Elucidating the modes of action for bioactive compounds in a cell-specific manner by large-scale chemically-induced transcriptomics

Application of GWAS summary data and drug-induced gene expression profiles of neural progenitor cells in psychiatric drug prioritization analysis

Common psychiatric disorders constitute one of the most substantial healthcare burdens worldwide. However, drug development in psychiatry remains hampered partially due to the lack of approaches to estimating drugs that can simultaneously modulate the expression of a nontrivial fraction of disease susceptibility genes. We proposed a new drug prioritization strategy under the framework of our previously proposed phenotype-associated tissues estimation approach (DESE) by investigating the drugs' selective perturbation effect on disease susceptibility genes. Based on the genome-wide association study summary data and drug-induced gene expression profiles of neural progenitor cells, we applied this strategy to prioritize candidate drugs for schizophrenia, depression and bipolar I disorder and identified several known therapeutic drugs among the top-ranked drug candidates. Also, our results revealed that the disease susceptibility genes involved in the selective gene perturbation analysis were enriched with many biologically sensible function terms and interacted with known therapeutic drugs. Our results suggested that selective gene perturbation analysis could be a promising starting point to prioritize biologically sensible drug candidates under the "one drug, multiple targets" paradigm for the drug development of common psychiatric disorders.

AutoTransOP: translating omics signatures without orthologue requirements using deep learning

The development of therapeutics and vaccines for human diseases requires a systematic understanding of human biology. Although animal and in vitro culture models can elucidate some disease mechanisms, they typically fail to adequately recapitulate human biology as evidenced by the predominant likelihood of clinical trial failure. To address this problem, we developed AutoTransOP, a neural network autoencoder framework, to map omics profiles from designated species or cellular contexts into a global latent space, from which germane information for different contexts can be identified without the typically imposed requirement of matched orthologues. This approach was found in general to perform at least as well as current alternative methods in identifying animal/culture-specific molecular features predictive of other contexts-most importantly without requiring homology matching. For an especially challenging test case, we successfully applied our framework to a set of inter-species vaccine serology studies, where 1-to-1 mapping between human and non-human primate features does not exist.

A polo-like kinase inhibitor identified by computational repositioning attenuates pulmonary fibrosis

BACKGROUND

Idiopathic pulmonary fibrosis (IPF) is a fatal fibrotic lung disease with few effective therapeutic options. Recently, drug repositioning, which involves identifying novel therapeutic potentials for existing drugs, has been popularized as a new approach for the development of novel therapeutic reagents. However, this approach has not yet been fully utilized in the field of pulmonary fibrosis.

METHODS

The present study identified novel therapeutic options for pulmonary fibrosis using a systematic computational approach for drug repositioning based on integration of public gene expression signatures of drug and diseases (in silico screening approach).

RESULTS

Among the top compounds predicted to be therapeutic for IPF by the in silico approach, we selected BI2536, a polo-like kinase (PLK) 1/2 inhibitor, as a candidate for treating pulmonary fibrosis using an in silico analysis. However, BI2536 accelerated mortality and weight loss rate in an experimental mouse model of pulmonary fibrosis. Because immunofluorescence staining revealed that PLK1 expression was dominant in myofibroblasts while PLK2 expression was dominant in lung epithelial cells, we next focused on the anti-fibrotic effect of the selective PLK1 inhibitor GSK461364. Consequently, GSK461364 attenuated pulmonary fibrosis with acceptable mortality and weight loss in mice.

CONCLUSIONS

These findings suggest that targeting PLK1 may be a novel therapeutic approach for pulmonary fibrosis by inhibiting lung fibroblast proliferation without affecting lung epithelial cells. In addition, while in silico screening is useful, it is essential to fully determine the biological activities of candidates by wet-lab validation studies.

Benchmarking causal reasoning algorithms for gene expression-based compound mechanism of action analysis

BACKGROUND

Elucidating compound mechanism of action (MoA) is beneficial to drug discovery, but in practice often represents a significant challenge. Causal Reasoning approaches aim to address this situation by inferring dysregulated signalling proteins using transcriptomics data and biological networks; however, a comprehensive benchmarking of such approaches has not yet been reported. Here we benchmarked four causal reasoning algorithms (SigNet, CausalR, CausalR ScanR and CARNIVAL) with four networks (the smaller Omnipath network vs. 3 larger MetaBase™ networks), using LINCS L1000 and CMap microarray data, and assessed to what extent each factor dictated the successful recovery of direct targets and compound-associated signalling pathways in a benchmark dataset comprising 269 compounds. We additionally examined impact on performance in terms of the functions and roles of protein targets and their connectivity bias in the prior knowledge networks.

RESULTS

According to statistical analysis (negative binomial model), the combination of algorithm and network most significantly dictated the performance of causal reasoning algorithms, with the SigNet recovering the greatest number of direct targets. With respect to the recovery of signalling pathways, CARNIVAL with the Omnipath network was able to recover the most informative pathways containing compound targets, based on the Reactome pathway hierarchy. Additionally, CARNIVAL, SigNet and CausalR ScanR all outperformed baseline gene expression pathway enrichment results. We found no significant difference in performance between L1000 data or microarray data, even when limited to just 978 'landmark' genes. Notably, all causal reasoning algorithms also outperformed pathway recovery based on input DEGs, despite these often being used for pathway enrichment. Causal reasoning methods performance was somewhat correlated with connectivity and biological role of the targets.

CONCLUSIONS

Overall, we conclude that causal reasoning performs well at recovering signalling proteins related to compound MoA upstream from gene expression changes by leveraging prior knowledge networks, and that the choice of network and algorithm has a profound impact on the performance of causal reasoning algorithms. Based on the analyses presented here this is true for both microarray-based gene expression data as well as those based on the L1000 platform.

In silico prediction and biological assessment of novel angiogenesis modulators from traditional Chinese medicine

Uncontrolled angiogenesis is a common denominator underlying many deadly and debilitating diseases such as myocardial infarction, chronic wounds, cancer, and age-related macular degeneration. As the current range of FDA-approved angiogenesis-based medicines are far from meeting clinical demands, the vast reserve of natural products from traditional Chinese medicine (TCM) offers an alternative source for developing pro-angiogenic or anti-angiogenic modulators. Here, we investigated 100 traditional Chinese medicine-derived individual metabolites which had reported gene expression in MCF7 cell lines in the Gene Expression Omnibus (GSE85871). We extracted literature angiogenic activities for 51 individual metabolites, and subsequently analysed their predicted targets and differentially expressed genes to understand their mechanisms of action. The angiogenesis phenotype was used to generate decision trees for rationalising the poly-pharmacology of known angiogenesis modulators such as ferulic acid and curculigoside and validated by an in vitro endothelial tube formation assay and a zebrafish model of angiogenesis. Moreover, using an in silico model we prospectively examined the angiogenesis-modulating activities of the remaining 49 individual metabolites. In vitro, tetrahydropalmatine and 1 beta-hydroxyalantolactone stimulated, while cinobufotalin and isoalantolactone inhibited endothelial tube formation. In vivo, ginsenosides Rb3 and Rc, 1 beta-hydroxyalantolactone and surprisingly cinobufotalin, restored angiogenesis against PTK787-induced impairment in zebrafish. In the absence of PTK787, deoxycholic acid and ursodeoxycholic acid did not affect angiogenesis. Despite some limitations, these results suggest further refinements of in silico prediction combined with biological assessment will be a valuable platform for accelerating the research and development of natural products from traditional Chinese medicine and understanding their mechanisms of action, and also for other traditional medicines for the prevention and treatment of angiogenic diseases.

Analyses of Transcriptomics Cell Signalling for Pre-Screening Applications in the Integrated Approach for Testing and Assessment of Non-Genotoxic Carcinogens

With recent rapid advancement of methodological tools, mechanistic understanding of biological processes leading to carcinogenesis is expanding. New approach methodologies such as transcriptomics can inform on non-genotoxic mechanisms of chemical carcinogens and can be developed for regulatory applications. The Organisation for the Economic Cooperation and Development (OECD) expert group developing an Integrated Approach to the Testing and Assessment (IATA) of Non-Genotoxic Carcinogens (NGTxC) is reviewing the possible assays to be integrated therein. In this context, we review the application of transcriptomics approaches suitable for pre-screening gene expression changes associated with phenotypic alterations that underlie the carcinogenic processes for subsequent prioritisation of downstream test methods appropriate to specific key events of non-genotoxic carcinogenesis. Using case studies, we evaluate the potential of gene expression analyses especially in relation to breast cancer, to identify the most relevant approaches that could be utilised as (pre-) screening tools, for example Gene Set Enrichment Analysis (GSEA). We also consider how to address the challenges to integrate gene panels and transcriptomic assays into the IATA, highlighting the pivotal omics markers identified for assay measurement in the IATA key events of inflammation, immune response, mitogenic signalling and cell injury.

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.

Chemical-induced gene expression ranking and its application to pancreatic cancer drug repurposing

Chemical-induced gene expression profiles provide critical information of chemicals in a biological system, thus offering new opportunities for drug discovery. Despite their success, large-scale analysis leveraging gene expressions is limited by time and cost. Although several methods for predicting gene expressions were proposed, they only focused on imputation and classification settings, which have limited applications to real-world scenarios of drug discovery. Therefore, a chemical-induced gene expression ranking (CIGER) framework is proposed to target a more realistic but more challenging setting in which overall rankings in gene expression profiles induced by de novo chemicals are predicted. The experimental results show that CIGER significantly outperforms existing methods in both ranking and classification metrics. Furthermore, a drug screening pipeline based on CIGER is proposed to identify potential treatments of drug-resistant pancreatic cancer. Our predictions have been validated by experiments, thereby showing the effectiveness of CIGER for phenotypic compound screening of precision medicine.

•

A new deep-learning method (CIGER) for chemical-induced gene expression ranking

•

CIGER can predict gene expression for de novo chemicals from chemical structures

•

We discovered drugs for the treatment of drug-resistant pancreatic cancer

In recent years, a phenotype-based drug discovery approach using chemical-induced gene expressions has shown to be effective in drug discovery and precision medicine. However, it is not feasible to experimentally determine chemical-induced gene expressions for all available chemicals of interest, thereby hindering the application of gene expression-based compound screening on a large scale. Thus, it is crucial to design a computational approach that can generate gene expression information for any chemicals. We proposed a new, deep-learning framework named chemical-induced gene expression ranking (CIGER) to predict a landmark gene expression profile (i.e., gene ranking) induced by de novo chemicals based on their chemical structures. Leveraging CIGER, we predicted and experimentally validated that several existing drugs can increase the therapeutic response on drug-resistant pancreatic cancer. Our results demonstrated the effectiveness of CIGER for precision drug discovery in practice.

The cellular response to drug perturbation is limited: comparison of large-scale chemogenomic fitness signatures

Background

Chemogenomic profiling is a powerful approach for understanding the genome-wide cellular response to small molecules. First developed in Saccharomyces cerevisiae, chemogenomic screens provide direct, unbiased identification of drug target candidates as well as genes required for drug resistance. While many laboratories have performed chemogenomic fitness assays, few have been assessed for reproducibility and accuracy. Here we analyze the two largest independent yeast chemogenomic datasets comprising over 35 million gene-drug interactions and more than 6000 unique chemogenomic profiles; the first from our own academic laboratory (HIPLAB) and the second from the Novartis Institute of Biomedical Research (NIBR).

Results

Despite substantial differences in experimental and analytical pipelines, the combined datasets revealed robust chemogenomic response signatures, characterized by gene signatures, enrichment for biological processes and mechanisms of drug action. We previously reported that the cellular response to small molecules is limited and can be described by a network of 45 chemogenomic signatures. In the present study, we show that the majority of these signatures (66%) are also found in the companion dataset, providing further support for their biological relevance as conserved systems-level, small molecule response systems.

Conclusions

Our results demonstrate the robustness of chemogenomic fitness profiling in yeast, while offering guidelines for performing other high-dimensional comparisons including parallel CRISPR screens in mammalian cells.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12864-022-08395-x.

Computational analyses of mechanism of action (MoA): data, methods and integration

The elucidation of a compound's Mechanism of Action (MoA) is a challenging task in the drug discovery process, but it is important in order to rationalise phenotypic findings and to anticipate potential side-effects. Bioinformatic approaches, advances in machine learning techniques and the increasing deposition of high-throughput data in public databases have significantly contributed to recent advances in the field, but it is not straightforward to decide which data and methods are most suitable to use in a given case. In this review, we focus on these methods and data and their applications in generating MoA hypotheses for subsequent experimental validation. We discuss compound-specific data such as -omics, cell morphology and bioactivity data, as well as commonly used supplementary prior knowledge such as network and pathway data, and provide information on databases where this data can be accessed. In terms of methodologies, we discuss both well-established methods (connectivity mapping, pathway enrichment) as well as more developing methods (neural networks and multi-omics integration). Finally, we review case studies where the MoA of a compound was successfully suggested from computational analysis by incorporating multiple data modalities and/or methodologies. Our aim for this review is to provide researchers with insights into the benefits and drawbacks of both the data and methods in terms of level of understanding, biases and interpretation - and to highlight future avenues of investigation which we foresee will improve the field of MoA elucidation, including greater public access to -omics data and methodologies which are capable of data integration.

Identification and characterization of the novel bioactive compounds from microalgae and cyanobacteria for pharmaceutical and nutraceutical applications

Microalgae and cyanobacteria (blue-green algae) are used as food by humans. They have gained a lot of attention in recent years because of their potential applications in biotechnology. Microalgae and cyanobacteria are good sources of many valuable compounds, including important biologically active compounds with antiviral, antibacterial, antifungal, and anticancer activities. Under optimal growth condition and stress factors, algal biomass produce varieties of potential bioactive compounds. In the current review, bioactive compounds production and their remarkable applications such as pharmaceutical and nutraceutical applications along with processes involved in identification and characterization of the novel bioactive compounds are discussed. Comprehensive knowledge about the exploration, extraction, screening, and trading of bioactive products from microalgae and cyanobacteria and their pharmaceutical and other applications will open up new avenues for drug discovery and bioprospecting.

AI-powered drug repurposing for developing COVID-19 treatments

Emerging infectious diseases are an ever-present threat to public health, and COVID-19 is the most recent example. There is an urgent need to develop a robust framework to combat the disease with safe and effective therapeutic options. Compared to de novo drug discovery, drug repurposing may offer a lower-cost and faster drug discovery paradigm to explore potential treatment options of existing drugs. This chapter elucidates the advantages of artificial intelligence (AI) in enhancing the drug repurposing process from a data science perspective, using COVID-19 as an example. First, we elaborate on how AI-powered drug repurposing benefits from the accumulated data and knowledge of COVID-19 natural history and pathogenesis. Second, we summarize the pros and cons of AI-powered drug repurposing strategies to facilitate fit-for-purpose selection. Finally, we outline challenges of AI-powered drug repurposing from a regulatory perspective and suggest some potential solutions.

•

AI-powered drug purposing is promising for emerging treatments for COVID-19 infection.

•

Accumulated biological data profiles facilitate AI-based drug repurposing efforts for development of COVID-19 therapies.

•

The ‘fit-for-purpose selection of AI-powered drug repurposing strategies is key to uncovering hidden information among drugs, targets, and diseases.

•

Efforts from different stakeholders boost the adoption of AI-powered drug repurposing in the regulatory setting.

TRIOMPHE: Transcriptome-Based Inference and Generation of Molecules with Desired Phenotypes by Machine Learning

One of the most challenging tasks in the drug-discovery process is the efficient identification of small molecules with desired phenotypes. In this study, we propose a novel computational method for omics-based de novo drug design, which we call TRIOMPHE (transcriptome-based inference and generation of molecules with desired phenotypes). We investigated the correlation between chemically induced transcriptome profiles (reflecting cellular responses to compound treatment) and genetically perturbed transcriptome profiles (reflecting cellular responses to gene knock-down or gene overexpression of target proteins) in terms of ligand-target interactions. Subsequently, we developed novel machine learning methods to generate the chemical structures of new molecules with desired transcriptome profiles in the framework of a variational autoencoder. The use of desired transcriptome profiles enables the automatic design of molecules that are likely to have bioactivities for target proteins of interest. We showed that our methods can generate chemically valid molecules that are likely to have biological activities on 10 target proteins; moreover, they can outperform previous methods that had the same objective. Our omics-based structure generator is expected to be useful for the de novo design of drugs for a variety of target proteins.

Evaluation of connectivity map shows limited reproducibility in drug repositioning

The Connectivity Map (CMap) is a popular resource designed for data-driven drug repositioning using a large transcriptomic compendium. However, evaluations of its performance are limited. We used two iterations of CMap (CMap 1 and 2) to assess their comparability and reliability. We queried CMap 2 with CMap 1-derived signatures, expecting CMap 2 would highly prioritize the queried compounds; the success rate was 17%. Analysis of previously published prioritizations yielded similar results. Low recall is caused by low differential expression (DE) reproducibility both between CMaps and within each CMap. DE strength was predictive of reproducibility, and is influenced by compound concentration and cell-line responsiveness. Reproducibility of CMap 2 sample expression levels was also lower than expected. We attempted to identify the "better" CMap by comparison with a third dataset, but they were mutually discordant. Our findings have implications for CMap usage and we suggest steps for investigators to limit false positives.

Machine Learning Uses Chemo-Transcriptomic Profiles to Stratify Antimalarial Compounds With Similar Mode of Action

The rapid development of antimalarial resistance motivates the continued search for novel compounds with a mode of action (MoA) different to current antimalarials. Phenotypic screening has delivered thousands of promising hit compounds without prior knowledge of the compounds’ exact target or MoA. Whilst the latter is not initially required to progress a compound in a medicinal chemistry program, identifying the MoA early can accelerate hit prioritization, hit-to-lead optimization and preclinical combination studies in malaria research. The effects of drug treatment on a cell can be observed on systems level in changes in the transcriptome, proteome and metabolome. Machine learning (ML) algorithms are powerful tools able to deconvolute such complex chemically-induced transcriptional signatures to identify pathways on which a compound act and in this manner provide an indication of the MoA of a compound. In this study, we assessed different ML approaches for their ability to stratify antimalarial compounds based on varied chemically-induced transcriptional responses. We developed a rational gene selection approach that could identify predictive features for MoA to train and generate ML models. The best performing model could stratify compounds with similar MoA with a classification accuracy of 76.6 ± 6.4%. Moreover, only a limited set of 50 biomarkers was required to stratify compounds with similar MoA and define chemo-transcriptomic fingerprints for each compound. These fingerprints were unique for each compound and compounds with similar targets/MoA clustered together. The ML model was specific and sensitive enough to group new compounds into MoAs associated with their predicted target and was robust enough to be extended to also generate chemo-transcriptomic fingerprints for additional life cycle stages like immature gametocytes. This work therefore contributes a new strategy to rapidly, specifically and sensitively indicate the MoA of compounds based on chemo-transcriptomic fingerprints and holds promise to accelerate antimalarial drug discovery programs.

The novel driver gene ASAP2 is a potential druggable target in pancreatic cancer

Targeting mutated oncogenes is an effective approach for treating cancer. The 4 main driver genes of pancreatic ductal adenocarcinoma (PDAC) are KRAS, TP53, CDKN2A, and SMAD4, collectively called the "big 4" of PDAC, however they remain challenging therapeutic targets. In this study, ArfGAP with SH3 domain, ankyrin repeat and PH domain 2 (ASAP2), one of the ArfGAP family, was identified as a novel driver gene in PDAC. Clinical analysis with PDAC datasets showed that ASAP2 was overexpressed in PDAC cells based on increased DNA copy numbers, and high ASAP2 expression contributed to a poor prognosis in PDAC. The biological roles of ASAP2 were investigated using ASAP2-knockout PDAC cells generated with CRISPR-Cas9 technology or transfected PDAC cells. In vitro and in vivo analyses showed that ASAP2 promoted tumor growth by facilitating cell cycle progression through phosphorylation of epidermal growth factor receptor (EGFR). A repositioned drug targeting the ASAP2 pathway was identified using a bioinformatics approach. The gene perturbation correlation method showed that niclosamide, an antiparasitic drug, suppressed PDAC growth by inhibition of ASAP2 expression. These data show that ASAP2 is a novel druggable driver gene that activates the EGFR signaling pathway. Furthermore, niclosamide was identified as a repositioned therapeutic agent for PDAC possibly targeting ASAP2.

Predicting mechanism of action of cellular perturbations with pathway activity signatures

MOTIVATION

Misregulation of signaling pathway activity is etiologic for many human diseases, and modulating activity of signaling pathways is often the preferred therapeutic strategy. Understanding the mechanism of action (MOA) of bioactive chemicals in terms of targeted signaling pathways is the essential first step in evaluating their therapeutic potential. Changes in signaling pathway activity are often not reflected in changes in expression of pathway genes which makes MOA inferences from transcriptional signatures (TSeses) a difficult problem.

RESULTS

We developed a new computational method for implicating pathway targets of bioactive chemicals and other cellular perturbations by integrated analysis of pathway network topology, the Library of Integrated Network-based Cellular Signature TSes of genetic perturbations of pathway genes and the TS of the perturbation. Our methodology accurately predicts signaling pathways targeted by the perturbation when current pathway analysis approaches utilizing only the TS of the perturbation fail.

AVAILABILITY AND IMPLEMENTATION

Open source R package paslincs is available at https://github.com/uc-bd2k/paslincs.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A deep learning framework for high-throughput mechanism-driven phenotype compound screening and its application to COVID-19 drug repurposing

Phenotype-based compound screening has advantages over target-based drug discovery, but is unscalable and lacks understanding of mechanism. Chemical-induced gene expression profile provides a mechanistic signature of phenotypic response. However, the use of such data is limited by their sparseness, unreliability, and relatively low throughput. Few methods can perform phenotype-based de novo chemical compound screening. Here, we propose a mechanism-driven neural network-based method DeepCE, which utilizes graph neural network and multi-head attention mechanism to model chemical substructure-gene and gene-gene associations, for predicting the differential gene expression profile perturbed by de novo chemicals. Moreover, we propose a novel data augmentation method which extracts useful information from unreliable experiments in L1000 dataset. The experimental results show that DeepCE achieves superior performances to state-of-the-art methods. The effectiveness of gene expression profiles generated from DeepCE is further supported by comparing them with observed data for downstream classification tasks. To demonstrate the value of DeepCE, we apply it to drug repurposing of COVID-19, and generate novel lead compounds consistent with clinical evidence. Thus, DeepCE provides a potentially powerful framework for robust predictive modeling by utilizing noisy omics data and screening novel chemicals for the modulation of a systemic response to disease.

DeepSIBA: chemical structure-based inference of biological alterations using deep learning

Predicting whether a chemical structure leads to a desired or adverse biological effect can have a significant impact for in silico drug discovery. In this study, we developed a deep learning model where compound structures are represented as graphs and then linked to their biological footprint. To make this complex problem computationally tractable, compound differences were mapped to biological effect alterations using Siamese Graph Convolutional Neural Networks. The proposed model was able to encode molecular graph pairs and identify structurally dissimilar compounds that affect similar biological processes with high precision. Additionally, by utilizing deep ensembles to estimate uncertainty, we were able to provide reliable and accurate predictions for chemical structures that are very different from the ones used during training. Finally, we present a novel inference approach, where the trained models are used to estimate the signaling pathway signature of a compound perturbation, using only its chemical structure as input, and subsequently identify which substructures influenced the predicted pathways. As a use case, this approach was used to infer important substructures and affected signaling pathways of FDA-approved anticancer drugs.

Learning to encode cellular responses to systematic perturbations with deep generative models

Cellular signaling systems play a vital role in maintaining homeostasis when a cell is exposed to different perturbations. Components of the systems are organized as hierarchical networks, and perturbing different components often leads to transcriptomic profiles that exhibit compositional statistical patterns. Mining such patterns to investigate how cellular signals are encoded is an important problem in systems biology, where artificial intelligence techniques can be of great assistance. Here, we investigated the capability of deep generative models (DGMs) to modeling signaling systems and learn representations of cellular states underlying transcriptomic responses to diverse perturbations. Specifically, we show that the variational autoencoder and the supervised vector-quantized variational autoencoder can accurately regenerate gene expression data in response to perturbagen treatments. The models can learn representations that reveal the relationships between different classes of perturbagens and enable mappings between drugs and their target genes. In summary, DGMs can adequately learn and depict how cellular signals are encoded. The resulting representations have broad applications, demonstrating the power of artificial intelligence in systems biology and precision medicine.

A deep learning framework for high-throughput mechanism-driven phenotype compound screening

Target-based high-throughput compound screening dominates conventional one-drug-one-gene drug discovery process. However, the readout from the chemical modulation of a single protein is poorly correlated with phenotypic response of organism, leading to high failure rate in drug development. Chemical-induced gene expression profile provides an attractive solution to phenotype-based screening. However, the use of such data is currently limited by their sparseness, unreliability, and relatively low throughput. Several methods have been proposed to impute missing values for gene expression datasets. However, few existing methods can perform de novo chemical compound screening. In this study, we propose a mechanism-driven neural network-based method named DeepCE (Deep Chemical Expression) which utilizes graph convolutional neural network to learn chemical representation and multi-head attention mechanism to model chemical substructure-gene and gene-gene feature associations. In addition, we propose a novel data augmentation method which extracts useful information from unreliable experiments in L1000 dataset. The experimental results show that DeepCE achieves the superior performances not only in de novo chemical setting but also in traditional imputation setting compared to state-of-the-art baselines for the prediction of chemical-induced gene expression. We further verify the effectiveness of gene expression profiles generated from DeepCE by comparing them with gene expression profiles in L1000 dataset for downstream classification tasks including drug-target and disease predictions. To demonstrate the value of DeepCE, we apply it to patient-specific drug repurposing of COVID-19 for the first time, and generate novel lead compounds consistent with clinical evidences. Thus, DeepCE provides a potentially powerful framework for robust predictive modeling by utilizing noisy omics data as well as screening novel chemicals for the modulation of systemic response to disease.

Drug repositioning in cancer: The current situation in Japan

Cancer is a leading cause of death worldwide, and the incidence continues to increase. Despite major research aimed at discovering and developing novel and effective anticancer drugs, oncology drug development is a lengthy and costly process, with high attrition rates. Drug repositioning (DR, also referred to as drug repurposing), the process of finding new uses for approved noncancer drugs, has been gaining popularity in the past decade. DR has become a powerful alternative strategy for discovering and developing novel anticancer drug candidates from the existing approved drug space. Indeed, the availability of several large established libraries of clinical drugs and rapid advances in disease biology, genomics/transcriptomics/proteomics and bioinformatics has accelerated the pace of activity‐based, literature‐based and in silico DR, thereby improving safety and reducing costs. However, DR still faces financial obstacles in clinical trials, which could limit its practical use in the clinic. Here, we provide a brief review of DR in cancer and discuss difficulties in the development of DR for clinical use. Furthermore, we introduce some promising DR candidates for anticancer therapy in Japan.

De novo generation of hit-like molecules from gene expression signatures using artificial intelligence

Finding new molecules with a desired biological activity is an extremely difficult task. In this context, artificial intelligence and generative models have been used for molecular de novo design and compound optimization. Herein, we report a generative model that bridges systems biology and molecular design, conditioning a generative adversarial network with transcriptomic data. By doing so, we can automatically design molecules that have a high probability to induce a desired transcriptomic profile. As long as the gene expression signature of the desired state is provided, this model is able to design active-like molecules for desired targets without any previous target annotation of the training compounds. Molecules designed by this model are more similar to active compounds than the ones identified by similarity of gene expression signatures. Overall, this method represents an alternative approach to bridge chemistry and biology in the long and difficult road of drug discovery.

In silico drug repositioning: from large-scale transcriptome data to therapeutics

Drug repositioning is an attractive alternative to conventional drug development when new beneficial effects of old drugs are clinically validated because pharmacokinetic and safety profiles are generally already available. Since ~ 30% of drugs newly approved by the US food and drug administration (FDA) are developed through drug repositioning, identifying novel usage for existing drugs is an emerging strategy for developing disease treatments. With advances in next-generation sequencing technologies, available transcriptome data related to diseases have expanded rapidly. Harnessing these resources enables a better understanding of disease mechanisms and drug mode of action (MOA), and moves toward personalized pharmacotherapy. In this review, we briefly outline publicly available large-scale transcriptome databases and tools for drug repositioning. We also highlight recent approaches leading to the discovery of novel drug targets, drug response biomarkers, drug indications, and drug MOA.

Comparison of Target Features for Predicting Drug-Target Interactions by Deep Neural Network Based on Large-Scale Drug-Induced Transcriptome Data

Uncovering drug-target interactions (DTIs) is pivotal to understand drug mode-of-action (MoA), avoid adverse drug reaction (ADR), and seek opportunities for drug repositioning (DR). For decades, in silico predictions for DTIs have largely depended on structural information of both targets and compounds, e.g., docking or ligand-based virtual screening. Recently, the application of deep neural network (DNN) is opening a new path to uncover novel DTIs for thousands of targets. One important question is which features for targets are most relevant to DTI prediction. As an early attempt to answer this question, we objectively compared three canonical target features extracted from: (i) the expression profiles by gene knockdown (GEPs); (ii) the protein–protein interaction network (PPI network); and (iii) the pathway membership (PM) of a target gene. For drug features, the large-scale drug-induced transcriptome dataset, or the Library of Integrated Network-based Cellular Signatures (LINCS) L1000 dataset was used. All these features are closely related to protein function or drug MoA, of which utility is only sparsely investigated. In particular, few studies have compared the three types of target features in DNN-based DTI prediction under the same evaluation scheme. Among the three target features, the PM and the PPI network show similar performances superior to GEPs. DNN models based on both features consistently outperformed other machine learning methods such as naïve Bayes, random forest, or logistic regression.

Predicting drug-induced transcriptome responses of a wide range of human cell lines by a novel tensor-train decomposition algorithm

MOTIVATION

Genome-wide identification of the transcriptomic responses of human cell lines to drug treatments is a challenging issue in medical and pharmaceutical research. However, drug-induced gene expression profiles are largely unknown and unobserved for all combinations of drugs and human cell lines, which is a serious obstacle in practical applications.

RESULTS

Here, we developed a novel computational method to predict unknown parts of drug-induced gene expression profiles for various human cell lines and predict new drug therapeutic indications for a wide range of diseases. We proposed a tensor-train weighted optimization (TT-WOPT) algorithm to predict the potential values for unknown parts in tensor-structured gene expression data. Our results revealed that the proposed TT-WOPT algorithm can accurately reconstruct drug-induced gene expression data for a range of human cell lines in the Library of Integrated Network-based Cellular Signatures. The results also revealed that in comparison with the use of original gene expression profiles, the use of imputed gene expression profiles improved the accuracy of drug repositioning. We also performed a comprehensive prediction of drug indications for diseases with gene expression profiles, which suggested many potential drug indications that were not predicted by previous approaches.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Drug candidate identification based on gene expression of treated cells using tensor decomposition-based unsupervised feature extraction for large-scale data

Background

Although in silico drug discovery is necessary for drug development, two major strategies, a structure-based and ligand-based approach, have not been completely successful. Currently, the third approach, inference of drug candidates from gene expression profiles obtained from the cells treated with the compounds under study requires the use of a training dataset. Here, the purpose was to develop a new approach that does not require any pre-existing knowledge about the drug–protein interactions, but these interactions can be inferred by means of an integrated approach using gene expression profiles obtained from the cells treated with the analysed compounds and the existing data describing gene–gene interactions.

Results

In the present study, using tensor decomposition-based unsupervised feature extraction, which represents an extension of the recently proposed principal-component analysis-based feature extraction, gene sets and compounds with a significant dose-dependent activity were screened without any training datasets. Next, after these results were combined with the data showing perturbations in single-gene expression profiles, genes targeted by the analysed compounds were inferred. The set of target genes thus identified was shown to significantly overlap with known target genes of the compounds under study.

Conclusions

The method is specifically designed for large-scale datasets (including hundreds of treatments with compounds), not for conventional small-scale datasets. The obtained results indicate that two compounds that have not been extensively studied, WZ-3105 and CGP-60474, represent promising drug candidates targeting multiple cancers, including melanoma, adenocarcinoma, liver carcinoma, and breast, colon, and prostate cancers, which were analysed in this in silico study.

Electronic supplementary material

The online version of this article (10.1186/s12859-018-2395-8) contains supplementary material, which is available to authorized users.

DDR: efficient computational method to predict drug-target interactions using graph mining and machine learning approaches

Motivation

Finding computationally drug–target interactions (DTIs) is a convenient strategy to identify new DTIs at low cost with reasonable accuracy. However, the current DTI prediction methods suffer the high false positive prediction rate.

Results

We developed DDR, a novel method that improves the DTI prediction accuracy. DDR is based on the use of a heterogeneous graph that contains known DTIs with multiple similarities between drugs and multiple similarities between target proteins. DDR applies non-linear similarity fusion method to combine different similarities. Before fusion, DDR performs a pre-processing step where a subset of similarities is selected in a heuristic process to obtain an optimized combination of similarities. Then, DDR applies a random forest model using different graph-based features extracted from the DTI heterogeneous graph. Using 5-repeats of 10-fold cross-validation, three testing setups, and the weighted average of area under the precision-recall curve (AUPR) scores, we show that DDR significantly reduces the AUPR score error relative to the next best start-of-the-art method for predicting DTIs by 31% when the drugs are new, by 23% when targets are new and by 34% when the drugs and the targets are known but not all DTIs between them are not known. Using independent sources of evidence, we verify as correct 22 out of the top 25 DDR novel predictions. This suggests that DDR can be used as an efficient method to identify correct DTIs.

Availability and implementation

The data and code are provided at https://bitbucket.org/RSO24/ddr/.

Supplementary information

Supplementary data are available at Bioinformatics online.

Pathway-Based Drug Repositioning for Cancers: Computational Prediction and Experimental Validation

Developing drugs with anticancer activity and low toxic side-effects at low costs is a challenging issue for cancer chemotherapy. In this work, we propose to use molecular pathways as the therapeutic targets and develop a novel computational approach for drug repositioning for cancer treatment. We analyzed chemically induced gene expression data of 1112 drugs on 66 human cell lines and searched for drugs that inactivate pathways involved in the growth of cancer cells (cell cycle) and activate pathways that contribute to the death of cancer cells (e.g., apoptosis and p53 signaling). Finally, we performed a large-scale prediction of potential anticancer effects for all the drugs and experimentally validated the prediction results via three in vitro cellular assays that evaluate cell viability, cytotoxicity, and apoptosis induction. Using this strategy, we successfully identified several potential anticancer drugs. The proposed pathway-based method has great potential to improve drug repositioning research for cancer treatment.

The Library of Integrated Network-Based Cellular Signatures NIH Program: System-Level Cataloging of Human Cells Response to Perturbations

The Library of Integrated Network-Based Cellular Signatures (LINCS) is an NIH Common Fund program that catalogs how human cells globally respond to chemical, genetic, and disease perturbations. Resources generated by LINCS include experimental and computational methods, visualization tools, molecular and imaging data, and signatures. By assembling an integrated picture of the range of responses of human cells exposed to many perturbations, the LINCS program aims to better understand human disease and to advance the development of new therapies. Perturbations under study include drugs, genetic perturbations, tissue micro-environments, antibodies, and disease-causing mutations. Responses to perturbations are measured by transcript profiling, mass spectrometry, cell imaging, and biochemical methods, among other assays. The LINCS program focuses on cellular physiology shared among tissues and cell types relevant to an array of diseases, including cancer, heart disease, and neurodegenerative disorders. This Perspective describes LINCS technologies, datasets, tools, and approaches to data accessibility and reusability.

Predicting inhibitory and activatory drug targets by chemically and genetically perturbed transcriptome signatures

Genome-wide identification of all target proteins of drug candidate compounds is a challenging issue in drug discovery. Moreover, emerging phenotypic effects, including therapeutic and adverse effects, are heavily dependent on the inhibition or activation of target proteins. Here we propose a novel computational method for predicting inhibitory and activatory targets of drug candidate compounds. Specifically, we integrated chemically-induced and genetically-perturbed gene expression profiles in human cell lines, which avoided dependence on chemical structures of compounds or proteins. Predictive models for individual target proteins were simultaneously constructed by the joint learning algorithm based on transcriptomic changes in global patterns of gene expression profiles following chemical treatments, and following knock-down and over-expression of proteins. This method discriminates between inhibitory and activatory targets and enables accurate identification of therapeutic effects. Herein, we comprehensively predicted drug-target-disease association networks for 1,124 drugs, 829 target proteins, and 365 human diseases, and validated some of these predictions in vitro. The proposed method is expected to facilitate identification of new drug indications and potential adverse effects.

Cell-specific prediction and application of drug-induced gene expression profiles

Gene expression profiling of in vitro drug perturbations is useful for many biomedical discovery applications including drug repurposing and elucidation of drug mechanisms. However, limited data availability across cell types has hindered our capacity to leverage or explore the cell-specificity of these perturbations. While recent efforts have generated a large number of drug perturbation profiles across a variety of human cell types, many gaps remain in this combinatorial drug-cell space. Hence, we asked whether it is possible to fill these gaps by predicting cell-specific drug perturbation profiles using available expression data from related conditions--i.e. from other drugs and cell types. We developed a computational framework that first arranges existing profiles into a three-dimensional array (or tensor) indexed by drugs, genes, and cell types, and then uses either local (nearest-neighbors) or global (tensor completion) information to predict unmeasured profiles. We evaluate prediction accuracy using a variety of metrics, and find that the two methods have complementary performance, each superior in different regions in the drug-cell space. Predictions achieve correlations of 0.68 with true values, and maintain accurate differentially expressed genes (AUC 0.81). Finally, we demonstrate that the predicted profiles add value for making downstream associations with drug targets and therapeutic classes.

Sparse Modeling to Analyze Drug-Target Interaction Networks

Most drugs produce their phenotypic effects by interacting with target proteins, and understanding the molecular features that underpin drug-target interactions is crucial when designing a novel drug. In this chapter, we introduce the protocols that have driven recent advances in sparse modeling methods for analyzing drug-target interaction networks within a chemogenomic framework. In this approach, the chemical structures of candidate drug compounds are correlated with the genomic sequences of the candidate target proteins. We demonstrate the use of sparse canonical correspondence analysis and sparsity-induced binary classifiers to extract the underlying molecular features that are most strongly involved in drug-target interactions. We focus on drug chemical substructures and protein domains. Workflows for applying these methods are presented, and an application is described in detail. We consider the characteristics of each method and suggest possible directions for future research.

Overcoming Obstacles to Drug Repositioning in Japan

Drug repositioning (DR) is the process of identifying new indications for existing drugs. DR usually focuses on drugs that have cleared phase-I safety trials but has yet to show efficacy for the intended indication. Therefore, DR can probably skip the preclinical and phase-I study, which can reduce the cost throughout drug development. However, the expensive phase-II/III trials are required to establish efficacy. The obstacles to DR include identification of new indications with a high success rate in clinical studies, obtaining funding for clinical studies, patent protection, and approval systems. To tackle these obstacles, various approaches have been applied to DR worldwide. In this perspective, we provide representative examples of DR and discuss the ongoing efforts to overcome obstacles to DR in Japan.