Anti-cancer Drug Response Prediction Research Articles

A hierarchical attention network integrating multi-scale relationship for drug response prediction

Anticancer drug response prediction with deep learning technology has become the foundation of precision medicine. It is essential for anticancer drug response prediction to incorporate multi-scale relationships within feature items and biomedical entities. Therefore, we propose MultiDRP that develops the hierarchical attention networks integrating multi-scale relationship for drug response prediction. MultiDRP can fuse both internal correlation of feature items and external relationship of biomedical entities by hierarchically integrating graph attention and self-attention networks to improve the anticancer drug response prediction. A variety of results showed that MultiDRP generated the great representation by integrating multi-scale relationships, and achieved higher performance compared to existing methods on various prediction scenarios. The results of network proximity, gene ontology biological process (GOBP) enrichment, and drug pathway association analysis show that MultiDRP can accurately screen the sensitive and resistant drugs for cancer cell lines. In vitro experiments, eight novel drugs predicted by MultiDRP exhibited high sensitivity to lung cancer cell line NCI-H23, seven of which showed IC50 values of less than 10nM. These results further suggest that MultiDRP can serve as a powerful tool for anticancer drug response prediction. The source data and code are available at https://github.com/pengsl-lab/MultiDRP.git

Text-mining-based feature selection for anticancer drug response prediction.

Predicting anticancer treatment response from baseline genomic data is a critical obstacle in personalized medicine. Machine learning methods are commonly used for predicting drug response from gene expression data. In the process of constructing these machine learning models, one of the most significant challenges is identifying appropriate features among a massive number of genes. In this study, we utilize features (genes) extracted using the text-mining of scientific literatures. Using two independent cancer pharmacogenomic datasets, we demonstrate that text-mining-based features outperform traditional feature selection techniques in machine learning tasks. In addition, our analysis reveals that text-mining feature-based machine learning models trained on in vitro data also perform well when predicting the response of in vivo cancer models. Our results demonstrate that text-mining-based feature selection is an easy to implement approach that is suitable for building machine learning models for anticancer drug response prediction. https://github.com/merlab/text_features.

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.

Integration of Computational Docking into Anti-Cancer Drug Response Prediction Models.

Cancer is a heterogeneous disease in that tumors of the same histology type can respond differently to a treatment. Anti-cancer drug response prediction is of paramount importance for both drug development and patient treatment design. Although various computational methods and data have been used to develop drug response prediction models, it remains a challenging problem due to the complexities of cancer mechanisms and cancer-drug interactions. To better characterize the interaction between cancer and drugs, we investigate the feasibility of integrating computationally derived features of molecular mechanisms of action into prediction models. Specifically, we add docking scores of drug molecules and target proteins in combination with cancer gene expressions and molecular drug descriptors for building response models. The results demonstrate a marginal improvement in drug response prediction performance when adding docking scores as additional features, through tests on large drug screening data. We discuss the limitations of the current approach and provide the research community with a baseline dataset of the large-scale computational docking for anti-cancer drugs.

CTDN (Convolutional Temporal Based Deep‐ Neural Network): An Improvised Stacked Hybrid Computational Approach for Anticancer Drug Response Prediction

The characterization of drug - metabolizing enzymes is a significant problem for customized therapy. It is important to choose the right drugs for cancer victims, and the ability to forecast how those drugs will react is usually based on the available information, genetic sequence, and structural properties. To the finest of our knowledge, this is the first study to evaluate optimization algorithms for selection of features and pharmacogenetics categorization using classification methods based on a successful evolutionary algorithm using datasets from the Cancer Cell Line Encyclopaedia (CCLE) and Genomics of Drug Sensitivity in Cancer (GDSC). The study proposes the uses of Firefly and Grey Wolf Optimization techniques for feature extraction, while comparing the traditional Machine Learning (ML), ensemble ML and Stacking Algorithm with the proposed Convolutional Temporal Deep Neural Network or CTDN. With the potential to increase efficiency from the suggested intelligible classifier model for a suggestive chemotherapeutic drugs response prediction, our study is important in particular for selecting an acceptable feature selection method. The comparison analysis demonstrates that the proposed model not only surpasses the prior state-of-the-art methods, but also uses Grey Wolf and Fire Fly Optimization to lessen multicollinearity and overfitting.

Preclinical-to-clinical Anti-cancer Drug Response Prediction and Biomarker Identification Using TINDL

Prediction of the response of cancer patients to different treatments and identification of biomarkers of drug response are two major goals of individualized medicine. Here, we developed a deep learning framework called TINDL, completely trained on preclinical cancer cell lines (CCLs), to predict the response of cancer patients to different treatments. TINDL utilizes a tissue-informed normalization to account for the tissue type and cancer type of the tumors and to reduce the statistical discrepancies between CCLs and patient tumors. Moreover, by making the deep learning black box interpretable, this model identifies a small set of genes whose expression levels are predictive of drug response in the trained model, enabling identification of biomarkers of drug response. Using data from two large databases of CCLs and cancer tumors, we showed that this model can distinguish between sensitive and resistant tumors for 10 (out of 14) drugs, outperforming various other machine learning models. In addition, our small interfering RNA (siRNA) knockdown experiments on 10 genes identified by this model for one of the drugs (tamoxifen) confirmed that tamoxifen sensitivity is substantially influenced by all of these genes in MCF7 cells, and seven of these genes in T47D cells. Furthermore, genes implicated for multiple drugs pointed to shared mechanism of action among drugs and suggested several important signaling pathways. In summary, this study provides a powerful deep learning framework for prediction of drug response and identification of biomarkers of drug response in cancer. The code can be accessed at https://github.com/ddhostallero/tindl.

DeepInsight-3D architecture for anti-cancer drug response prediction with deep-learning on multi-omics

Modern oncology offers a wide range of treatments and therefore choosing the best option for particular patient is very important for optimal outcome. Multi-omics profiling in combination with AI-based predictive models have great potential for streamlining these treatment decisions. However, these encouraging developments continue to be hampered by very high dimensionality of the datasets in combination with insufficiently large numbers of annotated samples. Here we proposed a novel deep learning-based method to predict patient-specific anticancer drug response from three types of multi-omics data. The proposed DeepInsight-3D approach relies on structured data-to-image conversion that then allows use of convolutional neural networks, which are particularly robust to high dimensionality of the inputs while retaining capabilities to model highly complex relationships between variables. Of particular note, we demonstrate that in this formalism additional channels of an image can be effectively used to accommodate data from different omics layers while implicitly encoding the connection between them. DeepInsight-3D was able to outperform other state-of-the-art methods applied to this task. The proposed improvements can facilitate the development of better personalized treatment strategies for different cancers in the future.

Gamma distribution based predicting model for breast cancer drug response based on multi-layer feature selection.

In the pursuit of precision medicine for cancer, a promising step is to predict drug response based on data mining, which can provide clinical decision support for cancer patients. Although some machine learning methods for predicting drug response from genomic data already exist, most of them focus on point prediction, which cannot reveal the distribution of predicted results. In this paper, we propose a three-layer feature selection combined with a gamma distribution based GLM and a two-layer feature selection combined with an ANN. The two regression methods are applied to the Encyclopedia of Cancer Cell Lines (CCLE) and the Cancer Drug Sensitivity Genomics (GDSC) datasets. Using ten-fold cross-validation, our methods achieve higher accuracy on anticancer drug response prediction compared to existing methods, with an R 2 and RMSE of 0.87 and 0.53, respectively. Through data validation, the significance of assessing the reliability of predictions by predicting confidence intervals and its role in personalized medicine are illustrated. The correlation analysis of the genes selected from the three layers of features also shows the effectiveness of our proposed methods.

Predicting cancer drug response using parallel heterogeneous graph convolutional networks with neighborhood interactions.

Due to cancer heterogeneity, the therapeutic effect may not be the same when a cohort of patients of the same cancer type receive the same treatment. The anticancer drug response prediction may help develop personalized therapy regimens to increase survival and reduce patients' expenses. Recently, graph neural network-based methods have aroused widespread interest and achieved impressive results on the drug response prediction task. However, most of them apply graph convolution to process cell line-drug bipartite graphs while ignoring the intrinsic differences between cell lines and drug nodes. Moreover, most of these methods aggregate node-wise neighbor features but fail to consider the element-wise interaction between cell lines and drugs. This work proposes a neighborhood interaction (NI)-based heterogeneous graph convolution network method, namely NIHGCN, for anticancer drug response prediction in an end-to-end way. Firstly, it constructs a heterogeneous network consisting of drugs, cell lines and the known drug response information. Cell line gene expression and drug molecular fingerprints are linearly transformed and input as node attributes into an interaction model. The interaction module consists of a parallel graph convolution network layer and a NI layer, which aggregates node-level features from their neighbors through graph convolution operation and considers the element-level of interactions with their neighbors in the NI layer. Finally, the drug response predictions are made by calculating the linear correlation coefficients of feature representations of cell lines and drugs. We have conducted extensive experiments to assess the effectiveness of our model on Cancer Drug Sensitivity Data (GDSC) and Cancer Cell Line Encyclopedia (CCLE) datasets. It has achieved the best performance compared with the state-of-the-art algorithms, especially in predicting drug responses for new cell lines, new drugs and targeted drugs. Furthermore, our model that was well trained on the GDSC dataset can be successfully applied to predict samples of PDX and TCGA, which verified the transferability of our model from cell line in vitro to the datasets in vivo. The source code can be obtained from https://github.com/weiba/NIHGCN. Supplementary data are available at Bioinformatics online.

Developing liver cancer drug response prediction system using late fusion of reduced deep features

Liver cancer is a major cause of death, with a high mortality rate worldwide. For better treatment and rehabilitation of liver cancer, assessing and evaluating drug delivery and response prediction is vital. In this study, we propose a novel approach for the prediction of the liver anticancer drug response using modified ResNet101 deep learning with transfer learning (TL) concept for deep features extraction. Dimension reduction algorithms, PCA and t-SNE are applied to capture global and local structures of deep features, respectively. Herein, a new fusion scheme is introduced that uses global and local levels of image information to improve the classification. Reduced deep fused features are used to develop a quadratic discriminant analysis (QDA) prediction model. The proposed approach is evaluated on fluorescent images of human hepatocellular carcinoma (HepG2) treated using an anticancer drug functionalized by cobalt ferrite@barium titanate (CFO@BTO) nanoparticles. A dataset comprising 203 HepG2 microscopic images is used to train and test the model using the split ratio of 75%:25% by employing a 5-fold cross-validation technique. The proposed system achieved a high accuracy of 98.0% compared to other state-of-the-art approaches. The developed pipeline is flexible and can be extended for prostate, lung, and breast cancers.

A Novel Defined Endoplasmic Reticulum Stress-Related lncRNA Signature for Prognosis Prediction and Immune Therapy in Glioma.

Gliomas are a group of the most aggressive primary central nervous system tumors with limited treatment options. The abnormal expression of long non-coding RNA (lncRNA) is related to the prognosis of glioma. However, the role of endoplasmic reticulum (ER) stress-associated lncRNAs in glioma prognosis has not been reported. In this paper, we obtained ER stress-related lncRNAs by co-expression analysis, and then a risk signature composed of 6 ER stress-related lncRNAs was constructed using Cox regression analysis. Glioma samples in The Cancer Genome Atlas (TCGA) were separated into high- and low-risk groups based on the median risk score. Compared with the low-risk group, patients in the high-risk group had shorter survival times. Additionally, we verified the predictive ability of these candidate lncRNAs in the testing set. Three glioma patient subgroups (cluster 1/2/3) were identified by consensus clustering. We further analysed the abundance of immune-infiltrating cells and the expression levels of immune checkpoint molecules in both three subgroups and two risk groups, respectively. Immunotherapy and anticancer drug response prediction showed that ER stress-related lncRNA risk signature positively correlates with responding to immune checkpoints and chemosensitivity. Functional analysis showed that these gene sets are enriched in the malignant process of tumors. Finally, LINC00519 was chosen for functional experiments. The silence of LINC00519 restrained the migration and invasion of glioma cells. Hence, those results indicated that ER stress-related lncRNA risk signature could be a potential treatment target and a prognosis biomarker for glioma patients.

A KRAS-Associated Signature for Prognostic, Immune and Chemical Anti-Cancer Drug-Response Prediction in Colon Cancer.

Background: KRAS mutation, one of the most important biological processes in colorectal cancer, leads to poor prognosis in patients. Although studies on KRAS have concentrated for a long time, there are currently no ideal drugs against KRAS mutations. Methods: Different expression analysis and weighted gene coexpression network analysis was conducted to select candidate genes. Log-rank tests and Cox regression picked out the prognostic genes to build a KRAS-related gene prognostic score (KRGPS). A nomogram based on KRGPS was built to predict survival of clinical patients. Comprehensive analysis showed the prognosis, immune microenvironment and response to immune therapy and chemotherapy in KRGPS subgroups. Results: We collected a KRGPS from the set of two genes GJB6 and NTNG1, with low-KRGSP patients having better progression-free survival (PFS). Low KRGPS is correlated with high infiltration of activated NK cells, plasma cells and activated memory CD4 T cells and that these cells benefit more from immune checkpoint inhibitor therapy. However, high KRGPS is associated with high infiltration of activated mast cells, pathways of immune dysregulation and a high ratio of TP53 and KRAS mutations. KRGPS subgroups are also sensitive to chemotherapy differently. A nomogram, established based on the KRGPS and pathological stage, predict 3- and 5-years PFS well. Conclusions: The KRAS-associated score acts as a promising signature to distinguish prognosis, molecular and immune characteristics, and benefits from immune and chemical therapy. These KRAS-associated genes could be promising targets for drug design.

Identification of an endoplasmic reticulum stress-related signature associated with clinical prognosis and immune therapy in glioma

BackgroundGlioma is the most common brain tumor in adults and is characterized by a short survival time and high resistance to chemotherapy. It is imperative to determine the prognosis and therapy-related targets for glioma. Endoplasmic reticulum stress (ERS), as an adaptive protective mechanism, indicates the unfolded protein response (UPR) to determine cell survival and affects chemotherapy sensitivity, which is related to the prognosis of glioma.MethodsOur research used the TCGA database as the training group and the CGGA database as the testing group. Lasso regression and Cox analysis were performed to construct an ERS signature-based risk score model in glioma. Three methods (time-dependent receiver operating characteristic analysis and multivariate and univariate Cox regression analysis) were applied to assess the independent prognostic effect of texture parameters. Consensus clustering was used to classify the two clusters. In addition, functional and immune analyses were performed to assess the malignant process and immune microenvironment. Immunotherapy and anticancer drug response prediction were adopted to evaluate immune checkpoint and chemotherapy sensitivity.ResultsThe results revealed that the 7-gene signature strongly predicts glioma prognosis. The two clusters have markedly distinct molecular and prognostic features. The validation group result revealed that the signature has exceptional repeatability and certainty. Functional analysis showed that the ERS-related gene signature was closely associated with the malignant process and prognosis of tumors. Immune analysis indicated that the ERS-related gene signature is strongly related to immune infiltration. Immunotherapy and anticancer drug response prediction indicated that the ERS-related gene signature is positively correlated with immune checkpoint and chemotherapy sensitivity.ConclusionsCollectively, the ERS-related risk model can provide a novel signature to predict glioma prognosis and treatment.

DWUT-MLP: Classification of anticancer drug response using various feature selection and classification techniques

Drug response classification constitutes a major challenge in personalized medicine. The suitable drug selection for cancer patients is substantial and the drug response prediction is generally based on the target information, genomic cohort and chemical structure. Hence, for classification process, feature selection approaches are highly essential, which is driven by prior knowledge of gene expression signatures, drug targets, and target pathways. Further, the classification is performed to assess the accurate drug response prediction. To the best of our knowledge, this is the first work to assess different optimization techniques for feature selection and performing drug response classification using different classifiers based on effective optimization algorithm using Cancer Cell Line Encyclopaedia- CCLE and Genomics of Drug Sensitivity in Cancer- GDSC dataset. For performing feature selection, Firefly, Whale and Grey wolf optimization algorithms are examined. Further, to perform classification, Adaboost, gradient boost and random forest classifiers are utilized. In addition to that, a newly developed classification approach, namely Discriminative Weight Updated Tuned Deep Multi-Layer Perceptron (DWUT-MLP) is used and compared with the other classifiers. The optimization algorithms with newly developed DWUT-MLP and other existing classification techniques are evaluated and results shows that the effective feature selection algorithm with suitable classification algorithm improves anticancer drug response prediction's accuracy. Thus, this research is substantial in general for choosing an appropriate feature selection approach, has the probability of improving the accuracy from the interpretable proposed classifier model for an indicative anticancer drug response prediction. From the comparative analysis, it shows that the proposed model performs nearly 10–15% better than existing frameworks in classifying the anticancer drug response.

Predicting Anticancer Drug Response With Deep Learning Constrained by Signaling Pathways.

Thanks to the availability of multiomics data of individual cancer patients, precision medicine or personalized medicine is becoming a promising treatment for individual cancer patients. However, the association patterns, that is, the mechanism of response (MoR) between large-scale multiomics features and drug response are complex and heterogeneous and remain unclear. Although there are existing computational models for predicting drug response using the high-dimensional multiomics features, it remains challenging to uncover the complex molecular mechanism of drug responses. To reduce the number of predictors/features and make the model more interpretable, in this study, 46 signaling pathways were used to build a deep learning model constrained by signaling pathways, consDeepSignaling, for anti–drug response prediction. Multiomics data, like gene expression and copy number variation, of individual genes can be integrated naturally in this model. The signaling pathway–constrained deep learning model was evaluated using the multiomics data of ∼1000 cancer cell lines in the Broad Institute Cancer Cell Line Encyclopedia (CCLE) database and the corresponding drug–cancer cell line response data set in the Genomics of Drug Sensitivity in Cancer (GDSC) database. The evaluation results showed that the proposed model outperformed the existing deep neural network models. Also, the model interpretation analysis indicated the distinctive patterns of importance of signaling pathways in anticancer drug response prediction.

Machine learning based anti-cancer drug response prediction and search for predictor genes using cancer cell line gene expression.

Although many models have been proposed to accurately predict the response of drugs in cell lines recent years, understanding the genome related to drug response is also the key for completing oncology precision medicine. In this paper, based on the cancer cell line gene expression and the drug response data, we established a reliable and accurate drug response prediction model and found predictor genes for some drugs of interest. To this end, we first performed pre-selection of genes based on the Pearson correlation coefficient and then used ElasticNet regression model for drug response prediction and fine gene selection. To find more reliable set of predictor genes, we performed regression twice for each drug, one with IC50 and the other with area under the curve (AUC) (or activity area). For the 12 drugs we tested, the predictive performance in terms of Pearson correlation coefficient exceeded 0.6 and the highest one was 17-AAG for which Pearson correlation coefficient was 0.811 for IC50 and 0.81 for AUC. We identify common predictor genes for IC50 and AUC, with which the performance was similar to those with genes separately found for IC50 and AUC, but with much smaller number of predictor genes. By using only common predictor genes, the highest performance was AZD6244 (0.8016 for IC50, 0.7945 for AUC) with 321 predictor genes.

Ensemble transfer learning for the prediction of anti-cancer drug response

Transfer learning, which transfers patterns learned on a source dataset to a related target dataset for constructing prediction models, has been shown effective in many applications. In this paper, we investigate whether transfer learning can be used to improve the performance of anti-cancer drug response prediction models. Previous transfer learning studies for drug response prediction focused on building models to predict the response of tumor cells to a specific drug treatment. We target the more challenging task of building general prediction models that can make predictions for both new tumor cells and new drugs. Uniquely, we investigate the power of transfer learning for three drug response prediction applications including drug repurposing, precision oncology, and new drug development, through different data partition schemes in cross-validation. We extend the classic transfer learning framework through ensemble and demonstrate its general utility with three representative prediction algorithms including a gradient boosting model and two deep neural networks. The ensemble transfer learning framework is tested on benchmark in vitro drug screening datasets. The results demonstrate that our framework broadly improves the prediction performance in all three drug response prediction applications with all three prediction algorithms.

Enhanced Co-Expression Extrapolation (COXEN) Gene Selection Method for Building Anti-Cancer Drug Response Prediction Models.

The co-expression extrapolation (COXEN) method has been successfully used in multiple studies to select genes for predicting the response of tumor cells to a specific drug treatment. Here, we enhance the COXEN method to select genes that are predictive of the efficacies of multiple drugs for building general drug response prediction models that are not specific to a particular drug. The enhanced COXEN method first ranks the genes according to their prediction power for each individual drug and then takes a union of top predictive genes of all the drugs, among which the algorithm further selects genes whose co-expression patterns are well preserved between cancer cases for building prediction models. We apply the proposed method on benchmark in vitro drug screening datasets and compare the performance of prediction models built based on the genes selected by the enhanced COXEN method to that of models built on genes selected by the original COXEN method and randomly picked genes. Models built with the enhanced COXEN method always present a statistically significantly improved prediction performance (adjusted p-value ≤ 0.05). Our results demonstrate the enhanced COXEN method can dramatically increase the power of gene expression data for predicting drug response.

ADRML: anticancer drug response prediction using manifold learning

One of the prominent challenges in precision medicine is to select the most appropriate treatment strategy for each patient based on the personalized information. The availability of massive data about drugs and cell lines facilitates the possibility of proposing efficient computational models for predicting anticancer drug response. In this study, we propose ADRML, a model for Anticancer Drug Response Prediction using Manifold Learning to systematically integrate the cell line information with the drug information to make accurate predictions about drug therapeutic. The proposed model maps the drug response matrix into the lower-rank spaces that lead to obtaining new perspectives about cell lines and drugs. The drug response for a new cell line-drug pair is computed using the low-rank features. The evaluation of ADRML performance on various types of cell lines and drug information, in addition to the comparisons with previously proposed methods, shows that ADRML provides accurate and robust predictions. Further investigations about the association between drug response and pathway activity scores reveal that the predicted drug responses can shed light on the underlying drug mechanism. Also, the case studies suggest that the predictions of ADRML about novel cell line-drug pairs are validated by reliable pieces of evidence from the literature. Consequently, the evaluations verify that ADRML can be used in accurately predicting and imputing the anticancer drug response.

An Improved Anticancer Drug-Response Prediction Based on an Ensemble Method Integrating Matrix Completion and Ridge Regression

In this study, we proposed an ensemble learning method, simultaneously integrating a low-rank matrix completion model and a ridge regression model to predict anticancer drug response on cancer cell lines. The model was applied to two benchmark datasets, including the Cancer Cell Line Encyclopedia (CCLE) and the Genomics of Drug Sensitivity in Cancer (GDSC). As previous studies suggest, the dual-layer integrated cell line-drug network model was one of the best models by far and outperformed most state-of-the-art models. Thus, we performed a head-to-head comparison between the dual-layer integrated cell line-drug network model and our model by a 10-fold crossvalidation study. For the CCLE dataset, our model has a higher Pearson correlation coefficient between predicted and observed drug responses than that of the dual-layer integrated cell line-drug network model in 18 out of 23 drugs. For the GDSC dataset, our model is better in 26 out of 28 drugs in the phosphatidylinositol 3-kinase (PI3K) pathway and 26 out of 30 drugs in the extracellular signal-regulated kinase (ERK) signaling pathway, respectively. Based on the prediction results, we carried out two types of case studies, which further verified the effectiveness of the proposed model on the drug-response prediction. In addition, our model is more biologically interpretable than the compared method, since it explicitly outputs the genes involved in the prediction, which are enriched in functions, like transcription, Src homology 2/3 (SH2/3) domain, cell cycle, ATP binding, and zinc finger.