Optimal drug prediction from personal genomics profiles

DRExplainer: Quantifiable interpretability in drug response prediction with directed graph convolutional network

Predicting the response of a cancer cell line to a therapeutic drug is pivotal for personalized medicine. Despite numerous deep learning methods that have been developed for drug response prediction, integrating diverse information about biological entities and predicting the directional response remain major challenges. Here, we propose a novel interpretable predictive model, DRExplainer, which leverages a directed graph convolutional network to enhance the prediction in a directed bipartite network framework. DRExplainer constructs a directed bipartite network integrating multi-omics profiles of cell lines, the chemical structure of drugs and known drug response to achieve directed prediction. Then, DRExplainer identifies the most relevant subgraph to each prediction in this directed bipartite network by learning a mask, facilitating critical medical decision-making. Additionally, we introduce a quantifiable method for model interpretability that leverages a ground truth benchmark dataset curated from biological features. In computational experiments, DRExplainer outperforms state-of-the-art predictive methods and another graph-based explanation method under the same experimental setting. Finally, the case studies further validate the interpretability and the effectiveness of DRExplainer in predictive novel drug response. Our code is available at: https://github.com/vshy-dream/DRExplainer.

A semi-supervised weighted SPCA- and convolution KAN-based model for drug response prediction

Motivation

Predicting the response of cell lines to characteristic drugs based on multi-omics gene information has become the core problem of precision oncology. At present, drug response prediction using multi-omics gene data faces the following three main challenges: first, how to design a gene probe feature extraction model with biological interpretation and high performance; second, how to develop multi-omics weighting modules for reasonably fusing genetic data of different lengths and noise conditions; third, how to construct deep learning models that can handle small sample sizes while minimizing the risk of possible overfitting.

Results

We propose an innovative drug response prediction model (NMDP). First, the NMDP model introduces an interpretable semi-supervised weighted SPCA module to solve the feature extraction problem in multi-omics gene data. Next, we construct a multi-omics data fusion framework based on sample similarity networks, bimodal tests, and variance information, which solves the data fusion problem and enables the NMDP model to focus on more relevant genomic data. Finally, we combine a one-dimensional convolution method and Kolmogorov-Arnold networks (KANs) to predict the drug response. We conduct five sets of real data experiments and compare NMDP against seven advanced drug response prediction methods. The results show that NMDP achieves the best performance, with sensitivity and specificity reaching 0.92 and 0.93, respectively-an improvement of 11%-57% compared to other models. Bio-enrichment experiments strongly support the biological interpretation of the NMDP model and its ability to identify potential targets for drug activity prediction.

Decoding Drug Response With Structurized Gridding Map-Based Cell Representation

A thorough understanding of cell-line drug response mechanisms is crucial for drug development, repurposing, and resistance reversal. While targeted anticancer therapies have shown promise, not all cancers have well-established biomarkers to stratify drug response. Single-gene associations only explain a small fraction of the observed drug sensitivity, so a more comprehensive method is needed. However, while deep learning models have shown promise in predicting drug response in cell lines, they still face significant challenges when it comes to their application in clinical applications. Therefore, this study proposed a new strategy called DD-Response for cell-line drug response prediction. First, a limitation of narrow modeling horizons was overcome to expand the model training domain by integrating multiple datasets through source-specific label binarization. Second, a modified representation based on a two-dimensional structurized gridding map (SGM) was developed for cell lines & drugs, avoiding feature correlation neglect and potential information loss. Third, a dual-branch, multi-channel convolutional neural network-based model for pairwise response prediction was constructed, enabling accurate outcomes and improved exploration of underlying mechanisms. As a result, the DD-Response demonstrated superior performance, captured cell-line characteristic variations, and provided insights into key factors impacting cell-line drug response. In addition, DD-Response exhibited scalability in predicting clinical patient responses to drug therapy. Overall, because of DD-response's excellent ability to predict drug response and capture key molecules behind them, DD-response is expected to greatly facilitate drug discovery, repurposing, resistance reversal, and therapeutic optimization.

Interpretable Dynamic Directed Graph Convolutional Network for Multi-Relational Prediction of Missense Mutation and Drug Response

Tumor heterogeneity presents a significant challenge in predicting drug responses, especially as missense mutations within the same gene can lead to varied outcomes such as drug resistance, enhanced sensitivity, or therapeutic ineffectiveness. These complex relationships highlight the need for advanced analytical approaches in oncology. Due to their powerful ability to handle heterogeneous data, graph convolutional networks (GCNs) represent a promising approach for predicting drug responses. However, simple bipartite graphs cannot accurately capture the complex relationships involved in missense mutation and drug response. Furthermore, Deep learning models for drug response are often considered "black boxes", and their interpretability remains a widely discussed issue. To address these challenges, we propose an Interpretable Dynamic Directed Graph Convolutional Network (IDDGCN) framework, which incorporates four key features: 1) the use of directed graphs to differentiate between sensitivity and resistance relationships, 2) the dynamic updating of node weights based on node-specific interactions, 3) the exploration of associations between different mutations within the same gene and drug response, and 4) the enhancement of interpretability models through the integration of a weighted mechanism that accounts for the biological significance, alongside a ground truth construction method to evaluate prediction transparency. The experimental results demonstrate that IDDGCN outperforms existing state-of-the-art models, exhibiting excellent predictive power. Both qualitative and quantitative evaluations of its interpretability further highlight its ability to explain predictions, offering a fresh perspective for precision oncology and targeted drug development.

MGATAF: multi-channel graph attention network with adaptive fusion for cancer-drug response prediction

BACKGROUND

Drug response prediction is critical in precision medicine to determine the most effective and safe treatments for individual patients. Traditional prediction methods relying on demographic and genetic data often fall short in accuracy and robustness. Recent graph-based models, while promising, frequently neglect the critical role of atomic interactions and fail to integrate drug fingerprints with SMILES for comprehensive molecular graph construction.

RESULTS

We introduce multimodal multi-channel graph attention network with adaptive fusion (MGATAF), a framework designed to enhance drug response predictions by capturing both local and global interactions among graph nodes. MGATAF improves drug representation by integrating SMILES and fingerprints, resulting in more precise predictions of drug effects. The methodology involves constructing multimodal molecular graphs, employing multi-channel graph attention networks to capture diverse interactions, and using adaptive fusion to integrate these interactions at multiple abstraction levels. Empirical results demonstrate MGATAF's superior performance compared to traditional and other graph-based techniques. For example, on the GDSC dataset, MGATAF achieved a 5.12% improvement in the Pearson correlation coefficient (PCC), reaching 0.9312 with an RMSE of 0.0225. Similarly, in new cell-line tests, MGATAF outperformed baselines with a PCC of 0.8536 and an RMSE of 0.0321 on the GDSC dataset, and a PCC of 0.7364 with an RMSE of 0.0531 on the CCLE dataset.

CONCLUSIONS

MGATAF significantly advances drug response prediction by effectively integrating multiple molecular data types and capturing complex interactions. This framework enhances prediction accuracy and offers a robust tool for personalized medicine, potentially leading to more effective and safer treatments for patients. Future research can expand on this work by exploring additional data modalities and refining the adaptive fusion mechanisms.

ASGCL: Adaptive Sparse Mapping-based graph contrastive learning network for cancer drug response prediction

Personalized cancer drug treatment is emerging as a frontier issue in modern medical research. Considering the genomic differences among cancer patients, determining the most effective drug treatment plan is a complex and crucial task. In response to these challenges, this study introduces the Adaptive Sparse Graph Contrastive Learning Network (ASGCL), an innovative approach to unraveling latent interactions in the complex context of cancer cell lines and drugs. The core of ASGCL is the GraphMorpher module, an innovative component that enhances the input graph structure via strategic node attribute masking and topological pruning. By contrasting the augmented graph with the original input, the model delineates distinct positive and negative sample sets at both node and graph levels. This dual-level contrastive approach significantly amplifies the model's discriminatory prowess in identifying nuanced drug responses. Leveraging a synergistic combination of supervised and contrastive loss, ASGCL accomplishes end-to-end learning of feature representations, substantially outperforming existing methodologies. Comprehensive ablation studies underscore the efficacy of each component, corroborating the model's robustness. Experimental evaluations further illuminate ASGCL's proficiency in predicting drug responses, offering a potent tool for guiding clinical decision-making in cancer therapy.

Dissecting the shared genetic landscape of anxiety, depression, and schizophrenia

BACKGROUND

Numerous studies highlight the genetic underpinnings of mental disorders comorbidity, particularly in anxiety, depression, and schizophrenia. However, their shared genetic loci are not well understood. Our study employs Mendelian randomization (MR) and colocalization analyses, alongside multi-omics data, to uncover potential genetic targets for these conditions, thereby informing therapeutic and drug development strategies.

METHODS

We utilized the Consortium for Linkage Disequilibrium Score Regression (LDSC) and Mendelian Randomization (MR) analysis to investigate genetic correlations among anxiety, depression, and schizophrenia. Utilizing GTEx V8 eQTL and deCODE Genetics pQTL data, we performed a three-step summary-data-based Mendelian randomization (SMR) and protein-protein interaction analysis. This helped assess causal and comorbid loci for these disorders and determine if identified loci share coincidental variations with psychiatric diseases. Additionally, phenome-wide association studies, drug prediction, and molecular docking validated potential drug targets.

RESULTS

We found genetic correlations between anxiety, depression, and schizophrenia, and under a meta-analysis of MR from multiple databases, the causal relationships among these disorders are supported. Based on this, three-step SMR and colocalization analyses identified ITIH3 and CCS as being related to the risk of developing depression, while CTSS and DNPH1 are related to the onset of schizophrenia. BTN3A1, PSMB4, and TIMP4 were identified as comorbidity loci for both disorders. Molecules that could not be determined through colocalization analysis were also presented. Drug prediction and molecular docking showed that some drugs and proteins have good binding affinity and available structural data.

CONCLUSIONS

Our study indicates genetic correlations and shared risk loci between anxiety, depression, and schizophrenia. These findings offer insights into the underlying mechanisms of their comorbidities and aid in drug development.

Proteomic analysis reveals the molecular mechanism of Astragaloside in the treatment of non-small cell lung cancer by inducing apoptosis

BACKGROUND

Astragaloside III (AS III), a saponin-like metabolite derived from the traditional Chinese medicine Astragali Radix, has been shown to be effective in the treatment of cancer and heart failure, and a variety of digestive disorders. However, its molecular mechanism in the treatment of non-small cell lung cancer (NSCLC) is unknown.

METHODS

Human lung cancer A549 cells and NCI-H460 cells and a normal human lung epithelial cell BEAS-2B were treated with different concentrations of AS III. CCK-8 and EdU staining were used to determine the anti-proliferative effects of AS III in vitro. Quantitative proteomic analysis was performed on A549 cells treated with the indicated concentrations of AS III, and the expression levels of apoptosis-related proteins were examined by Western blotting.

RESULTS

AS III treatment significantly inhibited proliferation and increased apoptosis in A549 and H460 cells and modulated functional signaling pathways associated with apoptosis and metabolism. At the molecular level, AS III promoted a reduction in the expression of ANXA1 (p < 0.01), with increased levels of cleaved Caspase 3 and PARP 1. In addition, AS III treatment significantly decreased the LC3-I/LC3-II ratio. The results of experiment in vitro showed that AS III promoted NSCLC apoptosis by down-regulating the phosphorylation levels of P38, JNK, and AKT (p < 0.01), inhibiting the expression of Bcl-2 (p < 0.01), and up-regulating the expression of Bax (p < 0.01).

CONCLUSION

These findings provide a mechanism whereby AS III treatment induces apoptosis in NSCLC cells, which may be achieved in part via modulation of the P38, ERK and mTOR signaling pathways.

Multi-omic characterization of ILC and ILC-like cell lines as part of ILC cell line encyclopedia (ICLE) defines new models to study potential biomarkers and explore therapeutic opportunities

Invasive lobular carcinoma (ILC), the most common histological "special type", accounts for ∼10-15% of all BC diagnoses, is characterized by unique features such as E-cadherin loss/deficiency, lower grade, hormone receptor positivity, larger diffuse tumors, and specific metastatic patterns. Despite ILC being acknowledged as a disease with distinct biology that necessitates specialized and precision medicine treatments, the further exploration of its molecular alterations with the goal of discovering new treatments has been hindered due to the scarcity of well-characterized cell line models for studying this disease. To address this, we generated the ILC Cell Line Encyclopedia (ICLE), providing a comprehensive multi-omic characterization of ILC and ILC-like cell lines. Using consensus multi-omic subtyping, we confirmed luminal status of previously established ILC cell lines and uncovered additional ILC/ILC-like cell lines with luminal features for modeling ILC disease. Furthermore, most of these luminal ILC/ILC-like cell lines also showed RNA and copy number similarity to ILC patient tumors. Similarly, ILC/ILC-like cell lines also retained molecular alterations in key ILC genes at similar frequency to both primary and metastatic ILC tumors. Importantly, ILC/ILC-like cell lines recapitulated the CDH1 alteration landscape of ILC patient tumors including enrichment of truncating mutations in and biallelic inactivation of CDH1 gene. Using whole-genome optical mapping, we uncovered novel genomic-rearrangements including novel structural variations in CDH1 and functional gene fusions and characterized breast cancer specific patterns of chromothripsis in chromosomes 8, 11 and 17. In addition, we systematically analyzed aberrant DNAm events and integrative analysis with RNA expression revealed epigenetic activation of TFAP2B - an emerging biomarker of lobular disease that is preferentially expressed in lobular disease. Finally, towards the goal of identifying novel druggable vulnerabilities in ILC, we analyzed publicly available RNAi loss of function breast cancer cell line datasets and revealed numerous putative vulnerabilities cytoskeletal components, focal adhesion and PI3K/AKT pathway in ILC/ILC-like vs NST cell lines. In summary, we addressed the lack of suitable models to study E-cadherin deficient breast cancers by first collecting both established and putative ILC models, then characterizing them comprehensively to show their molecular similarity to patient tumors along with uncovering their novel multi-omic features as well as highlighting putative novel druggable vulnerabilities. Not only we expand the array of suitable E-cadherin deficient cell lines available for modelling human-ILC disease but also employ them for studying epigenetic activation of a putative lobular biomarker as well as identifying potential druggable vulnerabilities for this disease towards enabling precision medicine research for human-ILC.

DROEG: a method for cancer drug response prediction based on omics and essential genes integration

Predicting therapeutic responses in cancer patients is a major challenge in the field of precision medicine due to high inter- and intra-tumor heterogeneity. Most drug response models need to be improved in terms of accuracy, and there is limited research to assess therapeutic responses of particular tumor types. Here, we developed a novel method DROEG (Drug Response based on Omics and Essential Genes) for prediction of drug response in tumor cell lines by integrating genomic, transcriptomic and methylomic data along with CRISPR essential genes, and revealed that the incorporation of tumor proliferation essential genes can improve drug sensitivity prediction. Concisely, DROEG integrates literature-based and statistics-based methods to select features and uses Support Vector Regression for model construction. We demonstrate that DROEG outperforms most state-of-the-art algorithms by both qualitative (prediction accuracy for drug-sensitive/resistant) and quantitative (Pearson correlation coefficient between the predicted and actual IC50) evaluation in Genomics of Drug Sensitivity in Cancer and Cancer Cell Line Encyclopedia datasets. In addition, DROEG is further applied to the pan-gastrointestinal tumor with high prevalence and mortality as a case study at both cell line and clinical levels to evaluate the model efficacy and discover potential prognostic biomarkers in Cisplatin and Epirubicin treatment. Interestingly, the CRISPR essential gene information is found to be the most important contributor to enhance the accuracy of the DROEG model. To our knowledge, this is the first study to integrate essential genes with multi-omics data to improve cancer drug response prediction and provide insights into personalized precision treatment.

Improving drug response prediction based on two-space graph convolution

Patients with the same cancer types may present different genomic features and therefore have different drug sensitivities. Accordingly, correctly predicting patients' responses to the drugs can guide treatment decisions and improve the outcome of cancer patients. Existing computational methods leverage the graph convolution network model to aggregate features of different types of nodes in the heterogeneous network. They most fail to consider the similarity between homogeneous nodes. To this end, we propose an algorithm based on two-space graph convolutional neural networks, TSGCNN, to predict the response of anticancer drugs. TSGCNN first constructs the cell line feature space and the drug feature space and separately performs the graph convolution operation on the feature spaces to diffuse similarity information among homogeneous nodes. After that, we generate a heterogeneous network based on the known cell line and drug relationship and perform graph convolution operations on the heterogeneous network to collect the features of different types of nodes. Subsequently, the algorithm produces the final feature representations for cell lines and drugs by adding their self features, the feature space representations, and the heterogeneous space representations. Finally, we leverage the linear correlation coefficient decoder to reconstruct the cell line-drug correlation matrix for drug response prediction based on the final representations. We tested our model on the Cancer Drug Sensitivity Data (GDSC) and Cancer Cell Line Encyclopedia (CCLE) databases. The results indicate that TSGCNN shows excellent performance drug response prediction compared with other eight state-of-the-art methods.

Prediction of drug sensitivity based on multi-omics data using deep learning and similarity network fusion approaches

With the rapid development of multi-omics technologies and accumulation of large-scale bio-datasets, many studies have conducted a more comprehensive understanding of human diseases and drug sensitivity from multiple biomolecules, such as DNA, RNA, proteins and metabolites. Using single omics data is difficult to systematically and comprehensively analyze the complex disease pathology and drug pharmacology. The molecularly targeted therapy-based approaches face some challenges, such as insufficient target gene labeling ability, and no clear targets for non-specific chemotherapeutic drugs. Consequently, the integrated analysis of multi-omics data has become a new direction for scientists to explore the mechanism of disease and drug. However, the available drug sensitivity prediction models based on multi-omics data still have problems such as overfitting, lack of interpretability, difficulties in integrating heterogeneous data, and the prediction accuracy needs to be improved. In this paper, we proposed a novel drug sensitivity prediction (NDSP) model based on deep learning and similarity network fusion approaches, which extracts drug targets using an improved sparse principal component analysis (SPCA) method for each omics data, and construct sample similarity networks based on the sparse feature matrices. Furthermore, the fused similarity networks are put into a deep neural network for training, which greatly reduces the data dimensionality and weakens the risk of overfitting problem. We use three omics of data, RNA sequence, copy number aberration and methylation, and select 35 drugs from Genomics of Drug Sensitivity in Cancer (GDSC) for experiments, including Food and Drug Administration (FDA)-approved targeted drugs, FDA-unapproved targeted drugs and non-specific therapies. Compared with some current deep learning methods, our proposed method can extract highly interpretable biological features to achieve highly accurate sensitivity prediction of targeted and non-specific cancer drugs, which is beneficial for the development of precision oncology beyond targeted therapy.

Network Control Models With Personalized Genomics Data for Understanding Tumor Heterogeneity in Cancer

Due to rapid development of high-throughput sequencing and biotechnology, it has brought new opportunities and challenges in developing efficient computational methods for exploring personalized genomics data of cancer patients. Because of the high-dimension and small sample size characteristics of these personalized genomics data, it is difficult for excavating effective information by using traditional statistical methods. In the past few years, network control methods have been proposed to solve networked system with high-dimension and small sample size. Researchers have made progress in the design and optimization of network control principles. However, there are few studies comprehensively surveying network control methods to analyze the biomolecular network data of individual patients. To address this problem, here we comprehensively surveyed complex network control methods on personalized omics data for understanding tumor heterogeneity in precision medicine of individual patients with cancer.

MALAT1 as master regulator of biomarkers predictive of pan-cancer multi-drug resistance in the context of recalcitrant NRAS signaling pathway identified using systems-oriented approach

NRAS, a protein mutated in several cancer types, is involved in key drug resistance mechanisms and is an intractable target. The development of drug resistance is one of the major impediments in targeted therapy. Currently, gene expression data is used as the most predictive molecular profile in pan-cancer drug sensitivity and resistance studies. However, the common regulatory mechanisms that drive drug sensitivity/resistance across cancer types are as yet, not fully understood. We focused on GDSC data on NRAS-mutant pan-cancer cell lines, to pinpoint key signaling targets in direct or indirect associations with NRAS, in order to identify other druggable targets involved in drug resistance. Large-scale gene expression, comparative gene co-expression and protein–protein interaction network analyses were performed on selected drugs inducing drug sensitivity/resistance. We validated our data from cell lines with those obtained from primary tissues from TCGA. From our big data studies validated with independent datasets, protein-coding hub genes FN1, CD44, TIMP1, SNAI2, and SPARC were found significantly enriched in signal transduction, proteolysis, cell adhesion and proteoglycans pathways in cancer as well as the PI3K/Akt-signaling pathway. Further studies of the regulation of these hub/driver genes by lncRNAs revealed several lncRNAs as prominent regulators, with MALAT1 as a possible master regulator. Transcription factor EGR1 may control the transcription rate of MALAT1 transcript. Synergizing these studies, we zeroed in on a pan-cancer regulatory axis comprising EGR1-MALAT1-driver coding genes playing a role. These identified gene regulators are bound to provide new paradigms in pan-cancer targeted therapy, a foundation for precision medicine, through the targeting of these key driver genes in the improvement of multi-drug sensitivity or resistance.

EBSRMF: Ensemble based similarity-regularized matrix factorization to predict anticancer drug responses

Drug sensitivity prediction to a panel of cancer cell lines using computational approaches has been a challenge for two decades. With the emergence of high-throughput screening technologies, thousands of compounds and cancer cell lines panels with drug sensitivity data are publicly available at various pharmacogenomics databases. Analyzing these data is crucial to improve cancer treatment and develop new anticancer drugs. In this work, we propose EBSRMF: Ensemble Based Similarity-Regularized Matrix Factorization, which is a bagging based framework to improve the drug sensitivity prediction on the Cancer Cell Line Encyclopedia (CCLE) data. Based on the fact that similar drugs and cell lines exhibit similar drug response, we have investigated cell line and drug similarity matrices based on gene expression profiles and chemical structure respectively. The drug sensitivity value is used as outcome values which are the half maximal inhibitory concentrations (IC50). In order to improve the generalization ability of the proposed model, a homogeneous ensemble based bagging learning approach is also investigated where multiple SRMF models are used to train N subsets of the input data. The outcome of each training algorithm is aggregated using the averaging method to predict the outcome. Experiments are conducted on two benchmark datasets: CCLE and GDSC. The proposed model is compared with state-of-the-art models using multiple evaluation metrics including Root Means Square Error (RMSE) and Pearson Correlation Coefficient (PCC). The proposed model is quite promising and achieves better performance on CCLE dataset when compared with the existing approaches.

An overview of machine learning methods for monotherapy drug response prediction

For an increasing number of preclinical samples, both detailed molecular profiles and their responses to various drugs are becoming available. Efforts to understand, and predict, drug responses in a data-driven manner have led to a proliferation of machine learning (ML) methods, with the longer term ambition of predicting clinical drug responses. Here, we provide a uniquely wide and deep systematic review of the rapidly evolving literature on monotherapy drug response prediction, with a systematic characterization and classification that comprises more than 70 ML methods in 13 subclasses, their input and output data types, modes of evaluation, and code and software availability. ML experts are provided with a fundamental understanding of the biological problem, and how ML methods are configured for it. Biologists and biomedical researchers are introduced to the basic principles of applicable ML methods, and their application to the problem of drug response prediction. We also provide systematic overviews of commonly used data sources used for training and evaluation methods.

Predicting Drug Response Based on Multi-omics Fusion and Graph Convolution

Different cancer patients may respond differently to cancer treatment due to the heterogeneity of cancer. It is an urgent task to develop an efficient computational method to identify drug responses in different cell lines, which guides us to design personalized therapy for an individual patient. Hence, we propose an end-to-end algorithm, namely MOFGCN, to predict drug response in cell lines based on Multi-Omics Fusion and Graph Convolution Network. MOFGCN first fuses multiple omics data to calculate the cell line similarity and then constructs a heterogeneous network by combining the cell line similarity, drug similarity, and the known cell line-drug associations. Secondly, it learns the latent features for cancer cell lines and drugs by performing graph convolution operations on the heterogeneous network. Finally, MOFGCN applies the linear correlation coefficient to reconstruct the cancer cell line-drug correlation matrix to predict drug sensitivity. To our knowledge, this is the first attempt to combine graph convolutional neural network and linear correlation coefficient for this significant task. We performed extensive evaluation experiments on the Genomics of Drug Sensitivity in Cancer (GDSC) and Cancer Cell Line Encyclopedia (CCLE) databases to validate MOFGCNs performance. The experimental results show that MOFGCN is superior to the state-of-the-art algorithms in predicting missing drug responses. It also leads to higher performance in predicting drug responses for new cell lines, new drugs, and targeted drugs.

Performance Comparisons of AlexNet and GoogLeNet in Cell Growth Inhibition IC50 Prediction

Drug responses in cancer are diverse due to heterogenous genomic profiles. Drug responsiveness prediction is important in clinical response to specific cancer treatments. Recently, multi-class drug responsiveness models based on deep learning (DL) models using molecular fingerprints and mutation statuses have emerged. However, for multi-class models for drug responsiveness prediction, comparisons between convolution neural network (CNN) models (e.g., AlexNet and GoogLeNet) have not been performed. Therefore, in this study, we compared the two CNN models, GoogLeNet and AlexNet, along with the least absolute shrinkage and selection operator (LASSO) model as a baseline model. We constructed the models by taking drug molecular fingerprints of drugs and cell line mutation statuses, as input, to predict high-, intermediate-, and low-class for half-maximal inhibitory concentration (IC50) values of the drugs in the cancer cell lines. Additionally, we compared the models in breast cancer patients as well as in an independent gastric cancer cell line drug responsiveness data. We measured the model performance based on the area under receiver operating characteristic (ROC) curves (AUROC) value. In this study, we compared CNN models for multi-class drug responsiveness prediction. The AlexNet and GoogLeNet showed better performances in comparison to LASSO. Thus, DL models will be useful tools for precision oncology in terms of drug responsiveness prediction.

Metabolic and transcriptional analysis of recombinant Saccharomyces?cerevisiae for xylose fermentation: a feasible and efficient approach

Lignocellulose is an abundant xylose-containing biomass found in agricultural wastes, and has arisen as a suitable alternative to fossil fuels for the production of bioethanol. Although Saccharomyces cerevisiae has been thoroughly used for the production of bioethanol, its potential to utilize lignocellulose remains poorly understood. In this work, xylose-metabolic genes of Pichia stipitis and Candida tropicalis, under the control of different promoters, were introduced into S. cerevisiae. RNA-seq analysis was use to examine the response of S. cerevisiae metabolism to the introduction of xylose-metabolic genes. The use of the PGK1 promoter to drive xylitol dehydrogenase (XDH) expression, instead of the TEF1 promoter, improved xylose utilization in ?XR-pXDH? strain by overexpressing xylose reductase (XR) and XDH from C. tropicalis, enhancing the production of xylitol (13.66 ? 0.54 g/L after 6 days fermentation). Overexpression of xylulokinase and XR/XDH from P. stipitis remarkably decreased xylitol accumulation (1.13 ? 0.06 g/L and 0.89 ? 0.04 g/L xylitol, respectively) and increased ethanol production (196.14% and 148.50% increases during the xylose utilization stage, respectively), in comparison with the results of XR-pXDH. This result may be produced due to the enhanced xylose transport, Embden?Meyerhof and pentose phosphate pathways, as well as alleviated oxidative stress. The low xylose consumption rate in these recombinant strains comparing with P. stipitis and C. tropicalis may be explained by the insufficient supplementation of NADPH and NAD+. The results obtained in this work provide new insights on the potential utilization of xylose using bioengineered S. cerevisiae strains.

Drug Repurposing in Oncology, an Attractive Opportunity for Novel Combinatorial Regimens

The costs of developing, validating and buying new drugs are dramatically increasing. On the other hand, sobering economies have difficulties in sustaining their healthcare systems, particularly in countries with an elderly population requiring increasing welfare. This conundrum requires immediate action, and a possible option is to study the large, already present arsenal of drugs approved and to use them for innovative therapies. This possibility is particularly interesting in oncology, where the complexity of the cancer genome dictates in most patients a multistep therapeutic approach. In this review, we discuss a) Computational approaches; b) preclinical models; c) currently ongoing or already published clinical trials in the drug repurposing field in oncology; and d) drug repurposing to overcome resistance to previous therapies.

Visualization of Protein-Drug Interactions for the Analysis of Drug Resistance in Lung Cancer

Non-small cell lung cancer (NSCLC) caused by mutation of the epidermal growth factor receptor (EGFR) is a major cause of death worldwide. Tyrosine kinase inhibitors (TKIs) of EGFR have been developed and show promising results at the initial stage of therapy. However, in most cases, their efficacy becomes limited due to the emergence of secondary mutations causing drug resistance after about a year. In this work, we investigated the mechanism of drug resistance due to these mutations. We performed molecular dynamics (MD) simulations of EGFR-drug interactions to obtain Euclidean distance and binding free energy values to analyse drug resistance and visualize drug-protein interactions. A PCA-based method is proposed to find normal, rigid, flexible, and critical residues. We have established a systematic method for the visualization of protein-drug interactions, which provides an effective framework for the analysis of drug resistance in lung cancer at the atomic level.

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.

Synergistic Drug Combination Prediction by Integrating Multiomics Data in Deep Learning Models

Intrinsic and acquired drug resistance is a major challenge in cancer therapy. Synergistic drug combinations could help to overcome drug resistance. However, the number of possible drug combinations is enormous, and it is infeasible to experimentally screen all drug combinations with limited resources. Therefore, computational models to predict and prioritize effective drug combinations are important for combination therapy discovery. Compared with existing models, we propose a novel deep learning model, AuDNNsynergy, to predict the synergy of pairwise drug combinations by integrating multiomics data. Specifically, three autoencoders are trained using the gene expression, copy number, and genetic mutation data of tumor samples from The Cancer Genome Atlas (TCGA). Then the gene expression, copy number, and mutation of individual cancer cell lines are coded using the three trained autoencoders. The physicochemical features of individual drugs and the encoded omics data of individual cancer cell lines are used as the input features of a deep neural network that predicts the synergy score of given pairwise drug combinations against the specific cancer cell lines. The comparison results showed the proposed AuDNNsynergy model outperforms, specifically in terms of rank correlation metric, four state-of-the-art approaches, namely, DeepSynergy, Gradient Boosting Machines, Random Forests, and Elastic Nets.

An Efficient and Easy-to-Use Network-Based Integrative Method of Multi-Omics Data for Cancer Genes Discovery

Identifying personalized driver genes is essential for discovering critical biomarkers and developing effective personalized therapies of cancers. However, few methods consider weights for different types of mutations and efficiently distinguish driver genes over a larger number of passenger genes. We propose MinNetRank (Minimum used for Network-based Ranking), a new method for prioritizing cancer genes that sets weights for different types of mutations, considers the incoming and outgoing degree of interaction network simultaneously, and uses minimum strategy to integrate multi-omics data. MinNetRank prioritizes cancer genes among multi-omics data for each sample. The sample-specific rankings of genes are then integrated into a population-level ranking. When evaluating the accuracy and robustness of prioritizing driver genes, our method almost always significantly outperforms other methods in terms of precision, F1 score, and partial area under the curve (AUC) on six cancer datasets. Importantly, MinNetRank is efficient in discovering novel driver genes. SP1 is selected as a candidate driver gene only by our method (ranked top three), and SP1 RNA and protein differential expression between tumor and normal samples are statistically significant in liver hepatocellular carcinoma. The top seven genes stratify patients into two subtypes exhibiting statistically significant survival differences in five cancer types. These top seven genes are associated with overall survival, as illustrated by previous researchers. MinNetRank can be very useful for identifying cancer driver genes, and these biologically relevant marker genes are associated with clinical outcome. The R package of MinNetRank is available at https://github.com/weitinging/MinNetRank.

Integrative network analysis identifies potential targets and drugs for ovarian cancer

BACKGROUND

Though accounts for 2.5% of all cancers in female, the death rate of ovarian cancer is high, which is the fifth leading cause of cancer death (5% of all cancer death) in female. The 5-year survival rate of ovarian cancer is less than 50%. The oncogenic molecular signaling of ovarian cancer are complicated and remain unclear, and there is a lack of effective targeted therapies for ovarian cancer treatment.

METHODS

In this study, we propose to investigate activated signaling pathways of individual ovarian cancer patients and sub-groups; and identify potential targets and drugs that are able to disrupt the activated signaling pathways. Specifically, we first identify the up-regulated genes of individual cancer patients using Markov chain Monte Carlo (MCMC), and then identify the potential activated transcription factors. After dividing ovarian cancer patients into several sub-groups sharing common transcription factors using K-modes method, we uncover the up-stream signaling pathways of activated transcription factors in each sub-group. Finally, we mapped all FDA approved drugs targeting on the upstream signaling.

RESULTS

The 427 ovarian cancer samples were divided into 3 sub-groups (with 100, 172, 155 samples respectively) based on the activated TFs (with 14, 25, 26 activated TFs respectively). Multiple up-stream signaling pathways, e.g., MYC, WNT, PDGFRA (RTK), PI3K, AKT TP53, and MTOR, are uncovered to activate the discovered TFs. In addition, 66 FDA approved drugs were identified targeting on the uncovered core signaling pathways. Forty-four drugs had been reported in ovarian cancer related reports. The signaling diversity and heterogeneity can be potential therapeutic targets for drug combination discovery.

CONCLUSIONS

The proposed integrative network analysis could uncover potential core signaling pathways, targets and drugs for ovarian cancer treatment.

Network-based Biased Tree Ensembles (NetBiTE) for Drug Sensitivity Prediction and Drug Sensitivity Biomarker Identification in Cancer

We present the Network-based Biased Tree Ensembles (NetBiTE) method for drug sensitivity prediction and drug sensitivity biomarker identification in cancer using a combination of prior knowledge and gene expression data. Our devised method consists of a biased tree ensemble that is built according to a probabilistic bias weight distribution. The bias weight distribution is obtained from the assignment of high weights to the drug targets and propagating the assigned weights over a protein-protein interaction network such as STRING. The propagation of weights, defines neighborhoods of influence around the drug targets and as such simulates the spread of perturbations within the cell, following drug administration. Using a synthetic dataset, we showcase how application of biased tree ensembles (BiTE) results in significant accuracy gains at a much lower computational cost compared to the unbiased random forests (RF) algorithm. We then apply NetBiTE to the Genomics of Drug Sensitivity in Cancer (GDSC) dataset and demonstrate that NetBiTE outperforms RF in predicting IC50 drug sensitivity, only for drugs that target membrane receptor pathways (MRPs): RTK, EGFR and IGFR signaling pathways. We propose based on the NetBiTE results, that for drugs that inhibit MRPs, the expression of target genes prior to drug administration is a biomarker for IC50 drug sensitivity following drug administration. We further verify and reinforce this proposition through control studies on, PI3K/MTOR signaling pathway inhibitors, a drug category that does not target MRPs, and through assignment of dummy targets to MRP inhibiting drugs and investigating the variation in NetBiTE accuracy.

The Cloud Gets Personal

Cloud computing, at its most fundamental level, is a technology that allows computing to occur as an on-demand utility. Personalized medicine is revolutionizing the field of medicine, and aims to provide individualized treatment for patients, based on their genetic material and medical history, through comparisons to genetic material from thousands of other patients. Better patient outcomes are expected in a personalized medicine domain as compared to more generic generalized options. In this paper the authors explore the use of cloud computing in the area of personalized medicine examining unique benefits and opportunities. They also recognize and discuss the presence of some inherent risks. Using the cloud for personalized medicine can expedite collaborations and data collection across different clinicians, researchers and other stakeholders involved in the fight against diseases. This paper examines key elements associated with using cloud computing in the specialized area of personalized medicine.