Predict Drug Response Research Articles

Non-Invasive Biomarkers for Diagnosis, Risk Prediction, and Therapy Guidance of Glomerular Kidney Diseases: A Comprehensive Review.

Effective management of glomerular kidney disease, one of the main categories of chronic kidney disease (CKD), requires accurate diagnosis, prognosis of progression, assessment of therapeutic efficacy, and, ideally, prediction of drug response. Multiple biomarkers and algorithms for the assessment of specific aspects of glomerular diseases have been reported in the literature. Though, the vast majority of these have not been implemented in clinical practice or are not available on a global scale due to limited access, missing medical infrastructure, or economical as well as political reasons. The aim of this review is to compile all currently available information on the diagnostic, prognostic, and predictive biomarkers currently available for the management of glomerular diseases, and provide guidance on the application of these biomarkers. As a result of the compiled evidence for the different biomarkers available, we present a decision tree for a non-invasive, biomarker-guided diagnostic path. The data currently available demonstrate that for the large majority of patients with glomerular diseases, valid biomarkers are available. However, despite the obvious disadvantages of kidney biopsy, being invasive and not applicable for monitoring, especially in the context of rare CKD etiologies, kidney biopsy still cannot be replaced by non-invasive strategies.

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

MotivationThe 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.ResultsAccurate 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.

EM-transcriptomic signature predicts drug response in advanced stages of high-grade serous ovarian carcinoma based on ascites-derived primary cultures.

Introduction: High-grade serous ovarian carcinoma (HGSOC) remains a medical challenge despite considerable improvements in the treatment. Unfortunately, over 75% of patients have already metastasized at the time of diagnosis. Advances in understanding the mechanisms underlying how ascites cause chemoresistance are urgently needed to derive novel therapeutic strategies. This study aimed to identify the molecular markers involved in drug sensitivity and highlight the use of ascites as a potential model to investigate HGSOC treatment options. Methods: After conducting an in silico analysis, eight epithelial-mesenchymal (EM)-associated genes related to chemoresistance were identified. To evaluate differences in EM-associated genes in HGSOC samples, we analyzed ascites-derived HGSOC primary cell culture (AS), tumor (T), and peritoneal nodule (NP) samples. Moreover, in vitro experiments were employed to measure tumor cell proliferation and cell migration in AS, following treatment with doxorubicin (DOX) and cisplatin (CIS) and expression of these markers. Results: Our results showed that AS exhibits a mesenchymal phenotype compared to tumor and peritoneal nodule samples. Moreover, DOX and CIS treatment leads to an invasive-intermediate epithelial-to-mesenchymal transition (EMT) state of the AS by different EM-associated marker expression. For instance, the treatment of AS showed that CDH1 and GATA6 decreased after CIS exposure and increased after DOX treatment. On the contrary, the expression of KRT18 has an opposite pattern. Conclusion: Taken together, our study reports a comprehensive investigation of the EM-associated genes after drug exposure of AS. Exploring ascites and their associated cellular and soluble components is promising for understanding the HGSOC progression and treatment response at a personalized level.

Predicting drug response through tumor deconvolution by cancer cell lines

Large-scale cancer drug sensitivity data have become available for a collection of cancer cell lines, but only limited drug response data from patients are available. Bridging the gap in pharmacogenomics knowledge between invitro and invivo datasets remains challenging. In this study, we trained a deep learning model, Scaden-CA, for deconvoluting tumor data into proportions of cancer-type-specific cell lines. Then, we developed a drug response prediction method using the deconvoluted proportions and the drug sensitivity data from cell lines. The Scaden-CA model showed excellent performance in terms of concordance correlation coefficients (>0.9 for model testing) and the correctly deconvoluted rate (>70% across most cancers) for model validation using Cancer Cell Line Encyclopedia (CCLE) bulk RNA data. We applied the model to tumors in The Cancer Genome Atlas (TCGA) dataset and examined associations between predicted cell viability and mutation status or gene expression levels to understand underlying mechanisms of potential value for drug repurposing.

Uncovering the subtype-specific disease module and the development of drug response prediction models for glioma

The poor prognosis of glioma patients brought attention to the need for effective therapeutic approaches for precision therapy. Here, we deployed algorithms relying on network medicine and artificial intelligence to design the framework for subtype-specific target identification and drug response prediction in glioma. We identified the driver mutations that were differentially expressed in each subtype of lower-grade glioma and glioblastoma multiforme and were linked to cancer-specific processes. Driver mutations that were differentially expressed were also subjected to subtype-specific disease module identification. The drugs from the drug bank database were retrieved to target these disease modules. However, the efficacy of anticancer drugs depends on the molecular profile of the cancer and varies among cancer patients due to intratumor heterogeneity. Hence, we developed a deep-learning-based drug response prediction framework using the experimental drug screening data. Models for 30 drugs that can target the disease module were developed, where drug response measured by IC50 was considered a response and gene expression and mutation data were considered predictor variables. The model construction consists of three steps: feature selection, data integration, and classification. We observed the consistent performance of the models in training, test, and validation datasets. Drug responses were predicted for particular cell lines derived from distinct subtypes of gliomas. We found that subtypes of gliomas respond differently to the drug, highlighting the importance of subtype-specific drug response prediction. Therefore, the development of personalized therapy by integrating network medicine and a deep learning-based approach can lead to cancer-specific treatment and improved patient care.

Genetic Determinants of Response to Statins in Cardiovascular Diseases.

Despite extensive efforts to identify patients with cardiovascular disease (CVD) who could most benefit from the treatment approach, patients vary in their benefit from therapy and propensity for adverse drug events. Genetic variability in individual responses to drugs (pharmacogenetics) is considered an essential determinant in responding to a drug. Thus, understanding these pharmacogenomic relationships has led to a substantial focus on mechanisms of disease and drug response. In turn, understanding the genomic and molecular bases of variables that might be involved in drug response is the main step in personalized medicine. There is a growing body of data evaluating drug-gene interactions in recent years, some of which have led to FDA recommendations and detection of markers to predict drug responses (e.g., genetic variant in VKORC1 and CYP2C9 genes for prediction of drug response in warfarin treatment). Also, statins are widely prescribed drugs for the prevention of CVD. Atorvastatin, fluvastatin, rosuvastatin, simvastatin, and lovastatin are the most common statins used to manage dyslipidemia. This review provides an overview of the current knowledge on the pharmacogenetics of statins, which are being used to treat cardiovascular diseases.

Unveiling the future: precision pharmacovigilance in the era of personalized medicine

In the era of personalized medicine, pharmacovigilance faces new challenges and opportunities, demanding a shift from traditional approaches. This article delves into the evolving landscape of drug safety monitoring in the context of personalized treatments. We aim to provide a succinct reflection on the intersection of tailored therapeutic strategies and vigilant pharmacovigilance practices. We discuss the integration of pharmacogenetics in enhancing drug safety, illustrating how genetic profiling aids in predicting drug responses and adverse reactions. Emphasizing the importance of phase IV—post-marketing surveillance, we explore the limitations of pre-marketing trials and the necessity for a comprehensive approach to drug safety. The article discusses the pivotal role of pharmacogenetics in pre-exposure risk management and the redefinition of pharmacoepidemiological methods for post-exposure surveillance. We highlight the significance of integrating patient-specific genetic profiles in creating personalized medication leaflets and the use of advanced computational methods in data analysis. Additionally, we examine the ethical, privacy, and data security challenges inherent in precision medicine, emphasizing their implications for patient consent and data management.

Sequential estimation for mixture of regression models for heterogeneous population

Heterogeneity among patients commonly exists in clinical studies and leads to challenges in medical research. It is widely accepted that there exist various sub-types in the population and they are distinct from each other. The approach of identifying the sub-types and thus tailoring disease prevention and treatment is known as precision medicine. The mixture model is a classical statistical model to cluster the heterogeneous population into homogeneous sub-populations. However, for the highly heterogeneous population with multiple components, its parameter estimation and clustering results may be ambiguous due to the dependence of the EM algorithm on the initial values. For sub-typing purposes, the finite mixture of regression models with concomitant variables is considered and a novel statistical method is proposed to identify the main components with large proportions in the mixture sequentially. Compared to existing typical statistical inferences, the new method not only requires no pre-specification on the number of components for model fitting, but also provides more reliable parameter estimation and clustering results. Simulation studies demonstrated the superiority of the proposed method. Real data analysis on the drug response prediction illustrated its reliability in the parameter estimation and capability to identify the important subgroup.

The Rise of Hypothesis-Driven Artificial Intelligence in Oncology.

Cancer is a complex disease involving the deregulation of intricate cellular systems beyond genetic aberrations and, as such, requires sophisticated computational approaches and high-dimensional data for optimal interpretation. While conventional artificial intelligence (AI) models excel in many prediction tasks, they often lack interpretability and are blind to the scientific hypotheses generated by researchers to enable cancer discoveries. Here we propose that hypothesis-driven AI, a new emerging class of AI algorithm, is an innovative approach to uncovering the complex etiology of cancer from big omics data. This review exemplifies how hypothesis-driven AI is different from conventional AI by citing its application in various areas of oncology including tumor classification, patient stratification, cancer gene discovery, drug response prediction, and tumor spatial organization. Our aim is to stress the feasibility of incorporating domain knowledge and scientific hypotheses to craft the design of new AI algorithms. We showcase the power of hypothesis-driven AI in making novel cancer discoveries that can be overlooked by conventional AI methods. Since hypothesis-driven AI is still in its infancy, open questions such as how to better incorporate new knowledge and biological perspectives to ameliorate bias and improve interpretability in the design of AI algorithms still need to be addressed. In conclusion, hypothesis-driven AI holds great promise in the discovery of new mechanistic and functional insights that explain the complexity of cancer etiology and potentially chart a new roadmap to improve treatment regimens for individual patients.

A systematic analysis of deep learning in genomics and histopathology for precision oncology

BackgroundDigitized histopathological tissue slides and genomics profiling data are available for many patients with solid tumors. In the last 5 years, Deep Learning (DL) has been broadly used to extract clinically actionable information and biological knowledge from pathology slides and genomic data in cancer. In addition, a number of recent studies have introduced multimodal DL models designed to simultaneously process both images from pathology slides and genomic data as inputs. By comparing patterns from one data modality with those in another, multimodal DL models are capable of achieving higher performance compared to their unimodal counterparts. However, the application of these methodologies across various tumor entities and clinical scenarios lacks consistency.MethodsHere, we present a systematic survey of the academic literature from 2010 to November 2023, aiming to quantify the application of DL for pathology, genomics, and the combined use of both data types. After filtering 3048 publications, our search identified 534 relevant articles which then were evaluated by basic (diagnosis, grading, subtyping) and advanced (mutation, drug response and survival prediction) application types, publication year and addressed cancer tissue.ResultsOur analysis reveals a predominant application of DL in pathology compared to genomics. However, there is a notable surge in DL incorporation within both domains. Furthermore, while DL applied to pathology primarily targets the identification of histology-specific patterns in individual tissues, DL in genomics is more commonly used in a pan-cancer context. Multimodal DL, on the contrary, remains a niche topic, evidenced by a limited number of publications, primarily focusing on prognosis predictions.ConclusionIn summary, our quantitative analysis indicates that DL not only has a well-established role in histopathology but is also being successfully integrated into both genomic and multimodal applications. In addition, there is considerable potential in multimodal DL for harnessing further advanced tasks, such as predicting drug response. Nevertheless, this review also underlines the need for further research to bridge the existing gaps in these fields.

Personalized Treatment of Recurrent, Metastatic Head and Neck Cancer Guided by Patient-Derived Xenograft Models.

Recurrent or metastatic head and neck squamous cell carcinoma (RMHNSCC) is associated with a poor prognosis and short survival duration. There is an urgent need to identify personalized predictors of drug response to guide theselection of the most effective therapy for each individual recurrence. We tested the feasibility of patient-derived xenografts (PDX) for guiding their RMHNSCC salvage treatment. Fresh tumor samples from eligible, consented patients were implanted into mice. Established tumors were expanded in mouse PDX cohorts to identify responses to candidate salvage drug treatments in parallel testing. Patients alive and suitable for chemotherapy were treated based on responses determined by PDX testing. Nine patient tumors were successfully engrafted in mice with an average time of 89.2±41.7 days. Four patients' PDX models underwent parallel drug testing. Two patients received PDX-guided therapy. In one of these patients, single agents of cetuximab and paclitaxel demonstrated the best responses in the PDX model, and this patient exhibited sequential partial responses to each drug, including a 17-month clinical response to cetuximab. The main limitation of PDX testing for RMHNSCC was the time delay in obtaining testing results. Despite this, parallel PDX testing may be feasible for a subset of patients and appears to correlate with clinical benefit.

Machine learning and bioinformatic analyses link the cell surface receptor transcript levels to the drug response of breast cancer cells and drug off-target effects.

Breast cancer responds variably to anticancer therapies, often leading to significant off-target effects. This study proposes that the variability in tumour responses and drug-induced adverse events is linked to the transcriptional profiles of cell surface receptors (CSRs) in breast tumours and normal tissues. We analysed multiple datasets to compare CSR expression in breast tumours with that in non-cancerous human tissues. Our findings correlate the drug responses of breast cancer cell lines with the expression levels of their targeted CSRs. Notably, we identified distinct differences in CSR expression between primary breast tumour subtypes and corresponding cell lines, which may influence drug response predictions. Additionally, we used clinical trial data to uncover associations between CSR gene expression in healthy tissues and the incidence of adverse drug reactions. This integrative approach facilitates the selection of optimal CSR targets for therapy, leveraging cell line dose-responses, CSR expression in normal tissues, and patient adverse event profiles.

The development of prognostic gene markers associated with disulfidptosis in gastric cancer and their application in predicting drug response

BackgroundGastric cancer (GC) is a malignancy known for its high fatality rate. Disulfidptosis, a potentially innovative therapeutic strategy for cancer treatment, has been proposed. Nevertheless, the specific involvement of disulfidptosis in the context of GC remains uncertain. MethodsThe mRNA expression profiles were obtained from the TCGA and GEO databases. Univariate and LASSO Cox regression analyses were employed to identify differentially expressed genes and develop a risk model for disulfidptosis-related genes. The performance of the model was evaluated using Kaplan-Meier curve, ROC curve, and nomogram. Univariate and multivariate Cox regression analyses were conducted to determine if the risk model could serve as an independent prognostic factor. The biological function of the identified genes was assessed through GO, KEGG, and GSEA analyses. The prediction of drug response was conducted employing the package “pRRophetic”. Furthermore, gene expression was determined using qRT-PCR. ResultsAn eight-gene signature were identified and utilized to categorize patients into low- and high-risk groups. Survival, receiver operating characteristic (ROC) curve, and Cox analyses provided clarification that these eight hub genes served as a favorable independent prognostic factor for patients with GC. A nomogram was constructed by integrating clinical parameters with the risk signatures, demonstrating high precision in predicting 1-, 3-, and 5-year survival rates. Additionally, drug sensitivity was different in the high-risk and low-risk groups, and the expression of three genes was verified by qRT-PCR. ConclusionThe prognostic risk model developed in this study demonstrates the potential to accurately forecast the prognosis of patients with GC.

Current Trends in the Biomarker'sDiscovery for the Treatment and Management of Colorectal Cancer: A ComprehensiveReview.

Colorectal cancer (CRC) is a significant health issue, with countless individuals suffering. With its bleak outlook, the number of deaths caused by CRC can only be reduced if new diagnostic and prognostic biomarkers are identified and developed quickly. Recent developments in screening programme development and patient management have been encouraging, but many unanswered questions still need to be addressed before a customized colorectal cancer approach can be implemented. Prevention of diseases, the detection of them in their early stages, the analysis of the severity, and the treatment of any metastasized diseases are all paramount. Despite the increased utilization of genetic profiles in decision-making processes, such as the selection of therapy and predicting drug response, there are only a limited number of validated biomarkers for colorectal cancer that are suitable for clinical practice. To further research into colorectal carcinogenesis, pinpoint prospective indicators, and validate these indicators, creating non-intrusive, sensitive, and exact biomarkers is an urgent requirement. This procedure is reliant on translational proteomics. This investigation serves as a comprehensive resource on the current state of genetic and epigenetic biomarkers in diagnosing, predicting, and evaluating colorectal cancer. It underscores the transformative potential of these biomarkers in advancing CRC patient care, from early detection to personalized treatment strategies. However, it also underscores the need for ongoing research and validation to realize their clinical utility fully.

DNA methylation modulates epigenetic regulation in colorectal cancer diagnosis, prognosis and precision medicine.

Colorectal cancer (CRC) is a multifaceted disease influenced by the interplay of genetic and environmental factors. The clinical heterogeneity of CRC cannot be attributed exclusively to genetic diversity and environmental exposures, and epigenetic markers, especially DNA methylation, play a critical role as key molecular markers of cancer. This review compiles a comprehensive body of evidence underscoring the significant involvement of DNA methylation modifications in the pathogenesis of CRC. Moreover, this review explores the potential utility of DNA methylation in cancer diagnosis, prognostics, assessment of disease activity, and prediction of drug responses. Recognizing the impact of DNA methylation will enhance the ability to identify distinct CRC subtypes, paving the way for personalized treatment strategies and advancing precision medicine in the management of CRC.

Mononuclear phagocyte system-related multi-omics features yield head and neck squamous cell carcinoma subtypes with distinct overall survival, drug, and immunotherapy responses

BackgroundRecent research reported that mononuclear phagocyte system (MPS) can contribute to immune defense but the classification of head and neck squamous cell carcinoma (HNSCC) patients based on MPS-related multi-omics features using machine learning lacked.MethodsIn this study, we obtain marker genes for MPS through differential analysis at the single-cell level and utilize “similarity network fusion” and “MoCluster” algorithms to cluster patients’ multi-omics features. Subsequently, based on the corresponding clinical information, we investigate the prognosis, drugs, immunotherapy, and biological differences between the subtypes. A total of 848 patients have been included in this study, and the results obtained from the training set can be verified by two independent validation sets using “the nearest template prediction”.ResultsWe identified two subtypes of HNSCC based on MPS-related multi-omics features, with CS2 exhibiting better predictive prognosis and drug response. CS2 represented better xenobiotic metabolism and higher levels of T and B cell infiltration, while the biological functions of CS1 were mainly enriched in coagulation function, extracellular matrix, and the JAK-STAT signaling pathway. Furthermore, we established a novel and stable classifier called “getMPsub” to classify HNSCC patients, demonstrating good consistency in the same training set. External validation sets classified by “getMPsub” also illustrated similar differences between the two subtypes.ConclusionsOur study identified two HNSCC subtypes by machine learning and explored their biological difference. Notably, we constructed a robust classifier that presented an excellent classifying prediction, providing new insight into the precision medicine of HNSCC.

Predicting drug response of small cell lung cancer cell lines based on enrichment analysis of complex gene signatures

Advances in the field of genomics and transcriptomics have enabled researchers to identify gene signatures related to development and treatment of Small Cell Lung Cancer. In most cases, complex gene expression patterns are identified, comprising of genes with differential behavior. Most tools use single-genes as predictors of drug response, with only limited options for multi-gene use. Here we examine the potential of predicting drug response using these complex gene expression signatures by employing clustering and signal enrichment in Small Cell Lung Cancer. Our results demonstrate clustering genes from complex expression patterns helps identify differential activity of gene groups with alternate function which can then be used to predict drug response.

A Comprehensive Investigation of Active Learning Strategies for Conducting Anti-Cancer Drug Screening

It is well-known that cancers of the same histology type can respond differently to a treatment. Thus, computational drug response prediction is of paramount importance for both preclinical drug screening studies and clinical treatment design. To build drug response prediction models, treatment response data need to be generated through screening experiments and used as input to train the prediction models. In this study, we investigate various active learning strategies of selecting experiments to generate response data for the purposes of (1) improving the performance of drug response prediction models built on the data and (2) identifying effective treatments. Here, we focus on constructing drug-specific response prediction models for cancer cell lines. Various approaches have been designed and applied to select cell lines for screening, including a random, greedy, uncertainty, diversity, combination of greedy and uncertainty, sampling-based hybrid, and iteration-based hybrid approach. All of these approaches are evaluated and compared using two criteria: (1) the number of identified hits that are selected experiments validated to be responsive, and (2) the performance of the response prediction model trained on the data of selected experiments. The analysis was conducted for 57 drugs and the results show a significant improvement on identifying hits using active learning approaches compared with the random and greedy sampling method. Active learning approaches also show an improvement on response prediction performance for some of the drugs and analysis runs compared with the greedy sampling method.

Integrated drug response prediction models pinpoint repurposed drugs with effectiveness against rhabdomyosarcoma.

Targeted therapies for inhibiting the growth of cancer cells or inducing apoptosis are urgently needed for effective rhabdomyosarcoma (RMS) treatment. However, identifying cancer-targeting compounds with few side effects, among the many potential compounds, is expensive and time-consuming. A computational approach to reduce the number of potential candidate drugs can facilitate the discovery of attractive lead compounds. To address this and obtain reliable predictions of novel cell-line-specific drugs, we apply prediction models that have the potential to improve drug discovery approaches for RMS treatment. The results of two prediction models were ensemble and validated via in vitro experiments. The computational models were trained using data extracted from the Genomics of Drug Sensitivity in Cancer database and tested on two RMS cell lines to select potential RMS drug candidates. Among 235 candidate drugs, 22 were selected following the result of the computational approach, and three candidate drugs were identified (NSC207895, vorinostat, and belinostat) that showed selective effectiveness in RMS cell lines in vitro via the induction of apoptosis. Our in vitro experiments have demonstrated that our proposed methods can effectively identify and repurpose drugs for treating RMS.

Liprin-α1 contributes to oncogenic MAPK signaling by counteracting ERK activity.

PTPRF interacting protein alpha 1 (PPFIA1) encodes for liprin-α1, a member of the leukocyte common antigen-related protein tyrosine phosphatase (LAR-RPTPs)-interacting protein family. Liprin-α1 localizes to adhesive and invasive structures in the periphery of cancer cells, where it modulates migration and invasion in head and neck squamous cell carcinoma (HNSCC) and breast cancer. To study the possible role of liprin-α1 in anticancer drug responses, we screened a library of oncology compounds in cell lines with high endogenous PPFIA1 expression. The compounds with the highest differential responses between high PPFIA1-expressing and silenced cells across cell lines were inhibitors targeting mitogen-activated protein kinase kinase (MEK)/extracellular signal-regulated kinases (ERK) signaling. KRAS proto-oncogene, GTPase (KRAS)-mutated MDA-MB-231 cells were more resistant to trametinib upon PPFIA1 knockdown compared with control cells. In contrast, liprin-α1-depleted HNSCC cells with low RAS activity showed a context-dependent response to MEK/ERK inhibitors. Importantly, we showed that liprin-α1 depletion leads to increased p-ERK1/2 levels in all our studied cell lines independent of KRAS mutational status, suggesting a role of liprin-α1 in the regulation of MAPK oncogenic signaling. Furthermore, liprin-α1 depletion led to more pronounced redistribution of RAS proteins to the cell membrane. Our data suggest that liprin-α1 is an important contributor to oncogenic RAS/MAPK signaling, and the status of liprin-α1 may assist in predicting drug responses in cancer cells in a context-dependent manner.