Data Portal for the Library of Integrated Network-based Cellular Signatures (LINCS) program: integrated access to diverse large-scale cellular perturbation response data

Computational drug repurposing for viral infectious diseases: a case study on monkeypox

The traditional method of drug reuse or repurposing has significantly contributed to the identification of new antiviral compounds and therapeutic targets, enabling rapid response to developing infectious illnesses. This article presents an overview of how modern computational methods are used in drug repurposing for the treatment of viral infectious diseases. These methods utilize data sets that include reviewed information on the host's response to pathogens and drugs, as well as various connections such as gene expression patterns and protein-protein interaction networks. We assess the potential benefits and limitations of these methods by examining monkeypox as a specific example, but the knowledge acquired can be applied to other comparable disease scenarios.

A network-based trans-omics approach for predicting synergistic drug combinations

BACKGROUND

Combination therapy can offer greater efficacy on medical treatments. However, the discovery of synergistic drug combinations is challenging. We propose a novel computational method, SyndrumNET, to predict synergistic drug combinations by network propagation with trans-omics analyses.

METHODS

The prediction is based on the topological relationship, network-based proximity, and transcriptional correlation between diseases and drugs. SyndrumNET was applied to analyzing six diseases including asthma, diabetes, hypertension, colorectal cancer, acute myeloid leukemia (AML), and chronic myeloid leukemia (CML).

RESULTS

Here we show that SyndrumNET outperforms the previous methods in terms of high accuracy. We perform in vitro cell survival assays to validate our prediction for CML. Of the top 17 predicted drug pairs, 14 drug pairs successfully exhibits synergistic anticancer effects. Our mode-of-action analysis also reveals that the drug synergy of the top predicted combination of capsaicin and mitoxantrone is due to the complementary regulation of 12 pathways, including the Rap1 signaling pathway.

CONCLUSIONS

The proposed method is expected to be useful for discovering synergistic drug combinations for various complex diseases.

Systematic computational strategies for identifying protein targets and lead discovery

Computational algorithms and tools have retrenched the drug discovery and development timeline. The applicability of computational approaches has gained immense relevance owing to the dramatic surge in the structural information of biomacromolecules and their heteromolecular complexes. Computational methods are now extensively used in identifying new protein targets, druggability assessment, pharmacophore mapping, molecular docking, the virtual screening of lead molecules, bioactivity prediction, molecular dynamics of protein-ligand complexes, affinity prediction, and for designing better ligands. Herein, we provide an overview of salient components of recently reported computational drug-discovery workflows that includes algorithms, tools, and databases for protein target identification and optimized ligand selection.

Evaluation of Toll-like Receptor 4 (TLR4) Involvement in Human Atrial Fibrillation: A Computational Study

In the present study, we have explored the involvement of Toll-like Receptor 4 (TLR4) in atrial fibrillation (AF), by using a meta-analysis of publicly available human transcriptomic data. The meta-analysis revealed 565 upregulated and 267 downregulated differentially expressed genes associated with AF. Pathway enrichment analysis highlighted a significant overrepresentation in immune-related pathways for the upregulated genes. A significant overlap between AF differentially expressed genes and TLR4-modulated genes was also identified, suggesting the potential role of TLR4 in AF-related transcriptional changes. Additionally, the analysis of other Toll-like receptors (TLRs) revealed a significant association with TLR2 and TLR3 in AF-related gene expression patterns. The examination of MYD88 and TICAM1, genes associated with TLR4 signalling pathways, indicated a significant yet nonspecific enrichment of AF differentially expressed genes. In summary, this study offers novel insights into the molecular aspects of AF, suggesting a pathophysiological role of TLR4 and other TLRs. By targeting these specific receptors, new treatments might be designed to better manage AF, offering hope for improved outcomes in affected patients.

Cancer cells forgo translating mRNA transcribed from genes of nonspecialized tasks

The coupling of transcription and translation enables prokaryotes to regulate mRNA stability and reduce nonfunctional transcripts. Eukaryotes evolved other means to perform these functions. Here, we quantify the disparity between gene expression and protein levels and attempt to explain its origins. We collected publicly available simultaneous measurements of gene expression, protein level, division rate, and growth inhibition of breast cancer cells under drug perturbation. We used the cell lines as entities with shared origin, different evolutionary trajectories, and cancer hallmarks to define tasks subject to specializing and trading-off. We observed varying average mRNA and protein correlation across cell lines, and it was consistently higher for the gene products in the cancer hallmarks. The enrichment of hallmark gene products signifies the resources invested in it as a task. Enrichment based on mRNA or protein abundance corresponds to the relative resources dedicated to transcription and translation. The differences in gene- and protein-based enrichment correlated with nominal division rates but not growth inhibition under drug perturbations. Comparing the range of enrichment scores of the hallmarks within each cell signifies the resources dedicated to each. Cells appear to have a wider range of enrichment in protein synthesis relative to gene transcription. The difference and range of enrichment of the hallmark genes and proteins correlated with cell division and inhibition in response to drug treatments. We posit that cancer cells may express the genes coding for seemingly nonspecialized tasks but do not translate them to the corresponding proteins. This trade-off may cost the cells under normal conditions but confer benefits during stress.

ITNR: Inversion Transformer-based Neural Ranking for cancer drug recommendations

Personalized drug response prediction is an approach for tailoring effective therapeutic strategies for patients based on their tumors' genomic characterization. While machine learning methods are widely employed in the literature, they often struggle to capture drug-cell line relations across various cell lines. In addressing this challenge, our study introduces a novel listwise Learning-to-Rank (LTR) model named Inversion Transformer-based Neural Ranking (ITNR). ITNR utilizes genomic features and a transformer architecture to decipher functional relationships and construct models that can predict patient-specific drug responses. Our experiments were conducted on three major drug response data sets, showing that ITNR reliably and consistently outperforms state-of-the-art LTR models.

Computational identification of natural senotherapeutic compounds that mimic dasatinib based on gene expression data

The major risk factor for chronic disease is chronological age, and age-related chronic diseases account for the majority of deaths worldwide. Targeting senescent cells that accumulate in disease-related tissues presents a strategy to reduce disease burden and to increase healthspan. The senolytic combination of the tyrosine-kinase inhibitor dasatinib and the flavonol quercetin is frequently used in clinical trials aiming to eliminate senescent cells. Here, our goal was to computationally identify natural senotherapeutic repurposing candidates that may substitute dasatinib based on their similarity in gene expression effects. The natural senolytic piperlongumine (a compound found in long pepper), and the natural senomorphics parthenolide, phloretin and curcumin (found in various edible plants) were identified as potential substitutes of dasatinib. The gene expression changes underlying the repositioning highlight apoptosis-related genes and pathways. The four compounds, and in particular the top-runner piperlongumine, may be combined with quercetin to obtain natural formulas emulating the dasatinib + quercetin formula.

Kinome-Wide Virtual Screening by Multi-Task Deep Learning

Deep learning is a machine learning technique to model high-level abstractions in data by utilizing a graph composed of multiple processing layers that experience various linear and non-linear transformations. This technique has been shown to perform well for applications in drug discovery, utilizing structural features of small molecules to predict activity. Here, we report a large-scale study to predict the activity of small molecules across the human kinome-a major family of drug targets, particularly in anti-cancer agents. While small-molecule kinase inhibitors exhibit impressive clinical efficacy in several different diseases, resistance often arises through adaptive kinome reprogramming or subpopulation diversity. Polypharmacology and combination therapies offer potential therapeutic strategies for patients with resistant diseases. Their development would benefit from a more comprehensive and dense knowledge of small-molecule inhibition across the human kinome. Leveraging over 650,000 bioactivity annotations for more than 300,000 small molecules, we evaluated multiple machine learning methods to predict the small-molecule inhibition of 342 kinases across the human kinome. Our results demonstrated that multi-task deep neural networks outperformed classical single-task methods, offering the potential for conducting large-scale virtual screening, predicting activity profiles, and bridging the gaps in the available data.

Standigm ASK™: knowledge graph and artificial intelligence platform applied to target discovery in idiopathic pulmonary fibrosis

Standigm ASK™ revolutionizes healthcare by addressing the critical challenge of identifying pivotal target genes in disease mechanisms-a fundamental aspect of drug development success. Standigm ASK™ integrates a unique combination of a heterogeneous knowledge graph (KG) database and an attention-based neural network model, providing interpretable subgraph evidence. Empowering users through an interactive interface, Standigm ASK™ facilitates the exploration of predicted results. Applying Standigm ASK™ to idiopathic pulmonary fibrosis (IPF), a complex lung disease, we focused on genes (AMFR, MDFIC and NR5A2) identified through KG evidence. In vitro experiments demonstrated their relevance, as TGFβ treatment induced gene expression changes associated with epithelial-mesenchymal transition characteristics. Gene knockdown reversed these changes, identifying AMFR, MDFIC and NR5A2 as potential therapeutic targets for IPF. In summary, Standigm ASK™ emerges as an innovative KG and artificial intelligence platform driving insights in drug target discovery, exemplified by the identification and validation of therapeutic targets for IPF.

Combined kinome inhibition states are predictive of cancer cell line sensitivity to kinase inhibitor combination therapies

Protein kinases are a primary focus in targeted therapy development for cancer, owing to their role as regulators in nearly all areas of cell life. Recent strategies targeting the kinome with combination therapies have shown promise, such as trametinib and dabrafenib in advanced melanoma, but empirical design for less characterized pathways remains a challenge. Computational combination screening is an attractive alternative, allowing in-silico filtering prior to experimental testing of drastically fewer leads, increasing efficiency and effectiveness of drug development pipelines. In this work, we generated combined kinome inhibition states of 40,000 kinase inhibitor combinations from kinobeads-based kinome profiling across 64 doses. We then integrated these with transcriptomics from CCLE to build machine learning models with elastic-net feature selection to predict cell line sensitivity across nine cancer types, with accuracy R2 ∼ 0.75-0.9. We then validated the model by using a PDX-derived TNBC cell line and saw good global accuracy (R2 ∼ 0.7) as well as high accuracy in predicting synergy using four popular metrics (R2 ∼ 0.9). Additionally, the model was able to predict a highly synergistic combination of trametinib and omipalisib for TNBC treatment, which incidentally was recently in phase I clinical trials. Our choice of tree-based models for greater interpretability allowed interrogation of highly predictive kinases in each cancer type, such as the MAPK, CDK, and STK kinases. Overall, these results suggest that kinome inhibition states of kinase inhibitor combinations are strongly predictive of cell line responses and have great potential for integration into computational drug screening pipelines. This approach may facilitate the identification of effective kinase inhibitor combinations and accelerate the development of novel cancer therapies, ultimately improving patient outcomes.

IUPHAR review - Data-driven computational drug repurposing approaches for opioid use disorder

Opioid Use Disorder (OUD) is a chronic and relapsing condition characterized by the misuse of opioid drugs, causing significant morbidity and mortality in the United States. Existing medications for OUD are limited, and there is an immediate need to discover treatments with enhanced safety and efficacy. Drug repurposing aims to find new indications for existing medications, offering a time-saving and cost-efficient alternative strategy to traditional drug discovery. Computational approaches have been developed to further facilitate the drug repurposing process. In this paper, we reviewed state-of-the-art data-driven computational drug repurposing approaches for OUD and discussed their advantages and potential challenges. We also highlighted promising repurposed candidate drugs for OUD that were identified by computational drug repurposing techniques and reviewed studies supporting their potential mechanisms of action in treating OUD.

Dark kinase annotation, mining, and visualization using the Protein Kinase Ontology

The Protein Kinase Ontology (ProKinO) is an integrated knowledge graph that conceptualizes the complex relationships among protein kinase sequence, structure, function, and disease in a human and machine-readable format. In this study, we have significantly expanded ProKinO by incorporating additional data on expression patterns and drug interactions. Furthermore, we have developed a completely new browser from the ground up to render the knowledge graph visible and interactive on the web. We have enriched ProKinO with new classes and relationships that capture information on kinase ligand binding sites, expression patterns, and functional features. These additions extend ProKinO's capabilities as a discovery tool, enabling it to uncover novel insights about understudied members of the protein kinase family. We next demonstrate the application of ProKinO. Specifically, through graph mining and aggregate SPARQL queries, we identify the p21-activated protein kinase 5 (PAK5) as one of the most frequently mutated dark kinases in human cancers with abnormal expression in multiple cancers, including a previously unappreciated role in acute myeloid leukemia. We have identified recurrent oncogenic mutations in the PAK5 activation loop predicted to alter substrate binding and phosphorylation. Additionally, we have identified common ligand/drug binding residues in PAK family kinases, underscoring ProKinO's potential application in drug discovery. The updated ontology browser and the addition of a web component, ProtVista, which enables interactive mining of kinase sequence annotations in 3D structures and Alphafold models, provide a valuable resource for the signaling community. The updated ProKinO database is accessible at https://prokino.uga.edu.

Integrated single-dose kinome profiling data is predictive of cancer cell line sensitivity to kinase inhibitors

Protein kinase activity forms the backbone of cellular information transfer, acting both individually and as part of a broader network, the kinome. Their central role in signaling leads to kinome dysfunction being a common driver of disease, and in particular cancer, where numerous kinases have been identified as having a causal or modulating role in tumor development and progression. As a result, the development of therapies targeting kinases has rapidly grown, with over 70 kinase inhibitors approved for use in the clinic and over double this number currently in clinical trials. Understanding the relationship between kinase inhibitor treatment and their effects on downstream cellular phenotype is thus of clear importance for understanding treatment mechanisms and streamlining compound screening in therapy development. In this work, we combine two large-scale kinome profiling data sets and use them to link inhibitor-kinome interactions with cell line treatment responses (AUC/IC50). We then built computational models on this data set that achieve a high degree of prediction accuracy (R2 of 0.7 and RMSE of 0.9) and were able to identify a set of well-characterized and understudied kinases that significantly affect cell responses. We further validated these models experimentally by testing predicted effects in breast cancer cell lines and extended the model scope by performing additional validation in patient-derived pancreatic cancer cell lines. Overall, these results demonstrate that broad quantification of kinome inhibition state is highly predictive of downstream cellular phenotypes.

Applying a Gene Reversal Rate Computational Methodology to Identify Drugs for a Rare Cancer: Inflammatory Breast Cancer

The aim of this study was to utilize a computational methodology based on Gene Reversal Rate (GRR) scoring to repurpose existing drugs for a rare and understudied cancer: inflammatory breast cancer (IBC). This method uses IBC-related gene expression signatures (GES) and drug-induced gene expression profiles from the LINCS database to calculate a GRR score for each candidate drug, and is based on the idea that a compound that can counteract gene expression changes of a disease may have potential therapeutic applications for that disease. Genes related to IBC with associated differential expression data (265 up-regulated and 122 down-regulated) were collated from PubMed-indexed publications. Drug-induced gene expression profiles were downloaded from the LINCS database and candidate drugs to treat IBC were predicted using their GRR scores. Thirty-two (32) drug perturbations that could potentially reverse the pre-compiled list of 297 IBC genes were obtained using the LINCS Canvas Browser (LCB) analysis. Binary combinations of the 32 perturbations were assessed computationally to identify combined perturbations with the highest GRR scores, and resulted in 131 combinations with GRR greater than 80%, that reverse up to 264 of the 297 genes in the IBC-GES. The top 35 combinations involve 20 unique individual drug perturbations, and 19 potential drug candidates. A comprehensive literature search confirmed 17 of the 19 known drugs as having either anti-cancer or anti-inflammatory activities. AZD-7545, BMS-754807, and nimesulide target known IBC relevant genes: PDK, Met, and COX, respectively. AG-14361, butalbital, and clobenpropit are known to be functionally relevant in DNA damage, cell cycle, and apoptosis, respectively. These findings support the use of the GRR approach to identify drug candidates and potential combination therapies that could be used to treat rare diseases such as IBC.

Drug Repurposing to Circumvent Immune Checkpoint Inhibitor Resistance in Cancer Immunotherapy

Immune checkpoint inhibitors (ICI) have achieved unprecedented clinical success in cancer treatment. However, drug resistance to ICI therapy is a major hurdle that prevents cancer patients from responding to the treatment or having durable disease control. Drug repurposing refers to the application of clinically approved drugs, with characterized pharmacological properties and known adverse effect profiles, to new indications. It has also emerged as a promising strategy to overcome drug resistance. In this review, we summarized the latest research about drug repurposing to overcome ICI resistance. Repurposed drugs work by either exerting immunostimulatory activities or abolishing the immunosuppressive tumor microenvironment (TME). Compared to the de novo drug design strategy, they provide novel and affordable treatment options to enhance cancer immunotherapy that can be readily evaluated in the clinic. Biomarkers are exploited to identify the right patient population to benefit from the repurposed drugs and drug combinations. Phenotypic screening of chemical libraries has been conducted to search for T-cell-modifying drugs. Genomics and integrated bioinformatics analysis, artificial intelligence, machine and deep learning approaches are employed to identify novel modulators of the immunosuppressive TME.

Unlocking therapeutic potential: integration of drug repurposing and immunotherapy for various disease targeting

Drug repurposing, also known as drug repositioning, entails the application of pre-approved or formerly assessed drugs having potentially functional therapeutic amalgams for curing various disorders or disease conditions distinctive from their original remedial indication. It has surfaced as a substitute for the development of drugs for treating cancer, cardiovascular diseases, neurodegenerative disorders, and various infectious diseases like Covid-19. Although the earlier lines of findings in this area were serendipitous, recent advancements are based on patient centered approaches following systematic, translational, drug targeting practices that explore pathophysiological ailment mechanisms. The presence of definite information and numerous records with respect to beneficial properties, harmfulness, and pharmacologic characteristics of repurposed drugs increase the chances of approval in the clinical trial stages. The last few years have showcased the successful emergence of repurposed drug immunotherapy in treating various diseases. In this light, the present review emphasises on incorporation of drug repositioning with Immunotherapy targeted for several disorders.

Combined kinome inhibition states are predictive of cancer cell line sensitivity to kinase inhibitor combination therapies

Protein kinases are a primary focus in targeted therapy development for cancer, owing to their role as regulators in nearly all areas of cell life. Kinase inhibitors are one of the fastest growing drug classes in oncology, but resistance acquisition to kinase-targeting monotherapies is inevitable due to the dynamic and interconnected nature of the kinome in response to perturbation. Recent strategies targeting the kinome with combination therapies have shown promise, such as the approval of Trametinib and Dabrafenib in advanced melanoma, but similar empirical combination design for less characterized pathways remains a challenge. Computational combination screening is an attractive alternative, allowing in-silico screening prior to in-vitro or in-vivo testing of drastically fewer leads, increasing efficiency and effectiveness of drug development pipelines. In this work, we generate combined kinome inhibition states of 40,000 kinase inhibitor combinations from kinobeads-based kinome profiling across 64 doses. We then integrated these with baseline transcriptomics from CCLE to build robust machine learning models to predict cell line sensitivity from NCI-ALMANAC across nine cancer types, with model accuracy R2 ~ 0.75-0.9 after feature selection using elastic-net regression. We further validated the model's ability to extend to real-world examples by using the best-performing breast cancer model to generate predictions for kinase inhibitor combination sensitivity and synergy in a PDX-derived TNBC cell line and saw reasonable global accuracy in our experimental validation (R2 ~ 0.7) as well as high accuracy in predicting synergy using four popular metrics (R2 ~ 0.9). Additionally, the model was able to predict a highly synergistic combination of Trametinib (MEK inhibitor) and Omipalisib (PI3K inhibitor) for TNBC treatment, which incidentally was recently in phase I clinical trials for TNBC. Our choice of tree-based models over networks for greater interpretability also allowed us to further interrogate which specific kinases were highly predictive of cell sensitivity in each cancer type, and we saw confirmatory strong predictive power in the inhibition of MAPK, CDK, and STK kinases. Overall, these results suggest that kinome inhibition states of kinase inhibitor combinations are strongly predictive of cell line responses and have great potential for integration into computational drug screening pipelines. This approach may facilitate the identification of effective kinase inhibitor combinations and accelerate the development of novel cancer therapies, ultimately improving patient outcomes.

Drug repurposing for Basal breast cancer subpopulations using modular network signatures

Breast cancer is characterized as being a heterogeneous pathology with a broad phenotype variability. Breast cancer subtypes have been developed in order to capture some of this heterogeneity. Each of these breast cancer subtypes, in turns retains varied characteristic features impacting diagnostic, prognostic and therapeutics. Basal breast tumors, in particular have been challenging in these regards. Basal breast cancer is often more aggressive, of rapid evolution and no tailor-made targeted therapies are available yet to treat it. Arguably, epigenetic variability is behind some of these intricacies. It is possible to further classify basal breast tumor in groups based on their non-coding transcriptome and methylome profiles. It is expected that these groups will have differences in survival as well as in sensitivity to certain classes of drugs. With this in mind, we implemented a computational learning approach to infer different subpopulations of basal breast cancer (from TCGA multi-omic data) based on their epigenetic signatures. Such epigenomic signatures were associated with different survival profiles; we then identified their associated gene co-expression network structure, extracted a signature based on modules within these networks, and use these signatures to find and prioritize drugs (in the LINCS dataset) that may be used to target these types of cancer. In this way we are introducing the analytical workflow for an epigenomic signature-based drug repurposing structure.

Combination of furosemide, gold, and dopamine as a potential therapy for breast cancer

Breast cancer is one of the leading causes of death in women worldwide. Initially, it develops in the epithelium of the ducts or lobules of the breast glandular tissues with limited growth and the potential to metastasize. It is a highly heterogeneous malignancy; however, the common molecular mechanisms could help identify new targeted drugs for treating its subtypes. This study uses computational drug repositioning approaches to explore fresh drug candidates for breast cancer treatment. We also implemented reversal gene expression and gene expression-based signatures to explore novel drug candidates computationally. The drug activity profiles and related gene expression changes were acquired from the DrugBank, PubChem, and LINCS databases, and then in silico drug screening, molecular dynamics (MD) simulation, replica exchange MD simulations, and simulated annealing molecular dynamics (SAMD) simulations were conducted to discover and verify the valid drug candidates. We have found that compounds like furosemide, gold, and dopamine showed significant outcomes. Furthermore, the expression of genes related to breast cancer was observed to be reversed by these shortlisted drugs. Therefore, we postulate that combining furosemide, gold, and dopamine would be a potential combination therapy measurement for breast cancer patients.

Pseudo-temporal dynamics of chemoresistant triple negative breast cancer cells reveal EGFR/HER2 inhibition as synthetic lethal during mid-neoadjuvant chemotherapy

In the absence of targetable hormonal axes, chemoresistance for triple-negative breast cancer (TNBC) often compromises patient outcomes. To investigate the underlying tumor dynamics, we performed trajectory analysis on the single-nuclei RNA-seq (snRNA-seq) of chemoresistant tumor clones during neoadjuvant chemotherapy (NAC). It revealed a common tumor trajectory across multiple patients with HER2-like expansions during NAC. Genome-wide CRISPR-Cas9 knock-out on mammary epithelial cells revealed chemosensitivity-promoting knock-outs were up-regulated along the tumor trajectory. Furthermore, we derived a consensus gene signature of TNBC chemoresistance by comparing the trajectory transcriptome with chemoresistant transcriptomes from TNBC cell lines and poor prognosis patient samples to predict FDA-approved drugs, including afatinib (pan-HER inhibitor), targeting the consensus signature. We validated the synergistic efficacy of afatinib and paclitaxel in chemoresistant TNBC cells and confirmed pharmacological suppression of the consensus signature. The study provides a dynamic model of chemoresistant tumor transcriptome, and computational framework for pharmacological intervention.

NeuroLINCS Proteomics: Defining human-derived iPSC proteomes and protein signatures of pluripotency

The National Institute of Health (NIH) Library of integrated network-based cellular signatures (LINCS) program is premised on the generation of a publicly available data resource of cell-based biochemical responses or "signatures" to genetic or environmental perturbations. NeuroLINCS uses human inducible pluripotent stem cells (hiPSCs), derived from patients and healthy controls, and differentiated into motor neuron cell cultures. This multi-laboratory effort strives to establish i) robust multi-omic workflows for hiPSC and differentiated neuronal cultures, ii) public annotated data sets and iii) relevant and targetable biological pathways of spinal muscular atrophy (SMA) and amyotrophic lateral sclerosis (ALS). Here, we focus on the proteomics and the quality of the developed workflow of hiPSC lines from 6 individuals, though epigenomics and transcriptomics data are also publicly available. Known and commonly used markers representing 73 proteins were reproducibly quantified with consistent expression levels across all hiPSC lines. Data quality assessments, data levels and metadata of all 6 genetically diverse human iPSCs analysed by DIA-MS are parsable and available as a high-quality resource to the public.

Drug repositioning prediction for psoriasis using the adverse event reporting database

Introduction

Inverse signals produced from disproportional analyses using spontaneous drug adverse event reports can be used for drug repositioning purposes. The purpose of this study is to predict drug candidates using a computational method that integrates reported drug adverse event data, disease-specific gene expression profiles, and drug-induced gene expression profiles.

Methods

Drug and adverse events from 2015 through 2020 were downloaded from the United States Food and Drug Administration Adverse Event Reporting System (FAERS). The reporting odds ratio (ROR), information component (IC) and empirical Bayes geometric mean (EBGM) were used to calculate the inverse signals. Psoriasis was selected as the target disease. Disease specific gene expression profiles were obtained by the meta-analysis of the Gene Expression Omnibus (GEO). The reverse gene expression scores were calculated using the Library of Integrated Network-based Cellular Signatures (LINCS) and their correlations with the inverse signals were obtained.

Results

Reversal genes and the candidate compounds were identified. Additionally, these correlations were validated using the relationship between the reverse gene expression scores and the half-maximal inhibitory concentration (IC50) values from the Chemical European Molecular Biology Laboratory (ChEMBL).

Conclusion

Inverse signals produced from a disproportional analysis can be used for drug repositioning and to predict drug candidates against psoriasis.

Navigating Transcriptomic Connectivity Mapping Workflows to Link Chemicals with Bioactivities

Screening new compounds for potential bioactivities against cellular targets is vital for drug discovery and chemical safety. Transcriptomics offers an efficient approach for assessing global gene expression changes, but interpreting chemical mechanisms from these data is often challenging. Connectivity mapping is a potential data-driven avenue for linking chemicals to mechanisms based on the observation that many biological processes are associated with unique gene expression signatures (gene signatures). However, mining the effects of a chemical on gene signatures for biological mechanisms is challenging because transcriptomic data contain thousands of noisy genes. New connectivity mapping approaches seeking to distinguish signal from noise continue to be developed, spurred by the promise of discovering chemical mechanisms, new drugs, and disease targets from burgeoning transcriptomic data. Here, we analyze these approaches in terms of diverse transcriptomic technologies, public databases, gene signatures, pattern-matching algorithms, and statistical evaluation criteria. To navigate the complexity of connectivity mapping, we propose a harmonized scheme to coherently organize and compare published workflows. We first standardize concepts underlying transcriptomic profiles and gene signatures based on various transcriptomic technologies such as microarrays, RNA-Seq, and L1000 and discuss the widely used data sources such as Gene Expression Omnibus, ArrayExpress, and MSigDB. Next, we generalize connectivity mapping as a pattern-matching task for finding similarity between a query (e.g., transcriptomic profile for new chemical) and a reference (e.g., gene signature of known target). Published pattern-matching approaches fall into two main categories: vector-based use metrics like correlation, Jaccard index, etc., and aggregation-based use parametric and nonparametric statistics (e.g., gene set enrichment analysis). The statistical methods for evaluating the performance of different approaches are described, along with comparisons reported in the literature on benchmark transcriptomic data sets. Lastly, we review connectivity mapping applications in toxicology and offer guidance on evaluating chemical-induced toxicity with concentration-response transcriptomic data. In addition to serving as a high-level guide and tutorial for understanding and implementing connectivity mapping workflows, we hope this review will stimulate new algorithms for evaluating chemical safety and drug discovery using transcriptomic data.

Drug repurposing using meta-analysis of gene expression in Alzheimer's disease

INTRODUCTION

Alzheimer's disease and other forms of dementia are disease that bring an increased global burden. However, the medicine developed to date remains limited. The purpose of this study is to predict drug repositioning candidates using a computational method that integrates gene expression profiles on Alzheimer's disease and compound-induced changes in gene expression levels.

METHODS

Gene expression data on Alzheimer's disease were obtained from the Gene Expression Omnibus (GEO) and we conducted a meta-analysis of their gene expression levels. The reverse scores of compound-induced gene expressions were computed based on the reversal relationship between disease and drug gene expression profiles.

RESULTS

Reversal genes and the candidate compounds were identified by the leave-one-out cross-validation procedure. Additionally, the half-maximal inhibitory concentration (IC50) values and the blood-brain barrier (BBB) permeability of candidate compounds were obtained from ChEMBL and PubChem, respectively.

CONCLUSION

New therapeutic target genes and drug candidates against Alzheimer's disease were identified by means of drug repositioning.

CORN-Condition Orientated Regulatory Networks: bridging conditions to gene networks

A transcriptional regulatory network (TRN) is a collection of transcription regulators with their associated downstream genes, which is highly condition-specific. Understanding how cell states can be programmed through small molecules/drugs or conditions by modulating the whole gene expression system granted us the potential to amend abnormal cells and cure diseases. Condition Orientated Regulatory Networks (CORN, https://qinlab.sysu.edu.cn/home) is a library of condition (small molecule/drug treatments and gene knockdowns)-based transcriptional regulatory sub-networks (TRSNs) that come with an online TRSN matching tool. It allows users to browse condition-associated TRSNs or match those TRSNs by inputting transcriptomic changes of interest. CORN utilizes transcriptomic changes data after specific conditional treatment in cells, and in vivo transcription factor (TF) binding data in cells, by combining TF binding information and calculations of significant expression alterations of TFs and genes after the conditional treatments, TRNs under the effect of different conditions were constructed. In short, CORN associated 1805 different types of specific conditions (small molecule/drug treatments and gene knockdowns) to 9553 TRSNs in 25 human cell lines, involving 204TFs. By linking and curating specific conditions to responsive TRNs, the scientific community can now perceive how TRNs are altered and controlled by conditions alone in an organized manner for the first time. This study demonstrated with examples that CORN can aid the understanding of molecular pathology, pharmacology and drug repositioning, and screened drugs with high potential for cancer and coronavirus disease 2019 (COVID-19) treatments.

Disulfiram in glioma: Literature review of drug repurposing

Gliomas are the most common malignant brain tumors. High-grade gliomas, represented by glioblastoma multiforme (GBM), have a poor prognosis and are prone to recurrence. The standard treatment strategy is tumor removal combined with radiotherapy and chemotherapy, such as temozolomide (TMZ). However, even after conventional treatment, they still have a high recurrence rate, resulting in an increasing demand for effective anti-glioma drugs. Drug repurposing is a method of reusing drugs that have already been widely approved for new indication. It has the advantages of reduced research cost, safety, and increased efficiency. Disulfiram (DSF), originally approved for alcohol dependence, has been repurposed for adjuvant chemotherapy in glioma. This article reviews the drug repurposing method and the progress of research on disulfiram reuse for glioma treatment.

Strongylopus grayii tadpole blastema extract exerts cytotoxic effects on embryonal rhabdomyosarcoma cells

Amphibians have regenerative capacity and are resistant to developing cancer. This suggests that the developing blastema, located at the tissue regeneration site, may secrete anti-cancer factors. Here, we investigate the anti-cancer potential of tadpole tail blastema extracts (TAD) from the stream frog, Strongylopus grayii, in embryonal rhabdomyosarcoma (ERMS) cells. ERMS originates in skeletal muscle tissue and is a common pediatric soft tissue sarcoma. We show using MTT assays that TAD inhibited ERMS cell viability in a concentration-dependent manner, and phase contrast/fluorescent microscopy revealed that it induced morphological markers of senescence and apoptosis. Western blotting showed that this was associated with DNA damage (γH2AX) and activation of the p38/MAPK stress signaling pathway as well as molecular markers of senescence (p16^INK4a), apoptosis (cleaved PARP), and inhibition of cell cycle promoters (cyclin A, CDK2, and cyclin B1). Furthermore, proteomics followed by gene ontology analyses showed that TAD treatment inhibited known tumor promoters and proteins required for cancer cell survival. Lastly, using the LINCS drug perturbation library, we show that there is an overlap between the proteomics signature induced by TAD and common anti-cancer drugs. Taken together, this study provides novel evidence that TAD exhibits cytotoxicity in ERMS cells.

Connecting omics signatures and revealing biological mechanisms with iLINCS

There are only a few platforms that integrate multiple omics data types, bioinformatics tools, and interfaces for integrative analyses and visualization that do not require programming skills. Here we present iLINCS ( http://ilincs.org ), an integrative web-based platform for analysis of omics data and signatures of cellular perturbations. The platform facilitates mining and re-analysis of the large collection of omics datasets (>34,000), pre-computed signatures (>200,000), and their connections, as well as the analysis of user-submitted omics signatures of diseases and cellular perturbations. iLINCS analysis workflows integrate vast omics data resources and a range of analytics and interactive visualization tools into a comprehensive platform for analysis of omics signatures. iLINCS user-friendly interfaces enable execution of sophisticated analyses of omics signatures, mechanism of action analysis, and signature-driven drug repositioning. We illustrate the utility of iLINCS with three use cases involving analysis of cancer proteogenomic signatures, COVID 19 transcriptomic signatures and mTOR signaling.

Improved prediction of gene expression through integrating cell signalling models with machine learning

BACKGROUND

A key problem in bioinformatics is that of predicting gene expression levels. There are two broad approaches: use of mechanistic models that aim to directly simulate the underlying biology, and use of machine learning (ML) to empirically predict expression levels from descriptors of the experiments. There are advantages and disadvantages to both approaches: mechanistic models more directly reflect the underlying biological causation, but do not directly utilize the available empirical data; while ML methods do not fully utilize existing biological knowledge.

RESULTS

Here, we investigate overcoming these disadvantages by integrating mechanistic cell signalling models with ML. Our approach to integration is to augment ML with similarity features (attributes) computed from cell signalling models. Seven sets of different similarity feature were generated using graph theory. Each set of features was in turn used to learn multi-target regression models. All the features have significantly improved accuracy over the baseline model - without the similarity features. Finally, the seven multi-target regression models were stacked together to form an overall prediction model that was significantly better than the baseline on 95% of genes on an independent test set. The similarity features enable this stacking model to provide interpretable knowledge about cancer, e.g. the role of ERBB3 in the MCF7 breast cancer cell line.

CONCLUSION

Integrating mechanistic models as graphs helps to both improve the predictive results of machine learning models, and to provide biological knowledge about genes that can help in building state-of-the-art mechanistic models.

COVID-19-specific transcriptomic signature detectable in blood across multiple cohorts

The coronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is spreading across the world despite vast global vaccination efforts. Consequently, many studies have looked for potential human host factors and immune mechanisms associated with the disease. However, most studies have focused on comparing COVID-19 patients to healthy controls, while fewer have elucidated the specific host factors distinguishing COVID-19 from other infections. To discover genes specifically related to COVID-19, we reanalyzed transcriptome data from nine independent cohort studies, covering multiple infections, including COVID-19, influenza, seasonal coronaviruses, and bacterial pneumonia. The identified COVID-19-specific signature consisted of 149 genes, involving many signals previously associated with the disease, such as induction of a strong immunoglobulin response and hemostasis, as well as dysregulation of cell cycle-related processes. Additionally, potential new gene candidates related to COVID-19 were discovered. To facilitate exploration of the signature with respect to disease severity, disease progression, and different cell types, we also offer an online tool for easy visualization of the selected genes across multiple datasets at both bulk and single-cell levels.

Disruption of cancer cell functions by task-specific drug perturbations

Cancer expands clonally, capitalizing on the variations between growing cells. Cancer cells specialize in one or more functions to gain an advantage. This study examined the prediction that cells would be vulnerable to drugs that perturb their specific tasks. We analyzed the correlation between gene expression and the response to drug perturbations in different cancer cells. Next, we assigned every cancer cell to an archetype based on gene expression. Finally, we calculated the enrichment of the cancer hallmark gene sets in each cell, archetypes, and response to drug treatment. We found that the extremes of gene expression were susceptible to change in response to perturbations. This correlation predicted the growth rate inhibition of breast cancer cells. Cancer hallmarks were enriched differently in the archetypes, and this enrichment predicted the cell’s response to perturbations. We present evidence that specialized cancer cells are sensitive to compounds that perturb their tasks.

Computational approaches for direct cell reprogramming: from the bulk omics era to the single cell era

Recent advances in direct cell reprogramming have made possible the conversion of one cell type to another cell type, offering a potential cell-based treatment to many major diseases. Despite much attention, substantial roadblocks remain including the inefficiency in the proportion of reprogrammed cells of current experiments, and the requirement of a significant amount of time and resources. To this end, several computational algorithms have been developed with the goal of guiding the hypotheses to be experimentally validated. These approaches can be broadly categorized into two main types: transcription factor identification methods which aim to identify candidate transcription factors for a desired cell conversion, and transcription factor perturbation methods which aim to simulate the effect of a transcription factor perturbation on a cell state. The transcription factor perturbation methods can be broken down into Boolean networks, dynamical systems and regression models. We summarize the contributions and limitations of each method and discuss the innovation that single cell technologies are bringing to these approaches and we provide a perspective on the future direction of this field.

SigCom LINCS: data and metadata search engine for a million gene expression signatures

Millions of transcriptome samples were generated by the Library of Integrated Network-based Cellular Signatures (LINCS) program. When these data are processed into searchable signatures along with signatures extracted from Genotype-Tissue Expression (GTEx) and Gene Expression Omnibus (GEO), connections between drugs, genes, pathways and diseases can be illuminated. SigCom LINCS is a webserver that serves over a million gene expression signatures processed, analyzed, and visualized from LINCS, GTEx, and GEO. SigCom LINCS is built with Signature Commons, a cloud-agnostic skeleton Data Commons with a focus on serving searchable signatures. SigCom LINCS provides a rapid signature similarity search for mimickers and reversers given sets of up and down genes, a gene set, a single gene, or any search term. Additionally, users of SigCom LINCS can perform a metadata search to find and analyze subsets of signatures and find information about genes and drugs. SigCom LINCS is findable, accessible, interoperable, and reusable (FAIR) with metadata linked to standard ontologies and vocabularies. In addition, all the data and signatures within SigCom LINCS are available via a well-documented API. In summary, SigCom LINCS, available at https://maayanlab.cloud/sigcom-lincs, is a rich webserver resource for accelerating drug and target discovery in systems pharmacology.

Getting Started with LINCS Datasets and Tools

The Library of Integrated Network-based Cellular Signatures (LINCS) was an NIH Common Fund program that aimed to expand our knowledge about human cellular responses to chemical, genetic, and microenvironment perturbations. Responses to perturbations were measured by transcriptomics, proteomics, cellular imaging, and other high content assays. The second phase of the LINCS program, which lasted 7 years, involved the engagement of six data and signature generation centers (DSGCs) and one data coordination and integration center (DCIC). The DSGCs and the DCIC developed several digital resources, including tools, databases, and workflows that aim to facilitate the use of the LINCS data and integrate this data with other publicly available data. The digital resources developed by the DSGCs and the DCIC can be used to gain new biological and pharmacological insights that can lead to the development of novel therapeutics. This protocol provides step-by-step instructions for processing the LINCS data into signatures, and utilizing the digital resources developed by the LINCS consortia for hypothesis generation and knowledge discovery. © 2022 The Authors. Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: Navigating L1000 tools and data in CLUE.io Basic Protocol 2: Computing signatures from the L1000 data with the CD method Basic Protocol 3: Analyzing lists of differentially expressed genes and querying them against the L1000 data with BioJupies and the Bulk RNA-seq Appyter Basic Protocol 4: Utilizing the L1000FWD resource for drug discovery Basic Protocol 5: KINOMEscan and the KINOMEscan Appyter Basic Protocol 6: LINCS P100 and GCP Proteomics Assays Basic Protocol 7: The LINCS Joint Project (LJP) Basic Protocol 8: The LINCS Data Portals and SigCom LINCS Basic Protocol 9: Creating and analyzing signatures with iLINCS.

Integrating knowledge and omics to decipher mechanisms via large-scale models of signaling networks

Signal transduction governs cellular behavior, and its dysregulation often leads to human disease. To understand this process, we can use network models based on prior knowledge, where nodes represent biomolecules, usually proteins, and edges indicate interactions between them. Several computational methods combine untargeted omics data with prior knowledge to estimate the state of signaling networks in specific biological scenarios. Here, we review, compare, and classify recent network approaches according to their characteristics in terms of input omics data, prior knowledge and underlying methodologies. We highlight existing challenges in the field, such as the general lack of ground truth and the limitations of prior knowledge. We also point out new omics developments that may have a profound impact, such as single-cell proteomics or large-scale profiling of protein conformational changes. We provide both an introduction for interested users seeking strategies to study cell signaling on a large scale and an update for seasoned modelers.

Imbalanced regression using regressor-classifier ensembles

We present an extension to the federated ensemble regression using classification algorithm, an ensemble learning algorithm for regression problems which leverages the distribution of the samples in a learning set to achieve improved performance. We evaluated the extension using four classifiers and four regressors, two discretizers, and 119 responses from a wide variety of datasets in different domains. Additionally, we compared our algorithm to two resampling methods aimed at addressing imbalanced datasets. Our results show that the proposed extension is highly unlikely to perform worse than the base case, and on average outperforms the two resampling methods with significant differences in performance.

Recent Advances in Cancer Drug Discovery Through the Use of Phenotypic Reporter Systems, Connectivity Mapping, and Pooled CRISPR Screening

Multi-omic approaches offer an unprecedented overview of the development, plasticity, and resistance of cancer. However, the translation from anti-cancer compounds identified in vitro to clinically active drugs have a notoriously low success rate. Here, we review how technical advances in cell culture, robotics, computational biology, and development of reporter systems have transformed drug discovery, enabling screening approaches tailored to clinically relevant functional readouts (e.g., bypassing drug resistance). Illustrating with selected examples of “success stories,” we describe the process of phenotype-based high-throughput drug screening to target malignant cells or the immune system. Second, we describe computational approaches that link transcriptomic profiling of cancers with existing pharmaceutical compounds to accelerate drug repurposing. Finally, we review how CRISPR-based screening can be applied for the discovery of mechanisms of drug resistance and sensitization. Overall, we explore how the complementary strengths of each of these approaches allow them to transform the paradigm of pre-clinical drug development.

Looking at the BiG Picture: Incorporating bipartite graphs in drug response prediction

MOTIVATION

The increasing number of publicly available databases containing drugs' chemical structures, their response in cell lines, and molecular profiles of the cell lines has garnered attention to the problem of drug response prediction. However, many existing methods do not fully leverage the information that is shared among cell lines and drugs with similar structure. As such, drug similarities in terms of cell line responses and chemical structures could prove to be useful in forming drug representations to improve drug response prediction accuracy.

RESULTS

We present two deep learning approaches, BiG-DRP and BiG-DRP+, for drug response prediction. Our models take advantage of the drugs' chemical structure and the underlying relationships of drugs and cell lines through a bipartite graph and a heterogenous graph convolutional network that incorporate sensitive and resistant cell line information in forming drug representations. Evaluation of our methods and other state-of-the-art models in different scenarios shows that incorporating this bipartite graph significantly improves the prediction performance. Additionally, genes that contribute significantly to the performance of our models also point to important biological processes and signaling pathways. Analysis of predicted drug response of patients' tumors using our model revealed important associations between mutations and drug sensitivity, illustrating the utility of our model in pharmacogenomics studies.

AVAILABILITY AND IMPLEMENTATION

An implementation of the algorithms in Python is provided in https://github.com/ddhostallero/BiG-DRP.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Drug target inference by mining transcriptional data using a novel graph convolutional network framework

A fundamental challenge that arises in biomedicine is the need to characterize compounds in a relevant cellular context in order to reveal potential on-target or off-target effects. Recently, the fast accumulation of gene transcriptional profiling data provides us an unprecedented opportunity to explore the protein targets of chemical compounds from the perspective of cell transcriptomics and RNA biology. Here, we propose a novel Siamese spectral-based graph convolutional network (SSGCN) model for inferring the protein targets of chemical compounds from gene transcriptional profiles. Although the gene signature of a compound perturbation only provides indirect clues of the interacting targets, and the biological networks under different experiment conditions further complicate the situation, the SSGCN model was successfully trained to learn from known compound-target pairs by uncovering the hidden correlations between compound perturbation profiles and gene knockdown profiles. On a benchmark set and a large time-split validation dataset, the model achieved higher target inference accuracy as compared to previous methods such as Connectivity Map. Further experimental validations of prediction results highlight the practical usefulness of SSGCN in either inferring the interacting targets of compound, or reversely, in finding novel inhibitors of a given target of interest.

Validating Small Molecule Chemical Probes for Biological Discovery

Small molecule chemical probes are valuable tools for interrogating protein biological functions and relevance as a therapeutic target. Rigorous validation of chemical probe parameters such as cellular potency and selectivity is critical to unequivocally linking biological and phenotypic data resulting from treatment with a chemical probe to the function of a specific target protein. A variety of modern technologies are available to evaluate cellular potency and selectivity, target engagement, and functional response biomarkers of chemical probe compounds. Here, we review these technologies and the rationales behind using them for the characterization and validation of chemical probes. In addition, large-scale phenotypic characterization of chemical probes through chemical genetic screening is increasingly leading to a wealth of information on the cellular pharmacology and disease involvement of potential therapeutic targets. Extensive compound validation approaches and integration of phenotypic information will lay foundations for further use of chemical probes in biological discovery. Expected final online publication date for the Annual Review of Biochemistry, Volume 91 is June 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

secDrug: a pipeline to discover novel drug combinations to kill drug-resistant multiple myeloma cells using a greedy set cover algorithm and single-cell multi-omics

Multiple myeloma, the second-most common hematopoietic malignancy in the United States, still remains an incurable disease with dose-limiting toxicities and resistance to primary drugs like proteasome inhibitors (PIs) and Immunomodulatory drugs (IMiDs).We have created a computational pipeline that uses pharmacogenomics data-driven optimization-regularization/greedy algorithm to predict novel drugs ("secDrugs") against drug-resistant myeloma. Next, we used single-cell RNA sequencing (scRNAseq) as a screening tool to predict top combination candidates based on the enrichment of target genes. For in vitro validation of secDrugs, we used a panel of human myeloma cell lines representing drug-sensitive, innate/refractory, and acquired/relapsed PI- and IMiD resistance. Next, we performed single-cell proteomics (CyTOF or Cytometry time of flight) in patient-derived bone marrow cells (ex vivo), genome-wide transcriptome analysis (bulk RNA sequencing), and functional assays like CRISPR-based gene editing to explore molecular pathways underlying secDrug efficacy and drug synergy. Finally, we developed a universally applicable R-software package for predicting novel secondary therapies in chemotherapy-resistant cancers that outputs a list of the top drug combination candidates with rank and confidence scores.Thus, using 17AAG (HSP90 inhibitor) + FK866 (NAMPT inhibitor) as proof of principle secDrugs, we established a novel pipeline to introduce several new therapeutic options for the management of PI and IMiD-resistant myeloma.

A survey of optimal strategy for signature-based drug repositioning and an application to liver cancer

Pharmacologic perturbation projects, such as Connectivity Map (CMap) and Library of Integrated Network-based Cellular Signatures (LINCS), have produced many perturbed expression data, providing enormous opportunities for computational therapeutic discovery. However, there is no consensus on which methodologies and parameters are the most optimal to conduct such analysis. Aiming to fill this gap, new benchmarking standards were developed to quantitatively evaluate drug retrieval performance. Investigations of potential factors influencing drug retrieval were conducted based on these standards. As a result, we determined an optimal approach for LINCS data-based therapeutic discovery. With this approach, homoharringtonine (HHT) was identified to be a candidate agent with potential therapeutic and preventive effects on liver cancer. The antitumor and antifibrotic activity of HHT was validated experimentally using subcutaneous xenograft tumor model and carbon tetrachloride (CCL₄)-induced liver fibrosis model, demonstrating the reliability of the prediction results. In summary, our findings will not only impact the future applications of LINCS data but also offer new opportunities for therapeutic intervention of liver cancer.

Drug repurposing for cancer therapy in the era of precision medicine

Drug repurposing refers to the identification of clinically approved drugs, with the known safety profiles and defined pharmacokinetic properties, to new indications. Despite the advances in oncology research, cancers are still associated with the most unmet medical needs. Drug repurposing has emerged as a useful approach for the search for effective and durable cancer treatment. It may also represent a promising strategy to facilitate precision cancer treatment and to overcome drug resistance. The repurposing of non-cancer drugs for precision oncology effectively extends the inventory of actionable molecular targets and thus increases the number of patients who may benefit from precision cancer treatment. In cancer types where genetic heterogeneity is so high that it is not feasible to identify strong repurposed drug candidates for standard treatment, the precision oncology approach offers individual patients access to novel treatment options. For repurposed candidates with low potency, a combination of multiple repurposed drugs may produce a synergistic therapeutic effect. Precautions should be taken when combining repurposed drugs with anticancer agents to avoid detrimental drug-drug interactions and unwanted side effects. New multifactorial data analysis and artificial intelligence methods are needed to untangle the complex association of molecular signatures influencing specific cancer subtypes to facilitate drug repurposing in precision oncology.

A cross-study analysis of drug response prediction in cancer cell lines

To enable personalized cancer treatment, machine learning models have been developed to predict drug response as a function of tumor and drug features. However, most algorithm development efforts have relied on cross-validation within a single study to assess model accuracy. While an essential first step, cross-validation within a biological data set typically provides an overly optimistic estimate of the prediction performance on independent test sets. To provide a more rigorous assessment of model generalizability between different studies, we use machine learning to analyze five publicly available cell line-based data sets: National Cancer Institute 60, ancer Therapeutics Response Portal (CTRP), Genomics of Drug Sensitivity in Cancer, Cancer Cell Line Encyclopedia and Genentech Cell Line Screening Initiative (gCSI). Based on observed experimental variability across studies, we explore estimates of prediction upper bounds. We report performance results of a variety of machine learning models, with a multitasking deep neural network achieving the best cross-study generalizability. By multiple measures, models trained on CTRP yield the most accurate predictions on the remaining testing data, and gCSI is the most predictable among the cell line data sets included in this study. With these experiments and further simulations on partial data, two lessons emerge: (1) differences in viability assays can limit model generalizability across studies and (2) drug diversity, more than tumor diversity, is crucial for raising model generalizability in preclinical screening.

A Multiparametric Pharmacogenomic Strategy for Drug Repositioning predicts Therapeutic Efficacy for Glioblastoma Cell Lines

Background

Poor prognosis of glioblastoma patients and the extensive heterogeneity of glioblastoma at both the molecular and cellular level necessitates developing novel individualized treatment modalities via genomics-driven approaches.

Methods

This study leverages numerous pharmacogenomic and tissue databases to examine drug repositioning for glioblastoma. RNAseq of glioblastoma tumor samples from The Cancer Genome Atlas (TCGA, n=117) were compared to “normal” frontal lobe samples from Genotype-Tissue Expression Portal (GTEX, n=120) to find differentially expressed genes (DEGs). Using compound-gene expression data and drug activity data from the Library of Integrated Network-Based Cellular Signatures (LINCS, n=66,512 compounds) CCLE (71 glioma cell lines), and Chemical European Molecular Biology Laboratory (ChEMBL) platforms, we employed a summarized reversal gene expression metric (sRGES) to “reverse” the resultant disease signature for GBM and its subtypes. A multi-parametric strategy was employed to stratify compounds capable of blood brain barrier penetrance with a favorable pharmacokinetic profile (CNS-MPO).

Results

Significant correlations were identified between sRGES and drug efficacy in GBM cell lines in both ChEMBL(r=0.37,p<.001) and Cancer Therapeutic Response Portal (CTRP) databases (r=0.35, p<0.001). Our multiparametric algorithm identified two classes of drugs with highest sRGES and CNS-MPO: HDAC inhibitors (vorinostat and entinostat) and topoisomerase inhibitors suitable for drug repurposing.

Conclusions

Our studies suggest that reversal of glioblastoma disease signature correlates with drug potency for various GBM subtypes. This multiparametric approach may set the foundation for an early-phase personalized -omics clinical trial for glioblastoma by effectively identifying drugs that are capable of reversing the disease signature and have favorable pharmacokinetic and safety profiles.

Glutamine-fructose-6-phosphate transaminase 2 (GFPT2) is upregulated in breast epithelial-mesenchymal transition and responds to oxidative stress

Breast cancer cells that have undergone partial epithelial–mesenchymal transition (EMT) are believed to be more invasive than cells that have completed EMT. To study metabolic reprogramming in different mesenchymal states, we analyzed protein expression following EMT in the breast epithelial cell model D492 with single-shot LFQ supported by a SILAC proteomics approach. The D492 EMT cell model contains three cell lines: the epithelial D492 cells, the mesenchymal D492M cells, and a partial mesenchymal, tumorigenic variant of D492 that overexpresses the oncogene HER2. The analysis classified the D492 and D492M cells as basal-like and D492HER2 as claudin-low. Comparative analysis of D492 and D492M to tumorigenic D492HER2 differentiated metabolic markers of migration from those of invasion. Glutamine-fructose-6-phosphate transaminase 2 (GFPT2) was one of the top dysregulated enzymes in D492HER2. Gene expression analysis of the cancer genome atlas showed that GFPT2 expression was a characteristic of claudin-low breast cancer. siRNA-mediated knockdown of GFPT2 influenced the EMT marker vimentin and both cell growth and invasion in vitro and was accompanied by lowered metabolic flux through the hexosamine biosynthesis pathway (HBP). Knockdown of GFPT2 decreased cystathionine and sulfide:quinone oxidoreductase (SQOR) in the transsulfuration pathway that regulates H₂S production and mitochondrial homeostasis. Moreover, GFPT2 was within the regulation network of insulin and EGF, and its expression was regulated by reduced glutathione (GSH) and suppressed by the oxidative stress regulator GSK3-β. Our results demonstrate that GFPT2 controls growth and invasion in the D492 EMT model, is a marker for oxidative stress, and associated with poor prognosis in claudin-low breast cancer.

•

GFPT2 is upregulated following EMT.

•

GFPT2 is a marker for claudin-low breast cancer.

•

GFPT2 affects vimentin, cell proliferation, and cell invasion.

•

GFPT2 responds to oxidative stress.

•

GFPT2 is regulated by insulin and EGF.

Transformational machine learning: Learning how to learn from many related scientific problems

Machine learning (ML) is the branch of artificial intelligence (AI) that develops computational systems that learn from experience. In supervised ML, the ML system generalizes from labelled examples to learn a model that can predict the labels of unseen examples. Examples are generally represented using features that directly describe the examples. For instance, in drug design, ML uses features that describe molecular shape and so on. In cases where there are multiple related ML problems, it is possible to use a different type of feature: predictions made about the examples by ML models learned on other problems. We call this transformational ML. We show that this results in better predictions and improved understanding when applied to scientific problems.

Almost all machine learning (ML) is based on representing examples using intrinsic features. When there are multiple related ML problems (tasks), it is possible to transform these features into extrinsic features by first training ML models on other tasks and letting them each make predictions for each example of the new task, yielding a novel representation. We call this transformational ML (TML). TML is very closely related to, and synergistic with, transfer learning, multitask learning, and stacking. TML is applicable to improving any nonlinear ML method. We tested TML using the most important classes of nonlinear ML: random forests, gradient boosting machines, support vector machines, k-nearest neighbors, and neural networks. To ensure the generality and robustness of the evaluation, we utilized thousands of ML problems from three scientific domains: drug design, predicting gene expression, and ML algorithm selection. We found that TML significantly improved the predictive performance of all the ML methods in all the domains (4 to 50% average improvements) and that TML features generally outperformed intrinsic features. Use of TML also enhances scientific understanding through explainable ML. In drug design, we found that TML provided insight into drug target specificity, the relationships between drugs, and the relationships between target proteins. TML leads to an ecosystem-based approach to ML, where new tasks, examples, predictions, and so on synergistically interact to improve performance. To contribute to this ecosystem, all our data, code, and our ∼50,000 ML models have been fully annotated with metadata, linked, and openly published using Findability, Accessibility, Interoperability, and Reusability principles (∼100 Gbytes).