Clinical drug response prediction from preclinical cancer cell lines by logistic matrix factorization approach.

Predicting tumor drug response using cancer cell line drug response values for a large number of anti-cancer drugs is a significant challenge in personalized medicine. Predicting patient response to drugs from data obtained from preclinical models is made easier by the availability of different knowledge on cell lines and drugs. This paper proposes the TCLMF method, a predictive model for predicting drug response in tumor samples that was trained on preclinical samples and is based on the logistic matrix factorization approach. The TCLMF model is designed based on gene expression profiles, tissue type information, the chemical structure of drugs and drug sensitivity (IC 50) data from cancer cell lines. We use preclinical data from the Genomics of Drug Sensitivity in Cancer dataset (GDSC) to train the proposed drug response model, which we then use to predict drug sensitivity of samples from the Cancer Genome Atlas (TCGA) dataset. The TCLMF approach focuses on identifying successful features of cell lines and drugs in order to calculate the probability of the tumor samples being sensitive to drugs. The closest cell line neighbours for each tumor sample are calculated using a description of similarity between tumor samples and cell lines in this study. The drug response for a new tumor is then calculated by averaging the low-rank features obtained from its neighboring cell lines. We compare the results of the TCLMF model with the results of the previously proposed methods using two databases and two approaches to test the model's performance. In the first approach, 12 drugs with enough known clinical drug response, considered in previous methods, are studied. For 7 drugs out of 12, the TCLMF can significantly distinguish between patients that are resistance to these drugs and the patients that are sensitive to them. These approaches are converted to classification models using a threshold in the second approach, and the results are compared. The results demonstrate that the TCLMF method provides accurate predictions across the results of the other algorithms. Finally, we accurately classify tumor tissue type using the latent vectors obtained from TCLMF's logistic matrix factorization process. These findings demonstrate that the TCLMF approach produces effective latent vectors for tumor samples. The source code of the TCLMF method is available in https://github.com/emdadi/TCLMF.

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

BACKGROUND: Predicting 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. RESULTS: This 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. CONCLUSIONS: We 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 .

DSPLMF: A Method for Cancer Drug Sensitivity Prediction Using a Novel Regularization Approach in Logistic Matrix Factorization.

The ability to predict the drug response for cancer disease based on genomics information is an essential problem in modern oncology, leading to personalized treatment. By predicting accurate anticancer responses, oncologists achieve a complete understanding of the effective treatment for each patient. In this paper, we present DSPLMF (Drug Sensitivity Prediction using Logistic Matrix Factorization) approach based on Recommender Systems. DSPLMF focuses on discovering effective features of cell lines and drugs for computing the probability of the cell lines are sensitive to drugs by logistic matrix factorization approach. Since similar cell lines and similar drugs may have similar drug responses and incorporating similarities between cell lines and drugs can potentially improve the drug response prediction, gene expression profile, copy number alteration, and single-nucleotide mutation information are used for cell line similarity and chemical structures of drugs are used for drug similarity. Evaluation of the proposed method on CCLE and GDSC datasets and comparison with some of the state-of-the-art methods indicates that the result of DSPLMF is significantly more accurate and more efficient than these methods. To demonstrate the ability of the proposed method, the obtained latent vectors are used to identify subtypes of cancer of the cell line and the predicted IC50 values are used to depict drug-pathway associations. The source code of DSPLMF method is available in https://github.com/emdadi/DSPLMF.

CAMND: Comparative analysis of metabolic network decomposition based on previous and two new criteria, a web based application.

Metabolic networks can model the behavior of metabolism in the cell. Since analyzing the whole metabolic networks is not easy, network modulation is an important issue to be investigated. Decomposing metabolic networks is a strategy to obtain better insight into metabolic functions. Additionally, decomposing these networks facilitates using computational methods, which are very slow when applied to the original genome-scale network. Several methods have been proposed for decomposing of the metabolic network. Therefore, it is necessary to evaluate these methods by suitable criteria. In this study, we introduce a web server package for decomposing of metabolic networks with 10 different methods, 9 datasets and the ability of computing 12 criteria, to evaluate and compare the results of different methods using ten previously defined and two new criteria which are based on Chebi ontology and Co-expression_of_Enzymes information. This package visualizes the obtained modules via "gephi" software. The ability of this package is that the user can examine whether two metabolites or reactions are in the same module or not. The functionality of the package can be easily extended to include new datasets and criteria. It also has the ability to compare the results of novel methods with the results of previously developed methods. The package is implemented in python and is available at http://eslahchilab.ir/softwares/dmn.

A novel algorithm for parameter estimation of Hidden Markov Model inspired by Ant Colony Optimization.

HMM is a powerful method to model data in various fields. Estimation of Hidden Markov Model parameters is an NP-Hard problem. We propose a heuristic algorithm called "AntMarkov" to improve the efficiency of estimating HMM parameters. We compared our method with four algorithms. The comparison was conducted on 5 different simulated datasets with different features. For further evaluation, we analyzed the performance of algorithms on the prediction of protein secondary structures problem. The results demonstrate that our algorithm obtains better results with respect to the results of the other algorithms in terms of time efficiency and the amount of similarity of estimated parameters to the original parameters and log-likelihood. The source code of our algorithm is available in https://github.com/emdadi/HMMPE.