Network approaches for modeling the effect of drugs and diseases

Untargeted Metabolome Atlas for Sleep Phenotypes in the Hispanic Community Health Study/Study of Latinos

Sleep is essential to maintaining health and wellbeing of individuals, influencing a variety of outcomes from mental health to cardiometabolic disease. This study aims to assess the relationships between various sleep phenotypes and blood metabolites. Utilizing data from the Hispanic Community Health Study/Study of Latinos, we performed association analyses between 40 sleep phenotypes, grouped in several domains (i.e., sleep disordered breathing (SDB), sleep duration, timing, insomnia symptoms, and heart rate during sleep), and 768 metabolites measured via untargeted metabolomics profiling. Network analysis was employed to visualize and interpret the associations between sleep phenotypes and metabolites. The patterns of statistically significant associations between sleep phenotypes and metabolites differed by superpathways, and highlighted subpathways of interest for future studies. For example, some xenobiotic metabolites were associated with sleep duration and heart rate phenotypes (e.g. 1H-indole-7-acetic acid, 4-allylphenol sulfate), while ketone bodies and fatty acid metabolism metabolites were associated with sleep timing measures (e.g. 3-hydroxybutyrate (BHBA), 3-hydroxyhexanoylcarnitine (1)). Heart rate phenotypes had the overall largest number of detected metabolite associations. Many of these associations were shared with both SDB and with sleep timing phenotypes, while SDB phenotypes shared relatively few metabolite associations with sleep duration measures. A number of metabolites were associated with multiple sleep phenotypes, from a few domains. The amino acids vanillylmandelate (VMA) and 1-carboxyethylisoleucine were associated with the greatest number of sleep phenotypes, from all domains other than insomnia. This atlas of sleep-metabolite associations will facilitate hypothesis generation and further study of the metabolic underpinnings of sleep health.

Optimal fusion of genotype and drug embeddings in predicting cancer drug response

Predicting cancer drug response using both genomics and drug features has shown some success compared to using genomics features alone. However, there has been limited research done on how best to combine or fuse the two types of features. Using a visible neural network with two deep learning branches for genes and drug features as the base architecture, we experimented with different fusion functions and fusion points. Our experiments show that injecting multiplicative relationships between gene and drug latent features into the original concatenation-based architecture DrugCell significantly improved the overall predictive performance and outperformed other baseline models. We also show that different fusion methods respond differently to different fusion points, indicating that the relationship between drug features and different hierarchical biological level of gene features is optimally captured using different methods. Considering both predictive performance and runtime speed, tensor product partial is the best-performing fusion function to combine late-stage representations of drug and gene features to predict cancer drug response.

Computational model for drug research

This special issue focuses on computational model for drug research regarding drug bioactivity prediction, drug-related interaction prediction, modelling for immunotherapy and modelling for treatment of a specific disease, as conveyed by the following six research and four review articles. Notably, these 10 papers described a wide variety of in-depth drug research from the computational perspective and may represent a snapshot of the wide research landscape.

Network-based cytokine inference implicates Oncostatin M as a driver of an inflammation phenotype in knee osteoarthritis

Inflammatory cytokines released by synovium after trauma disturb the gene regulatory network and have been implicated in the pathophysiology of osteoarthritis. A mechanistic understanding of how aging perturbs this process can help identify novel interventions. Here, we introduced network paradigms to simulate cytokine-mediated pathological communication between the synovium and cartilage. Cartilage-specific network analysis of injured young and aged murine knees revealed aberrant matrix remodeling as a transcriptomic response unique to aged knees displaying accelerated cartilage degradation. Next, network-based cytokine inference with pharmacological manipulation uncovered IL6 family member, Oncostatin M (OSM), as a driver of the aberrant matrix remodeling. By implementing a phenotypic drug discovery approach, we identified that the activation of OSM recapitulated an "inflammatory" phenotype of knee osteoarthritis and highlighted high-value targets for drug development and repurposing. These findings offer translational opportunities targeting the inflammation-driven osteoarthritis phenotype.

Assessing network-based methods in the context of system toxicology

Introduction: Network-based methods are promising approaches in systems toxicology because they can be used to predict the effects of drugs and chemicals on health, to elucidate the mode of action of compounds, and to identify biomarkers of toxicity. Over the years, the network biology community has developed a wide range of methods, and users are faced with the task of choosing the most appropriate method for their own application. Furthermore, the advantages and limitations of each method are difficult to determine without a proper standard and comparative evaluation of their performance. This study aims to evaluate different network-based methods that can be used to gain biological insight into the mechanisms of drug toxicity, using valproic acid (VPA)-induced liver steatosis as a benchmark. Methods: We provide a comprehensive analysis of the results produced by each method and highlight the fact that the experimental design (how the method is applied) is relevant in addition to the method specifications. We also contribute with a systematic methodology to analyse the results of the methods individually and in a comparative manner. Results: Our results show that the evaluated tools differ in their performance against the benchmark and in their ability to provide novel insights into the mechanism of adverse effects of the drug. We also suggest that aggregation of the results provided by different methods provides a more confident set of candidate genes and processes to further the knowledge of the drug's mechanism of action. Discussion: By providing a detailed and systematic analysis of the results of different network-based tools, we aim to assist users in making informed decisions about the most appropriate method for systems toxicology applications.

Experimental Murine Models for Colorectal Cancer Research

Colorectal cancer (CRC) is the third most prevalent malignancy worldwide and in both sexes. Numerous animal models for CRC have been established to study its biology, namely carcinogen-induced models (CIMs) and genetically engineered mouse models (GEMMs). CIMs are valuable for assessing colitis-related carcinogenesis and studying chemoprevention. On the other hand, CRC GEMMs have proven to be useful for evaluating the tumor microenvironment and systemic immune responses, which have contributed to the discovery of novel therapeutic approaches. Although metastatic disease can be induced by orthotopic injection of CRC cell lines, the resulting models are not representative of the full genetic diversity of the disease due to the limited number of cell lines suitable for this purpose. On the other hand, patient-derived xenografts (PDX) are the most reliable for preclinical drug development due to their ability to retain pathological and molecular characteristics. In this review, the authors discuss the various murine CRC models with a focus on their clinical relevance, benefits, and drawbacks. From all models discussed, murine CRC models will continue to be an important tool in advancing our understanding and treatment of this disease, but additional research is required to find a model that can correctly reflect the pathophysiology of CRC.

A systematic evaluation of deep learning methods for the prediction of drug synergy in cancer

One of the main obstacles to the successful treatment of cancer is the phenomenon of drug resistance. A common strategy to overcome resistance is the use of combination therapies. However, the space of possibilities is huge and efficient search strategies are required. Machine Learning (ML) can be a useful tool for the discovery of novel, clinically relevant anti-cancer drug combinations. In particular, deep learning (DL) has become a popular choice for modeling drug combination effects. Here, we set out to examine the impact of different methodological choices on the performance of multimodal DL-based drug synergy prediction methods, including the use of different input data types, preprocessing steps and model architectures. Focusing on the NCI ALMANAC dataset, we found that feature selection based on prior biological knowledge has a positive impact-limiting gene expression data to cancer or drug response-specific genes improved performance. Drug features appeared to be more predictive of drug response, with a 41% increase in coefficient of determination (R2) and 26% increase in Spearman correlation relative to a baseline model that used only cell line and drug identifiers. Molecular fingerprint-based drug representations performed slightly better than learned representations-ECFP4 fingerprints increased R2 by 5.3% and Spearman correlation by 2.8% w.r.t the best learned representations. In general, fully connected feature-encoding subnetworks outperformed other architectures. DL outperformed other ML methods by more than 35% (R2) and 14% (Spearman). Additionally, an ensemble combining the top DL and ML models improved performance by about 6.5% (R2) and 4% (Spearman). Using a state-of-the-art interpretability method, we showed that DL models can learn to associate drug and cell line features with drug response in a biologically meaningful way. The strategies explored in this study will help to improve the development of computational methods for the rational design of effective drug combinations for cancer therapy.

Network-based approaches for modeling disease regulation and progression

Molecular interaction networks lay the foundation for studying how biological functions are controlled by the complex interplay of genes and proteins. Investigating perturbed processes using biological networks has been instrumental in uncovering mechanisms that underlie complex disease phenotypes. Rapid advances in omics technologies have prompted the generation of high-throughput datasets, enabling large-scale, network-based analyses. Consequently, various modeling techniques, including network enrichment, differential network extraction, and network inference, have proven to be useful for gaining new mechanistic insights. We provide an overview of recent network-based methods and their core ideas to facilitate the discovery of disease modules or candidate mechanisms. Knowledge generated from these computational efforts will benefit biomedical research, especially drug development and precision medicine. We further discuss current challenges and provide perspectives in the field, highlighting the need for more integrative and dynamic network approaches to model disease development and progression.

Adverse effect signature extraction and prediction for drugs treating COVID-19

Given the considerable cost of drug discovery, drug repurposing is becoming attractive as it can effectively shorten the development timeline and reduce the development cost. However, most existing drug-repurposing methods omitted the heterogeneous health conditions of different COVID-19 patients. In this study, we evaluated the adverse effect (AE) profiles of 106 COVID-19 drugs. We extracted four AE signatures to characterize the AE distribution of 106 COVID-19 drugs by non-negative matrix factorization (NMF). By integrating the information from four distinct databases (AE, bioassay, chemical structure, and gene expression information), we predicted the AE profiles of 91 drugs with inadequate AE feedback. For each of the drug clusters, discriminant genes accounting for mechanisms of different AE signatures were identified by sparse linear discriminant analysis. Our findings can be divided into three parts. First, drugs abundant with AE-signature 1 (for example, remdesivir) should be taken with caution for patients with poor liver, renal, or cardiac functions, where the functional genes accumulate in the RHO GTPases Activate NADPH Oxidases pathway. Second, drugs featuring AE-signature 2 (for example, hydroxychloroquine) are unsuitable for patients with vascular disorders, with relevant genes enriched in signal transduction pathways. Third, drugs characterized by AE signatures 3 and 4 have relatively mild AEs. Our study showed that NMF and network-based frameworks contribute to more precise drug recommendations.