scholarly journals SUBSTRA: Supervised Bayesian Patient Stratification

2019 ◽  
Vol 35 (18) ◽  
pp. 3263-3272
Author(s):  
Sahand Khakabimamaghani ◽  
Yogeshwar D Kelkar ◽  
Bruno M Grande ◽  
Ryan D Morin ◽  
Martin Ester ◽  
...  
Keyword(s):  
Drug Response ◽  
Bayesian Method ◽  
State Of The Art ◽  
Transplant Rejection ◽  
Simulated Data ◽  
Predictive Performance ◽  
Response Prediction ◽  
Supplementary Information ◽  
Patient Stratification ◽  
Feature Importance

Abstract Motivation Patient stratification methods are key to the vision of precision medicine. Here, we consider transcriptional data to segment the patient population into subsets relevant to a given phenotype. Whereas most existing patient stratification methods focus either on predictive performance or interpretable features, we developed a method striking a balance between these two important goals. Results We introduce a Bayesian method called SUBSTRA that uses regularized biclustering to identify patient subtypes and interpretable subtype-specific transcript clusters. The method iteratively re-weights feature importance to optimize phenotype prediction performance by producing more phenotype-relevant patient subtypes. We investigate the performance of SUBSTRA in finding relevant features using simulated data and successfully benchmark it against state-of-the-art unsupervised stratification methods and supervised alternatives. Moreover, SUBSTRA achieves predictive performance competitive with the supervised benchmark methods and provides interpretable transcriptional features in diverse biological settings, such as drug response prediction, cancer diagnosis, or kidney transplant rejection. Availability and implementation The R code of SUBSTRA is available at https://github.com/sahandk/SUBSTRA. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals SUBSTRA: Supervised Bayesian Patient Stratification

2019 ◽  
Author(s):  
Sahand Khakabimamaghani ◽  
Yogeshwar Kelkar ◽  
Bruno Grande ◽  
Ryan Morin ◽  
Martin Ester ◽  
...  
Keyword(s):  
Drug Response ◽  
Bayesian Method ◽  
State Of The Art ◽  
Transplant Rejection ◽  
Simulated Data ◽  
Predictive Performance ◽  
Response Prediction ◽  
Patient Stratification ◽  
Specific Transcript ◽  
Feature Importance

Patient stratification methods are key to the vision of precision medicine. Here, we consider transcriptional data to segment the patient population into subsets relevant to a given phenotype. Whereas most existing patient stratification methods focus either on predictive performance or interpretable features, we developed a method striking a balance between these two important goals. We introduce a Bayesian method called SUBSTRA that uses regularized biclustering to identify patient subtypes and interpretable subtype-specific transcript clusters. The method iteratively re-weights feature importance to optimize phenotype prediction performance by producing more phenotype-relevant patient subtypes. We investigate the performance of SUBSTRA in finding relevant features using simulated data and successfully benchmark it against state-of-the-art unsupervised stratification methods and supervised alternatives. Moreover, SUBSTRA achieves predictive performance competitive with supervised benchmark methods and provides interpretable transcriptional features in diverse biological settings, such as drug response prediction, cancer diagnosis, or kidney transplant rejection.

scholarly journals FORESEE: a tool for the systematic comparison of translational drug response modeling pipelines

2018 ◽  
Author(s):  
Lisa-Katrin Turnhoff ◽  
Ali Hadizadeh Esfahani ◽  
Maryam Montazeri ◽  
Nina Kusch ◽  
Andreas Schuppert
Keyword(s):  
Drug Response ◽  
Drug Efficacy ◽  
Response Prediction ◽  
R Package ◽  
Supplementary Information ◽  
Supplementary File ◽  
Data Sets ◽  
Training Algorithms ◽  
Model Training

Translational models that utilize omics data generated in in vitro studies to predict the drug efficacy of anti-cancer compounds in patients are highly distinct, which complicates the benchmarking process for new computational approaches. In reaction to this, we introduce the uniFied translatiOnal dRug rESponsE prEdiction platform FORESEE, an open-source R-package. FORESEE not only provides a uniform data format for public cell line and patient data sets, but also establishes a standardized environment for drug response prediction pipelines, incorporating various state-of-the-art preprocessing methods, model training algorithms and validation techniques. The modular implementation of individual elements of the pipeline facilitates a straightforward development of combinatorial models, which can be used to re-evaluate and improve already existing pipelines as well as to develop new ones. Availability and Implementation: FORESEE is licensed under GNU General Public License v3.0 and available at https://github.com/JRC-COMBINE/FORESEE . Supplementary Information: Supplementary Files 1 and 2 provide detailed descriptions of the pipeline and the data preparation process, while Supplementary File 3 presents basic use cases of the package. Contact: [email protected]

scholarly journals PRECISE: a domain adaptation approach to transfer predictors of drug response from pre-clinical models to tumors

2019 ◽  
Vol 35 (14) ◽  
pp. i510-i519 ◽  
Author(s):  
Soufiane Mourragui ◽  
Marco Loog ◽  
Mark A van de Wiel ◽  
Marcel J T Reinders ◽  
Lodewyk F A Wessels
Keyword(s):  
Cell Lines ◽  
Drug Response ◽  
Domain Adaptation ◽  
Predictive Performance ◽  
Human Tumors ◽  
Supplementary Information ◽  
Patient Response ◽  
Common Information ◽  
Response Predictors ◽  
Clinical Models

Abstract Motivation Cell lines and patient-derived xenografts (PDXs) have been used extensively to understand the molecular underpinnings of cancer. While core biological processes are typically conserved, these models also show important differences compared to human tumors, hampering the translation of findings from pre-clinical models to the human setting. In particular, employing drug response predictors generated on data derived from pre-clinical models to predict patient response remains a challenging task. As very large drug response datasets have been collected for pre-clinical models, and patient drug response data are often lacking, there is an urgent need for methods that efficiently transfer drug response predictors from pre-clinical models to the human setting. Results We show that cell lines and PDXs share common characteristics and processes with human tumors. We quantify this similarity and show that a regression model cannot simply be trained on cell lines or PDXs and then applied on tumors. We developed PRECISE, a novel methodology based on domain adaptation that captures the common information shared amongst pre-clinical models and human tumors in a consensus representation. Employing this representation, we train predictors of drug response on pre-clinical data and apply these predictors to stratify human tumors. We show that the resulting domain-invariant predictors show a small reduction in predictive performance in the pre-clinical domain but, importantly, reliably recover known associations between independent biomarkers and their companion drugs on human tumors. Availability and implementation PRECISE and the scripts for running our experiments are available on our GitHub page (https://github.com/NKI-CCB/PRECISE). Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals MOLI: multi-omics late integration with deep neural networks for drug response prediction

2019 ◽  
Vol 35 (14) ◽  
pp. i501-i509 ◽  
Author(s):  
Hossein Sharifi-Noghabi ◽  
Olga Zolotareva ◽  
Colin C Collins ◽  
Martin Ester
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Prediction Accuracy ◽  
Drug Response ◽  
Deep Neural Networks ◽  
Response Prediction ◽  
Supplementary Information ◽  
Precision Oncology

Abstract Motivation Historically, gene expression has been shown to be the most informative data for drug response prediction. Recent evidence suggests that integrating additional omics can improve the prediction accuracy which raises the question of how to integrate the additional omics. Regardless of the integration strategy, clinical utility and translatability are crucial. Thus, we reasoned a multi-omics approach combined with clinical datasets would improve drug response prediction and clinical relevance. Results We propose MOLI, a multi-omics late integration method based on deep neural networks. MOLI takes somatic mutation, copy number aberration and gene expression data as input, and integrates them for drug response prediction. MOLI uses type-specific encoding sub-networks to learn features for each omics type, concatenates them into one representation and optimizes this representation via a combined cost function consisting of a triplet loss and a binary cross-entropy loss. The former makes the representations of responder samples more similar to each other and different from the non-responders, and the latter makes this representation predictive of the response values. We validate MOLI on in vitro and in vivo datasets for five chemotherapy agents and two targeted therapeutics. Compared to state-of-the-art single-omics and early integration multi-omics methods, MOLI achieves higher prediction accuracy in external validations. Moreover, a significant improvement in MOLI’s performance is observed for targeted drugs when training on a pan-drug input, i.e. using all the drugs with the same target compared to training only on drug-specific inputs. MOLI’s high predictive power suggests it may have utility in precision oncology. Availability and implementation https://github.com/hosseinshn/MOLI. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Graph Transformer for drug response prediction

2021 ◽  
Author(s):  
Tuan Thanh Nguyen ◽  
Thang Chu
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Drug Response ◽  
State Of The Art ◽  
Response Prediction ◽  
Graph Representation ◽  
Omics Data ◽  
Information Redundancy ◽  
Fully Connected ◽  
Deep Learning Model

Previous models have shown that learning drug features from their graph representation is more efficient than learning from their strings or numeric representations. Furthermore, integrating multi-omics data of cell lines increases the performance of drug response prediction. However, these models showed drawbacks in extracting drug features from graph representation and incorporating redundancy information from multi-omics data. This paper proposes a deep learning model, GraTransDRP, to better drug representation and reduce information redundancy. First, the Graph transformer was utilized to extract the drug representation more efficiently. Next, Convolutional neural networks were used to learn the mutation, meth, and transcriptomics features. However, the dimension of transcriptomics features is up to 17737. Therefore, KernelPCA was applied to transcriptomics features to reduce the dimension and transform them into a dense presentation before putting them through the CNN model. Finally, drug and omics features were combined to predict a response value by a fully connected network. Experimental results show that our model outperforms some state-of-the-art methods, including GraphDRP, GraOmicDRP.

scholarly journals FORESEE: a tool for the systematic comparison of translational drug response modeling pipelines

2019 ◽  
Vol 35 (19) ◽  
pp. 3846-3848 ◽  
Author(s):  
Lisa-Katrin Turnhoff ◽  
Ali Hadizadeh Esfahani ◽  
Maryam Montazeri ◽  
Nina Kusch ◽  
Andreas Schuppert
Keyword(s):  
Drug Response ◽  
Drug Efficacy ◽  
Response Prediction ◽  
R Package ◽  
Supplementary Information ◽  
Training Algorithms ◽  
Anti Cancer ◽  
Model Training ◽  
Response Modeling

Abstract Summary Translational models that utilize omics data generated in in vitro studies to predict the drug efficacy of anti-cancer compounds in patients are highly distinct, which complicates the benchmarking process for new computational approaches. In reaction to this, we introduce the uniFied translatiOnal dRug rESponsE prEdiction platform FORESEE, an open-source R-package. FORESEE not only provides a uniform data format for public cell line and patient datasets, but also establishes a standardized environment for drug response prediction pipelines, incorporating various state-of-the-art pre-processing methods, model training algorithms and validation techniques. The modular implementation of individual elements of the pipeline facilitates a straightforward development of combinatorial models, which can be used to re-evaluate and improve already existing pipelines as well as to develop new ones. Availability and implementation FORESEE is licensed under GNU General Public License v3.0 and available at https://github.com/JRC-COMBINE/FORESEE and https://doi.org/10.17605/OSF.IO/RF6QK, and provides vignettes for documentation and application both online and in the Supplementary Files 2 and 3. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals PRECISE: A domain adaptation approach to transfer predictors of drug response from pre-clinical models to tumors

2019 ◽  
Author(s):  
Soufiane Mourragui ◽  
Marco Loog ◽  
Marcel JT Reinders ◽  
Lodewyk FA Wessels
Keyword(s):  
Cell Lines ◽  
Drug Response ◽  
Domain Adaptation ◽  
Predictive Performance ◽  
Human Tumors ◽  
Supplementary Information ◽  
Patient Response ◽  
Common Information ◽  
Response Predictors ◽  
Clinical Models

AbstractMotivationCell lines and patient-derived xenografts (PDX) have been used extensively to understand the molecular underpinnings of cancer. While core biological processes are typically conserved, these models also show important differences compared to human tumors, hampering the translation of findings from pre-clinical models to the human setting. In particular, employing drug response predictors generated on data derived from pre-clinical models to predict patient response, remains a challenging task. As very large drug response datasets have been collected for pre-clinical models, and patient drug response data is often lacking, there is an urgent need for methods that efficiently transfer drug response predictors from pre-clinical models to the human setting.ResultsWe show that cell lines and PDXs share common characteristics and processes with human tumors. We quantify this similarity and show that a regression model cannot simply be trained on cell lines or PDXs and then applied on tumors. We developed PRECISE, a novel methodology based on domain adaptation that captures the common information shared amongst pre-clinical models and human tumors in a consensus representation. Employing this representation, we train predictors of drug response on pre-clinical data and apply these predictors to stratify human tumors. We show that the resulting domain-invariant predictors show a small reduction in predictive performance in the pre-clinical domain but, importantly, reliably recover known associations between independent biomarkers and their companion drugs on human tumors.AvailabilityPRECISE and the scripts for running our experiments are available on our GitHub page (https://github.com/NKI-CCB/PRECISE)[email protected] informationSupplementary data are available. online.

scholarly journals iTOP: Inferring the Topology of Omics Data

2018 ◽  
Author(s):  
Nanne Aben ◽  
Johan A. Westerhuis ◽  
Yipeng Song ◽  
Henk A.L. Kiers ◽  
Magali Michaut ◽  
...  
Keyword(s):  
Gene Expression ◽  
Binary Data ◽  
Drug Response ◽  
Response Prediction ◽  
R Package ◽  
Supplementary Information ◽  
Omics Data ◽  
Reconstruction Algorithms ◽  
Phenotypic Data ◽  
Rv Coefficient

AbstractMotivationIn biology, we are often faced with multiple datasets recorded on the same set of objects, such as multi-omics and phenotypic data of the same tumors. These datasets are typically not independent from each other. For example, methylation may influence gene expression, which may, in turn, influence drug response. Such relationships can strongly affect analyses performed on the data, as we have previously shown for the identification of biomarkers of drug response. Therefore, it is important to be able to chart the relationships between datasets.ResultsWe present iTOP, a methodology to infera topology of relationships between datasets. We base this methodology on the RV coefficient, a measure of matrix correlation, which can be used to determine how much information is shared between two datasets. We extended the RV coefficient for partial matrix correlations, which allows the use of graph reconstruction algorithms, such as the PC algorithm, to infer the topologies. In addition, since multi-omics data often contain binary data (e.g. mutations), we also extended the RV coefficient for binary data. Applying iTOP to pharmacogenomics data, we found that gene expression acts as a mediator between most other datasets and drug response: only proteomics clearly shares information with drug response that is not present in gene expression. Based on this result, we used TANDEM, a method for drug response prediction, to identify which variables predictive of drug response were distinct to either gene expression or proteomics.AvailabilityAn implementation of our methodology is available in the R package iTOP on CRAN. Additionally, an R Markdown document with code to reproduce all figures is provided as Supplementary [email protected] and [email protected] informationSupplementary data are available at Bioinformatics online.

scholarly journals DECO: decompose heterogeneous population cohorts for patient stratification and discovery of sample biomarkers using omic data profiling

2019 ◽  
Vol 35 (19) ◽  
pp. 3651-3662 ◽  
Author(s):  
F J Campos-Laborie ◽  
A Risueño ◽  
M Ortiz-Estévez ◽  
B Rosón-Burgo ◽  
C Droste ◽  
...  
Keyword(s):  
Correspondence Analysis ◽  
Large Scale ◽  
Simulated Data ◽  
R Package ◽  
Heterogeneous Data ◽  
Supplementary Information ◽  
Patient Stratification ◽  
Differential Analysis ◽  
Data Profiling ◽  
Omic Data

Abstract Motivation Patient and sample diversity is one of the main challenges when dealing with clinical cohorts in biomedical genomics studies. During last decade, several methods have been developed to identify biomarkers assigned to specific individuals or subtypes of samples. However, current methods still fail to discover markers in complex scenarios where heterogeneity or hidden phenotypical factors are present. Here, we propose a method to analyze and understand heterogeneous data avoiding classical normalization approaches of reducing or removing variation. Results DEcomposing heterogeneous Cohorts using Omic data profiling (DECO) is a method to find significant association among biological features (biomarkers) and samples (individuals) analyzing large-scale omic data. The method identifies and categorizes biomarkers of specific phenotypic conditions based on a recurrent differential analysis integrated with a non-symmetrical correspondence analysis. DECO integrates both omic data dispersion and predictor–response relationship from non-symmetrical correspondence analysis in a unique statistic (called h-statistic), allowing the identification of closely related sample categories within complex cohorts. The performance is demonstrated using simulated data and five experimental transcriptomic datasets, and comparing to seven other methods. We show DECO greatly enhances the discovery and subtle identification of biomarkers, making it especially suited for deep and accurate patient stratification. Availability and implementation DECO is freely available as an R package (including a practical vignette) at Bioconductor repository (http://bioconductor.org/packages/deco/). Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Dr.VAE: improving drug response prediction via modeling of drug perturbation effects

2019 ◽  
Vol 35 (19) ◽  
pp. 3743-3751 ◽  
Author(s):  
Ladislav Rampášek ◽  
Daniel Hidru ◽  
Petr Smirnov ◽  
Benjamin Haibe-Kains ◽  
Anna Goldenberg
Keyword(s):  
Prior Knowledge ◽  
Drug Response ◽  
Probabilistic Approach ◽  
Response Prediction ◽  
Joint Modeling ◽  
Supplementary Information ◽  
Great Effort ◽  
Drug Induced ◽  
Standard Classification ◽  
Approved Drugs

Abstract Motivation Individualized drug response prediction is a fundamental part of personalized medicine for cancer. Great effort has been made to discover biomarkers or to develop machine learning methods for accurate drug response prediction in cancers. Incorporating prior knowledge of biological systems into these methods is a promising avenue to improve prediction performance. High-throughput cell line assays of drug-induced transcriptomic perturbation effects are a prior knowledge that has not been fully incorporated into a drug response prediction model yet. Results We introduce a unified probabilistic approach, Drug Response Variational Autoencoder (Dr.VAE), that simultaneously models both drug response in terms of viability and transcriptomic perturbations. Dr.VAE is a deep generative model based on variational autoencoders. Our experimental results showed Dr.VAE to do as well or outperform standard classification methods for 23 out of 26 tested Food and Drug Administration-approved drugs. In a series of ablation experiments we showed that the observed improvement of Dr.VAE can be credited to the incorporation of drug-induced perturbation effects with joint modeling of treatment sensitivity. Availability and implementation Processed data and software implementation using PyTorch (Paszke et al., 2017) are available at: https://github.com/rampasek/DrVAE. Supplementary information Supplementary data are available at Bioinformatics online.

Sign in / Sign up

Export Citation Format

Share Document