Pharmacogenomics of GPCR Drug Targets.

Natural genetic variation in the human genome is a cause of individual differences in responses to medications and is an underappreciated burden on public health. Although 108 G-protein-coupled receptors (GPCRs) are the targets of 475 (∼34%) Food and Drug Administration (FDA)-approved drugs and account for a global sales volume of over 180 billion US dollars annually, the prevalence of genetic variation among GPCRs targeted by drugs is unknown. By analyzing data from 68,496 individuals, we find that GPCRs targeted by drugs show genetic variation within functional regions such as drug- and effector-binding sites in the human population. We experimentally show that certain variants of µ-opioid and Cholecystokinin-A receptors could lead to altered or adverse drug response. By analyzing UK National Health Service drug prescription and sales data, we suggest that characterizing GPCR variants could increase prescription precision, improving patients' quality of life, and relieve the economic and societal burden due to variable drug responsiveness. VIDEO ABSTRACT.

Tumor Evolution and Drug Response in Patient-Derived Organoid Models of Bladder Cancer.

Bladder cancer is the fifth most prevalent cancer in the U.S., yet is understudied, and few laboratory models exist that reflect the biology of the human disease. Here, we describe a biobank of patient-derived organoid lines that recapitulates the histopathological and molecular diversity of human bladder cancer. Organoid lines can be established efficiently from patient biopsies acquired before and after disease recurrence and are interconvertible with orthotopic xenografts. Notably, organoid lines often retain parental tumor heterogeneity and exhibit a spectrum of genomic changes that are consistent with tumor evolution in culture. Analyses of drug response using bladder tumor organoids show partial correlations with mutational profiles, as well as changes associated with treatment resistance, and specific responses can be validated using xenografts in vivo. Our studies indicate that patient-derived bladder tumor organoids represent a faithful model system for studying tumor evolution and treatment response in the context of precision cancer medicine.

Improving drug response prediction via integrating gene relationships with deep learning.

Predicting the drug response of cancer cell lines is crucial for advancing personalized cancer treatment, yet remains challenging due to tumor heterogeneity and individual diversity. In this study, we present a deep learning-based framework named Deep neural network Integrating Prior Knowledge (DIPK) (DIPK), which adopts self-supervised techniques to integrate multiple valuable information, including gene interaction relationships, gene expression profiles and molecular topologies, to enhance prediction accuracy and robustness. We demonstrated the superior performance of DIPK compared to existing methods on both known and novel cells and drugs, underscoring the importance of gene interaction relationships in drug response prediction. In addition, DIPK extends its applicability to single-cell RNA sequencing data, showcasing its capability for single-cell-level response prediction and cell identification. Further, we assess the applicability of DIPK on clinical data. DIPK accurately predicted a higher response to paclitaxel in the pathological complete response (pCR) group compared to the residual disease group, affirming the better response of the pCR group to the chemotherapy compound. We believe that the integration of DIPK into clinical decision-making processes has the potential to enhance individualized treatment strategies for cancer patients.

FERREG: ferroptosis-based regulation of disease occurrence, progression and therapeutic response.

Ferroptosis is a non-apoptotic, iron-dependent regulatory form of cell death characterized by the accumulation of intracellular reactive oxygen species. In recent years, a large and growing body of literature has investigated ferroptosis. Since ferroptosis is associated with various physiological activities and regulated by a variety of cellular metabolism and mitochondrial activity, ferroptosis has been closely related to the occurrence and development of many diseases, including cancer, aging, neurodegenerative diseases, ischemia-reperfusion injury and other pathological cell death. The regulation of ferroptosis mainly focuses on three pathways: system Xc-/GPX4 axis, lipid peroxidation and iron metabolism. The genes involved in these processes were divided into driver, suppressor and marker. Importantly, small molecules or drugs that mediate the expression of these genes are often good treatments in the clinic. Herein, a newly developed database, named 'FERREG', is documented to (i) providing the data of ferroptosis-related regulation of diseases occurrence, progression and drug response; (ii) explicitly describing the molecular mechanisms underlying each regulation; and (iii) fully referencing the collected data by cross-linking them to available databases. Collectively, FERREG contains 51 targets, 718 regulators, 445 ferroptosis-related drugs and 158 ferroptosis-related disease responses. FERREG can be accessed at https://idrblab.org/ferreg/.

PANCDR: precise medicine prediction using an adversarial network for cancer drug response.

Pharmacogenomics aims to provide personalized therapy to patients based on their genetic variability. However, accurate prediction of cancer drug response (CDR) is challenging due to genetic heterogeneity. Since clinical data are limited, most studies predicting drug response use preclinical data to train models. However, such models might not be generalizable to external clinical data due to differences between the preclinical and clinical datasets. In this study, a Precision Medicine Prediction using an Adversarial Network for Cancer Drug Response (PANCDR) model is proposed. PANCDR consists of two sub-models, an adversarial model and a CDR prediction model. The adversarial model reduces the gap between the preclinical and clinical datasets, while the CDR prediction model extracts features and predicts responses. PANCDR was trained using both preclinical data and unlabeled clinical data. Subsequently, it was tested on external clinical data, including The Cancer Genome Atlas and brain tumor patients. PANCDR outperformed other machine learning models in predicting external test data. Our results demonstrate the robustness of PANCDR and its potential in precision medicine by recommending patient-specific drug candidates. The PANCDR codes and data are available at https://github.com/DMCB-GIST/PANCDR.

Genomic hallmarks and therapeutic targets of ribosome biogenesis in cancer.

Hyperactive ribosome biogenesis (RiboSis) fuels unrestricted cell proliferation, whereas genomic hallmarks and therapeutic targets of RiboSis in cancers remain elusive, and efficient approaches to quantify RiboSis activity are still limited. Here, we have established an in silico approach to conveniently score RiboSis activity based on individual transcriptome data. By employing this novel approach and RNA-seq data of 14 645 samples from TCGA/GTEx dataset and 917 294 single-cell expression profiles across 13 cancer types, we observed the elevated activity of RiboSis in malignant cells of various human cancers, and high risk of severe outcomes in patients with high RiboSis activity. Our mining of pan-cancer multi-omics data characterized numerous molecular alterations of RiboSis, and unveiled the predominant somatic alteration in RiboSis genes was copy number variation. A total of 128 RiboSis genes, including EXOSC4, BOP1, RPLP0P6 and UTP23, were identified as potential therapeutic targets. Interestingly, we observed that the activity of RiboSis was associated with TP53 mutations, and hyperactive RiboSis was associated with poor outcomes in lung cancer patients without TP53 mutations, highlighting the importance of considering TP53 mutations during therapy by impairing RiboSis. Moreover, we predicted 23 compounds, including methotrexate and CX-5461, associated with the expression signature of RiboSis genes. The current study generates a comprehensive blueprint of molecular alterations in RiboSis genes across cancers, which provides a valuable resource for RiboSis-based anti-tumor therapy.

Advancing drug-response prediction using multi-modal and -omics machine learning integration (MOMLIN): a case study on breast cancer clinical data.

The inherent heterogeneity of cancer contributes to highly variable responses to any anticancer treatments. This underscores the need to first identify precise biomarkers through complex multi-omics datasets that are now available. Although much research has focused on this aspect, identifying biomarkers associated with distinct drug responders still remains a major challenge. Here, we develop MOMLIN, a multi-modal and -omics machine learning integration framework, to enhance drug-response prediction. MOMLIN jointly utilizes sparse correlation algorithms and class-specific feature selection algorithms, which identifies multi-modal and -omics-associated interpretable components. MOMLIN was applied to 147 patients' breast cancer datasets (clinical, mutation, gene expression, tumor microenvironment cells and molecular pathways) to analyze drug-response class predictions for non-responders and variable responders. Notably, MOMLIN achieves an average AUC of 0.989, which is at least 10% greater when compared with current state-of-the-art (data integration analysis for biomarker discovery using latent components, multi-omics factor analysis, sparse canonical correlation analysis). Moreover, MOMLIN not only detects known individual biomarkers such as genes at mutation/expression level, most importantly, it correlates multi-modal and -omics network biomarkers for each response class. For example, an interaction between ER-negative-HMCN1-COL5A1 mutations-FBXO2-CSF3R expression-CD8 emerge as a multimodal biomarker for responders, potentially affecting antimicrobial peptides and FLT3 signaling pathways. In contrast, for resistance cases, a distinct combination of lymph node-TP53 mutation-PON3-ENSG00000261116 lncRNA expression-HLA-E-T-cell exclusions emerged as multimodal biomarkers, possibly impacting neurotransmitter release cycle pathway. MOMLIN, therefore, is expected advance precision medicine, such as to detect context-specific multi-omics network biomarkers and better predict drug-response classifications.

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 drug discovery for castration-resistant prostate cancers through in vitro drug response modeling.

Prostate cancer (PC) is the most frequently diagnosed malignancy and a leading cause of cancer deaths in US men. Many PC cases metastasize and develop resistance to systemic hormonal therapy, a stage known as castration-resistant prostate cancer (CRPC). Therefore, there is an urgent need to develop effective therapeutic strategies for CRPC. Traditional drug discovery pipelines require significant time and capital input, which highlights a need for novel methods to evaluate the repositioning potential of existing drugs. Here, we present a computational framework to predict drug sensitivities of clinical CRPC tumors to various existing compounds and identify treatment options with high potential for clinical impact. We applied this method to a CRPC patient cohort and nominated drugs to combat resistance to hormonal therapies including abiraterone and enzalutamide. The utility of this method was demonstrated by nomination of multiple drugs that are currently undergoing clinical trials for CRPC. Additionally, this method identified the tetracycline derivative COL-3, for which we validated higher efficacy in an isogenic cell line model of enzalutamide-resistant vs. enzalutamide-sensitive CRPC. In enzalutamide-resistant CRPC cells, COL-3 displayed higher activity for inhibiting cell growth and migration, and for inducing G1-phase cell cycle arrest and apoptosis. Collectively, these findings demonstrate the utility of a computational framework for independent validation of drugs being tested in CRPC clinical trials, and for nominating drugs with enhanced biological activity in models of enzalutamide-resistant CRPC. The efficiency of this method relative to traditional drug development approaches indicates a high potential for accelerating drug development for CRPC.

Measuring Pharmacogene Variant Function at Scale Using Multiplexed Assays.

As costs of next-generation sequencing decrease, identification of genetic variants has far outpaced our ability to understand their functional consequences. This lack of understanding is a central challenge to a key promise of pharmacogenomics: using genetic information to guide drug selection and dosing. Recently developed multiplexed assays of variant effect enable experimental measurement of the function of thousands of variants simultaneously. Here, we describe multiplexed assays that have been performed on nearly 25,000 variants in eight key pharmacogenes (ADRB2, CYP2C9, CYP2C19, NUDT15, SLCO1B1, TMPT, VKORC1, and the LDLR promoter), discuss advances in experimental design, and explore key challenges that must be overcome to maximize the utility of multiplexed functional data.

Improved drug response prediction by drug target data integration via network-based profiling.

Drug response prediction (DRP) is important for precision medicine to predict how a patient would react to a drug before administration. Existing studies take the cell line transcriptome data, and the chemical structure of drugs as input and predict drug response as IC50 or AUC values. Intuitively, use of drug target interaction (DTI) information can be useful for DRP. However, use of DTI is difficult because existing drug response database such as CCLE and GDSC do not have information about transcriptome after drug treatment. Although transcriptome after drug treatment is not available, if we can compute the perturbation effects by the pharmacologic modulation of target gene, we can utilize the DTI information in CCLE and GDSC. In this study, we proposed a framework that can improve existing deep learning-based DRP models by effectively utilizing drug target information. Our framework includes NetGP, a module to compute gene perturbation scores by the network propagation technique on a network. NetGP produces genes in a ranked list in terms of gene perturbation scores and the ranked genes are input to a multi-layer perceptron to generate a fixed dimension vector for the integration with existing DRP models. This integration is done in a model-agnostic way so that any existing DRP tool can be incorporated. As a result, our framework boosts the performance of existing DRP models, in 64 of 72 comparisons. The performance gains are larger especially for test scenarios with samples with unseen drugs by large margins up to 34% in Pearson's correlation coefficient.

iBT-Net: an incremental broad transformer network for cancer drug response prediction.

In modern precision medicine, it is an important research topic to predict cancer drug response. Due to incomplete chemical structures and complex gene features, however, it is an ongoing work to design efficient data-driven methods for predicting drug response. Moreover, since the clinical data cannot be easily obtained all at once, the data-driven methods may require relearning when new data are available, resulting in increased time consumption and cost. To address these issues, an incremental broad Transformer network (iBT-Net) is proposed for cancer drug response prediction. Different from the gene expression features learning from cancer cell lines, structural features are further extracted from drugs by Transformer. Broad learning system is then designed to integrate the learned gene features and structural features of drugs to predict the response. With the capability of incremental learning, the proposed method can further use new data to improve its prediction performance without retraining totally. Experiments and comparison studies demonstrate the effectiveness and superiority of iBT-Net under different experimental configurations and continuous data learning.

Benchmark of embedding-based methods for accurate and transferable prediction of drug response.

Prediction of therapy response has been a major challenge in cancer precision medicine due to the extensive tumor heterogeneity. Recently, several deep learning methods have been developed to predict drug response by utilizing various omics data. Most of them train models by using the drug-response screening data generated from cell lines and then use these models to predict response in cancer patient data. In this study, we focus on and evaluate deep learning methods using transcriptome data for the long-standing question of personalized drug-response prediction. We developed an embedding-based approach for drug-response prediction and benchmarked similar methods for their performance. For all methods, we used pretreatment transcriptome data to train models and then conducted a comprehensive evaluation and comparison of the models using cross-panels, cross-datasets and target genes. We further validated the methods using three independent datasets assessing multiple compounds for their predictive capability of drug response, survival outcome and cell line status. As a result, the methods building on gene embeddings had an overall competitive performance with reduced overfitting when we applied evaluation parameters for model fitting as well as the correlation with clinical outcomes in the validation data. We further developed an ensemble model to combine the results from the three most competitive methods for an overall prediction. Finally, we developed DrVAEN (https://bioinfo.uth.edu/drvaen), a user-friendly and easy-accessible web-server that hosts all these methods for drug-response prediction and model comparison for broad use in cancer research, method evaluation and drug development.

GADRP: graph convolutional networks and autoencoders for cancer drug response prediction.

Drug response prediction in cancer cell lines is of great significance in personalized medicine. In this study, we propose GADRP, a cancer drug response prediction model based on graph convolutional networks (GCNs) and autoencoders (AEs). We first use a stacked deep AE to extract low-dimensional representations from cell line features, and then construct a sparse drug cell line pair (DCP) network incorporating drug, cell line, and DCP similarity information. Later, initial residual and layer attention-based GCN (ILGCN) that can alleviate over-smoothing problem is utilized to learn DCP features. And finally, fully connected network is employed to make prediction. Benchmarking results demonstrate that GADRP can significantly improve prediction performance on all metrics compared with baselines on five datasets. Particularly, experiments of predictions of unknown DCP responses, drug-cancer tissue associations， and drug-pathway associations illustrate the predictive power of GADRP. All results highlight the effectiveness of GADRP in predicting drug responses, and its potential value in guiding anti-cancer drug selection.

A systematic assessment of deep learning methods for drug response prediction: from in vitro to clinical applications.

Drug response prediction is an important problem in personalized cancer therapy. Among various newly developed models, significant improvement in prediction performance has been reported using deep learning methods. However, systematic comparisons of deep learning methods, especially of the transferability from preclinical models to clinical cohorts, are currently lacking. To provide a more rigorous assessment, the performance of six representative deep learning methods for drug response prediction using nine evaluation metrics, including the overall prediction accuracy, predictability of each drug, potential associated factors and transferability to clinical cohorts, in multiple application scenarios was benchmarked. Most methods show promising prediction within cell line datasets, and TGSA, with its lower time cost and better performance, is recommended. Although the performance metrics decrease when applying models trained on cell lines to patients, a certain amount of power to distinguish clinical response on some drugs can be maintained using CRDNN and TGSA. With these assessments, we provide a guidance for researchers to choose appropriate methods, as well as insights into future directions for the development of more effective methods in clinical scenarios.

SpaRx: elucidate single-cell spatial heterogeneity of drug responses for personalized treatment.

Spatial cellular authors heterogeneity contributes to differential drug responses in a tumor lesion and potential therapeutic resistance. Recent emerging spatial technologies such as CosMx, MERSCOPE and Xenium delineate the spatial gene expression patterns at the single cell resolution. This provides unprecedented opportunities to identify spatially localized cellular resistance and to optimize the treatment for individual patients. In this work, we present a graph-based domain adaptation model, SpaRx, to reveal the heterogeneity of spatial cellular response to drugs. SpaRx transfers the knowledge from pharmacogenomics profiles to single-cell spatial transcriptomics data, through hybrid learning with dynamic adversarial adaption. Comprehensive benchmarking demonstrates the superior and robust performance of SpaRx at different dropout rates, noise levels and transcriptomics coverage. Further application of SpaRx to the state-of-the-art single-cell spatial transcriptomics data reveals that tumor cells in different locations of a tumor lesion present heterogenous sensitivity or resistance to drugs. Moreover, resistant tumor cells interact with themselves or the surrounding constituents to form an ecosystem for drug resistance. Collectively, SpaRx characterizes the spatial therapeutic variability, unveils the molecular mechanisms underpinning drug resistance and identifies personalized drug targets and effective drug combinations.

µPhos: a scalable and sensitive platform for high-dimensional phosphoproteomics.

Mass spectrometry has revolutionized cell signaling research by vastly simplifying the analysis of many thousands of phosphorylation sites in the human proteome. Defining the cellular response to perturbations is crucial for further illuminating the functionality of the phosphoproteome. Here we describe µPhos ('microPhos'), an accessible phosphoproteomics platform that permits phosphopeptide enrichment from 96-well cell culture and small tissue amounts in <8 h total processing time. By greatly minimizing transfer steps and liquid volumes, we demonstrate increased sensitivity, >90% selectivity, and excellent quantitative reproducibility. Employing highly sensitive trapped ion mobility mass spectrometry, we quantify ~17,000 Class I phosphosites in a human cancer cell line using 20 µg starting material, and confidently localize ~6200 phosphosites from 1 µg. This depth covers key signaling pathways, rendering sample-limited applications and perturbation experiments with hundreds of samples viable. We employ µPhos to study drug- and time-dependent response signatures in a leukemia cell line, and by quantifying 30,000 Class I phosphosites in the mouse brain we reveal distinct spatial kinase activities in subregions of the hippocampal formation.

Illuminating phenotypic drug responses of sarcoma cells to kinase inhibitors by phosphoproteomics.

Kinase inhibitors (KIs) are important cancer drugs but often feature polypharmacology that is molecularly not understood. This disconnect is particularly apparent in cancer entities such as sarcomas for which the oncogenic drivers are often not clear. To investigate more systematically how the cellular proteotypes of sarcoma cells shape their response to molecularly targeted drugs, we profiled the proteomes and phosphoproteomes of 17 sarcoma cell lines and screened the same against 150 cancer drugs. The resulting 2550 phenotypic profiles revealed distinct drug responses and the cellular activity landscapes derived from deep (phospho)proteomes (9-10,000 proteins and 10-27,000 phosphorylation sites per cell line) enabled several lines of analysis. For instance, connecting the (phospho)proteomic data with drug responses revealed known and novel mechanisms of action (MoAs) of KIs and identified markers of drug sensitivity or resistance. All data is publicly accessible via an interactive web application that enables exploration of this rich molecular resource for a better understanding of active signalling pathways in sarcoma cells, identifying treatment response predictors and revealing novel MoA of clinical KIs.

Improving anti-cancer drug response prediction using multi-task learning on graph convolutional networks.

Predicting the therapeutic effect of anti-cancer drugs on tumors based on the characteristics of tumors and patients is one of the important contents of precision oncology. Existing computational methods regard the drug response prediction problem as a classification or regression task. However, few of them consider leveraging the relationship between the two tasks. In this work, we propose a Multi-task Interaction Graph Convolutional Network (MTIGCN) for anti-cancer drug response prediction. MTIGCN first utilizes an graph convolutional network-based model to produce embeddings for both cell lines and drugs. After that, the model employs multi-task learning to predict anti-cancer drug response, which involves training the model on three different tasks simultaneously: the main task of the drug sensitive or resistant classification task and the two auxiliary tasks of regression prediction and similarity network reconstruction. By sharing parameters and optimizing the losses of different tasks simultaneously, MTIGCN enhances the feature representation and reduces overfitting. The results of the experiments on two in vitro datasets demonstrated that MTIGCN outperformed seven state-of-the-art baseline methods. Moreover, the well-trained model on the in vitro dataset GDSC exhibited good performance when applied to predict drug responses in in vivo datasets PDX and TCGA. The case study confirmed the model's ability to discover unknown drug responses in cell lines.

Simple, fast, and flexible framework for matrix completion with infinite width neural networks.

Matrix completion problems arise in many applications including recommendation systems, computer vision, and genomics. Increasingly larger neural networks have been successful in many of these applications but at considerable computational costs. Remarkably, taking the width of a neural network to infinity allows for improved computational performance. In this work, we develop an infinite width neural network framework for matrix completion that is simple, fast, and flexible. Simplicity and speed come from the connection between the infinite width limit of neural networks and kernels known as neural tangent kernels (NTK). In particular, we derive the NTK for fully connected and convolutional neural networks for matrix completion. The flexibility stems from a feature prior, which allows encoding relationships between coordinates of the target matrix, akin to semisupervised learning. The effectiveness of our framework is demonstrated through competitive results for virtual drug screening and image inpainting/reconstruction. We also provide an implementation in Python to make our framework accessible on standard hardware to a broad audience.