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.

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.

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.

DeepAEG: a model for predicting cancer drug response based on data enhancement and edge-collaborative update strategies.

MOTIVATION: The prediction of cancer drug response is a challenging subject in modern personalized cancer therapy due to the uncertainty of drug efficacy and the heterogeneity of patients. It has been shown that the characteristics of the drug itself and the genomic characteristics of the patient can greatly influence the results of cancer drug response. Therefore, accurate, efficient, and comprehensive methods for drug feature extraction and genomics integration are crucial to improve the prediction accuracy. RESULTS: Accurate prediction of cancer drug response is vital for guiding the design of anticancer drugs. In this study, we propose an end-to-end deep learning model named DeepAEG which is based on a complete-graph update mode to predict IC50. Specifically, we integrate an edge update mechanism on the basis of a hybrid graph convolutional network to comprehensively learn the potential high-dimensional representation of topological structures in drugs, including atomic characteristics and chemical bond information. Additionally, we present a novel approach for enhancing simplified molecular input line entry specification data by employing sequence recombination to eliminate the defect of single sequence representation of drug molecules. Our extensive experiments show that DeepAEG outperforms other existing methods across multiple evaluation parameters in multiple test sets. Furthermore, we identify several potential anticancer agents, including bortezomib, which has proven to be an effective clinical treatment option. Our results highlight the potential value of DeepAEG in guiding the design of specific cancer treatment regimens.

A cross-study analysis of drug response prediction in cancer cell lines.

To enable personalized cancer treatment, machine learning models have been developed to predict drug response as a function of tumor and drug features. However, most algorithm development efforts have relied on cross-validation within a single study to assess model accuracy. While an essential first step, cross-validation within a biological data set typically provides an overly optimistic estimate of the prediction performance on independent test sets. To provide a more rigorous assessment of model generalizability between different studies, we use machine learning to analyze five publicly available cell line-based data sets: National Cancer Institute 60, ancer Therapeutics Response Portal (CTRP), Genomics of Drug Sensitivity in Cancer, Cancer Cell Line Encyclopedia and Genentech Cell Line Screening Initiative (gCSI). Based on observed experimental variability across studies, we explore estimates of prediction upper bounds. We report performance results of a variety of machine learning models, with a multitasking deep neural network achieving the best cross-study generalizability. By multiple measures, models trained on CTRP yield the most accurate predictions on the remaining testing data, and gCSI is the most predictable among the cell line data sets included in this study. With these experiments and further simulations on partial data, two lessons emerge: (1) differences in viability assays can limit model generalizability across studies and (2) drug diversity, more than tumor diversity, is crucial for raising model generalizability in preclinical screening.

Representation of molecules for drug response prediction.

The rapid development of machine learning and deep learning algorithms in the recent decade has spurred an outburst of their applications in many research fields. In the chemistry domain, machine learning has been widely used to aid in drug screening, drug toxicity prediction, quantitative structure-activity relationship prediction, anti-cancer synergy score prediction, etc. This review is dedicated to the application of machine learning in drug response prediction. Specifically, we focus on molecular representations, which is a crucial element to the success of drug response prediction and other chemistry-related prediction tasks. We introduce three types of commonly used molecular representation methods, together with their implementation and application examples. This review will serve as a brief introduction of the broad field of molecular representations.

DeepTTA: a transformer-based model for predicting cancer drug response.

Identifying new lead molecules to treat cancer requires more than a decade of dedicated effort. Before selected drug candidates are used in the clinic, their anti-cancer activity is generally validated by in vitro cellular experiments. Therefore, accurate prediction of cancer drug response is a critical and challenging task for anti-cancer drugs design and precision medicine. With the development of pharmacogenomics, the combination of efficient drug feature extraction methods and omics data has made it possible to use computational models to assist in drug response prediction. In this study, we propose DeepTTA, a novel end-to-end deep learning model that utilizes transformer for drug representation learning and a multilayer neural network for transcriptomic data prediction of the anti-cancer drug responses. Specifically, DeepTTA uses transcriptomic gene expression data and chemical substructures of drugs for drug response prediction. Compared to existing methods, DeepTTA achieved higher performance in terms of root mean square error, Pearson correlation coefficient and Spearman's rank correlation coefficient on multiple test sets. Moreover, we discovered that anti-cancer drugs bortezomib and dactinomycin provide a potential therapeutic option with multiple clinical indications. With its excellent performance, DeepTTA is expected to be an effective method in cancer drug design.

GraphCDR: a graph neural network method with contrastive learning for cancer drug response prediction.

Predicting the response of a cancer cell line to a therapeutic drug is an important topic in modern oncology that can help personalized treatment for cancers. Although numerous machine learning methods have been developed for cancer drug response (CDR) prediction, integrating diverse information about cancer cell lines, drugs and their known responses still remains a great challenge. In this paper, we propose a graph neural network method with contrastive learning for CDR prediction. GraphCDR constructs a graph neural network based on multi-omics profiles of cancer cell lines, the chemical structure of drugs and known cancer cell line-drug responses for CDR prediction, while a contrastive learning task is presented as a regularizer within a multi-task learning paradigm to enhance the generalization ability. In the computational experiments, GraphCDR outperforms state-of-the-art methods under different experimental configurations, and the ablation study reveals the key components of GraphCDR: biological features, known cancer cell line-drug responses and contrastive learning are important for the high-accuracy CDR prediction. The experimental analyses imply the predictive power of GraphCDR and its potential value in guiding anti-cancer drug selection.

How much can deep learning improve prediction of the responses to drugs in cancer cell lines?

The drug response prediction problem arises from personalized medicine and drug discovery. Deep neural networks have been applied to the multi-omics data being available for over 1000 cancer cell lines and tissues for better drug response prediction. We summarize and examine state-of-the-art deep learning methods that have been published recently. Although significant progresses have been made in deep learning approach in drug response prediction, deep learning methods show their weakness for predicting the response of a drug that does not appear in the training dataset. In particular, all the five evaluated deep learning methods performed worst than the similarity-regularized matrix factorization (SRMF) method in our drug blind test. We outline the challenges in applying deep learning approach to drug response prediction and suggest unique opportunities for deep learning integrated with established bioinformatics analyses to overcome some of these challenges.

GPDRP: a multimodal framework for drug response prediction with graph transformer.

BACKGROUND: In the field of computational personalized medicine, drug response prediction (DRP) is a critical issue. However, existing studies often characterize drugs as strings, a representation that does not align with the natural description of molecules. Additionally, they ignore gene pathway-specific combinatorial implication. RESULTS: In this study, we propose drug Graph and gene Pathway based Drug response prediction method (GPDRP), a new multimodal deep learning model for predicting drug responses based on drug molecular graphs and gene pathway activity. In GPDRP, drugs are represented by molecular graphs, while cell lines are described by gene pathway activity scores. The model separately learns these two types of data using Graph Neural Networks (GNN) with Graph Transformers and deep neural networks. Predictions are subsequently made through fully connected layers. CONCLUSIONS: Our results indicate that Graph Transformer-based model delivers superior performance. We apply GPDRP on hundreds of cancer cell lines' bulk RNA-sequencing data, and it outperforms some recently published models. Furthermore, the generalizability and applicability of GPDRP are demonstrated through its predictions on unknown drug-cell line pairs and xenografts. This underscores the interpretability achieved by incorporating gene pathways.

Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models.

The goal of precision oncology is to tailor treatment for patients individually using the genomic profile of their tumors. Pharmacogenomics datasets such as cancer cell lines are among the most valuable resources for drug sensitivity prediction, a crucial task of precision oncology. Machine learning methods have been employed to predict drug sensitivity based on the multiple omics data available for large panels of cancer cell lines. However, there are no comprehensive guidelines on how to properly train and validate such machine learning models for drug sensitivity prediction. In this paper, we introduce a set of guidelines for different aspects of training gene expression-based predictors using cell line datasets. These guidelines provide extensive analysis of the generalization of drug sensitivity predictors and challenge many current practices in the community including the choice of training dataset and measure of drug sensitivity. The application of these guidelines in future studies will enable the development of more robust preclinical biomarkers.

oncoPredict: an R package for predicting in vivo or cancer patient drug response and biomarkers from cell line screening data.

Cell line drug screening datasets can be utilized for a range of different drug discovery applications from drug biomarker discovery to building translational models of drug response. Previously, we described three separate methodologies to (1) correct for general levels of drug sensitivity to enable drug-specific biomarker discovery, (2) predict clinical drug response in patients and (3) associate these predictions with clinical features to perform in vivo drug biomarker discovery. Here, we unite and update these methodologies into one R package (oncoPredict) to facilitate the development and adoption of these tools. This new OncoPredict R package can be applied to various in vitro and in vivo contexts for drug and biomarker discovery.

Improving drug response prediction by integrating multiple data sources: matrix factorization, kernel and network-based approaches.

Predicting the response of cancer cell lines to specific drugs is one of the central problems in personalized medicine, where the cell lines show diverse characteristics. Researchers have developed a variety of computational methods to discover associations between drugs and cell lines, and improved drug sensitivity analyses by integrating heterogeneous biological data. However, choosing informative data sources and methods that can incorporate multiple sources efficiently is the challenging part of successful analysis in personalized medicine. The reason is that finding decisive factors of cancer and developing methods that can overcome the problems of integrating data, such as differences in data structures and data complexities, are difficult. In this review, we summarize recent advances in data integration-based machine learning for drug response prediction, by categorizing methods as matrix factorization-based, kernel-based and network-based methods. We also present a short description of relevant databases used as a benchmark in drug response prediction analyses, followed by providing a brief discussion of challenges faced in integrating and interpreting data from multiple sources. Finally, we address the advantages of combining multiple heterogeneous data sources on drug sensitivity analysis by showing an experimental comparison. Contact:  betul.guvenc@aalto.fi.

A survey and systematic assessment of computational methods for drug response prediction.

Drug response prediction arises from both basic and clinical research of personalized therapy, as well as drug discovery for cancers. With gene expression profiles and other omics data being available for over 1000 cancer cell lines and tissues, different machine learning approaches have been applied to drug response prediction. These methods appear in a body of literature and have been evaluated on different datasets with only one or two accuracy metrics. We systematically assess 17 representative methods for drug response prediction, which have been developed in the past 5 years, on four large public datasets in nine metrics. This study provides insights and lessons for future research into drug response prediction.

Advances towards the use of gastrointestinal tumor patient-derived organoids as a therapeutic decision-making tool.

In December 2022 the US Food and Drug Administration (FDA) removed the requirement that drugs in development must undergo animal testing before clinical evaluation, a declaration that now demands the establishment and verification of ex vivo preclinical models that closely represent tumor complexity and that can predict therapeutic response. Fortunately, the emergence of patient-derived organoid (PDOs) culture has enabled the ex vivo mimicking of the pathophysiology of human tumors with the reassembly of tissue-specific features. These features include histopathological variability, molecular expression profiles, genetic and cellular heterogeneity of parental tissue, and furthermore growing evidence suggests the ability to predict patient therapeutic response. Concentrating on the highly lethal and heterogeneous gastrointestinal (GI) tumors, herein we present the state-of-the-art and the current methodology of PDOs. We highlight the potential additions, improvements and testing required to allow the ex vivo of study the tumor microenvironment, as well as offering commentary on the predictive value of clinical response to treatments such as chemotherapy and immunotherapy.

Cytokine responses in nonlesional psoriatic skin as clinical predictor to anti-TNF agents.

BACKGROUND: A major issue with the current management of psoriasis is our inability to predict treatment response. OBJECTIVE: Our aim was to evaluate the ability to use baseline molecular expression profiling to assess treatment outcome for patients with psoriasis. METHODS: We conducted a longitudinal study of 46 patients with chronic plaque psoriasis treated with anti-TNF agent etanercept, and molecular profiles were assessed in more than 200 RNA-seq samples. RESULTS: We demonstrated correlation between clinical response and molecular changes during the course of the treatment, particularly for genes responding to IL-17A/TNF in keratinocytes. Intriguingly, baseline gene expressions in nonlesional, but not lesional, skin were the best marker of treatment response at week 12. We identified USP18, a known regulator of IFN responses, as positively correlated with Psoriasis Area and Severity Index (PASI) improvement (P = 9.8 × 10-4) and demonstrate its role in regulating IFN/TNF responses in keratinocytes. Consistently, cytokine gene signatures enriched in baseline nonlesional skin expression profiles had strong correlations with PASI improvement. Using this information, we developed a statistical model for predicting PASI75 (ie, 75% of PASI improvement) at week 12, achieving area under the receiver-operating characteristic curve value of 0.75 and up to 80% accurate PASI75 prediction among the top predicted responders. CONCLUSIONS: Our results illustrate feasibility of assessing drug response in psoriasis using nonlesional skin and implicate involvement of IFN regulators in anti-TNF responses.

Methods and resources to access mutation-dependent effects on cancer drug treatment.

In clinical cancer treatment, genomic alterations would often affect the response of patients to anticancer drugs. Studies have shown that molecular features of tumors could be biomarkers predictive of sensitivity or resistance to anticancer agents, but the identification of actionable mutations are often constrained by the incomplete understanding of cancer genomes. Recent progresses of next-generation sequencing technology greatly facilitate the extensive molecular characterization of tumors and promote precision medicine in cancers. More and more clinical studies, cancer cell lines studies, CRISPR screening studies as well as patient-derived model studies were performed to identify potential actionable mutations predictive of drug response, which provide rich resources of molecularly and pharmacologically profiled cancer samples at different levels. Such abundance of data also enables the development of various computational models and algorithms to solve the problem of drug sensitivity prediction, biomarker identification and in silico drug prioritization by the integration of multiomics data. Here, we review the recent development of methods and resources that identifies mutation-dependent effects for cancer treatment in clinical studies, functional genomics studies and computational studies and discuss the remaining gaps and future directions in this area.