Auto-HMM-LMF: feature selection based method for prediction of drug response via autoencoder and hidden Markov model

Akram Emdadi,Changiz Eslahchi

doi:10.1186/s12859-021-03974-3

Abstract

BackgroundPredicting the response of cancer cell lines to specific drugs is an essential problem in personalized medicine. Since drug response is closely associated with genomic information in cancer cells, some large panels of several hundred human cancer cell lines are organized with genomic and pharmacogenomic data. Although several methods have been developed to predict the drug response, there are many challenges in achieving accurate predictions. This study proposes a novel feature selection-based method, named Auto-HMM-LMF, to predict cell line-drug associations accurately. Because of the vast dimensions of the feature space for predicting the drug response, Auto-HMM-LMF focuses on the feature selection issue for exploiting a subset of inputs with a significant contribution.ResultsThis research introduces a novel method for feature selection of mutation data based on signature assignments and hidden Markov models. Also, we use the autoencoder models for feature selection of gene expression and copy number variation data. After selecting features, the logistic matrix factorization model is applied to predict drug response values. Besides, by comparing to one of the most powerful feature selection methods, the ensemble feature selection method (EFS), we showed that the performance of the predictive model based on selected features introduced in this paper is much better for drug response prediction. Two datasets, the Genomics of Drug Sensitivity in Cancer (GDSC) and Cancer Cell Line Encyclopedia (CCLE) are used to indicate the efficiency of the proposed method across unseen patient cell-line. Evaluation of the proposed model showed that Auto-HMM-LMF could improve the accuracy of the results of the state-of-the-art algorithms, and it can find useful features for the logistic matrix factorization method.ConclusionsWe depicted an application of Auto-HMM-LMF in exploring the new candidate drugs for head and neck cancer that showed the proposed method is useful in drug repositioning and personalized medicine. The source code of Auto-HMM-LMF method is available in https://github.com/emdadi/Auto-HMM-LMF.

Highlights

Predicting the response of cancer cell lines to specific drugs is an essential problem in personalized medicine
By comparing to the ensemble feature selection method (EFS), we showed that two considered strategies for feature selection in the Auto-hidden Markov model (HMM)-LMF method could select proper features that significantly improved the prediction result
Evaluation of prediction performance of Auto‐HMM‐LMF Using the feature selection approaches is one of the common methods to reduce the dimensions of the features in drug response prediction problems

Summary

Introduction

Predicting the response of cancer cell lines to specific drugs is an essential problem in personalized medicine. Computational models for personalized medicine make it possible to understand cancer cell lines on the basis of genomic information This knowledge makes it possible to recommend individualized therapies to patients with different types of cancer by measuring drug responses. Since drug response to cancer treatment depends on multiple factors such as the patient’s genomic profile, this process is a complicated problem in cancer treatment These challenges have generated large-scale experiments on human cancer cell lines and various anticancer drugs. The various genetic features for the panels of cancer cell lines, such as gene expression profile, copy number alteration, single nucleotide mutation and methylation data, have been provided By using these databases, machine learning algorithms are increasingly being applied to the predictions of drug responses by integrating data from different sources in a statistically meaningful way

Methods

Results

Conclusion