKGROUND: Autosomal dominant polycystic kidney disease (ADPKD) is one of the most prevalent monogenic human diseases. It is mostly caused by pathogenic variants in PKD1 or PKD2 genes that encode interacting transmembrane proteins polycystin-1 (PC1) and polycystin-2 (PC2). Among many pathogenic processes described in ADPKD, those associated with cAMP signaling, inflammation, and metabolic reprogramming appear to regulate the disease manifestations. Tolvaptan, a vasopressin receptor-2 antagonist that regulates cAMP pathway, is the only FDA-approved ADPKD therapeutic. Tolvaptan reduces renal cyst growth and kidney function loss, but it is not tolerated by many patients and is associated with idiosyncratic liver toxicity. Therefore, additional therapeutic options for ADPKD treatment are needed. METHODS: As drug repurposing of FDA-approved drug candidates can significantly decrease the time and cost associated with traditional drug discovery, we used the computational approach signature reversion to detect inversely related drug response gene expression signatures from the Library of Integrated Network-Based Cellular Signatures (LINCS) database and identified compounds predicted to reverse disease-associated transcriptomic signatures in three publicly available Pkd2 kidney transcriptomic data sets of mouse ADPKD models. We focused on a pre-cystic model for signature reversion, as it was less impacted by confounding secondary disease mechanisms in ADPKD, and then compared the resulting candidates' target differential expression in the two cystic mouse models. We further prioritized these drug candidates based on their known mechanism of action, FDA status, targets, and by functional enrichment analysis. RESULTS: With this in-silico approach, we prioritized 29 unique drug targets differentially expressed in Pkd2 ADPKD cystic models and 16 prioritized drug repurposing candidates that target them, including bromocriptine and mirtazapine, which can be further tested in-vitro and in-vivo. CONCLUSION: Collectively, these results indicate drug targets and repurposing candidates that may effectively treat pre-cystic as well as cystic ADPKD.

Reconciling multiple connectivity scores for drug repurposing.

The basis of several recent methods for drug repurposing is the key principle that an efficacious drug will reverse the disease molecular 'signature' with minimal side effects. This principle was defined and popularized by the influential 'connectivity map' study in 2006 regarding reversal relationships between disease- and drug-induced gene expression profiles, quantified by a disease-drug 'connectivity score.' Over the past 15 years, several studies have proposed variations in calculating connectivity scores toward improving accuracy and robustness in light of massive growth in reference drug profiles. However, these variations have been formulated inconsistently using various notations and terminologies even though they are based on a common set of conceptual and statistical ideas. Therefore, we present a systematic reconciliation of multiple disease-drug similarity metrics ($ES$, $css$, $Sum$, $Cosine$, $XSum$, $XCor$, $XSpe$, $XCos$, $EWCos$) and connectivity scores ($CS$, $RGES$, $NCS$, $WCS$, $Tau$, $CSS$, $EMUDRA$) by defining them using consistent notation and terminology. In addition to providing clarity and deeper insights, this coherent definition of connectivity scores and their relationships provides a unified scheme that newer methods can adopt, enabling the computational drug-development community to compare and investigate different approaches easily. To facilitate the continuous and transparent integration of newer methods, this article will be available as a live document (https://jravilab.github.io/connectivity_scores) coupled with a GitHub repository (https://github.com/jravilab/connectivity_scores) that any researcher can build on and push changes to.

In Silico Drug Repurposing in Multiple Sclerosis Using scRNA-Seq Data.

Multiple sclerosis (MS) is an autoimmune disease of the central nervous system still lacking a cure. Treatment typically focuses on slowing the progression and managing MS symptoms. Single-cell transcriptomics allows the investigation of the immune system-the key player in MS onset and development-in great detail increasing our understanding of MS mechanisms and stimulating the discovery of the targets for potential therapies. Still, de novo drug development takes decades; however, this can be reduced by drug repositioning. A promising approach is to select potential drugs based on activated or inhibited genes and pathways. In this study, we explored the public single-cell RNA data from an experiment with six patients on single-cell RNA peripheral blood mononuclear cells (PBMC) and cerebrospinal fluid cells (CSF) of patients with MS and idiopathic intracranial hypertension. We demonstrate that AIM2 inflammasome, SMAD2/3 signaling, and complement activation pathways are activated in MS in different CSF and PBMC immune cells. Using genes from top-activated pathways, we detected several promising small molecules to reverse MS immune cells' transcriptomic signatures, including AG14361, FGIN-1-27, CA-074, ARP 101, Flunisolide, and JAK3 Inhibitor VI. Among these molecules, we also detected an FDA-approved MS drug Mitoxantrone, supporting the reliability of our approach.

Connectivity Map Analysis of a Single-Cell RNA-Sequencing -Derived Transcriptional Signature of mTOR Signaling.

In the connectivity map (CMap) approach to drug repositioning and development, transcriptional signature of disease is constructed by differential gene expression analysis between the diseased tissue or cells and the control. The negative correlation between the transcriptional disease signature and the transcriptional signature of the drug, or a bioactive compound, is assumed to indicate its ability to "reverse" the disease process. A major limitation of traditional CMaP analysis is the use of signatures derived from bulk disease tissues. Since the key driver pathways are most likely dysregulated in only a subset of cells, the "averaged" transcriptional signatures resulting from bulk analysis lack the resolution to effectively identify effective therapeutic agents. The use of single-cell RNA-seq (scRNA-seq) transcriptomic assay facilitates construction of disease signatures that are specific to individual cell types, but methods for using scRNA-seq data in the context of CMaP analysis are lacking. Lymphangioleiomyomatosis (LAM) mutations in TSC1 or TSC2 genes result in the activation of the mTOR complex 1 (mTORC1). The mTORC1 inhibitor Sirolimus is the only FDA-approved drug to treat LAM. Novel therapies for LAM are urgently needed as the disease recurs with discontinuation of the treatment and some patients are insensitive to the drug. We developed methods for constructing disease transcriptional signatures and CMaP analysis using scRNA-seq profiling and applied them in the analysis of scRNA-seq data of lung tissue from naïve and sirolimus-treated LAM patients. New methods successfully implicated mTORC1 inhibitors, including Sirolimus, as capable of reverting the LAM transcriptional signatures. The CMaP analysis mimicking standard bulk-tissue approach failed to detect any connection between the LAM signature and mTORC1 signaling. This indicates that the precise signature derived from scRNA-seq data using our methods is the crucial difference between the success and the failure to identify effective therapeutic treatments in CMaP analysis.

Oxytocin's anti-inflammatory and proimmune functions in COVID-19: a transcriptomic signature-based approach.

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a worldwide pandemic, infecting over 16 million people worldwide with a significant mortality rate. However, there is no current Food and Drug Administration-approved drug that treats coronavirus disease 2019 (COVID-19). Damage to T lymphocytes along with the cytokine storm are important factors that lead to exacerbation of clinical cases. Here, we are proposing intravenous oxytocin (OXT) as a candidate for adjunctive therapy for COVID-19. OXT has anti-inflammatory and proimmune adaptive functions. Using the Library of Integrated Network-Based Cellular Signatures (LINCS), we used the transcriptomic signature for carbetocin, an OXT agonist, and compared it to gene knockdown signatures of inflammatory (such as interleukin IL-1ß and IL-6) and proimmune markers (including T cell and macrophage cell markers like CD40 and ARG1). We found that carbetocin's transcriptomic signature has a pattern of concordance with inflammation and immune marker knockdown signatures that are consistent with reduction of inflammation and promotion and sustaining of immune response. This suggests that carbetocin may have potent effects in modulating inflammation, attenuating T cell inhibition, and enhancing T cell activation. Our results also suggest that carbetocin is more effective at inducing immune cell responses than either lopinavir or hydroxychloroquine, both of which have been explored for the treatment of COVID-19.

Recursive model for dose-time responses in pharmacological studies.

BACKGROUND: Clinical studies often track dose-response curves of subjects over time. One can easily model the dose-response curve at each time point with Hill equation, but such a model fails to capture the temporal evolution of the curves. On the other hand, one can use Gompertz equation to model the temporal behaviors at each dose without capturing the evolution of time curves across dosage. RESULTS: In this article, we propose a parametric model for dose-time responses that follows Gompertz law in time and Hill equation across dose approximately. We derive a recursion relation for dose-response curves over time capturing the temporal evolution and then specify a regression model connecting the parameters controlling the dose-time responses with individual level proteomic data. The resultant joint model allows us to predict the dose-response curves over time for new individuals. CONCLUSION: We have compared the efficacy of our proposed Recursive Hybrid model with individual dose-response predictive models at desired time points. We note that our proposed model exhibits a superior performance compared to the individual ones for both synthetic data and actual pharmacological data. For the desired dose-time varying genetic characterization and drug response values, we have used the HMS-LINCS database and demonstrated the effectiveness of our model for all available anticancer compounds.

In Vitro and In Vivo Pipeline for Validation of Disease-Modifying Effects of Systems Biology-Derived Network Treatments for Traumatic Brain Injury-Lessons Learned.

We developed a pipeline for the discovery of transcriptomics-derived disease-modifying therapies and used it to validate treatments in vitro and in vivo that could be repurposed for TBI treatment. Desmethylclomipramine, ionomycin, sirolimus and trimipramine, identified by in silico LINCS analysis as candidate treatments modulating the TBI-induced transcriptomics networks, were tested in neuron-BV2 microglial co-cultures, using tumour necrosis factor α as a monitoring biomarker for neuroinflammation, nitrite for nitric oxide-mediated neurotoxicity and microtubule associated protein 2-based immunostaining for neuronal survival. Based on (a) therapeutic time window in silico, (b) blood-brain barrier penetration and water solubility, (c) anti-inflammatory and neuroprotective effects in vitro (p < 0.05) and (d) target engagement of Nrf2 target genes (p < 0.05), desmethylclomipramine was validated in a lateral fluid-percussion model of TBI in rats. Despite the favourable in silico and in vitro outcomes, in vivo assessment of clomipramine, which metabolizes to desmethylclomipramine, failed to demonstrate favourable effects on motor and memory tests. In fact, clomipramine treatment worsened the composite neuroscore (p < 0.05). Weight loss (p < 0.05) and prolonged upregulation of plasma cytokines (p < 0.05) may have contributed to the worsened somatomotor outcome. Our pipeline provides a rational stepwise procedure for evaluating favourable and unfavourable effects of systems-biology discovered compounds that modulate post-TBI transcriptomics.

Network-Based Assessment of Adverse Drug Reaction Risk in Polypharmacy Using High-Throughput Screening Data.

The risk of adverse drug reactions increases in a polypharmacology setting. High-throughput drug screening with transcriptomics applied to human cells has shown that drugs have effects on several molecular pathways, and these affected pathways may be predictive proxy for adverse drug reactions. Depending on the way that different drugs may contribute to adverse drug reactions, different options may exist in the clinical setting. Here, we formulate a network framework to integrate the relationships between drugs, biological functions, and adverse drug reactions based on the high-throughput drug perturbation data from the Library of Integrated Network-Based Cellular Signatures (LINCS) project. We present network-based parameters that indicate whether a given reaction may be related to the effect of a single drug or to the combination of several drugs, as well as the relative risk of adverse drug reaction manifestation given a certain drug combination.

Deep learning-based transcriptome data classification for drug-target interaction prediction.

BACKGROUND: The ability to predict the interaction of drugs with target proteins is essential to research and development of drug. However, the traditional experimental paradigm is costly, and previous in silico prediction paradigms have been impeded by the wide range of data platforms and data scarcity. RESULTS: In this paper, we modeled the prediction of drug-target interactions as a binary classification task. Using transcriptome data from the L1000 database of the LINCS project, we developed a framework based on a deep-learning algorithm to predict potential drug target interactions. Once fully trained, the model achieved over 98% training accuracy. The results of our research demonstrated that our framework could discover more reliable DTIs than found by other methods. This conclusion was validated further across platforms with a high percentage of overlapping interactions. CONCLUSIONS: Our model's capacity of integrating transcriptome data from drugs and genes strongly suggests the strength of its potential for DTI prediction, thereby improving the drug discovery process.

Mechanistic insights into the differential effects of thalidomide and lenalidomide in metastatic prostate cancer.

AIM: To understand why thalidomide and lenalidomide exhibit different responses in metastatic prostate cancer (mPCa) treatment. METHODS: We analyzed the perturbation signatures of thalidomide, lenalidomide, flutamide treated mPCa cell line from Library of Integrated Network-based Cellular Signatures database and transcriptome of docetaxel-treated mPCa patients. RESULTS: Flutamide and docetaxel downregulated 'Steroid Biosynthesis', 'Cell cycle' and PCa specific transcription factor networks. Thalidomide inhibited 'Cell cycle' and 'E2F network', possibly accounting for its synergistic effects with docetaxel. Conversely, lenalidomide promoted 'Cell cycle' and 'Cholesterol biosynthesis'. CONCLUSION: Hence, we propose that lenalidomide upregulates cholesterol synthesis followed by enhanced rate of cell cycle, thereby nurturing a hyperproliferative tumor microenvironment. In summary, this study offers a possible explanation for the differential outcomes in the treatment of mPCa with thalidomide and lenalidomide.

Ontological representation, integration, and analysis of LINCS cell line cells and their cellular responses.

BACKGROUND: Aiming to understand cellular responses to different perturbations, the NIH Common Fund Library of Integrated Network-based Cellular Signatures (LINCS) program involves many institutes and laboratories working on over a thousand cell lines. The community-based Cell Line Ontology (CLO) is selected as the default ontology for LINCS cell line representation and integration. RESULTS: CLO has consistently represented all 1097 LINCS cell lines and included information extracted from the LINCS Data Portal and ChEMBL. Using MCF 10A cell line cells as an example, we demonstrated how to ontologically model LINCS cellular signatures such as their non-tumorigenic epithelial cell type, three-dimensional growth, latrunculin-A-induced actin depolymerization and apoptosis, and cell line transfection. A CLO subset view of LINCS cell lines, named LINCS-CLOview, was generated to support systematic LINCS cell line analysis and queries. In summary, LINCS cell lines are currently associated with 43 cell types, 131 tissues and organs, and 121 cancer types. The LINCS-CLO view information can be queried using SPARQL scripts. CONCLUSIONS: CLO was used to support ontological representation, integration, and analysis of over a thousand LINCS cell line cells and their cellular responses.

High-throughput validation of ceRNA regulatory networks.

BACKGROUND: MicroRNAs (miRNAs) play multiple roles in tumor biology. Interestingly, reports from multiple groups suggest that miRNA targets may be coupled through competitive stoichiometric sequestration. Specifically, computational models predicted and experimental assays confirmed that miRNA activity is dependent on miRNA target abundance, and consequently, changes in the abundance of some miRNA targets lead to changes to the regulation and abundance of their other targets. The resulting indirect regulatory influence between miRNA targets resembles competition and has been dubbed competitive endogenous RNA (ceRNA). Recent studies have questioned the physiological relevance of ceRNA interactions, our ability to accurately predict these interactions, and the number of genes that are impacted by ceRNA interactions in specific cellular contexts. RESULTS: To address these concerns, we reverse engineered ceRNA networks (ceRNETs) in breast and prostate adenocarcinomas using context-specific TCGA profiles, and tested whether ceRNA interactions can predict the effects of RNAi-mediated gene silencing perturbations in PC3 and MCF7 cells._ENREF_22 Our results, based on tests of thousands of inferred ceRNA interactions that are predicted to alter hundreds of cancer genes in each of the two tumor contexts, confirmed statistically significant effects for half of the predicted targets. CONCLUSIONS: Our results suggest that the expression of a significant fraction of cancer genes may be regulated by ceRNA interactions in each of the two tumor contexts.

GRcalculator: an online tool for calculating and mining dose-response data.

BACKGROUND: Quantifying the response of cell lines to drugs or other perturbagens is the cornerstone of pre-clinical drug development and pharmacogenomics as well as a means to study factors that contribute to sensitivity and resistance. In dividing cells, traditional metrics derived from dose-response curves such as IC 50 , AUC, and E max , are confounded by the number of cell divisions taking place during the assay, which varies widely for biological and experimental reasons. Hafner et al. (Nat Meth 13:521-627, 2016) recently proposed an alternative way to quantify drug response, normalized growth rate (GR) inhibition, that is robust to such confounders. Adoption of the GR method is expected to improve the reproducibility of dose-response assays and the reliability of pharmacogenomic associations (Hafner et al. 500-502, 2017). RESULTS: We describe here an interactive website ( www.grcalculator.org ) for calculation, analysis, and visualization of dose-response data using the GR approach and for comparison of GR and traditional metrics. Data can be user-supplied or derived from published datasets. The web tools are implemented in the form of three integrated Shiny applications (grcalculator, grbrowser, and grtutorial) deployed through a Shiny server. Intuitive graphical user interfaces (GUIs) allow for interactive analysis and visualization of data. The Shiny applications make use of two R packages (shinyLi and GRmetrics) specifically developed for this purpose. The GRmetrics R package is also available via Bioconductor and can be used for offline data analysis and visualization. Source code for the Shiny applications and associated packages (shinyLi and GRmetrics) can be accessed at www.github.com/uc-bd2k/grcalculator and www.github.com/datarail/gr_metrics . CONCLUSIONS: GRcalculator is a powerful, user-friendly, and free tool to facilitate analysis of dose-response data. It generates publication-ready figures and provides a unified platform for investigators to analyze dose-response data across diverse cell types and perturbagens (including drugs, biological ligands, RNAi, etc.). GRcalculator also provides access to data collected by the NIH LINCS Program ( http://www.lincsproject.org /) and other public domain datasets. The GRmetrics Bioconductor package provides computationally trained users with a platform for offline analysis of dose-response data and facilitates inclusion of GR metrics calculations within existing R analysis pipelines. These tools are therefore well suited to users in academia as well as industry.

Molecular dynamics simulations of lipid membranes with lateral force: rupture and dynamic properties.

Membranes' response to lateral tension, and eventual rupture, remains poorly understood. In this study, pure dipalmitoylphosphatidylcholine (DPPC) lipid bilayers, under tension/pressure, were studied using molecular dynamics (MD) simulations. The irreversible membrane breakdown is demonstrated to depend on the amplitude of lateral tension, loading rate, and the size of the bilayer. In all of our simulations, -200bar lateral pressure was found to be enough to rupture lipid membrane regardless of the loading rate or the membrane size. Loading rate and membrane size had a significant impact on rupture. A variety of dynamic properties of lipid molecules, probability distribution of area per lipid particularly, have been determined, and found to be fundamental for describing membrane behavior in detail, thus providing the quantitative description for the requirement of membrane rupture.

New ways to boost molecular dynamics simulations.

We describe a set of algorithms that allow to simulate dihydrofolate reductase (DHFR, a common benchmark) with the AMBER all-atom force field at 160 nanoseconds/day on a single Intel Core i7 5960X CPU (no graphics processing unit (GPU), 23,786 atoms, particle mesh Ewald (PME), 8.0 Å cutoff, correct atom masses, reproducible trajectory, CPU with 3.6 GHz, no turbo boost, 8 AVX registers). The new features include a mixed multiple time-step algorithm (reaching 5 fs), a tuned version of LINCS to constrain bond angles, the fusion of pair list creation and force calculation, pressure coupling with a "densostat," and exploitation of new CPU instruction sets like AVX2. The impact of Intel's new transactional memory, atomic instructions, and sloppy pair lists is also analyzed. The algorithms map well to GPUs and can automatically handle most Protein Data Bank (PDB) files including ligands. An implementation is available as part of the YASARA molecular modeling and simulation program from www.YASARA.org.

Data Valuation with Gradient Similarity.

High-quality data is crucial for accurate machine learning and actionable analytics, however, mislabeled or noisy data is a common problem in many domains. Distinguishing low- from high-quality data can be challenging, often requiring expert knowledge and considerable manual intervention. Data Valuation algorithms are a class of methods that seek to quantify the value of each sample in a dataset based on its contribution or importance to a given predictive task. These data values have shown an impressive ability to identify mislabeled observations, and filtering low-value data can boost machine learning performance. In this work, we present a simple alternative to existing methods, termed Data Valuation with Gradient Similarity (DVGS). This approach can be easily applied to any gradient descent learning algorithm, scales well to large datasets, and performs comparably or better than baseline valuation methods for tasks such as corrupted label discovery and noise quantification. We evaluate the DVGS method on tabular, image and RNA expression datasets to show the effectiveness of the method across domains. Our approach has the ability to rapidly and accurately identify low-quality data, which can reduce the need for expert knowledge and manual intervention in data cleaning tasks.

Drug Repurposing Using FDA Adverse Event Reporting System (FAERS) Database.

Drug repurposing is an emerging approach to reassigning existing pre-approved therapies for new indications. The FDA Adverse Event Reporting System (FAERS) is a large database of over 28 million adverse event reports submitted by medical providers, patients, and drug manufacturers and provides extensive drug safety signal data. In this review, four common drug repurposing strategies using FAERS are described, including inverse signal detection for a single disease, drug-drug interactions that mitigate a target ADE, identifying drug-ADE pairs with opposing gene perturbation signatures and identifying drug-drug pairs with congruent gene perturbation signatures. The purpose of this review is to provide an overview of these different approaches to FAERS-based drug repurposing using existing successful applications in the literature. With the fast expansion of adverse drug event reports, FAERS-based drug repurposing represents a versatile and promising strategy for discovering new uses for existing therapies.

Accelerating drug repurposing for COVID-19 treatment by modeling mechanisms of action using cell image features and machine learning.

The novel coronavirus disease, COVID-19, has rapidly spread worldwide. Developing methods to identify the therapeutic activity of drugs based on phenotypic data can improve the efficiency of drug development. Here, a state-of-the-art machine-learning method was used to identify drug mechanism of actions (MoAs) based on the cell image features of 1105 drugs in the  LINCS database. As the multi-dimensional features of cell images are affected by non-experimental factors, the characteristics of similar drugs vary considerably, and it is difficult to effectively identify the MoA of drugs as there is substantial noise. By applying the supervised information theoretic metric-learning (ITML) algorithm, a linear transformation made drugs with the same MoA aggregate. By clustering drugs to communities and performing enrichment analysis, we found that transferred image features were more conducive to the recognition of drug MoAs. Image features analysis showed that different features play important roles in identifying different drug functions. Drugs that significantly affect cell survival or proliferation, such as cyclin-dependent kinase inhibitors, were more likely to be enriched in communities, whereas other drugs might be decentralized. Chloroquine and clomiphene, which block the entry of virus, were clustered into the same community, indicating that similar MoA could be reflected by the cell image. Overall, the findings of the present study laid the foundation for the discovery of MoAs of new drugs, based on image data. In addition, it provided a new method of drug repurposing for COVID-19. Supplementary Information: The online version contains supplementary material available at 10.1007/s11571-021-09727-5.