Extending in silico mechanism-of-action analysis by annotating targets with pathways: application to cellular cytotoxicity readouts

Early Pharmacological Profiling of Antiproliferative Compounds by Live Cell Imaging

Natural products represent an excellent source of unprecedented anticancer compounds. However, the identification of the mechanism of action remains a major challenge. Several techniques and methodologies have been considered, but with limited success. In this work, we explored the combination of live cell imaging and machine learning techniques as a promising tool to depict in a fast and affordable test the mode of action of natural compounds with antiproliferative activity. To develop the model, we selected the non-small cell lung cancer cell line SW1573, which was exposed to the known antimitotic drugs paclitaxel, colchicine and vinblastine. The novelty of our methodology focuses on two main features with the highest relevance, (a) meaningful phenotypic metrics, and (b) fast Fourier transform (FFT) of the time series of the phenotypic parameters into their corresponding amplitudes and phases. The resulting algorithm was able to cluster the microtubule disruptors, and meanwhile showed a negative correlation between paclitaxel and the other treatments. The FFT approach was able to group the samples as efficiently as checking by eye. This methodology could easily scale to group a large amount of data without visual supervision.

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.

High-content phenotypic and pathway profiling to advance drug discovery in diseases of unmet need

Conventional thinking in modern drug discovery postulates that the design of highly selective molecules which act on a single disease-associated target will yield safer and more effective drugs. However, high clinical attrition rates and the lack of progress in developing new effective treatments for many important diseases of unmet therapeutic need challenge this hypothesis. This assumption also impinges upon the efficiency of target agnostic phenotypic drug discovery strategies, where early target deconvolution is seen as a critical step to progress phenotypic hits. In this review we provide an overview of how emerging phenotypic and pathway-profiling technologies integrate to deconvolute the mechanism-of-action of phenotypic hits. We propose that such in-depth mechanistic profiling may support more efficient phenotypic drug discovery strategies that are designed to more appropriately address complex heterogeneous diseases of unmet need.

Elucidating Compound Mechanism of Action and Predicting Cytotoxicity Using Machine Learning Approaches, Taking Prediction Confidence into Account

The modes of action (MoAs) of drugs frequently are unknown, because many are small molecules initially identified from phenotypic screens, giving rise to the need to elucidate their MoAs. In addition, the high attrition rate for candidate drugs in preclinical studies due to intolerable toxicity has motivated the development of computational approaches to predict drug candidate (cyto)toxicity as early as possible in the drug-discovery process. Here, we provide detailed instructions for capitalizing on bioactivity predictions to elucidate the MoAs of small molecules and infer their underlying phenotypic effects. We illustrate how these predictions can be used to infer the underlying antidepressive effects of marketed drugs. We also provide the necessary functionalities to model cytotoxicity data using single and ensemble machine-learning algorithms. Finally, we give detailed instructions on how to calculate confidence intervals for individual predictions using the conformal prediction framework. © 2019 by John Wiley & Sons, Inc.

Prediction of modes of action of components of traditional medicinal preparations

Traditional medicine preparations are used to treat many ailments in multiple regions across the world. Despite their widespread use, the mode of action of these preparations and their constituents are not fully understood. Traditional methods of elucidating the modes of action of these natural products (NPs) can be expensive and time consuming e. g. biochemical methods, bioactivity guided fractionation, etc. In this review, we discuss some methods for the prediction of the modes of action of traditional medicine preparations, both in mixtures and as isolated NPs. These methods are useful to predict targets of NPs before they are experimentally validated. Case studies of the applications of these methods are also provided herein.

Leveraging heterogeneous data from GHS toxicity annotations, molecular and protein target descriptors and Tox21 assay readouts to predict and rationalise acute toxicity

Despite the increasing knowledge in both the chemical and biological domains the assimilation and exploration of heterogeneous datasets, encoding information about the chemical, bioactivity and phenotypic properties of compounds, remains a challenge due to requirement for overlap between chemicals assayed across the spaces. Here, we have constructed a novel dataset, larger than we have used in prior work, comprising 579 acute oral toxic compounds and 1427 non-toxic compounds derived from regulatory GHS information, along with their corresponding molecular and protein target descriptors and qHTS in vitro assay readouts from the Tox21 project. We found no clear association between the results of a FAFDrugs4 toxicophore screen and the acute oral toxicity classifications for our compound set; and a screen using a subset of the ToxAlerts toxicophores was also of limited utility, with only slight enrichment toward the toxic set (odds ratio of 1.48). We then investigated to what degree toxic and non-toxic compounds could be separated in each of the spaces, to compare their potential contribution to further analyses. Using an LDA projection, we found the largest degree of separation using chemical descriptors (Cohen’s d of 1.95) and the lowest degree of separation between toxicity classes using qHTS descriptors (Cohen’s d of 0.67). To compare the predictivity of the feature spaces for the toxicity endpoint, we next trained Random Forest (RF) acute oral toxicity classifiers on either molecular, protein target and qHTS descriptors. RFs trained on molecular and protein target descriptors were most predictive, with ROC AUC values of 0.80–0.92 and 0.70–0.85, respectively, across three test sets. RFs trained on both chemical and protein target descriptors combined exhibited similar predictive performance to the single-domain models (ROC AUC of 0.80–0.91). Model interpretability was improved by the inclusion of protein target descriptors, which allow the identification of specific targets (e.g. Retinal dehydrogenase) with literature links to toxic modes of action (e.g. oxidative stress). The dataset compiled in this study has been made available for future application.

In Silico Target Prediction for Small Molecules

Drugs modulate disease states through their actions on targets in the body. Determining these targets aids the focused development of new treatments, and helps to better characterize those already employed. One means of accomplishing this is through the deployment of in silico methodologies, harnessing computational analytical and predictive power to produce educated hypotheses for experimental verification. Here, we provide an overview of the current state of the art, describe some of the well-established methods in detail, and reflect on how they, and emerging technologies promoting the incorporation of complex and heterogeneous data-sets, can be employed to improve our understanding of (poly)pharmacology.

Extending in Silico Protein Target Prediction Models to Include Functional Effects

In silico protein target deconvolution is frequently used for mechanism-of-action investigations; however existing protocols usually do not predict compound functional effects, such as activation or inhibition, upon binding to their protein counterparts. This study is hence concerned with including functional effects in target prediction. To this end, we assimilated a bioactivity training set for 332 targets, comprising 817,239 active data points with unknown functional effect (binding data) and 20,761,260 inactive compounds, along with 226,045 activating and 1,032,439 inhibiting data points from functional screens. Chemical space analysis of the data first showed some separation between compound sets (binding and inhibiting compounds were more similar to each other than both binding and activating or activating and inhibiting compounds), providing a rationale for implementing functional prediction models. We employed three different architectures to predict functional response, ranging from simplistic random forest models ('Arch1') to cascaded models which use separate binding and functional effect classification steps ('Arch2' and 'Arch3'), differing in the way training sets were generated. Fivefold stratified cross-validation outlined cascading predictions provides superior precision and recall based on an internal test set. We next prospectively validated the architectures using a temporal set of 153,467 of in-house data points (after a 4-month interim from initial data extraction). Results outlined Arch3 performed with the highest target class averaged precision and recall scores of 71% and 53%, which we attribute to the use of inactive background sets. Distance-based applicability domain (AD) analysis outlined that Arch3 provides superior extrapolation into novel areas of chemical space, and thus based on the results presented here, propose as the most suitable architecture for the functional effect prediction of small molecules. We finally conclude including functional effects could provide vital insight in future studies, to annotate cases of unanticipated functional changeover, as outlined by our CHRM1 case study.

Systemic QSAR and phenotypic virtual screening: chasing butterflies in drug discovery

Current advances in systems biology suggest a new change of paradigm reinforcing the holistic nature of the drug discovery process. According to the principles of systems biology, a simple drug perturbing a network of targets can trigger complex reactions. Therefore, it is possible to connect initial events with final outcomes and consequently prioritize those events, leading to a desired effect. Here, we introduce a new concept, 'Systemic Chemogenomics/Quantitative Structure-Activity Relationship (QSAR)'. To elaborate on the concept, relevant information surrounding it is addressed. The concept is challenged by implementing a systemic QSAR approach for phenotypic virtual screening (VS) of candidate ligands acting as neuroprotective agents in Parkinson's disease (PD). The results support the suitability of the approach for the phenotypic prioritization of drug candidates.

Network Analysis Reveals Similar Transcriptomic Responses to Intrinsic Properties of Carbon Nanomaterials in Vitro and in Vivo

Understanding the complex molecular alterations related to engineered nanomaterial (ENM) exposure is essential for carrying out toxicity assessment. Current experimental paradigms rely on both in vitro and in vivo exposure setups that often are difficult to compare, resulting in questioning the real efficacy of cell models to mimic more complex exposure scenarios at the organism level. Here, we have systematically investigated transcriptomic responses of the THP-1 macrophage cell line and lung tissues of mice, after exposure to several carbon nanomaterials (CNMs). Under the assumption that the CNM exposure related molecular alterations are mixtures of signals related to their intrinsic properties, we inferred networks of responding genes, whose expression levels are coordinately altered in response to specific CNM intrinsic properties. We observed only a minute overlap between the sets of intrinsic property-correlated genes at different exposure scenarios, suggesting specific transcriptional programs working in different exposure scenarios. However, when the effects of the CNM were investigated at the level of significantly altered molecular functions, a broader picture of substantial commonality emerged. Our results imply that in vitro exposures can efficiently recapitulate the complex molecular functions altered in vivo. In this study, altered molecular pathways in response to specific CNM intrinsic properties have been systematically characterized from transcriptomic data generated from multiple exposure setups. Our computational approach to the analysis of network response modules further revealed similarities between in vitro and in vivo exposures that could not be detected by traditional analysis of transcriptomics data. Our analytical strategy also opens a possibility to look for pathways of toxicity and understanding the molecular and cellular responses identified across predefined biological themes.

Understanding Cytotoxicity and Cytostaticity in a High-Throughput Screening Collection

While mechanisms of cytotoxicity and cytostaticity have been studied extensively from the biological side, relatively little is currently understood regarding areas of chemical space leading to cytotoxicity and cytostasis in large compound collections. Predicting and rationalizing potential adverse mechanism-of-actions (MoAs) of small molecules is however crucial for screening library design, given the link of even low level cytotoxicity and adverse events observed in man. In this study, we analyzed results from a cell-based cytotoxicity screening cascade, comprising 296 970 nontoxic, 5784 cytotoxic and cytostatic, and 2327 cytostatic-only compounds evaluated on the THP-1 cell-line. We employed an in silico MoA analysis protocol, utilizing 9.5 million active and 602 million inactive bioactivity points to generate target predictions, annotate predicted targets with pathways, and calculate enrichment metrics to highlight targets and pathways. Predictions identify known mechanisms for the top ranking targets and pathways for both phenotypes after review and indicate that while processes involved in cytotoxicity versus cytostaticity seem to overlap, differences between both phenotypes seem to exist to some extent. Cytotoxic predictions highlight many kinases, including the potentially novel cytotoxicity-related target STK32C, while cytostatic predictions outline targets linked with response to DNA damage, metabolism, and cytoskeletal machinery. Fragment analysis was also employed to generate a library of toxicophores to improve general understanding of the chemical features driving toxicity. We highlight substructures with potential kinase-dependent and kinase-independent mechanisms of toxicity. We also trained a cytotoxic classification model on proprietary and public compound readouts, and prospectively validated these on 988 novel compounds comprising difficult and trivial testing instances, to establish the applicability domain of models. The proprietary model performed with precision and recall scores of 77.9% and 83.8%, respectively. The MoA results and top ranking substructures with accompanying MoA predictions are available as a platform to assess screening collections.

Global Mapping of Traditional Chinese Medicine into Bioactivity Space and Pathways Annotation Improves Mechanistic Understanding and Discovers Relationships between Therapeutic Action (Sub)classes

Traditional Chinese medicine (TCM) still needs more scientific rationale to be proven for it to be accepted further in the West. We are now in the position to propose computational hypotheses for the mode-of-actions (MOAs) of 45 TCM therapeutic action (sub)classes from in silico target prediction algorithms, whose target was later annotated with Kyoto Encyclopedia of Genes and Genomes pathway, and to discover the relationship between them by generating a hierarchical clustering. The results of 10,749 TCM compounds showed 183 enriched targets and 99 enriched pathways from Estimation Score ≤ 0 and ≥ 5% of compounds/targets in a (sub)class. The MOA of a (sub)class was established from supporting literature. Overall, the most frequent top three enriched targets/pathways were immune-related targets such as tyrosine-protein phosphatase nonreceptor type 2 (PTPN2) and digestive system such as mineral absorption. We found two major protein families, G-protein coupled receptor (GPCR), and protein kinase family contributed to the diversity of the bioactivity space, while digestive system was consistently annotated pathway motif, which agreed with the important treatment principle of TCM, “the foundation of acquired constitution” that includes spleen and stomach. In short, the TCM (sub)classes, in many cases share similar targets/pathways despite having different indications.

Target prediction utilising negative bioactivity data covering large chemical space

BACKGROUND

In silico analyses are increasingly being used to support mode-of-action investigations; however many such approaches do not utilise the large amounts of inactive data held in chemogenomic repositories. The objective of this work is concerned with the integration of such bioactivity data in the target prediction of orphan compounds to produce the probability of activity and inactivity for a range of targets. To this end, a novel human bioactivity data set was constructed through the assimilation of over 195 million bioactivity data points deposited in the ChEMBL and PubChem repositories, and the subsequent application of a sphere-exclusion selection algorithm to oversample presumed inactive compounds.

RESULTS

A Bernoulli Naïve Bayes algorithm was trained using the data and evaluated using fivefold cross-validation, achieving a mean recall and precision of 67.7 and 63.8 % for active compounds and 99.6 and 99.7 % for inactive compounds, respectively. We show the performances of the models are considerably influenced by the underlying intraclass training similarity, the size of a given class of compounds, and the degree of additional oversampling. The method was also validated using compounds extracted from WOMBAT producing average precision-recall AUC and BEDROC scores of 0.56 and 0.85, respectively. Inactive data points used for this test are based on presumed inactivity, producing an approximated indication of the true extrapolative ability of the models. A distance-based applicability domain analysis was also conducted; indicating an average Tanimoto Coefficient distance of 0.3 or greater between a test and training set can be used to give a global measure of confidence in model predictions. A final comparison to a method trained solely on active data from ChEMBL performed with precision-recall AUC and BEDROC scores of 0.45 and 0.76.

CONCLUSIONS

The inclusion of inactive data for model training produces models with superior AUC and improved early recognition capabilities, although the results from internal and external validation of the models show differing performance between the breadth of models. The realised target prediction protocol is available at https://github.com/lhm30/PIDGIN.Graphical abstractThe inclusion of large scale negative training data for in silico target prediction improves the precision and recall AUC and BEDROC scores for target models.