Identification of structural features in chemicals associated with cancer drug response: a systematic data-driven analysis

A subcomponent-guided deep learning method for interpretable cancer drug response prediction

Accurate prediction of cancer drug response (CDR) is a longstanding challenge in modern oncology that underpins personalized treatment. Current computational methods implement CDR prediction by modeling responses between entire drugs and cell lines, without the consideration that response outcomes may primarily attribute to a few finer-level 'subcomponents', such as privileged substructures of the drug or gene signatures of the cancer cell, thus producing predictions that are hard to explain. Herein, we present SubCDR, a subcomponent-guided deep learning method for interpretable CDR prediction, to recognize the most relevant subcomponents driving response outcomes. Technically, SubCDR is built upon a line of deep neural networks that enables a set of functional subcomponents to be extracted from each drug and cell line profile, and breaks the CDR prediction down to identifying pairwise interactions between subcomponents. Such a subcomponent interaction form can offer a traceable path to explicitly indicate which subcomponents contribute more to the response outcome. We verify the superiority of SubCDR over state-of-the-art CDR prediction methods through extensive computational experiments on the GDSC dataset. Crucially, we found many predicted cases that demonstrate the strength of SubCDR in finding the key subcomponents driving responses and exploiting these subcomponents to discover new therapeutic drugs. These results suggest that SubCDR will be highly useful for biomedical researchers, particularly in anti-cancer drug design.

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.

A hierarchical Bayesian model to find brain-behaviour associations in incomplete data sets

Canonical Correlation Analysis (CCA) and its regularised versions have been widely used in the neuroimaging community to uncover multivariate associations between two data modalities (e.g., brain imaging and behaviour). However, these methods have inherent limitations: (1) statistical inferences about the associations are often not robust; (2) the associations within each data modality are not modelled; (3) missing values need to be imputed or removed. Group Factor Analysis (GFA) is a hierarchical model that addresses the first two limitations by providing Bayesian inference and modelling modality-specific associations. Here, we propose an extension of GFA that handles missing data, and highlight that GFA can be used as a predictive model. We applied GFA to synthetic and real data consisting of brain connectivity and non-imaging measures from the Human Connectome Project (HCP). In synthetic data, GFA uncovered the underlying shared and specific factors and predicted correctly the non-observed data modalities in complete and incomplete data sets. In the HCP data, we identified four relevant shared factors, capturing associations between mood, alcohol and drug use, cognition, demographics and psychopathological measures and the default mode, frontoparietal control, dorsal and ventral networks and insula, as well as two factors describing associations within brain connectivity. In addition, GFA predicted a set of non-imaging measures from brain connectivity. These findings were consistent in complete and incomplete data sets, and replicated previous findings in the literature. GFA is a promising tool that can be used to uncover associations between and within multiple data modalities in benchmark datasets (such as, HCP), and easily extended to more complex models to solve more challenging tasks.

Representation of molecules for drug response prediction

The rapid development of machine learning and deep learning algorithms in the recent decade has spurred an outburst of their applications in many research fields. In the chemistry domain, machine learning has been widely used to aid in drug screening, drug toxicity prediction, quantitative structure-activity relationship prediction, anti-cancer synergy score prediction, etc. This review is dedicated to the application of machine learning in drug response prediction. Specifically, we focus on molecular representations, which is a crucial element to the success of drug response prediction and other chemistry-related prediction tasks. We introduce three types of commonly used molecular representation methods, together with their implementation and application examples. This review will serve as a brief introduction of the broad field of molecular representations.

Detecting Novel Ototoxins and Potentiation of Ototoxicity by Disease Settings

Over 100 drugs and chemicals are associated with permanent hearing loss, tinnitus, and vestibular deficits, collectively known as ototoxicity. The ototoxic potential of drugs is rarely assessed in pre-clinical drug development or during clinical trials, so this debilitating side-effect is often discovered as patients begin to report hearing loss. Furthermore, drug-induced ototoxicity in adults, and particularly in elderly patients, may go unrecognized due to hearing loss from a variety of etiologies because of a lack of baseline assessments immediately prior to novel therapeutic treatment. During the current pandemic, there is an intense effort to identify new drugs or repurpose FDA-approved drugs to treat COVID-19. Several potential COVID-19 therapeutics are known ototoxins, including chloroquine (CQ) and lopinavir-ritonavir, demonstrating the necessity to identify ototoxic potential in existing and novel medicines. Furthermore, several factors are emerging as potentiators of ototoxicity, such as inflammation (a hallmark of COVID-19), genetic polymorphisms, and ototoxic synergy with co-therapeutics, increasing the necessity to evaluate a drug's potential to induce ototoxicity under varying conditions. Here, we review the potential of COVID-19 therapies to induce ototoxicity and factors that may compound their ototoxic effects. We then discuss two models for rapidly detecting the potential for ototoxicity: mammalian auditory cell lines and the larval zebrafish lateral line. These models offer considerable value for pre-clinical drug development, including development of COVID-19 therapies. Finally, we show the validity of in silico screening for ototoxic potential using a computational model that compares structural similarity of compounds of interest with a database of known ototoxins and non-ototoxins. Preclinical screening at in silico, in vitro, and in vivo levels can provide an earlier indication of the potential for ototoxicity and identify the subset of candidate therapeutics for treating COVID-19 that need to be monitored for ototoxicity as for other widely-used clinical therapeutics, like aminoglycosides and cisplatin.

Understanding the Molecular Drivers of Disease Heterogeneity in Crohn's Disease Using Multi-omic Data Integration and Network Analysis

Crohn's disease (CD), a form of inflammatory bowel disease (IBD), is characterized by heterogeneity along multiple clinical axes, which in turn impacts disease progression and treatment modalities. Using advanced data integration approaches and systems biology tools, we studied the contribution of CD susceptibility variants and gene expression in distinct peripheral immune cell subsets (CD14+ monocytes and CD4+ T cells) to relevant clinical traits. Our analyses revealed that most clinical traits capturing CD heterogeneity could be associated with CD14+ and CD4+ gene expression rather than disease susceptibility variants. By disentangling the sources of variation, we identified molecular features that could potentially be driving the heterogeneity of various clinical traits of CD patients. Further downstream analyses identified contextual hub proteins such as genes encoding barrier functions, antimicrobial peptides, chemokines, and their receptors, which are either targeted by drugs used in CD or other inflammatory diseases or are relevant to the biological functions implicated in disease pathology. These hubs could be used as cell type-specific targets to treat specific subtypes of CD patients in a more individualized approach based on the underlying biology driving their disease subtypes. Our study highlights the importance of data integration and systems approaches to investigate complex and heterogeneous diseases such as IBD.

Modelling Public Sentiments about Juul Flavors on Twitter through Machine Learning

INTRODUCTION

The availability of a variety of e-cigarettes flavors is one of the frequently cited reasons for their adoption. An active stream of discussion about flavoring can be observed online. Analyzing these real-time conversations offers nuanced insights into key factors related to the adoption of flavors, subsequently supporting public health interventions.

METHODS

Google's BERT, a state-of-the-art deep learning method was employed to model the first sentiment corpus on JUUL flavors. BERT, which is pre-trained with the complete English Wikipedia was fine-tuned by integrating a classification model, with human labeled Tweets, as training data. A collection of 30,075 Tweets about JUUL flavors was classified into positive and negative sentiments. Finally, using topic models, we identify and grouped thematic areas into positive and negative Tweets.

RESULTS

With an average of 89% cross-validation precision for classifying tweets, the finetuned BERT model classified 24,114 Tweets as positive and 5,961 Tweets as negative. Through the topic modeling approach 10 thematic topics were identified from the predicted positive and negative sentiments expressed in the Tweets.

CONCLUSIONS

JUUL flavors, notably mango, mint, and cucumber, provoke overwhelmingly positive sentiments indicating a strong likeness due to favoarble taste and odor. Negative discourse about JUUL flavors revolve around addictiveness, high nicotine content, and youth targeted marketing.

IMPLICATIONS

Limiting the content related to flavors and positive perceptions on social media is necessary to minimize exposure to youth. The novel methodology used in this study may be adopted to monitor e-cigarette discourse periodically, as well as other critical public health phenomena online.

In silico health effect prioritization of environmental chemicals through transcriptomics data exploration from a chemo-centric view

With the explosive growth of synthetic compounds, the health effects caused by exogenous chemical exposure have attracted more and more public attention. The prediction of health effect is a never-ending story. Collective resource of transcriptomics data offers an opportunity to understand and identify the multiple health effects of small molecule. Inspired by the fact that environmental chemicals of high health risk frequently share both similar gene expression profile and common structural feature of certain drugs, we here propose a novel computational effect prioritization method for environmental chemicals through transcriptomics data exploration from a chemo-centric view. Specifically, non-negative matrix factorization (NMF) method has been adopted to get the association network linking structural features with transcriptomics characteristics of drugs with specific effects. The model yields 13 pivotal types of effects, so-called components, that represent drug categories with common chemo- and geno- type features. Moreover, the established model effectively prioritizes potential toxic effects for the external chemicals from the endocrine disruptor screening program (EDSP) for their potential estrogenicity and other verified risks. Even if only the highest priority is set for the estrogenic effect, the precision and recall can reach 0.76 and 0.77 respectively for these chemicals. Our effort provides a successful endeavor as to profile potential toxic effects simultaneously for environmental chemicals using both chemical and omics data.

Systems Approach to Pathogenic Mechanism of Type 2 Diabetes and Drug Discovery Design Based on Deep Learning and Drug Design Specifications

In this study, we proposed a systems biology approach to investigate the pathogenic mechanism for identifying significant biomarkers as drug targets and a systematic drug discovery strategy to design a potential multiple-molecule targeting drug for type 2 diabetes (T2D) treatment. We first integrated databases to construct the genome-wide genetic and epigenetic networks (GWGENs), which consist of protein–protein interaction networks (PPINs) and gene regulatory networks (GRNs) for T2D and non-T2D (health), respectively. Second, the relevant “real GWGENs” are identified by system identification and system order detection methods performed on the T2D and non-T2D RNA-seq data. To simplify network analysis, principal network projection (PNP) was thereby exploited to extract core GWGENs from real GWGENs. Then, with the help of KEGG pathway annotation, core signaling pathways were constructed to identify significant biomarkers. Furthermore, in order to discover potential drugs for the selected pathogenic biomarkers (i.e., drug targets) from the core signaling pathways, not only did we train a deep neural network (DNN)-based drug–target interaction (DTI) model to predict candidate drug’s binding with the identified biomarkers but also considered a set of design specifications, including drug regulation ability, toxicity, sensitivity, and side effects to sieve out promising drugs suitable for T2D.

An integrative machine learning approach to discovering multi-level molecular mechanisms of obesity using data from monozygotic twin pairs

We combined clinical, cytokine, genomic, methylation and dietary data from 43 young adult monozygotic twin pairs (aged 22-36 years, 53% female), where 25 of the twin pairs were substantially weight discordant (delta body mass index > 3 kg m^-2). These measurements were originally taken as part of the TwinFat study, a substudy of The Finnish Twin Cohort study. These five large multivariate datasets (comprising 42, 71, 1587, 1605 and 63 variables, respectively) were jointly analysed using an integrative machine learning method called group factor analysis (GFA) to offer new hypotheses into the multi-molecular-level interactions associated with the development of obesity. New potential links between cytokines and weight gain are identified, as well as associations between dietary, inflammatory and epigenetic factors. This encouraging case study aims to enthuse the research community to boldly attempt new machine learning approaches which have the potential to yield novel and unintuitive hypotheses. The source code of the GFA method is publically available as the R package GFA.

Investigating Core Signaling Pathways of Hepatitis B Virus Pathogenesis for Biomarkers Identification and Drug Discovery via Systems Biology and Deep Learning Method

Hepatitis B Virus (HBV) infection is a major cause of morbidity and mortality worldwide. However, poor understanding of its pathogenesis often gives rise to intractable immune escape and prognosis recurrence. Thus, a valid systematic approach based on big data mining and genome-wide RNA-seq data is imperative to further investigate the pathogenetic mechanism and identify biomarkers for drug design. In this study, systems biology method was applied to trim false positives from the host/pathogen genetic and epigenetic interaction network (HPI-GEN) under HBV infection by two-side RNA-seq data. Then, via the principal network projection (PNP) approach and the annotation of KEGG (Kyoto Encyclopedia of Genes and Genomes) pathways, significant biomarkers related to cellular dysfunctions were identified from the core cross-talk signaling pathways as drug targets. Further, based on the pre-trained deep learning-based drug-target interaction (DTI) model and the validated pharmacological properties from databases, i.e., drug regulation ability, toxicity, and sensitivity, a combination of promising multi-target drugs was designed as a multiple-molecule drug to create more possibility for the treatment of HBV infection. Therefore, with the proposed systems medicine discovery and repositioning procedure, we not only shed light on the etiologic mechanism during HBV infection but also efficiently provided a potential drug combination for therapeutic treatment of Hepatitis B.

Identification of chlorprothixene as a potential drug that induces apoptosis and autophagic cell death in acute myeloid leukemia cells

Although acute myeloid leukemia (AML) is a highly heterogeneous malignance, the common molecular mechanisms shared by different AML subtypes play critical roles in AML development. It is possible to identify new drugs that are effective for various AML subtypes based on the common molecular mechanisms. Therefore, we developed a hypothesis-driven bioinformatic drug screening framework by integrating multiple omics data. In this study, we identified that chlorprothixene, a dopamine receptor antagonist, could effectively inhibit growth of AML cells from different subtypes. RNA-seq analysis suggested that chlorprothixene perturbed a series of crucial biological processes such as cell cycle, apoptosis, and autophagy in AML cells. Further investigations indicated that chlorprothixene could induce both apoptosis and autophagy in AML cells, and apoptosis and autophagy could act as partners to induce cell death cooperatively. Remarkably, chlorprothixene was found to inhibit tumor growth and induce in situ leukemic cell apoptosis in the murine xenograft model. Furthermore, chlorprothixene treatment could reduce the level of oncofusion proteins PML-RARα and AML1-ETO, thus elevate the expression of apoptosis-related genes, and lead to AML cell death. Our results provided new insights for drug repositioning of AML therapy and confirmed that chlorprothixene might be a potential candidate for treatment of different subtypes of AML by reducing expression of oncofusion proteins. DATABASE: RNA-seq data are available in GEO database under the accession number GSE124316.

Predictive power of the Triticum root elongation test for the assessment of novel anti‑proliferative therapies

The use of alternative techniques to reduce the number of animals used in anticancer research is an issue of current interest. The aim of this study was to validate the use of a simple and efficient alternative tool for the assessment of the potential of novel anti‑proliferative agents. A set of 20 compounds with various mechanisms were tested in the Triticum aestivum root elongation assay, using aminophylline as negative control. Hierarchical cluster analyses were performed using the furthest neighbor method based on Euclidean distance measure, and the compounds were statistically analyzed in reference to their anti‑proliferative pattern registered in the NCI60 human tumor cell line anticancer drug screen. A correlation between the Triticum test results and the NCI60 anti‑proliferative profile was made for a number of human cells that we defined as the Triticum cell panel. Linear equations were computed that can be used to transform the inhibitory effect measured in any future Triticum assay in order to predict the effect on particular human cells. Of the tested anti‑proliferative agents, methotrexate, colchicine, cantharidin, cisplatin and verapamil produced a growth inhibition over 50%. On the whole, the findings of this study suggest that the Triticum test can be used to detect several types of anti‑proliferative mechanisms, particularly those targeting tubulin, rendering it a useful tool with which to identify novel mitotic spindle inhibitors.

Development of Orthogonal Linear Separation Analysis (OLSA) to Decompose Drug Effects into Basic Components

Drugs have multiple, not single, effects. Decomposition of drug effects into basic components helps us to understand the pharmacological properties of a drug and contributes to drug discovery. We have extended factor analysis and developed a novel profile data analysis method: orthogonal linear separation analysis (OLSA). OLSA contracted 11,911 genes to 118 factors from transcriptome data of MCF7 cells treated with 318 compounds in a Connectivity Map. Ontology of the main genes constituting the factors detected significant enrichment of the ontology in 65 of 118 factors and similar results were obtained in two other data sets. In further analysis of the Connectivity Map data set, one factor discriminated two Hsp90 inhibitors, geldanamycin and radicicol, while clustering analysis could not. Doxorubicin and other topoisomerase inhibitors were estimated to inhibit Na+/K+ ATPase, one of the suggested mechanisms of doxorubicin-induced cardiotoxicity. Based on the factor including PI3K/AKT/mTORC1 inhibition activity, 5 compounds were predicted to be novel inducers of autophagy, and other analyses including western blotting revealed that 4 of the 5 actually induced autophagy. These findings indicate the potential of OLSA to decompose the effects of a drug and identify its basic components.

Multi-Omics Factor Analysis-a framework for unsupervised integration of multi-omics data sets

Multi-omics studies promise the improved characterization of biological processes across molecular layers. However, methods for the unsupervised integration of the resulting heterogeneous data sets are lacking. We present Multi-Omics Factor Analysis (MOFA), a computational method for discovering the principal sources of variation in multi-omics data sets. MOFA infers a set of (hidden) factors that capture biological and technical sources of variability. It disentangles axes of heterogeneity that are shared across multiple modalities and those specific to individual data modalities. The learnt factors enable a variety of downstream analyses, including identification of sample subgroups, data imputation and the detection of outlier samples. We applied MOFA to a cohort of 200 patient samples of chronic lymphocytic leukaemia, profiled for somatic mutations, RNA expression, DNA methylation and ex vivo drug responses. MOFA identified major dimensions of disease heterogeneity, including immunoglobulin heavy-chain variable region status, trisomy of chromosome 12 and previously underappreciated drivers, such as response to oxidative stress. In a second application, we used MOFA to analyse single-cell multi-omics data, identifying coordinated transcriptional and epigenetic changes along cell differentiation.

A review of connectivity map and computational approaches in pharmacogenomics

Large-scale perturbation databases, such as Connectivity Map (CMap) or Library of Integrated Network-based Cellular Signatures (LINCS), provide enormous opportunities for computational pharmacogenomics and drug design. A reason for this is that in contrast to classical pharmacology focusing at one target at a time, the transcriptomics profiles provided by CMap and LINCS open the door for systems biology approaches on the pathway and network level. In this article, we provide a review of recent developments in computational pharmacogenomics with respect to CMap and LINCS and related applications.

A review of connectivity map and computational approaches in pharmacogenomics

Large-scale perturbation databases, such as Connectivity Map (CMap) or Library of Integrated Network-based Cellular Signatures (LINCS), provide enormous opportunities for computational pharmacogenomics and drug design. A reason for this is that in contrast to classical pharmacology focusing at one target at a time, the transcriptomics profiles provided by CMap and LINCS open the door for systems biology approaches on the pathway and network level. In this article, we provide a review of recent developments in computational pharmacogenomics with respect to CMap and LINCS and related applications.

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.

Comparing structural and transcriptional drug networks reveals signatures of drug activity and toxicity in transcriptional responses

We performed an integrated analysis of drug chemical structures and drug-induced transcriptional responses. We demonstrated that a network representing three-dimensional structural similarities among 5452 compounds can be used to automatically group together drugs with similar scaffolds, physicochemical parameters and mode-of-action. We compared the structural network to a network representing transcriptional similarities among a subset of 1309 drugs for which transcriptional response were available in the Connectivity Map data set. Analysis of structurally similar, but transcriptionally different drugs sharing the same MOA enabled us to detect and remove weak and noisy transcriptional responses, greatly enhancing the reliability of transcription-based approaches to drug discovery and drug repositioning. Cardiac glycosides exhibited the strongest transcriptional responses with a significant induction of pathways related to epigenetic regulation, which suggests an epigenetic mechanism of action for these drugs. Drug classes with the weakest transcriptional responses tended to induce expression of cytochrome P450 enzymes, hinting at drug-induced drug resistance. Analysis of transcriptionally similar, but structurally different drugs with unrelated MOA, led us to the identification of a 'toxic' transcriptional signature indicative of lysosomal stress (lysosomotropism) and lipid accumulation (phospholipidosis) partially masking the target-specific transcriptional effects of these drugs. We found that this transcriptional signature is shared by 258 compounds and it is associated to the activation of the transcription factor TFEB, a master regulator of lysosomal biogenesis and autophagy. Finally, we built a predictive Random Forest model of these 258 compounds based on 128 physicochemical parameters, which should help in the early identification of potentially toxic drug candidates.

Transcriptional responses to drug treatment can reveal mechanism of action and off-target effects thus enabling drug repositioning, but only if measured in the appropriate cells at clinically relevant concentrations. A team led by Diego di Bernardo and Diego Medina generated a network representing structural similarities among compounds to automatically group together drugs with similar scaffolds and MOA. By comparing the structural drug network with a transcriptional drug network based on similarities in transcriptional response, the team observed broad differences between the two. This observation led to the identification of a transcriptional signature related lysosomal stress and phospholipidosis, and a physicochemical model to identify such compounds. These results provide general guidelines to prevent erroneous conclusion when using transcriptional responses of small molecules for drug discovery and drug repositioning

Comparing the performance of linear and nonlinear principal components in the context of high-dimensional genomic data integration

Linear principal component analysis (PCA) is a widely used approach to reduce the dimension of gene or miRNA expression data sets. This method relies on the linearity assumption, which often fails to capture the patterns and relationships inherent in the data. Thus, a nonlinear approach such as kernel PCA might be optimal. We develop a copula-based simulation algorithm that takes into account the degree of dependence and nonlinearity observed in these data sets. Using this algorithm, we conduct an extensive simulation to compare the performance of linear and kernel principal component analysis methods towards data integration and death classification. We also compare these methods using a real data set with gene and miRNA expression of lung cancer patients. First few kernel principal components show poor performance compared to the linear principal components in this occasion. Reducing dimensions using linear PCA and a logistic regression model for classification seems to be adequate for this purpose. Integrating information from multiple data sets using either of these two approaches leads to an improved classification accuracy for the outcome.

Integrative Cancer Pharmacogenomics to Infer Large-Scale Drug Taxonomy

Identification of drug targets and mechanism of action (MoA) for new and uncharacterized anticancer drugs is important for optimization of treatment efficacy. Current MoA prediction largely relies on prior information including side effects, therapeutic indication, and chemoinformatics. Such information is not transferable or applicable for newly identified, previously uncharacterized small molecules. Therefore, a shift in the paradigm of MoA predictions is necessary toward development of unbiased approaches that can elucidate drug relationships and efficiently classify new compounds with basic input data. We propose here a new integrative computational pharmacogenomic approach, referred to as Drug Network Fusion (DNF), to infer scalable drug taxonomies that rely only on basic drug characteristics toward elucidating drug-drug relationships. DNF is the first framework to integrate drug structural information, high-throughput drug perturbation, and drug sensitivity profiles, enabling drug classification of new experimental compounds with minimal prior information. DNF taxonomy succeeded in identifying pertinent and novel drug-drug relationships, making it suitable for investigating experimental drugs with potential new targets or MoA. The scalability of DNF facilitated identification of key drug relationships across different drug categories, providing a flexible tool for potential clinical applications in precision medicine. Our results support DNF as a valuable resource to the cancer research community by providing new hypotheses on compound MoA and potential insights for drug repurposing. Cancer Res; 77(11); 3057-69. ©2017 AACR.

A network based approach to drug repositioning identifies plausible candidates for breast cancer and prostate cancer

BACKGROUND

The high cost and the long time required to bring drugs into commerce is driving efforts to repurpose FDA approved drugs-to find new uses for which they weren't intended, and to thereby reduce the overall cost of commercialization, and shorten the lag between drug discovery and availability. We report on the development, testing and application of a promising new approach to repositioning.

METHODS

Our approach is based on mining a human functional linkage network for inversely correlated modules of drug and disease gene targets. The method takes account of multiple information sources, including gene mutation, gene expression, and functional connectivity and proximity of within module genes.

RESULTS

The method was used to identify candidates for treating breast and prostate cancer. We found that (i) the recall rate for FDA approved drugs for breast (prostate) cancer is 20/20 (10/11), while the rates for drugs in clinical trials were 131/154 and 82/106; (ii) the ROC/AUC performance substantially exceeds that of comparable methods; (iii) preliminary in vitro studies indicate that 5/5 candidates have therapeutic indices superior to that of Doxorubicin in MCF7 and SUM149 cancer cell lines. We briefly discuss the biological plausibility of the candidates at a molecular level in the context of the biological processes that they mediate.

CONCLUSIONS

Our method appears to offer promise for the identification of multi-targeted drug candidates that can correct aberrant cellular functions. In particular the computational performance exceeded that of other CMap-based methods, and in vitro experiments indicate that 5/5 candidates have therapeutic indices superior to that of Doxorubicin in MCF7 and SUM149 cancer cell lines. The approach has the potential to provide a more efficient drug discovery pipeline.

From drug response profiling to target addiction scoring in cancer cell models

Deconvoluting the molecular target signals behind observed drug response phenotypes is an important part of phenotype-based drug discovery and repurposing efforts. We demonstrate here how our network-based deconvolution approach, named target addiction score (TAS), provides insights into the functional importance of druggable protein targets in cell-based drug sensitivity testing experiments. Using cancer cell line profiling data sets, we constructed a functional classification across 107 cancer cell models, based on their common and unique target addiction signatures. The pan-cancer addiction correlations could not be explained by the tissue of origin, and only correlated in part with molecular and genomic signatures of the heterogeneous cancer cells. The TAS-based cancer cell classification was also shown to be robust to drug response data resampling, as well as predictive of the transcriptomic patterns in an independent set of cancer cells that shared similar addiction signatures with the 107 cancers. The critical protein targets identified by the integrated approach were also shown to have clinically relevant mutation frequencies in patients with various cancer subtypes, including not only well-established pan-cancer genes, such as PTEN tumor suppressor, but also a number of targets that are less frequently mutated in specific cancer types, including ABL1 oncoprotein in acute myeloid leukemia. An application to leukemia patient primary cell models demonstrated how the target deconvolution approach offers functional insights into patient-specific addiction patterns, such as those indicative of their receptor-type tyrosine-protein kinase FLT3 internal tandem duplication (FLT3-ITD) status and co-addiction partners, which may lead to clinically actionable, personalized drug treatment developments. To promote its application to the future drug testing studies, we have made available an open-source implementation of the TAS calculation in the form of a stand-alone R package.

Sparse group factor analysis for biclustering of multiple data sources

MOTIVATION

Modelling methods that find structure in data are necessary with the current large volumes of genomic data, and there have been various efforts to find subsets of genes exhibiting consistent patterns over subsets of treatments. These biclustering techniques have focused on one data source, often gene expression data. We present a Bayesian approach for joint biclustering of multiple data sources, extending a recent method Group Factor Analysis to have a biclustering interpretation with additional sparsity assumptions. The resulting method enables data-driven detection of linear structure present in parts of the data sources.

RESULTS

Our simulation studies show that the proposed method reliably infers biclusters from heterogeneous data sources. We tested the method on data from the NCI-DREAM drug sensitivity prediction challenge, resulting in an excellent prediction accuracy. Moreover, the predictions are based on several biclusters which provide insight into the data sources, in this case on gene expression, DNA methylation, protein abundance, exome sequence, functional connectivity fingerprints and drug sensitivity.

AVAILABILITY AND IMPLEMENTATION

http://research.cs.aalto.fi/pml/software/GFAsparse/

CONTACTS

: kerstin.bunte@googlemail.com or samuel.kaski@aalto.fi.

Transcriptional response networks for elucidating mechanisms of action of multitargeted agents

Drug discovery is moving away from the single target-based approach towards harnessing the potential of polypharmacological agents that modulate the activity of multiple nodes in the complex networks of deregulations underlying disease phenotypes. Computational network pharmacology methods that use systems-level drug-response phenotypes, such as those originating from genome-wide transcriptomic profiles, have proved particularly effective for elucidating the mechanisms of action of multitargeted compounds. Here, we show, via the case study of the natural product pinosylvin, how the combination of two complementary network-based methods can provide novel, unexpected mechanistic insights. This case study also illustrates that elucidating the mechanism of action of multitargeted natural products through transcriptional response-based approaches is a challenging endeavor, often requiring multiple computational-experimental iterations.

Network pharmacology applications to map the unexplored target space and therapeutic potential of natural products

It is widely accepted that drug discovery often requires a systems-level polypharmacology approach to tackle problems such as lack of efficacy and emerging resistance of single-targeted compounds. Network pharmacology approaches are increasingly being developed and applied to find new therapeutic opportunities and to re-purpose approved drugs. However, these recent advances have been relatively slow to be translated into the field of natural products. Here, we argue that a network pharmacology approach would enable an effective mapping of the yet unexplored target space of natural products, hence providing a systematic means to extend the druggable space of proteins implicated in various complex diseases. We give an overview of the key network pharmacology concepts and recent experimental-computational approaches that have been successfully applied to natural product research, including unbiased elucidation of mechanisms of action as well as systematic prediction of effective therapeutic combinations. We focus specifically on anticancer applications that use in vivo and in vitro functional phenotypic measurements, such as genome-wide transcriptomic response profiles, which enable a global modelling of the multi-target activity at the level of the biological pathways and interaction networks. We also provide representative examples of other disease applications, databases and tools as well as existing and emerging resources, which may prove useful for future natural product research. Finally, we offer our personal view of the current limitations, prospective developments and open questions in this exciting field.