pRRophetic: An R Package for Prediction of Clinical Chemotherapeutic Response from Tumor Gene Expression Levels

We recently described a methodology that reliably predicted chemotherapeutic response in multiple independent clinical trials. The method worked by building statistical models from gene expression and drug sensitivity data in a very large panel of cancer cell lines, then applying these models to gene expression data from primary tumor biopsies. Here, to facilitate the development and adoption of this methodology we have created an R package called pRRophetic. This also extends the previously described pipeline, allowing prediction of clinical drug response for many cancer drugs in a user-friendly R environment. We have developed several other important use cases; as an example, we have shown that prediction of bortezomib sensitivity in multiple myeloma may be improved by training models on a large set of neoplastic hematological cell lines. We have also shown that the package facilitates model development and prediction using several different classes of data.     

Predicting in vitro drug sensitivity using Random Forests

MOTIVATION: Panels of cell lines such as the NCI-60 have long been used to test drug candidates for their ability to inhibit proliferation. Predictive models of in vitro drug sensitivity have previously been constructed using gene expression signatures generated from gene expression microarrays. These statistical models allow the prediction of drug response for cell lines not in the original NCI-60. We improve on existing techniques by developing a novel multistep algorithm that builds regression models of drug response using Random Forest, an ensemble approach based on classification and regression trees (CART). RESULTS: This method proved successful in predicting drug response for both a panel of 19 Breast Cancer and 7 Glioma cell lines, outperformed other methods based on differential gene expression, and has general utility for any application that seeks to relate gene expression data to a continuous output variable. Implementation: Software was written in the R language and will be available together with associated gene expression and drug response data as the package ivDrug at http://r-forge.r-project.org.     

基于多组学数据的肿瘤药物敏感性预测北大核心CSCD

肿瘤药物敏感性预测在指导患者临床用药方面具有重要意义。本文基于癌症药物敏感性基因组学数据库(genomics of drug sensitivity in cancer, GDSC) 198种药物的细胞系敏感性IC50数据,通过Stacking集成学习构建了包含基因表达、基因突变、拷贝数变异数据的多组学癌症药物敏感性预测模型。采用多种特征选择方法对基因特征进行降维,使用Stacking方法集成6种初级学习器和1种次级学习器进行建模,采用5折交叉进行模型验证。预测结果中AUC大于0.9的占比为36.4%,在0.8–0.9之间的占比为49.0%,最低AUC为0.682。基于Stacking构建的多组学预测模型较已有单组学和多组学模型的准确性和稳定性具有优势。多组学整合预测药物敏感性优于单一组学。特征基因功能注释和富集分析解析了肿瘤对sorafenib潜在的耐药机制,从生物学角度提供了模型可解释性及其应用于临床用药指导的价值。     

Exploring effects of DNA methylation and gene expression on pan-cancer drug response by mathematical models

Since genetic alteration only accounts for 20%–30% in the drug effect-related factors, the role of epigenetic regulation mechanisms in drug response is gradually being valued. However, how epigenetic changes and abnormal gene expression affect the chemotherapy response remains unclear. Therefore, we constructed a variety of mathematical models based on the integrated DNA methylation, gene expression, and anticancer drug response data of cancer cell lines from pan-cancer levels to identify genes whose DNA methylation is associated with drug response and then to assess the impact of epigenetic regulation of gene expression on the sensitivity of anticancer drugs. The innovation of the mathematical models lies in: Linear regression model is followed by logistic regression model, which greatly shortens the calculation time and ensures the reliability of results by considering the covariates. Second, reconstruction of prediction models based on multiple dataset partition methods not only evaluates the model stability but also optimizes the drug-gene pairs. For 368,520 drug-gene pairs with P < 0.05 in linear models, 999 candidate pairs with both AUC ≥ 0.8 and P < 0.05 were obtained by logistic regression models between drug response and DNA methylation. Then 931 drug-gene pairs with 45 drugs and 491 genes were optimized by model stability assessment. Integrating both DNA methylation and gene expression markedly increased predictive power for 732 drug-gene pairs where 598 drug-gene pairs including 44 drugs and 359 genes were prioritized. Several drug target genes were enriched in the modules of the drug-gene-weighted interaction network. Besides, for cancer driver genes such as EGFR, MET, and TET2, synergistic effects of DNA methylation and gene expression can predict certain anticancer drugs’ responses. In summary, we identified potential drug sensitivity-related markers from pan-cancer levels and concluded that synergistic regulation of DNA methylation and gene expression affect anticancer drug response.     

PREDICT: a method for inferring novel drug indications with application to personalized medicine

Inferring potential drug indications, for either novel or approved drugs, is a key step in drug development. Previous computational methods in this domain have focused on either drug repositioning or matching drug and disease gene expression profiles. Here, we present a novel method for the large‐scale prediction of drug indications (PREDICT) that can handle both approved drugs and novel molecules. Our method is based on the observation that similar drugs are indicated for similar diseases, and utilizes multiple drug–drug and disease–disease similarity measures for the prediction task. On cross‐validation, it obtains high specificity and sensitivity (AUC=0.9) in predicting drug indications, surpassing existing methods. We validate our predictions by their overlap with drug indications that are currently under clinical trials, and by their agreement with tissue‐specific expression information on the drug targets. We further show that disease‐specific genetic signatures can be used to accurately predict drug indications for new diseases (AUC=0.92). This lays the computational foundation for future personalized drug treatments, where gene expression signatures from individual patients would replace the disease‐specific signatures.     

Gene Expression Ratios Lead to Accurate and Translatable Predictors of DR5 Agonism across Multiple Tumor Lineages

Death Receptor 5 (DR5) agonists demonstrate anti-tumor activity in preclinical models but have yet to demonstrate robust clinical responses. A key limitation may be the lack of patient selection strategies to identify those most likely to respond to treatment. To overcome this limitation, we screened a DR5 agonist Nanobody across >600 cell lines representing 21 tumor lineages and assessed molecular features associated with response. High expression of DR5 and Casp8 were significantly associated with sensitivity, but their expression thresholds were difficult to translate due to low dynamic ranges. To address the translational challenge of establishing thresholds of gene expression, we developed a classifier based on ratios of genes that predicted response across lineages. The ratio classifier outperformed the DR5+Casp8 classifier, as well as standard approaches for feature selection and classification using genes, instead of ratios. This classifier was independently validated using 11 primary patient-derived pancreatic xenograft models showing perfect predictions as well as a striking linearity between prediction probability and anti-tumor response. A network analysis of the genes in the ratio classifier captured important biological relationships mediating drug response, specifically identifying key positive and negative regulators of DR5 mediated apoptosis, including DR5, CASP8, BID, cFLIP, XIAP and PEA15. Importantly, the ratio classifier shows translatability across gene expression platforms (from Affymetrix microarrays to RNA-seq) and across model systems (in vitro to in vivo). Our approach of using gene expression ratios presents a robust and novel method for constructing translatable biomarkers of compound response, which can also probe the underlying biology of treatment response.     

Multiclass Decision Forest--a novel pattern recognition method for multiclass classification in microarray data analysis

The wealth of knowledge imbedded in gene expression data from DNA microarrays portends rapid advances in both research and clinic. Turning the prodigious and noisy data into knowledge is a challenge to the field of bioinformatics, and development of classifiers using supervised learning techniques is the primary methodological approach for clinical application using gene expression data. In this paper, we present a novel classification method, multiclass Decision Forest (DF), that is the direct extension of the two-class DF previously developed in our lab. Central to DF is the synergistic combining of multiple heterogenic but comparable decision trees to reach a more accurate and robust classification model. The computationally inexpensive multiclass DF algorithm integrates gene selection and model development, and thus eliminates the bias of gene preselection in crossvalidation. Importantly, the method provides several statistical means for assessment of prediction accuracy, prediction confidence, and diagnostic capability. We demonstrate the method by application to gene expression data for 83 small round blue-cell tumors (SRBCTs) samples belonging to one of four different classes. Based on 500 runs of 10-fold crossvalidation, tumor prediction accuracy was approximately 97%, sensitivity was approximately 95%, diagnostic sensitivity was approximately 91%, and diagnostic accuracy was approximately 99.5%. Among 25 genes selected to distinguish tumor class, 12 have functional information in the literature implicating their involvement in cancer. The four types of SRBCTs samples are also distinguishable in a clustering analysis based on the expression profiles of these 25 genes. The results demonstrated that the multiclass DF is an effective classification method for analysis of gene expression data for the purpose of molecular diagnostics.     

A pharmacogenomic method for individualized prediction of drug sensitivity

Identifying the best drug for each cancer patient requires an efficient individualized strategy. We present MATCH (M erging genomic and pharmacologic A nalyses for T herapy CH oice), an approach using public genomic resources and drug testing of fresh tumor samples to link drugs to patients. Valproic acid (VPA) is highlighted as a proof‐of‐principle. In order to predict specific tumor types with high probability of drug sensitivity, we create drug response signatures using publically available gene expression data and assess sensitivity in a data set of >40 cancer types. Next, we evaluate drug sensitivity in matched tumor and normal tissue and exclude cancer types that are no more sensitive than normal tissue. From these analyses, breast tumors are predicted to be sensitive to VPA. A meta‐analysis across breast cancer data sets shows that aggressive subtypes are most likely to be sensitive to VPA, but all subtypes have sensitive tumors. MATCH predictions correlate significantly with growth inhibition in cancer cell lines and three‐dimensional cultures of fresh tumor samples. MATCH accurately predicts reduction in tumor growth rate following VPA treatment in patient tumor xenografts. MATCH uses genomic analysis with in vitro testing of patient tumors to select optimal drug regimens before clinical trial initiation.     

A link prediction approach to cancer drug sensitivity prediction

Background

Predicting the response to a drug for cancer disease patients based on genomic information is an important problem in modern clinical oncology. This problem occurs in part because many available drug sensitivity prediction algorithms do not consider better quality cancer cell lines and the adoption of new feature representations; both lead to the accurate prediction of drug responses. By predicting accurate drug responses to cancer, oncologists gain a more complete understanding of the effective treatments for each patient, which is a core goal in precision medicine.

Results

In this paper, we model cancer drug sensitivity as a link prediction, which is shown to be an effective technique. We evaluate our proposed link prediction algorithms and compare them with an existing drug sensitivity prediction approach based on clinical trial data. The experimental results based on the clinical trial data show the stability of our link prediction algorithms, which yield the highest area under the ROC curve (AUC) and are statistically significant.

Conclusions

We propose a link prediction approach to obtain new feature representation. Compared with an existing approach, the results show that incorporating the new feature representation to the link prediction algorithms has significantly improved the performance.

     

Use of gene networks for identifying and validating drug targets

We propose a new method for identifying and validating drug targets by using gene networks, which are estimated from cDNA microarray gene expression profile data. We created novel gene disruption and drug response microarray gene expression profile data libraries for the purpose of drug target elucidation. We use two types of microarray gene expression profile data for estimating gene networks and then identifying drug targets. The estimated gene networks play an essential role in understanding drug response data and this information is unattainable from clustering methods, which are the standard for gene expression analysis. In the construction of gene networks, we use the Bayesian network model. We use an actual example from analysis of the Saccharomyces cerevisiae gene expression profile data to express a concrete strategy for the application of gene network information to drug discovery.     

Integration of clinical and gene expression data has a synergetic effect on predicting breast cancer outcome

Breast cancer outcome can be predicted using models derived from gene expression data or clinical data. Only a few studies have created a single prediction model using both gene expression and clinical data. These studies often remain inconclusive regarding an obtained improvement in prediction performance. We rigorously compare three different integration strategies (early, intermediate, and late integration) as well as classifiers employing no integration (only one data type) using five classifiers of varying complexity. We perform our analysis on a set of 295 breast cancer samples, for which gene expression data and an extensive set of clinical parameters are available as well as four breast cancer datasets containing 521 samples that we used as independent validation.mOn the 295 samples, a nearest mean classifier employing a logical OR operation (late integration) on clinical and expression classifiers significantly outperforms all other classifiers. Moreover, regardless of the integration strategy, the nearest mean classifier achieves the best performance. All five classifiers achieve their best performance when integrating clinical and expression data. Repeating the experiments using the 521 samples from the four independent validation datasets also indicated a significant performance improvement when integrating clinical and gene expression data. Whether integration also improves performances on other datasets (e.g. other tumor types) has not been investigated, but seems worthwhile pursuing. Our work suggests that future models for predicting breast cancer outcome should exploit both data types by employing a late OR or intermediate integration strategy based on nearest mean classifiers.     

Harnessing gene expression to identify the genetic basis of drug resistance

The advent of cost‐effective genotyping and sequencing methods have recently made it possible to ask questions that address the genetic basis of phenotypic diversity and how natural variants interact with the environment. We developed Camelot (CAusal Modelling with Expression Linkage for cOmplex Traits), a statistical method that integrates genotype, gene expression and phenotype data to automatically build models that both predict complex quantitative phenotypes and identify genes that actively influence these traits. Camelot integrates genotype and gene expression data, both generated under a reference condition, to predict the response to entirely different conditions. We systematically applied our algorithm to data generated from a collection of yeast segregants, using genotype and gene expression data generated under drug‐free conditions to predict the response to 94 drugs and experimentally confirmed 14 novel gene–drug interactions. Our approach is robust, applicable to other phenotypes and species, and has potential for applications in personalized medicine, for example, in predicting how an individual will respond to a previously unseen drug.     

Improved prediction of smoking status via isoform-aware RNA-seq deep learning models

Most predictive models based on gene expression data do not leverage information related to gene splicing, despite the fact that splicing is a fundamental feature of eukaryotic gene expression. Cigarette smoking is an important environmental risk factor for many diseases, and it has profound effects on gene expression. Using smoking status as a prediction target, we developed deep neural network predictive models using gene, exon, and isoform level quantifications from RNA sequencing data in 2,557 subjects in the COPDGene Study. We observed that models using exon and isoform quantifications clearly outperformed gene-level models when using data from 5 genes from a previously published prediction model. Whereas the test set performance of the previously published model was 0.82 in the original publication, our exon-based models including an exon-to-isoform mapping layer achieved a test set AUC (area under the receiver operating characteristic) of 0.88, which improved to an AUC of 0.94 using exon quantifications from a larger set of genes. Isoform variability is an important source of latent information in RNA-seq data that can be used to improve clinical prediction models.     

A framework for personalized medicine: prediction of drug sensitivity in cancer by proteomic profiling

Background

The goal of personalized medicine is to provide patients optimal drug screening and treatment based on individual genomic or proteomic profiles. Reverse-Phase Protein Array (RPPA) technology offers proteomic information of cancer patients which may be directly related to drug sensitivity. For cancer patients with different drug sensitivity, the proteomic profiling reveals important pathophysiologic information which can be used to predict chemotherapy responses.

Results

The goal of this paper is to present a framework for personalized medicine using both RPPA and drug sensitivity (drug resistance or intolerance). In the proposed personalized medicine system, the prediction of drug sensitivity is obtained by a proposed augmented naive Bayesian classifier (ANBC) whose edges between attributes are augmented in the network structure of naive Bayesian classifier. For discriminative structure learning of ANBC, local classification rate (LCR) is used to score augmented edges, and greedy search algorithm is used to find the discriminative structure that maximizes classification rate (CR). Once a classifier is trained by RPPA and drug sensitivity using cancer patient samples, the classifier is able to predict the drug sensitivity given RPPA information from a patient.

Conclusion

In this paper we proposed a framework for personalized medicine where a patient is profiled by RPPA and drug sensitivity is predicted by ANBC and LCR. Experimental results with lung cancer data demonstrate that RPPA can be used to profile patients for drug sensitivity prediction by Bayesian network classifier, and the proposed ANBC for personalized cancer medicine achieves better prediction accuracy than naive Bayes classifier in small sample size data on average and outperforms other the state-of-the-art classifier methods in terms of classification accuracy.

     

Impact of between-tissue differences on pan-cancer predictions of drug sensitivity

Increased availability of drug response and genomics data for many tumor cell lines has accelerated the development of pan-cancer prediction models of drug response. However, it is unclear how much between-tissue differences in drug response and molecular characteristics may contribute to pan-cancer predictions. Also unknown is whether the performance of pan-cancer models could vary by cancer type. Here, we built a series of pan-cancer models using two datasets containing 346 and 504 cell lines, each with MEK inhibitor (MEKi) response and mRNA expression, point mutation, and copy number variation data, and found that, while the tissue-level drug responses are accurately predicted (between-tissue ρ = 0.88–0.98), only 5 of 10 cancer types showed successful within-tissue prediction performance (within-tissue ρ = 0.11–0.64). Between-tissue differences make substantial contributions to the performance of pan-cancer MEKi response predictions, as exclusion of between-tissue signals leads to a decrease in Spearman’s ρ from a range of 0.43–0.62 to 0.30–0.51. In practice, joint analysis of multiple cancer types usually has a larger sample size, hence greater power, than for one cancer type; and we observe that higher accuracy of pan-cancer prediction of MEKi response is almost entirely due to the sample size advantage. Success of pan-cancer prediction reveals how drug response in different cancers may invoke shared regulatory mechanisms despite tissue-specific routes of oncogenesis, yet predictions in different cancer types require flexible incorporation of between-cancer and within-cancer signals. As most datasets in genome sciences contain multiple levels of heterogeneity, careful parsing of group characteristics and within-group, individual variation is essential when making robust inference.     

Identifying drug targets for neurological and psychiatric disease via genetics and the brain transcriptome

Discovering drugs that efficiently treat brain diseases has been challenging. Genetic variants that modulate the expression of potential drug targets can be utilized to assess the efficacy of therapeutic interventions. We therefore employed Mendelian Randomization (MR) on gene expression measured in brain tissue to identify drug targets involved in neurological and psychiatric diseases. We conducted a two-sample MR using cis-acting brain-derived expression quantitative trait loci (eQTLs) from the Accelerating Medicines Partnership for Alzheimer’s Disease consortium (AMP-AD) and the CommonMind Consortium (CMC) meta-analysis study (n = 1,286) as genetic instruments to predict the effects of 7,137 genes on 12 neurological and psychiatric disorders. We conducted Bayesian colocalization analysis on the top MR findings (using P<6x10^-7 as evidence threshold, Bonferroni-corrected for 80,557 MR tests) to confirm sharing of the same causal variants between gene expression and trait in each genomic region. We then intersected the colocalized genes with known monogenic disease genes recorded in Online Mendelian Inheritance in Man (OMIM) and with genes annotated as drug targets in the Open Targets platform to identify promising drug targets. 80 eQTLs showed MR evidence of a causal effect, from which we prioritised 47 genes based on colocalization with the trait. We causally linked the expression of 23 genes with schizophrenia and a single gene each with anorexia, bipolar disorder and major depressive disorder within the psychiatric diseases and 9 genes with Alzheimer’s disease, 6 genes with Parkinson’s disease, 4 genes with multiple sclerosis and two genes with amyotrophic lateral sclerosis within the neurological diseases we tested. From these we identified five genes (ACE, GPNMB, KCNQ5, RERE and SUOX) as attractive drug targets that may warrant follow-up in functional studies and clinical trials, demonstrating the value of this study design for discovering drug targets in neuropsychiatric diseases.