Dataset Information

Identifying Heat Shock Protein Families from Imbalanced Data by Using Combined Features.

ABSTRACT: Heat shock proteins (HSPs) are ubiquitous in living organisms. HSPs are an essential component for cell growth and survival; the main function of HSPs is controlling the folding and unfolding process of proteins. According to molecular function and mass, HSPs are categorized into six different families: HSP20 (small HSPS), HSP40 (J-proteins), HSP60, HSP70, HSP90, and HSP100. In this paper, improved methods for HSP prediction are proposed-the split amino acid composition (SAAC), the dipeptide composition (DC), the conjoint triad feature (CTF), and the pseudoaverage chemical shift (PseACS) were selected to predict the HSPs with a support vector machine (SVM). In order to overcome the imbalance data classification problems, the syntactic minority oversampling technique (SMOTE) was used to balance the dataset. The overall accuracy was 99.72% with a balanced dataset in the jackknife test by using the optimized combination feature SAAC+DC+CTF+PseACS, which was 4.81% higher than the imbalanced dataset with the same combination feature. The Sn, Sp, Acc, and MCC of HSP families in our predictive model were higher than those in existing methods. This improved method may be helpful for protein function prediction.

SUBMITTER: Jing XY

PROVIDER: S-EPMC7530508 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identifying Heat Shock Protein Families from Imbalanced Data by Using Combined Features.

Jing Xiao-Yang XY Li Feng-Min FM

Computational and mathematical methods in medicine 20200923

Heat shock proteins (HSPs) are ubiquitous in living organisms. HSPs are an essential component for cell growth and survival; the main function of HSPs is controlling the folding and unfolding process of proteins. According to molecular function and mass, HSPs are categorized into six different families: HSP20 (small HSPS), HSP40 (J-proteins), HSP60, HSP70, HSP90, and HSP100. In this paper, improved methods for HSP prediction are proposed-the split amino acid composition (SAAC), the dipeptide com ...[more]

PMID: 33029195

Similar Datasets

Project description:In order to provide the most effective therapy for cancer, it is important to be able to diagnose whether a patient's cancer will respond to a proposed treatment. Methylation profiling could contain information from which such predictions could be made. Currently, hypothesis testing is used to determine whether possible biomarkers for cancer progression produce statistically significant results. However, this approach requires the identification of individual genes, or sets of genes, as candidate hypotheses, and with the increasing size of modern microarrays, this task is becoming progressively harder. Exhaustive testing of small sets of genes is computationally infeasible, and so hypothesis generation depends either on the use of established biological knowledge or on heuristic methods. As an alternative machine learning, methods can be used to identify groups of genes that are acting together within sets of cancer data and associate their behaviors with cancer progression. These methods have the advantage of being multivariate and unbiased but unfortunately also rapidly become computationally infeasible as the number of gene probes and datasets increases. To address this problem, we have investigated a way of utilizing prior knowledge to segment microarray datasets in such a way that machine learning can be used to identify candidate sets of genes for hypothesis testing. A methylation dataset is divided into subsets, where each subset contains only the probes that relate to a known gene pathway. Each of these pathway subsets is used independently for classification. The classification method is AdaBoost with decision trees as weak classifiers. Since each pathway subset contains a relatively small number of gene probes, it is possible to train and test its classification accuracy quickly and determine whether it has valuable diagnostic information. Finally, genes from successful pathway subsets can be combined to create a classifier of high accuracy.

Project description:A gene regulatory module (GRM) is a set of genes that is regulated by the same set of transcription factors (TFs). By organizing the genome into GRMs, a living cell can coordinate the activities of many genes in response to various internal and external stimuli. Therefore, identifying GRMs is helpful for understanding gene regulation.Integrating transcription factor binding site (TFBS), mutant, ChIP-chip, and heat shock time series gene expression data, we develop a method, called Heat-Inducible Module Identification Algorithm (HIMIA), for reconstructing GRMs of yeast heat shock response. Unlike previous module inference tools which are static statistics-based methods, HIMIA is a dynamic system model-based method that utilizes the dynamic nature of time series gene expression data. HIMIA identifies 29 GRMs, which in total contain 182 heat-inducible genes regulated by 12 heat-responsive TFs. Using various types of published data, we validate the biological relevance of the identified GRMs. Our analysis suggests that different combinations of a fairly small number of heat-responsive TFs regulate a large number of genes involved in heat shock response and that there may exist crosstalk between heat shock response and other cellular processes. Using HIMIA, we identify 68 uncharacterized genes that may be involved in heat shock response and we also identify their plausible heat-responsive regulators. Furthermore, HIMIA is capable of assigning the regulatory roles of the TFs that regulate GRMs and Cst6, Hsf1, Msn2, Msn4, and Yap1 are found to be activators of several GRMs. In addition, HIMIA refines two clusters of genes involved in heat shock response and provides a better understanding of how the complex expression program of heat shock response is regulated. Finally, we show that HIMIA outperforms four current module inference tools (GRAM, MOFA, ReMoDisvovery, and SAMBA), and we conduct two randomization tests to show that the output of HIMIA is statistically meaningful.HIMIA is effective for reconstructing GRMs of yeast heat shock response. Indeed, many of the reconstructed GRMs are in agreement with previous studies. Further, HIMIA predicts several interesting new modules and novel TF combinations. Our study shows that integrating multiple types of data is a powerful approach to studying complex biological systems.

Dataset Information

Identifying Heat Shock Protein Families from Imbalanced Data by Using Combined Features.

Publications

Identifying Heat Shock Protein Families from Imbalanced Data by Using Combined Features.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets