Large-Scale Off-Target Identification Using Fast and Accurate Dual Regularized One-Class Collaborative Filtering and Its Application to Drug Repurposing

Comprehensive applications of the artificial intelligence technology in new drug research and development

Purpose

Target-based strategy is a prevalent means of drug research and development (R&D), since targets provide effector molecules of drug action and offer the foundation of pharmacological investigation. Recently, the artificial intelligence (AI) technology has been utilized in various stages of drug R&D, where AI-assisted experimental methods show higher efficiency than sole experimental ones. It is a critical need to give a comprehensive review of AI applications in drug R &D for biopharmaceutical field.

Methods

Relevant literatures about AI-assisted drug R&D were collected from the public databases (Including Google Scholar, Web of Science, PubMed, IEEE Xplore Digital Library, Springer, and ScienceDirect) through a keyword searching strategy with the following terms [("Artificial Intelligence" OR "Knowledge Graph" OR "Machine Learning") AND ("Drug Target Identification" OR "New Drug Development")].

Results

In this review, we first introduced common strategies and novel trends of drug R&D, followed by characteristic description of AI algorithms widely used in drug R&D. Subsequently, we depicted detailed applications of AI algorithms in target identification, lead compound identification and optimization, drug repurposing, and drug analytical platform construction. Finally, we discussed the challenges and prospects of AI-assisted methods for drug discovery.

Conclusion

Collectively, this review provides comprehensive overview of AI applications in drug R&D and presents future perspectives for biopharmaceutical field, which may promote the development of drug industry.

Network-based approach for drug repurposing against mpox

The current outbreak of mpox presents a significant threat to the global community. However, the lack of mpox-specific drugs necessitates the identification of additional candidates for clinical trials. In this study, a network medicine framework was used to investigate poxviruses-human interactions to identify potential drugs effective against the mpox virus (MPXV). The results indicated that poxviruses preferentially target hubs on the human interactome, and that these virally-targeted proteins (VTPs) tend to aggregate together within specific modules. Comorbidity analysis revealed that mpox is closely related to immune system diseases. Based on predicted drug-target interactions, 268 drugs were identified using the network proximity approach, among which 23 drugs displaying the least side-effects and significant proximity to MPXV were selected as the final candidates. Lastly, specific drugs were explored based on VTPs, differentially expressed proteins, and intermediate nodes, corresponding to different categories. These findings provide novel insights that can contribute to a deeper understanding of the pathogenesis of MPXV and development of ready-to-use treatment strategies based on drug repurposing.

Innovative target mining stratagems to navigate drug repurposing endeavours

The conventional theory linking a single gene with a particular disease and a specific drug contributes to the dwindling success rates of traditional drug discovery. This requires a substantial shift focussing on contemporary drug design or drug repurposing, which entails linking multiple genes to diverse physiological or pathological pathways and drugs. Lately, drug repurposing, the art of discovering new/unlabelled indications for existing drugs or candidates in clinical trials, is gaining attention owing to its success rates. The rate-limiting phase of this strategy lies in target identification, which is generally driven through disease-centric and/or drug-centric approaches. The disease-centric approach is based on exploration of crucial biomolecules such as genes or proteins underlying pathological cascades of the disease of interest. Investigating these pathological interplays aids in the identification of potential drug targets that can be leveraged for novel therapeutic interventions. The drug-centric approach involves various strategies such as exploring the mechanism of adverse drug reactions that can unearth potential targets, as these untoward reactions might be considered desirable therapeutic actions in other disease conditions. Currently, artificial intelligence is an emerging robust tool that can be used to translate the aforementioned intricate biological networks to render interpretable data for extracting precise molecular targets. Integration of multiple approaches, big data analytics, and clinical corroboration are essential for successful target mining. This chapter highlights the contemporary strategies steering target identification and diverse frameworks for drug repurposing. These strategies are illustrated through case studies curated from recent drug repurposing research inclined towards neurodegenerative diseases, cancer, infections, immunological, and cardiovascular disorders.

Histone deacetylase inhibitor RG2833 has therapeutic potential for Alzheimer's disease in females

Nearly two-thirds of patients with Alzheimer's are women. Identifying therapeutics specific for women is critical to lowering their elevated risk for developing this major cause of adult dementia. Moreover, targeting epigenetic processes that regulate multiple cellular pathways is advantageous given Alzheimer's multifactorial nature. Histone acetylation is an epigenetic process heavily involved in memory consolidation. Its disruption is linked to Alzheimer's. Through our computational studies, we predicted that the investigational drug RG2833 (N-[6-(2-aminoanilino)-6-oxohexyl]-4-methylbenzamide) has repurposing potential for Alzheimer's. RG2833 is a histone deacetylase HDAC1/3 inhibitor that is orally bioavailable and permeates the blood-brain-barrier. We investigated the RG2833 therapeutic potential in TgF344-AD rats, which are a model of Alzheimer's that exhibits age-dependent progression, thus mimicking this aspect of Alzheimer's patients that is difficult to establish in animal models. We investigated the RG2833 effects on cognitive performance, gene expression, and AD-like pathology in 11-month TgF344-AD female and male rats. A total of 89 rats were used: wild type n = 45 (17 females, 28 males), and TgF344-AD n = 44 (24 females, 20 males)] across multiple cohorts. No obvious toxicity was detected in the TgF344-AD rats up to 6 months of RG2833-treatment starting at 5 months of age administering the drug in rodent chow at ∼30mg/kg of body weight. We started treatment early in the course of pathology when therapeutic intervention is predicted to be more effective than in later stages of the disease. The drug-treatment significantly mitigated hippocampal-dependent spatial memory deficits in 11-month TgF344-AD females but not in males, compared to wild type littermates. This female sex-specific drug effect has not been previously reported. RG2833-treatment failed to ameliorate amyloid beta accumulation and microgliosis in female and male TgF344-AD rats. However, RNAseq analysis of hippocampal tissue from TgF344-AD rats showed that drug-treatment in females upregulated the expression of immediate early genes, such as Arc, Egr1 and c-Fos, and other genes involved in synaptic plasticity and memory consolidation. Remarkably, out of 17,168 genes analyzed for each sex, no significant changes in gene expression were detected in males at P < 0.05, false discovery rate < 0.05, and fold-change ≥ 1.5. Our data suggest that histone modifying therapeutics such as RG2833 improve cognitive behavior by modulating the expression of immediate early, neuroprotective and synaptic plasticity genes. Our preclinical study supports that RG2833 has therapeutic potential specifically for female Alzheimer's patients. RG2833 evaluations using other AD-related models is necessary to confirm our findings.

Clustering Protein Binding Pockets and Identifying Potential Drug Interactions: A Novel Ligand-Based Featurization Method

Protein-ligand interactions are essential to drug discovery and drug development efforts. Desirable on-target or multitarget interactions are the first step in finding an effective therapeutic, while undesirable off-target interactions are the first step in assessing safety. In this work, we introduce a novel ligand-based featurization and mapping of human protein pockets to identify closely related protein targets and to project novel drugs into a hybrid protein-ligand feature space to identify their likely protein interactions. Using structure-based template matches from PDB, protein pockets are featured by the ligands that bind to their best co-complex template matches. The simplicity and interpretability of this approach provide a granular characterization of the human proteome at the protein-pocket level instead of the traditional protein-level characterization by family, function, or pathway. We demonstrate the power of this featurization method by clustering a subset of the human proteome and evaluating the predicted cluster associations of over 7000 compounds.

An effective multi-task learning framework for drug repurposing based on graph representation learning

Drug repurposing, which typically applies the procedure of drug-disease associations (DDAs) prediction, is a feasible solution to drug discovery. Compared with traditional methods, drug repurposing can reduce the cost and time for drug development and advance the success rate of drug discovery. Although many methods for drug repurposing have been proposed and the obtained results are relatively acceptable, there is still some room for improving the predictive performance, since those methods fail to consider fully the issue of sparseness in known drug-disease associations. In this paper, we propose a novel multi-task learning framework based on graph representation learning to identify DDAs for drug repurposing. In our proposed framework, a heterogeneous information network is first constructed by combining multiple biological datasets. Then, a module consisting of multiple layers of graph convolutional networks is utilized to learn low-dimensional representations of nodes in the constructed heterogeneous information network. Finally, two types of auxiliary tasks are designed to help to train the target task of DDAs prediction in the multi-task learning framework. Comprehensive experiments are conducted on real data and the results demonstrate the effectiveness of the proposed method for drug repurposing.

Network-Based Prediction of Side Effects of Repurposed Antihypertensive Sartans against COVID-19 via Proteome and Drug-Target Interactomes

The potential of targeting the Renin-Angiotensin-Aldosterone System (RAAS) as a treatment for the coronavirus disease 2019 (COVID-19) is currently under investigation. One way to combat this disease involves the repurposing of angiotensin receptor blockers (ARBs), which are antihypertensive drugs, because they bind to angiotensin-converting enzyme 2 (ACE2), which in turn interacts with the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike protein. However, there has been no in silico analysis of the potential toxicity risks associated with the use of these drugs for the treatment of COVID-19. To address this, a network-based bioinformatics methodology was used to investigate the potential side effects of known Food and Drug Administration (FDA)-approved antihypertensive drugs, Sartans. This involved identifying the human proteins targeted by these drugs, their first neighbors, and any drugs that bind to them using publicly available experimentally supported data, and subsequently constructing proteomes and protein-drug interactomes. This methodology was also applied to Pfizer's Paxlovid, an antiviral drug approved by the FDA for emergency use in mild-to-moderate COVID-19 treatment. The study compares the results for both drug categories and examines the potential for off-target effects, undesirable involvement in various biological processes and diseases, possible drug interactions, and the potential reduction in drug efficiency resulting from proteoform identification.

Artificial Intelligence and Machine Learning for Lead-to-Candidate Decision-Making and Beyond

The use of artificial intelligence (AI) and machine learning (ML) in pharmaceutical research and development has to date focused on research: target identification; docking-, fragment-, and motif-based generation of compound libraries; modeling of synthesis feasibility; rank-ordering likely hits according to structural and chemometric similarity to compounds having known activity and affinity to the target(s); optimizing a smaller library for synthesis and high-throughput screening; and combining evidence from screening to support hit-to-lead decisions. Applying AI/ML methods to lead optimization and lead-to-candidate (L2C) decision-making has shown slower progress, especially regarding predicting absorption, distribution, metabolism, excretion, and toxicology properties. The present review surveys reasons why this is so, reports progress that has occurred in recent years, and summarizes some of the issues that remain. Effective AI/ML tools to derisk L2C and later phases of development are important to accelerate the pharmaceutical development process, ameliorate escalating development costs, and achieve greater success rates.

Hyperbolic matrix factorization improves prediction of drug-target associations

Past research in computational systems biology has focused more on the development and applications of advanced statistical and numerical optimization techniques and much less on understanding the geometry of the biological space. By representing biological entities as points in a low dimensional Euclidean space, state-of-the-art methods for drug-target interaction (DTI) prediction implicitly assume the flat geometry of the biological space. In contrast, recent theoretical studies suggest that biological systems exhibit tree-like topology with a high degree of clustering. As a consequence, embedding a biological system in a flat space leads to distortion of distances between biological objects. Here, we present a novel matrix factorization methodology for drug-target interaction prediction that uses hyperbolic space as the latent biological space. When benchmarked against classical, Euclidean methods, hyperbolic matrix factorization exhibits superior accuracy while lowering embedding dimension by an order of magnitude. We see this as additional evidence that the hyperbolic geometry underpins large biological networks.

Concepts and applications of chemical fingerprint for hit and lead screening

Molecular fingerprints are used to represent chemical (structural, physicochemical, etc.) properties of large-scale chemical sets in a low computational cost way. They have a prominent role in transforming chemical data sets into consistent input formats (bit strings or numeric values) suitable for in silico approaches. In this review, we summarize and classify common and state-of-the-art fingerprints into eight different types (dictionary based, circular, topological, pharmacophore, protein-ligand interaction, shape based, reinforced, and multi). We also highlight applications of fingerprints in early drug research and development (R&D). Thus, this review provides a guide for the selection of appropriate fingerprints of compounds (or ligand-protein complexes) for use in drug R&D.

A Knowledge Graph-Enhanced Tensor Factorisation Model for Discovering Drug Targets

The drug discovery and development process is a long and expensive one, costing over 1 billion USD on average per drug and taking 10-15 years. To reduce the high levels of attrition throughout the process, there has been a growing interest in applying machine learning methodologies to various stages of drug discovery and development in the recent decade, especially at the earliest stage - identification of druggable disease genes. In this paper, we have developed a new tensor factorisation model to predict potential drug targets (genes or proteins) for treating diseases. We created a three-dimensional data tensor consisting of 1,048 gene targets, 860 diseases and 230,011 evidence attributes and clinical outcomes connecting them, using data extracted from the Open Targets and PharmaProjects databases. We enriched the data with gene target representations learned from a drug discovery-oriented knowledge graph and applied our proposed method to predict the clinical outcomes for unseen gene target and disease pairs. We designed three evaluation strategies to measure the prediction performance and benchmarked several commonly used machine learning classifiers together with Bayesian matrix and tensor factorisation methods. The result shows that incorporating knowledge graph embeddings significantly improves the prediction accuracy and that training tensor factorisation alongside a dense neural network outperforms all other baselines. In summary, our framework combines two actively studied machine learning approaches to disease target identification, namely tensor factorisation and knowledge graph representation learning, which could be a promising avenue for further exploration in data-driven drug discovery.

A Neighborhood-Based Global Network Model to Predict Drug-Target Interactions

The detection of drug-target interactions (DTIs) plays an important role in drug discovery and development, making DTI prediction urgent to be solved. Existing computational methods usually utilize drug similarity, target similarity and DTI information to make prediction, providing the convenience of fast time and low cost. However, they usually learn features for drugs and targets separately, lacking of a global consideration. In this study, we proposed a novel neighborhood-based global network model, named as NGN, to accurately predict DTIs from the global perspective. We designed a distance constraint for features of all entities (drugs and targets) in the latent space to ensure the close distance between adjacent entities, and defined a global probability matrix to compute the predicted DTI scores on our constructed neighborhood-based global network. Results showed that NGN obtained advantageous performance compared with other state-of-the-art methods, especially surpassing them by 4.2-9.1 percent on AUPR values in the biggest dataset. Furthermore, several novel high-ranked DTIs were successfully predicted with confirmations by public sources, demonstrating the effectiveness of our method.

Overcoming Sparseness of Biomedical Networks to Identify Drug Repositioning Candidates

Modeling complex biological systems is necessary to understand biochemical interactions behind pharmacological effects of drugs. Successful in silico drug repurposing relies on exploration of diverse biochemical concepts and their relationships, including drug's adverse reactions, drug targets, disease symptoms, as well as disease associated genes and their pathways, to name a few. We present a computational method for inferring drug-disease associations from complex but incomplete and biased biological networks. Our method employs matrix completion to overcome the sparseness of biomedical data and to enrich the set of relationships between different biomedical entities. We present a strategy for identifying network paths supportive of drug efficacy as well as a computational procedure capable of combining different network patterns to better distinguish treatments from non-treatments. The algorithms is available at http://bioinfo.cs.uni.edu/AEONET.html.

A comprehensive review of Artificial Intelligence and Network based approaches to drug repurposing in Covid-19

Conventional drug discovery and development is tedious and time-taking process; because of which it has failed to keep the required pace to mitigate threats and cater demands of viral and re-occurring diseases, such as Covid-19. The main reasons of this delay in traditional drug development are: high attrition rates, extensive time requirements, and huge financial investment with significant risk. The effective solution to de novo drug discovery is drug repurposing. Previous studies have shown that the network-based approaches and analysis are versatile platform for repurposing as the network biology is used to model the interactions between variety of biological concepts. Herein, we provide a comprehensive background of machine learning and deep learning in drug repurposing while specifically focusing on the applications of network-based approach to drug repurposing in Covid-19, data sources, and tools used. Furthermore, use of network proximity, network diffusion, and AI on network-based drug repurposing for Covid-19 is well-explained. Finally, limitations of network-based approaches in general and specific to network are stated along with future recommendations for better network-based models.

Boost-RS: boosted embeddings for recommender systems and its application to enzyme-substrate interaction prediction

MOTIVATION

Despite experimental and curation efforts, the extent of enzyme promiscuity on substrates continues to be largely unexplored and under documented. Providing computational tools for the exploration of the enzyme-substrate interaction space can expedite experimentation and benefit applications such as constructing synthesis pathways for novel biomolecules, identifying products of metabolism on ingested compounds, and elucidating xenobiotic metabolism. Recommender systems (RS), which are currently unexplored for the enzyme-substrate interaction prediction problem, can be utilized to provide enzyme recommendations for substrates, and vice versa. The performance of Collaborative-Filtering (CF) RSs; however, hinges on the quality of embedding vectors of users and items (enzymes and substrates in our case). Importantly, enhancing CF embeddings with heterogeneous auxiliary data, specially relational data (e.g. hierarchical, pairwise or groupings), remains a challenge.

RESULTS

We propose an innovative general RS framework, termed Boost-RS that enhances RS performance by 'boosting' embedding vectors through auxiliary data. Specifically, Boost-RS is trained and dynamically tuned on multiple relevant auxiliary learning tasks Boost-RS utilizes contrastive learning tasks to exploit relational data. To show the efficacy of Boost-RS for the enzyme-substrate prediction interaction problem, we apply the Boost-RS framework to several baseline CF models. We show that each of our auxiliary tasks boosts learning of the embedding vectors, and that contrastive learning using Boost-RS outperforms attribute concatenation and multi-label learning. We also show that Boost-RS outperforms similarity-based models. Ablation studies and visualization of learned representations highlight the importance of using contrastive learning on some of the auxiliary data in boosting the embedding vectors.

AVAILABILITY AND IMPLEMENTATION

A Python implementation for Boost-RS is provided at https://github.com/HassounLab/Boost-RS. The enzyme-substrate interaction data is available from the KEGG database (https://www.genome.jp/kegg/).

Targeting matrix metallopeptidase 2 by hydroxyurea selectively kills acute myeloid mixed-lineage leukemia

Oncogene-induced tumorigenesis results in the variation of epigenetic modifications, and in addition to promoting cell immortalization, cancer cells undergo more intense cellular stress than normal cells and depend on other support genes for survival. Chromosomal translocations of mixed-lineage leukemia (MLL) induce aggressive leukemias with an inferior prognosis. Unfortunately, most MLL-rearranged (MLL-r) leukemias are resistant to conventional chemotherapies. Here, we showed that hydroxyurea (HU) could kill MLL-r acute myeloid leukemia (AML) cells through the necroptosis process. HU target these cells by matrix metallopeptidase 2 (MMP2) deficiency rather than subordinate ribonucleotide reductase regulatory subunit M2 (RRM2) inhibition, where MLL directly regulates MMP2 expression and is decreased in most MLL-r AMLs. Moreover, iron chelation of HU is also indispensable for inducing cell stress, and MMP2 is the support factor to protect cells from death. Our preliminary study indicates that MMP2 might play a role in the nonsense-mediated mRNA decay pathway that prevents activation of unfolding protein response under innocuous endoplasmic reticulum stress. Hence, these results reveal a possible strategy of HU application in MLL-r AML treatment and shed new light upon HU repurposing.

DeepREAL: A Deep Learning Powered Multi-scale Modeling Framework for Predicting Out-of-distribution Ligand-induced GPCR Activity

Motivation

Drug discovery has witnessed intensive exploration of predictive modeling of drug–target physical interactions over two decades. However, a critical knowledge gap needs to be filled for correlating drug–target interactions with clinical outcomes: predicting genome-wide receptor activities or function selectivity, especially agonist versus antagonist, induced by novel chemicals. Two major obstacles compound the difficulty on this task: known data of receptor activity is far too scarce to train a robust model in light of genome-scale applications, and real-world applications need to deploy a model on data from various shifted distributions.

Results

To address these challenges, we have developed an end-to-end deep learning framework, DeepREAL, for multi-scale modeling of genome-wide ligand-induced receptor activities. DeepREAL utilizes self-supervised learning on tens of millions of protein sequences and pre-trained binary interaction classification to solve the data distribution shift and data scarcity problems. Extensive benchmark studies on G-protein coupled receptors (GPCRs), which simulate real-world scenarios, demonstrate that DeepREAL achieves state-of-the-art performances in out-of-distribution settings. DeepREAL can be extended to other gene families beyond GPCRs.

Availability and implementation

All data used are downloaded from Pfam (Mistry et al., 2020), GLASS (Chan et al., 2015) and IUPHAR/BPS and the data from reference (Sakamuru et al., 2021). Readers are directed to their official website for original data. Code is available on GitHub https://github.com/XieResearchGroup/DeepREAL.

Supplementary information

Supplementary data are available at Bioinformatics online.

A Comprehensive Evaluation of Sdox, a Promising H2S-Releasing Doxorubicin for the Treatment of Chemoresistant Tumors

Sdox is a hydrogen sulfide (H₂S)-releasing doxorubicin effective in P-glycoprotein-overexpressing/doxorubicin-resistant tumor models and not cytotoxic, as the parental drug, in H9c2 cardiomyocytes. The aim of this study was the assessment of Sdox drug-like features and its absorption, distribution, metabolism, and excretion (ADME)/toxicity properties, by a multi- and transdisciplinary in silico, in vitro, and in vivo approach. Doxorubicin was used as the reference compound. The in silico profiling suggested that Sdox possesses higher lipophilicity and lower solubility compared to doxorubicin, and the off-targets prediction revealed relevant differences between Dox and Sdox towards several cancer targets, suggesting different toxicological profiles. In vitro data showed that Sdox is a substrate with lower affinity for P-glycoprotein, less hepatotoxic, and causes less oxidative damage than doxorubicin. Both anthracyclines inhibited CYP3A4, but not hERG currents. Unlike doxorubicin, the percentage of zebrafish live embryos at 72 hpf was not affected by Sdox treatment. In conclusion, these findings demonstrate that Sdox displays a more favorable drug-like ADME/toxicity profile than doxorubicin, different selectivity towards cancer targets, along with a greater preclinical efficacy in resistant tumors. Therefore, Sdox represents a prototype of innovative anthracyclines, worthy of further investigations in clinical settings.

Hypergraph-based logistic matrix factorization for metabolite-disease interaction prediction

MOTIVATION

Function-related metabolites, the terminal products of the cell regulation, show a close association with complex diseases. The identification of disease-related metabolites is critical to the diagnosis, prevention and treatment of diseases. However, most existing computational approaches build networks by calculating pairwise relationships, which is inappropriate for mining higher-order relationships.

RESULTS

In this study, we presented a novel approach with hypergraph-based logistic matrix factorization, HGLMF, to predict the potential interactions between metabolites and disease. First, the molecular structures and gene associations of metabolites and the hierarchical structures and GO functional annotations of diseases were extracted to build various similarity measures of metabolites and diseases. Next, the kernel neighborhood similarity of metabolites (or diseases) was calculated according to the completed interactive network. Second, multiple networks of metabolites and diseases were fused, respectively, and the hypergraph structures of metabolites and diseases were built. Finally, a logistic matrix factorization based on hypergraph was proposed to predict potential metabolite-disease interactions. In computational experiments, HGLMF accurately predicted the metabolite-disease interaction, and performed better than other state-of-the-art methods. Moreover, HGLMF could be used to predict new metabolites (or diseases). As suggested from the case studies, the proposed method could discover novel disease-related metabolites, which has been confirmed in existing studies.

AVAILABILITY AND IMPLEMENTATION

The codes and dataset are available at: https://github.com/Mayingjun20179/HGLMF.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Evaluating the performance of drug-repurposing technologies

Drug-repurposing technologies are growing in number and maturing. However, comparisons to each other and to reality are hindered because of a lack of consensus with respect to performance evaluation. Such comparability is necessary to determine scientific merit and to ensure that only meaningful predictions from repurposing technologies carry through to further validation and eventual patient use. Here, we review and compare performance evaluation measures for these technologies using version 2 of our shotgun repurposing Computational Analysis of Novel Drug Opportunities (CANDO) platform to illustrate their benefits, drawbacks, and limitations. Understanding and using different performance evaluation metrics ensures robust cross-platform comparability, enabling us to continue to strive toward optimal repurposing by decreasing the time and cost of drug discovery and development.

A unified drug-target interaction prediction framework based on knowledge graph and recommendation system

Prediction of drug-target interactions (DTI) plays a vital role in drug development in various areas, such as virtual screening, drug repurposing and identification of potential drug side effects. Despite extensive efforts have been invested in perfecting DTI prediction, existing methods still suffer from the high sparsity of DTI datasets and the cold start problem. Here, we develop KGE_NFM, a unified framework for DTI prediction by combining knowledge graph (KG) and recommendation system. This framework firstly learns a low-dimensional representation for various entities in the KG, and then integrates the multimodal information via neural factorization machine (NFM). KGE_NFM is evaluated under three realistic scenarios, and achieves accurate and robust predictions on four benchmark datasets, especially in the scenario of the cold start for proteins. Our results indicate that KGE_NFM provides valuable insight to integrate KG and recommendation system-based techniques into a unified framework for novel DTI discovery.

MSA-Regularized Protein Sequence Transformer toward Predicting Genome-Wide Chemical-Protein Interactions: Application to GPCRome Deorphanization

Small molecules play a critical role in modulating biological systems. Knowledge of chemical-protein interactions helps address fundamental and practical questions in biology and medicine. However, with the rapid emergence of newly sequenced genes, the endogenous or surrogate ligands of a vast number of proteins remain unknown. Homology modeling and machine learning are two major methods for assigning new ligands to a protein but mostly fail when sequence homology between an unannotated protein and those with known functions or structures is low. In this study, we develop a new deep learning framework to predict chemical binding to evolutionary divergent unannotated proteins, whose ligand cannot be reliably predicted by existing methods. By incorporating evolutionary information into self-supervised learning of unlabeled protein sequences, we develop a novel method, distilled sequence alignment embedding (DISAE), for the protein sequence representation. DISAE can utilize all protein sequences and their multiple sequence alignment (MSA) to capture functional relationships between proteins without the knowledge of their structure and function. Followed by the DISAE pretraining, we devise a module-based fine-tuning strategy for the supervised learning of chemical-protein interactions. In the benchmark studies, DISAE significantly improves the generalizability of machine learning models and outperforms the state-of-the-art methods by a large margin. Comprehensive ablation studies suggest that the use of MSA, sequence distillation, and triplet pretraining critically contributes to the success of DISAE. The interpretability analysis of DISAE suggests that it learns biologically meaningful information. We further use DISAE to assign ligands to human orphan G-protein coupled receptors (GPCRs) and to cluster the human GPCRome by integrating their phylogenetic and ligand relationships. The promising results of DISAE open an avenue for exploring the chemical landscape of entire sequenced genomes.

Imputation of spatially-resolved transcriptomes by graph-regularized tensor completion

High-throughput spatial-transcriptomics RNA sequencing (sptRNA-seq) based on in-situ capturing technologies has recently been developed to spatially resolve transcriptome-wide mRNA expressions mapped to the captured locations in a tissue sample. Due to the low RNA capture efficiency by in-situ capturing and the complication of tissue section preparation, sptRNA-seq data often only provides an incomplete profiling of the gene expressions over the spatial regions of the tissue. In this paper, we introduce a graph-regularized tensor completion model for imputing the missing mRNA expressions in sptRNA-seq data, namely FIST, Fast Imputation of Spatially-resolved transcriptomes by graph-regularized Tensor completion. We first model sptRNA-seq data as a 3-way sparse tensor in genes (p-mode) and the (x, y) spatial coordinates (x-mode and y-mode) of the observed gene expressions, and then consider the imputation of the unobserved entries or fibers as a tensor completion problem in Canonical Polyadic Decomposition (CPD) form. To improve the imputation of highly sparse sptRNA-seq data, we also introduce a protein-protein interaction network to add prior knowledge of gene functions, and a spatial graph to capture the the spatial relations among the capture spots. The tensor completion model is then regularized by a Cartesian product graph of protein-protein interaction network and the spatial graph to capture the high-order relations in the tensor. In the experiments, FIST was tested on ten 10x Genomics Visium spatial transcriptomic datasets of different tissue sections with cross-validation among the known entries in the imputation. FIST significantly outperformed the state-of-the-art methods for single-cell RNAseq data imputation. We also demonstrate that both the spatial graph and PPI network play an important role in improving the imputation. In a case study, we further analyzed the gene clusters obtained from the imputed gene expressions to show that the imputations by FIST indeed capture the spatial characteristics in the gene expressions and reveal functions that are highly relevant to three different kinds of tissues in mouse kidney.

Biological tissues are composed of different types of structurally organized cell units playing distinct functional roles. The exciting new spatial gene expression profiling methods have enabled the analysis of spatially resolved transcriptomes to understand the spatial and functional characteristics of these cells in the context of eco-environment of tissue. Due to the technical limitations, spatial transcriptomics data suffers from only sparsely measured mRNAs by in-situ capture and possibly missing spots in tissue regions that entirely failed fixing and permeabilizing RNAs. Our method, FIST (Fast Imputation of Spatially-resolved transcriptomes by graph-regularized Tensor completion), focuses on the spatial and high-sparsity nature of spatial transcriptomics data by modeling the data as a 3-way gene-by-(x, y)-location tensor and a product graph of a spatial graph and a protein-protein interaction network. Our comprehensive evaluation of FIST on ten 10x Genomics Visium spatial genomics datasets and comparison with the methods for single-cell RNA sequencing data imputation demonstrate that FIST is a better method more suitable for spatial gene expression imputation. Overall, we found FIST a useful new method for analyzing spatially resolved gene expressions based on novel modeling of spatial and functional information.

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.

A New Weighted Imputed Neighborhood-Regularized Tri-Factorization One-Class Collaborative Filtering Algorithm: Application to Target Gene Prediction of Transcription Factors

Identifying target genes of transcription factors (TFs) is crucial to understand transcriptional regulation. However, our understanding of genome-wide TF targeting profile is limited due to the cost of large-scale experiments and intrinsic complexity of gene regulation. Thus, computational prediction methods are useful to predict unobserved TF-gene associations. Here, we develop a new Weighted Imputed Neighborhood-regularized Tri-Factorization one-class collaborative filtering algorithm, WINTF. It predicts unobserved target genes for TFs using known but noisy, incomplete, and biased TF-gene associations and protein-protein interaction networks. Our benchmark study shows that WINTF significantly outperforms its counterpart matrix factorization-based algorithms and tri-factorization methods that do not include weight, imputation, and neighbor-regularization, for TF-gene association prediction. When evaluated by independent datasets, accuracy is 37.8 percent on the top 495 predicted associations, an enrichment factor of 4.19 compared with random guess. Furthermore, many predicted novel associations are supported by literature evidence. Although we only use canonical TF-gene interaction data, WINTF can directly be applied to tissue-specific data when available. Thus, WINTF provides a potentially useful framework to integrate multiple omics data for further improvement of TF-gene prediction and applications to other sparse and noisy biological data. The benchmark dataset and source code are freely available at https://github.com/XieResearchGroup/WINTF.

A review of computational drug repositioning: strategies, approaches, opportunities, challenges, and directions

Drug repositioning is the process of identifying novel therapeutic potentials for existing drugs and discovering therapies for untreated diseases. Drug repositioning, therefore, plays an important role in optimizing the pre-clinical process of developing novel drugs by saving time and cost compared to the traditional de novo drug discovery processes. Since drug repositioning relies on data for existing drugs and diseases the enormous growth of publicly available large-scale biological, biomedical, and electronic health-related data along with the high-performance computing capabilities have accelerated the development of computational drug repositioning approaches. Multidisciplinary researchers and scientists have carried out numerous attempts, with different degrees of efficiency and success, to computationally study the potential of repositioning drugs to identify alternative drug indications. This study reviews recent advancements in the field of computational drug repositioning. First, we highlight different drug repositioning strategies and provide an overview of frequently used resources. Second, we summarize computational approaches that are extensively used in drug repositioning studies. Third, we present different computing and experimental models to validate computational methods. Fourth, we address prospective opportunities, including a few target areas. Finally, we discuss challenges and limitations encountered in computational drug repositioning and conclude with an outline of further research directions.

iDrug: Integration of drug repositioning and drug-target prediction via cross-network embedding

Computational drug repositioning and drug-target prediction have become essential tasks in the early stage of drug discovery. In previous studies, these two tasks have often been considered separately. However, the entities studied in these two tasks (i.e., drugs, targets, and diseases) are inherently related. On one hand, drugs interact with targets in cells to modulate target activities, which in turn alter biological pathways to promote healthy functions and to treat diseases. On the other hand, both drug repositioning and drug-target prediction involve the same drug feature space, which naturally connects these two problems and the two domains (diseases and targets). By using the wisdom of the crowds, it is possible to transfer knowledge from one of the domains to the other. The existence of relationships among drug-target-disease motivates us to jointly consider drug repositioning and drug-target prediction in drug discovery. In this paper, we present a novel approach called iDrug, which seamlessly integrates drug repositioning and drug-target prediction into one coherent model via cross-network embedding. In particular, we provide a principled way to transfer knowledge from these two domains and to enhance prediction performance for both tasks. Using real-world datasets, we demonstrate that iDrug achieves superior performance on both learning tasks compared to several state-of-the-art approaches. Our code and datasets are available at: https://github.com/Case-esaC/iDrug.

Turning liabilities into opportunities: Off-target based drug repurposing in cancer

Targeted drugs and precision medicine have transformed the landscape of cancer therapy and significantly improved patient outcomes in many cases. However, as therapies are becoming more and more tailored to smaller patient populations and acquired resistance is limiting the duration of clinical responses, there is an ever increasing demand for new drugs, which is not easily met considering steadily rising drug attrition rates and development costs. Considering these challenges drug repurposing is an attractive complementary approach to traditional drug discovery that can satisfy some of these needs. This is facilitated by the fact that most targeted drugs, despite their implicit connotation, are not singularly specific, but rather display a wide spectrum of target selectivity. Importantly, some of the unintended drug "off-targets" are known anticancer targets in their own right. Others are becoming recognized as such in the process of elucidating off-target mechanisms that in fact are responsible for a drug's anticancer activity, thereby revealing potentially new cancer vulnerabilities. Harnessing such beneficial off-target effects can therefore lead to novel and promising precision medicine approaches. Here, we will discuss experimental and computational methods that are employed to specifically develop single target and network-based off-target repurposing strategies, for instance with drug combinations or polypharmacology drugs. By illustrating concrete examples that have led to clinical translation we will furthermore examine the various scientific and non-scientific factors that cumulatively determine the success of these efforts and thus can inform the future development of new and potentially lifesaving off-target based drug repurposing strategies for cancers that constitute important unmet medical needs.

Database of adverse events associated with drugs and drug combinations

Due to the aging world population and increasing trend in clinical practice to treat patients with multiple drugs, adverse events (AEs) are becoming a major challenge in drug discovery and public health. In particular, identifying AEs caused by drug combinations remains a challenging task. Clinical trials typically focus on individual drugs rather than drug combinations and animal models are unreliable. An added difficulty is the combinatorial explosion in the number of possible combinations that can be made using the increasingly large set of FDA approved chemicals. We present a statistical and computational technique for identifying AEs caused by two-drug combinations. Taking advantage of the large and increasing data deposited in FDA’s postmarketing reports, we demonstrate that the task of predicting AEs for 2-drug combinations is amenable to the Likelihood Ratio Test (LRT). Our pAERS database constructed with LRT contains almost 77 thousand associations between pairs of drugs and corresponding AEs caused solely by drug-drug interactions (DDIs). The DDIs stored in pAERS complement the existing data sets. Due to our stringent statistical test, we expect many of the associations in pAERS to be unrecorded or poorly documented in the literature.

Biological representation of chemicals using latent target interaction profile

Background

Computational prediction of a phenotypic response upon the chemical perturbation on a biological system plays an important role in drug discovery, and many other applications. Chemical fingerprints are a widely used feature to build machine learning models. However, the fingerprints that are derived from chemical structures ignore the biological context, thus, they suffer from several problems such as the activity cliff and curse of dimensionality. Fundamentally, the chemical modulation of biological activities is a multi-scale process. It is the genome-wide chemical-target interactions that modulate chemical phenotypic responses. Thus, the genome-scale chemical-target interaction profile will more directly correlate with in vitro and in vivo activities than the chemical structure. Nevertheless, the scope of direct application of the chemical-target interaction profile is limited due to the severe incompleteness, biasness, and noisiness of bioassay data.

Results

To address the aforementioned problems, we developed a novel chemical representation method: Latent Target Interaction Profile (LTIP). LTIP embeds chemicals into a low dimensional continuous latent space that represents genome-scale chemical-target interactions. Subsequently LTIP can be used as a feature to build machine learning models. Using the drug sensitivity of cancer cell lines as a benchmark, we have shown that the LTIP robustly outperforms chemical fingerprints regardless of machine learning algorithms. Moreover, the LTIP is complementary with the chemical fingerprints. It is possible for us to combine LTIP with other fingerprints to further improve the performance of bioactivity prediction.

Conclusions

Our results demonstrate the potential of LTIP in particular and multi-scale modeling in general in predictive modeling of chemical modulation of biological activities.

The Route to 'Chemobrain' - Computational probing of neuronal LTP pathway

Chemotherapy causes deleterious side effects during the course of cancer management. The toxic effects may be extended to CNS chronically resulting in altered cognitive function like learning and memory. The present study follows a computational assessment of 64 chemotherapeutic drugs for their off-target interactions against the major proteins involved in neuronal long term potentiation pathway. The cancer chemo-drugs were subjected to induced fit docking followed by scoring alignment and drug-targets interaction analysis. The results were further probed by electrostatic potential computation and ligand binding affinity prediction of the top complexes. The study identified novel off-target interactions by Dactinomycin, Temsirolimus, and Everolimus against NMDA, AMPA, PKA and ERK2, while Irinotecan, Bromocriptine and Dasatinib were top interacting drugs for CaMKII. This study presents with basic foundational knowledge regarding potential chemotherapeutic interference in LTP pathway which may modulate neurotransmission and synaptic plasticity in patient receiving these chemotherapies.

Rational discovery of dual-indication multi-target PDE/Kinase inhibitor for precision anti-cancer therapy using structural systems pharmacology

Many complex diseases such as cancer are associated with multiple pathological manifestations. Moreover, the therapeutics for their treatments often lead to serious side effects. Thus, it is needed to develop multi-indication therapeutics that can simultaneously target multiple clinical indications of interest and mitigate the side effects. However, conventional one-drug-one-gene drug discovery paradigm and emerging polypharmacology approach rarely tackle the challenge of multi-indication drug design. For the first time, we propose a one-drug-multi-target-multi-indication strategy. We develop a novel structural systems pharmacology platform 3D-REMAP that uses ligand binding site comparison and protein-ligand docking to augment sparse chemical genomics data for the machine learning model of genome-scale chemical-protein interaction prediction. Experimentally validated predictions systematically show that 3D-REMAP outperforms state-of-the-art ligand-based, receptor-based, and machine learning methods alone. As a proof-of-concept, we utilize the concept of drug repurposing that is enabled by 3D-REMAP to design dual-indication anti-cancer therapy. The repurposed drug can demonstrate anti-cancer activity for cancers that do not have effective treatment as well as reduce the risk of heart failure that is associated with all types of existing anti-cancer therapies. We predict that levosimendan, a PDE inhibitor for heart failure, inhibits serine/threonine-protein kinase RIOK1 and other kinases. Subsequent experiments and systems biology analyses confirm this prediction, and suggest that levosimendan is active against multiple cancers, notably lymphoma, through the direct inhibition of RIOK1 and RNA processing pathway. We further develop machine learning models to predict cancer cell-line's and a patient's response to levosimendan. Our findings suggest that levosimendan can be a promising novel lead compound for the development of safe, effective, and precision multi-indication anti-cancer therapy. This study demonstrates the potential of structural systems pharmacology in designing polypharmacology for precision medicine. It may facilitate transforming the conventional one-drug-one-gene-one-disease drug discovery process and single-indication polypharmacology approach into a new one-drug-multi-target-multi-indication paradigm for complex diseases.

Target Gene Prediction of Transcription Factor Using a New Neighborhood-regularized Tri-factorization One-class Collaborative Filtering Algorithm

Identifying the target genes of transcription factors (TFs) is one of the key factors to understand transcriptional regulation. However, our understanding of genome-wide TF targeting profile is limited due to the cost of large scale experiments and intrinsic complexity. Thus, computational prediction methods are useful to predict the unobserved associations. Here, we developed a new one-class collaborative filtering algorithm tREMAP that is based on regularized, weighted nonnegative matrix tri-factorization. The algorithm predicts unobserved target genes for TFs using known gene-TF associations and protein-protein interaction network. Our benchmark study shows that tREMAP significantly outperforms its counterpart REMAP, a bi-factorization-based algorithm, for transcription factor target gene prediction in all four performance metrics AUC, MAP, MPR, and HLU. When evaluated by independent data sets, the prediction accuracy is 37.8% on the top 495 predicted associations, an enrichment factor of 4.19 compared with the random guess. Furthermore, many of the predicted novel associations by tREMAP are supported by evidence from literature. Although we only use canonical TF-target gene interaction data in this study, tREMAP can be directly applied to tissue-specific data sets. tREMAP provides a framework to integrate multiple omics data for the further improvement of TF target gene prediction. Thus, tREMAP is a potentially useful tool in studying gene regulatory networks. The benchmark data set and the source code of tREMAP are freely available at https://github.com/hansaimlim/REMAP/tree/master/TriFacREMAP.

Omics Data Integration and Analysis for Systems Pharmacology

Systems pharmacology aims to understand drug actions on a multi-scale from atomic details of drug-target interactions to emergent properties of biological network and rationally design drugs targeting an interacting network instead of a single gene. Multifaceted data-driven studies, including machine learning-based predictions, play a key role in systems pharmacology. In such works, the integration of multiple omics data is the key initial step, followed by optimization and prediction. Here, we describe the overall procedures for drug-target association prediction using REMAP, a large-scale off-target prediction tool. The method introduced here can be applied to other relation inference problems in systems pharmacology.

ANTENNA, a Multi-Rank, Multi-Layered Recommender System for Inferring Reliable Drug-Gene-Disease Associations: Repurposing Diazoxide as a Targeted Anti-Cancer Therapy

Existing drug discovery processes follow a reductionist model of "one-drug-one-gene-one-disease," which is inadequate to tackle complex diseases involving multiple malfunctioned genes. The availability of big omics data offers opportunities to transform drug discovery process into a new paradigm of systems pharmacology that focuses on designing drugs to target molecular interaction networks instead of a single gene. Here, we develop a reliable multi-rank, multi-layered recommender system, ANTENNA, to mine large-scale chemical genomics and disease association data for prediction of novel drug-gene-disease associations. ANTENNA integrates a novel tri-factorization based dual-regularized weighted and imputed One Class Collaborative Filtering (OCCF) algorithm, tREMAP, with a statistical framework based on Random Walk with Restart and assess the reliability of specific predictions. In the benchmark, tREMAP clearly outperforms the single-rank OCCF. We apply ANTENNA to a real-world problem: repurposing old drugs for new clinical indications without effective treatments. We discover that FDA-approved drug diazoxide can inhibit multiple kinase genes responsible for many diseases including cancer and kill triple negative breast cancer (TNBC) cells efficiently [Formula: see text]. TNBC is a deadly disease without effective targeted therapies. Our finding demonstrates the power of big data analytics in drug discovery and developing a targeted therapy for TNBC.

Review and comparative assessment of similarity-based methods for prediction of drug–protein interactions in the druggable human proteome

Drug–protein interactions (DPIs) underlie the desired therapeutic actions and the adverse side effects of a significant majority of drugs. Computational prediction of DPIs facilitates research in drug discovery, characterization and repurposing. Similarity-based methods that do not require knowledge of protein structures are particularly suitable for druggable genome-wide predictions of DPIs. We review 35 high-impact similarity-based predictors that were published in the past decade. We group them based on three types of similarities and their combinations that they use. We discuss and compare key aspects of these methods including source databases, internal databases and their predictive models. Using our novel benchmark database, we perform comparative empirical analysis of predictive performance of seven types of representative predictors that utilize each type of similarity individually and all possible combinations of similarities. We assess predictive quality at the database-wide DPI level and we are the first to also include evaluation over individual drugs. Our comprehensive analysis shows that predictors that use more similarity types outperform methods that employ fewer similarities, and that the model combining all three types of similarities secures area under the receiver operating characteristic curve of 0.93. We offer a comprehensive analysis of sensitivity of predictive performance to intrinsic and extrinsic characteristics of the considered predictors. We find that predictive performance is sensitive to low levels of similarities between sequences of the drug targets and several extrinsic properties of the input drug structures, drug profiles and drug targets. The benchmark database and a webserver for the seven predictors are freely available at http://biomine.cs.vcu.edu/servers/CONNECTOR/.

Exploring Landscape of Drug-Target-Pathway-Side Effect Associations

Side effects are the second and the fourth leading causes of drug attrition and death in the US. Thus, accurate prediction of side effects and understanding their mechanism of action will significantly impact drug discovery and clinical practice. Here, we show REMAP, a neighborhood-regularized weighted and imputed one-class collaborative filtering algorithm, is effective in predicting drug-side effect associations from a drug-side effect association network, and significantly outperforms the state-of-the-art multi-target learning algorithm for predicting rare side effects. We also apply FASCINATE, an extension of REMAP for multi-layered networks, to infer associations among side effects and drug targets from drug-target-side effect networks. Then, using random permutation analysis and gene overrepresentation tests, we infer statistically significant side effect-pathway associations. The predicted drug-side effect associations and side effect-causing pathways are consistent with clinical evidences. We expect more novel drug-side effect associations and side effect-causing pathways to be identified when applying REMAP and FASCINATE to large-scale chemical-gene-side effect networks.

Realizing drug repositioning by adapting a recommendation system to handle the process

Background

Drug repositioning is the process of identifying new targets for known drugs. It can be used to overcome problems associated with traditional drug discovery by adapting existing drugs to treat new discovered diseases. Thus, it may reduce associated risk, cost and time required to identify and verify new drugs. Nowadays, drug repositioning has received more attention from industry and academia. To tackle this problem, researchers have applied many different computational methods and have used various features of drugs and diseases.

Results

In this study, we contribute to the ongoing research efforts by combining multiple features, namely chemical structures, protein interactions and side-effects to predict new indications of target drugs. To achieve our target, we realize drug repositioning as a recommendation process and this leads to a new perspective in tackling the problem. The utilized recommendation method is based on Pareto dominance and collaborative filtering. It can also integrate multiple data-sources and multiple features. For the computation part, we applied several settings and we compared their performance. Evaluation results show that the proposed method can achieve more concentrated predictions with high precision, where nearly half of the predictions are true.

Conclusions

Compared to other state of the art methods described in the literature, the proposed method is better at making right predictions by having higher precision. The reported results demonstrate the applicability and effectiveness of recommendation methods for drug repositioning.

Opportunities and obstacles for deep learning in biology and medicine

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

Evidence-Based Precision Oncology with the Cancer Targetome

A core tenet of precision oncology is the rational choice of drugs to interact with patient-specific biological targets of interest, but it is currently difficult for researchers to obtain consistent and well-supported target information for pharmaceutical drugs. We review current drug-target interaction resources and critically assess how supporting evidence is handled. We introduce the concept of a unified Cancer Targetome to aggregate drug-target interactions in an evidence-based framework. We discuss current unmet needs and the implications for evidence-based clinical omics. The focus of this review is precision oncology but the discussion is highly relevant to targeted therapies in any area.

Computational-experimental approach to drug-target interaction mapping: A case study on kinase inhibitors

Due to relatively high costs and labor required for experimental profiling of the full target space of chemical compounds, various machine learning models have been proposed as cost-effective means to advance this process in terms of predicting the most potent compound-target interactions for subsequent verification. However, most of the model predictions lack direct experimental validation in the laboratory, making their practical benefits for drug discovery or repurposing applications largely unknown. Here, we therefore introduce and carefully test a systematic computational-experimental framework for the prediction and pre-clinical verification of drug-target interactions using a well-established kernel-based regression algorithm as the prediction model. To evaluate its performance, we first predicted unmeasured binding affinities in a large-scale kinase inhibitor profiling study, and then experimentally tested 100 compound-kinase pairs. The relatively high correlation of 0.77 (p < 0.0001) between the predicted and measured bioactivities supports the potential of the model for filling the experimental gaps in existing compound-target interaction maps. Further, we subjected the model to a more challenging task of predicting target interactions for such a new candidate drug compound that lacks prior binding profile information. As a specific case study, we used tivozanib, an investigational VEGF receptor inhibitor with currently unknown off-target profile. Among 7 kinases with high predicted affinity, we experimentally validated 4 new off-targets of tivozanib, namely the Src-family kinases FRK and FYN A, the non-receptor tyrosine kinase ABL1, and the serine/threonine kinase SLK. Our sub-sequent experimental validation protocol effectively avoids any possible information leakage between the training and validation data, and therefore enables rigorous model validation for practical applications. These results demonstrate that the kernel-based modeling approach offers practical benefits for probing novel insights into the mode of action of investigational compounds, and for the identification of new target selectivities for drug repurposing applications.

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.

Water permeation through the internal water pathway in activated GPCR rhodopsin

Rhodopsin is a light-driven G-protein-coupled receptor that mediates signal transduction in eyes. Internal water molecules mediate activation of the receptor in a rhodopsin cascade reaction and contribute to conformational stability of the receptor. However, it remains unclear how internal water molecules exchange between the bulk and protein inside, in particular through a putative solvent pore on the cytoplasmic. Using all-atom molecular dynamics simulations, we identified the solvent pore on cytoplasmic side in both the Meta II state and the Opsin. On the other hand, the solvent pore does not exist in the dark-adapted rhodopsin. We revealed two characteristic narrow regions located within the solvent pore in the Meta II state. The narrow regions distinguish bulk and the internal hydration sites, one of which is adjacent to the conserved structural motif "NPxxY". Water molecules in the solvent pore diffuse by pushing or sometimes jumping a preceding water molecule due to the geometry of the solvent pore. These findings revealed a total water flux between the bulk and the protein inside in the Meta II state, and suggested that these pathways provide water molecules to the crucial sites of the activated rhodopsin.

Improved genome-scale multi-target virtual screening via a novel collaborative filtering approach to cold-start problem

Conventional one-drug-one-gene approach has been of limited success in modern drug discovery. Polypharmacology, which focuses on searching for multi-targeted drugs to perturb disease-causing networks instead of designing selective ligands to target individual proteins, has emerged as a new drug discovery paradigm. Although many methods for single-target virtual screening have been developed to improve the efficiency of drug discovery, few of these algorithms are designed for polypharmacology. Here, we present a novel theoretical framework and a corresponding algorithm for genome-scale multi-target virtual screening based on the one-class collaborative filtering technique. Our method overcomes the sparseness of the protein-chemical interaction data by means of interaction matrix weighting and dual regularization from both chemicals and proteins. While the statistical foundation behind our method is general enough to encompass genome-wide drug off-target prediction, the program is specifically tailored to find protein targets for new chemicals with little to no available interaction data. We extensively evaluate our method using a number of the most widely accepted gene-specific and cross-gene family benchmarks and demonstrate that our method outperforms other state-of-the-art algorithms for predicting the interaction of new chemicals with multiple proteins. Thus, the proposed algorithm may provide a powerful tool for multi-target drug design.