Small Gene Networks Delineate Immune Cell States and Characterize Immunotherapy Response in Melanoma.

Single-cell technologies have elucidated mechanisms responsible for immune checkpoint inhibitor (ICI) response, but are not amenable to a clinical diagnostic setting. In contrast, bulk RNA sequencing (RNA-seq) is now routine for research and clinical applications. Our workflow uses transcription factor (TF)-directed coexpression networks (regulons) inferred from single-cell RNA-seq data to deconvolute immune functional states from bulk RNA-seq data. Regulons preserve the phenotypic variation in CD45+ immune cells from metastatic melanoma samples (n = 19, discovery dataset) treated with ICIs, despite reducing dimensionality by >100-fold. Four cell states, termed exhausted T cells, monocyte lineage cells, memory T cells, and B cells were associated with therapy response, and were characterized by differentially active and cell state-specific regulons. Clustering of bulk RNA-seq melanoma samples from four independent studies (n = 209, validation dataset) according to regulon-inferred scores identified four groups with significantly different response outcomes (P < 0.001). An intercellular link was established between exhausted T cells and monocyte lineage cells, whereby their cell numbers were correlated, and exhausted T cells predicted prognosis as a function of monocyte lineage cell number. The ligand-receptor expression analysis suggested that monocyte lineage cells drive exhausted T cells into terminal exhaustion through programs that regulate antigen presentation, chronic inflammation, and negative costimulation. Together, our results demonstrate how regulon-based characterization of cell states provide robust and functionally informative markers that can deconvolve bulk RNA-seq data to identify ICI responders.

A review of biomedical datasets relating to drug discovery: a knowledge graph perspective.

Drug discovery and development is a complex and costly process. Machine learning approaches are being investigated to help improve the effectiveness and speed of multiple stages of the drug discovery pipeline. Of these, those that use Knowledge Graphs (KG) have promise in many tasks, including drug repurposing, drug toxicity prediction and target gene-disease prioritization. In a drug discovery KG, crucial elements including genes, diseases and drugs are represented as entities, while relationships between them indicate an interaction. However, to construct high-quality KGs, suitable data are required. In this review, we detail publicly available sources suitable for use in constructing drug discovery focused KGs. We aim to help guide machine learning and KG practitioners who are interested in applying new techniques to the drug discovery field, but who may be unfamiliar with the relevant data sources. The datasets are selected via strict criteria, categorized according to the primary type of information contained within and are considered based upon what information could be extracted to build a KG. We then present a comparative analysis of existing public drug discovery KGs and an evaluation of selected motivating case studies from the literature. Additionally, we raise numerous and unique challenges and issues associated with the domain and its datasets, while also highlighting key future research directions. We hope this review will motivate KGs use in solving key and emerging questions in the drug discovery domain.

Implications of topological imbalance for representation learning on biomedical knowledge graphs.

Adoption of recently developed methods from machine learning has given rise to creation of drug-discovery knowledge graphs (KGs) that utilize the interconnected nature of the domain. Graph-based modelling of the data, combined with KG embedding (KGE) methods, are promising as they provide a more intuitive representation and are suitable for inference tasks such as predicting missing links. One common application is to produce ranked lists of genes for a given disease, where the rank is based on the perceived likelihood of association between the gene and the disease. It is thus critical that these predictions are not only pertinent but also biologically meaningful. However, KGs can be biased either directly due to the underlying data sources that are integrated or due to modelling choices in the construction of the graph, one consequence of which is that certain entities can get topologically overrepresented. We demonstrate the effect of these inherent structural imbalances, resulting in densely connected entities being highly ranked no matter the context. We provide support for this observation across different datasets, models as well as predictive tasks. Further, we present various graph perturbation experiments which yield more support to the observation that KGE models can be more influenced by the frequency of entities rather than any biological information encoded within the relations. Our results highlight the importance of data modelling choices, and emphasizes the need for practitioners to be mindful of these issues when interpreting model outputs and during KG composition.

Probabilistic Random Forest improves bioactivity predictions close to the classification threshold by taking into account experimental uncertainty.

Measurements of protein-ligand interactions have reproducibility limits due to experimental errors. Any model based on such assays will consequentially have such unavoidable errors influencing their performance which should ideally be factored into modelling and output predictions, such as the actual standard deviation of experimental measurements (σ) or the associated comparability of activity values between the aggregated heterogenous activity units (i.e., Ki versus IC50 values) during dataset assimilation. However, experimental errors are usually a neglected aspect of model generation. In order to improve upon the current state-of-the-art, we herein present a novel approach toward predicting protein-ligand interactions using a Probabilistic Random Forest (PRF) classifier. The PRF algorithm was applied toward in silico protein target prediction across ~ 550 tasks from ChEMBL and PubChem. Predictions were evaluated by taking into account various scenarios of experimental standard deviations in both training and test sets and performance was assessed using fivefold stratified shuffled splits for validation. The largest benefit in incorporating the experimental deviation in PRF was observed for data points close to the binary threshold boundary, when such information was not considered in any way in the original RF algorithm. For example, in cases when σ ranged between 0.4-0.6 log units and when ideal probability estimates between 0.4-0.6, the PRF outperformed RF with a median absolute error margin of ~ 17%. In comparison, the baseline RF outperformed PRF for cases with high confidence to belong to the active class (far from the binary decision threshold), although the RF models gave errors smaller than the experimental uncertainty, which could indicate that they were overtrained and/or over-confident. Finally, the PRF models trained with putative inactives decreased the performance compared to PRF models without putative inactives and this could be because putative inactives were not assigned an experimental pXC50 value, and therefore they were considered inactives with a low uncertainty (which in practice might not be true). In conclusion, PRF can be useful for target prediction models in particular for data where class boundaries overlap with the measurement uncertainty, and where a substantial part of the training data is located close to the classification threshold.

Comparison of Chemical Structure and Cell Morphology Information for Multitask Bioactivity Predictions.

The understanding of the mechanism-of-action (MoA) of compounds and the prediction of potential drug targets play an important role in small-molecule drug discovery. The aim of this work was to compare chemical and cell morphology information for bioactivity prediction. The comparison was performed using bioactivity data from the ExCAPE database, image data (in the form of CellProfiler features) from the Cell Painting data set (the largest publicly available data set of cell images with ∼30,000 compound perturbations), and extended connectivity fingerprints (ECFPs) using the multitask Bayesian matrix factorization (BMF) approach Macau. We found that the BMF Macau and random forest (RF) performance were overall similar when ECFPs were used as compound descriptors. However, BMF Macau outperformed RF in 159 out of 224 targets (71%) when image data were used as compound information. Using BMF Macau, 100 (corresponding to about 45%) and 90 (about 40%) of the 224 targets were predicted with high predictive performance (AUC > 0.8) with ECFP data and image data as side information, respectively. There were targets better predicted by image data as side information, such as ß-catenin, and others better predicted by fingerprint-based side information, such as proteins belonging to the G-protein-Coupled Receptor 1 family, which could be rationalized from the underlying data distributions in each descriptor domain. In conclusion, both cell morphology changes and chemical structure information contain information about compound bioactivity, which is also partially complementary, and can hence contribute to in silico MoA analysis.

Drug Screening in Human PSC-Cardiac Organoids Identifies Pro-proliferative Compounds Acting via the Mevalonate Pathway.

We have previously developed a high-throughput bioengineered human cardiac organoid (hCO) platform, which provides functional contractile tissue with biological properties similar to native heart tissue, including mature, cell-cycle-arrested cardiomyocytes. In this study, we perform functional screening of 105 small molecules with pro-regenerative potential. Our findings reveal surprising discordance between our hCO system and traditional 2D assays. In addition, functional analyses uncovered detrimental effects of many hit compounds. Two pro-proliferative small molecules without detrimental impacts on cardiac function were identified. High-throughput proteomics in hCO revealed synergistic activation of the mevalonate pathway and a cell-cycle network by the pro-proliferative compounds. Cell-cycle reentry in hCO and in vivo required the mevalonate pathway as inhibition of the mevalonate pathway with a statin attenuated pro-proliferative effects. This study highlights the utility of human cardiac organoids for pro-regenerative drug development, including identification of underlying biological mechanisms and minimization of adverse side effects.

Orally Bioavailable and Blood-Brain Barrier-Penetrating ATM Inhibitor (AZ32) Radiosensitizes Intracranial Gliomas in Mice.

Inhibition of ataxia-telangiectasia mutated (ATM) during radiotherapy of glioblastoma multiforme (GBM) may improve tumor control by short-circuiting the response to radiation-induced DNA damage. A major impediment for clinical implementation is that current inhibitors have limited central nervous system (CNS) bioavailability; thus, the goal was to identify ATM inhibitors (ATMi) with improved CNS penetration. Drug screens and refinement of lead compounds identified AZ31 and AZ32. The compounds were then tested in vivo for efficacy and impact on tumor and healthy brain. Both AZ31 and AZ32 blocked the DNA damage response and radiosensitized GBM cells in vitro AZ32, with enhanced blood-brain barrier (BBB) penetration, was highly efficient in vivo as radiosensitizer in syngeneic and human, orthotopic mouse glioma model compared with AZ31. Furthermore, human glioma cell lines expressing mutant p53 or having checkpoint-defective mutations were particularly sensitive to ATMi radiosensitization. The mechanism for this p53 effect involves a propensity to undergo mitotic catastrophe relative to cells with wild-type p53. In vivo, apoptosis was >6-fold higher in tumor relative to healthy brain after exposure to AZ32 and low-dose radiation. AZ32 is the first ATMi with oral bioavailability shown to radiosensitize glioma and improve survival in orthotopic mouse models. These findings support the development of a clinical-grade, BBB-penetrating ATMi for the treatment of GBM. Importantly, because many GBMs have defective p53 signaling, the use of an ATMi concurrent with standard radiotherapy is expected to be cancer-specific, increase the therapeutic ratio, and maintain full therapeutic effect at lower radiation doses. Mol Cancer Ther; 17(8); 1637-47. ©2018 AACR.

Kinase Inhibition Leads to Hormesis in a Dual Phosphorylation-Dephosphorylation Cycle.

Many antimicrobial and anti-tumour drugs elicit hormetic responses characterised by low-dose stimulation and high-dose inhibition. While this can have profound consequences for human health, with low drug concentrations actually stimulating pathogen or tumour growth, the mechanistic understanding behind such responses is still lacking. We propose a novel, simple but general mechanism that could give rise to hormesis in systems where an inhibitor acts on an enzyme. At its core is one of the basic building blocks in intracellular signalling, the dual phosphorylation-dephosphorylation motif, found in diverse regulatory processes including control of cell proliferation and programmed cell death. Our analytically-derived conditions for observing hormesis provide clues as to why this mechanism has not been previously identified. Current mathematical models regularly make simplifying assumptions that lack empirical support but inadvertently preclude the observation of hormesis. In addition, due to the inherent population heterogeneities, the presence of hormesis is likely to be masked in empirical population-level studies. Therefore, examining hormetic responses at single-cell level coupled with improved mathematical models could substantially enhance detection and mechanistic understanding of hormesis.

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.

Cancer genome analysis informatics.

The analysis of cancer genomes has benefited from the advances in technology that enable data to be generated on an unprecedented scale, describing a tumour genome's sequence and composition at increasingly high resolution and reducing cost. This progress is likely to increase further over the coming years as next-generation sequencing approaches are applied to the study of cancer genomes, in tandem with large-scale efforts such as the Cancer Genome Atlas and recently announced International Cancer Genome Consortium efforts to complement those already established such as the Sanger Institute Cancer Genome Project. This presents challenges for the cancer researcher and the research community in general, in terms of analysing the data generated in one's own projects and also in coordinating and interrogating data that are publicly available. This review aims to provide a brief overview of some of the main informatics resources currently available and their use, and some of the informatics approaches that may be applied in the study of cancer genomes.