Dataset Information

A Three-Stage Teacher, Student Neural Networks and Sequential Feed Forward Selection-Based Feature Selection Approach for the Classification of Autism Spectrum Disorder.

ABSTRACT: Autism disorder, generally known as Autism Spectrum Disorder (ASD) is a brain disorder characterized by lack of communication skills, social aloofness and repetitions in the actions in the patients, which is affecting millions of the people across the globe. Accurate identification of autistic patients is considered a challenging task in the domain of brain disorder science. To address this problem, we have proposed a three-stage feature selection approach for the classification of ASD on the preprocessed Autism Brain Imaging Data Exchange (ABIDE) rs-fMRI Dataset. In the first stage, a large neural network which we call a "Teacher " was trained on the correlation-based connectivity matrix to learn the latent representation of the input. In the second stage an autoencoder which we call a "Student" autoencoder was given the task to learn those trained "Teacher" embeddings using the connectivity matrix input. Lastly, an SFFS-based algorithm was employed to select the subset of most discriminating features between the autistic and healthy controls. On the combined site data across 17 sites, we achieved the maximum 10-fold accuracy of 82% and for the individual site-wise data, based on 5-fold accuracy, our results outperformed other state of the art methods in 13 out of the total 17 site-wise comparisons.

SUBMITTER: Khan NA

PROVIDER: S-EPMC7603385 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Three-Stage Teacher, Student Neural Networks and Sequential Feed Forward Selection-Based Feature Selection Approach for the Classification of Autism Spectrum Disorder.

Khan Naseer Ahmed NA Waheeb Samer Abdulateef SA Riaz Atif A Shang Xuequn X

Brain sciences 20201019 10

Autism disorder, generally known as Autism Spectrum Disorder (ASD) is a brain disorder characterized by lack of communication skills, social aloofness and repetitions in the actions in the patients, which is affecting millions of the people across the globe. Accurate identification of autistic patients is considered a challenging task in the domain of brain disorder science. To address this problem, we have proposed a three-stage feature selection approach for the classification of ASD on the pr ...[more]

PMID: 33086634

Similar Datasets

Project description:BackgroundAs one of the most common types of co-regulatory motifs, feed-forward loops (FFLs) control many cell functions and play an important role in human cancers. Therefore, it is crucial to reconstruct and analyze cancer-related FFLs that are controlled by transcription factor (TF) and microRNA (miRNA) simultaneously, in order to find out how miRNAs and TFs cooperate with each other in cancer cells and how they contribute to carcinogenesis. Current FFL studies rely on predicted regulation information and therefore suffer the false positive issue in prediction results. More critically, FFLs generated by existing approaches cannot represent the dynamic and conditional regulation relationship under different experimental conditions.Methodology/principal findingsIn this study, we proposed a novel filter-wrapper feature selection method to accurately identify co-regulatory mechanism by incorporating prior information from predicted regulatory interactions with parallel miRNA/mRNA expression datasets. By applying this method, we reconstructed 208 and 110 TF-miRNA co-regulatory FFLs from human pan-cancer and prostate datasets, respectively. Further analysis of these cancer-related FFLs showed that the top-ranking TF STAT3 and miRNA hsa-let-7e are key regulators implicated in human cancers, which have regulated targets significantly enriched in cellular process regulations and signaling pathways that are involved in carcinogenesis.Conclusions/significanceIn this study, we introduced an efficient computational approach to reconstruct co-regulatory FFLs by accurately identifying gene co-regulatory interactions. The strength of the proposed feature selection method lies in the fact it can precisely filter out false positives in predicted regulatory interactions by quantitatively modeling the complex co-regulation of target genes mediated by TFs and miRNAs simultaneously. Moreover, the proposed feature selection method can be generally applied to other gene regulation studies using parallel expression data with respect to different biological contexts.

Project description:BackgroundFeature selection is an approach to overcome the 'curse of dimensionality' in complex researches like disease classification using microarrays. Statistical methods are utilized more in this domain. Most of them do not fit for a wide range of datasets. The transform oriented signal processing domains are not probed much when other fields like image and video processing utilize them well. Wavelets, one of such techniques, have the potential to be utilized in feature selection method. The aim of this paper is to assess the capability of Haar wavelet power spectrum in the problem of clustering and gene selection based on expression data in the context of disease classification and to propose a method based on Haar wavelet power spectrum.ResultsHaar wavelet power spectra of genes were analysed and it was observed to be different in different diagnostic categories. This difference in trend and magnitude of the spectrum may be utilized in gene selection. Most of the genes selected by earlier complex methods were selected by the very simple present method. Each earlier works proved only few genes are quite enough to approach the classification problem 1. Hence the present method may be tried in conjunction with other classification methods. The technique was applied without removing the noise in data to validate the robustness of the method against the noise or outliers in the data. No special software or complex implementation is needed. The qualities of the genes selected by the present method were analysed through their gene expression data. Most of them were observed to be related to solve the classification issue since they were dominant in the diagnostic category of the dataset for which they were selected as features.ConclusionIn the present paper, the problem of feature selection of microarray gene expression data was considered. We analyzed the wavelet power spectrum of genes and proposed a clustering and feature selection method useful for classification based on Haar wavelet power spectrum. Application of this technique in this area is novel, simple, and faster than other methods, fit for a wide range of data types. The results are encouraging and throw light into the possibility of using this technique for problem domains like disease classification, gene network identification and personalized drug design.

Project description:BackgroundIn the typical setting of gene-selection problems from high-dimensional data, e.g., gene expression data from microarray or next-generation sequencing-based technologies, an enormous volume of high-throughput data is generated, and there is often a need for a simple, computationally-inexpensive, non-parametric screening procedure than can quickly and accurately find a low-dimensional variable subset that preserves biological information from the original very high-dimensional data (dimension p > 40,000). This is in contrast to the very sophisticated variable selection methods that are computationally expensive, need pre-processing routines, and often require calibration of priors.ResultsWe present a tree-based sequential CART (S-CART) approach to variable selection in the binary classification setting and compare it against the more sophisticated procedures using simulated and real biological data. In simulated data, we analyze S-CART performance versus (i) a random forest (RF), (ii) a fully-parametric Bayesian stochastic search variable selection (SSVS), and (iii) the moderated t-test statistic from the LIMMA package in R. The simulation study is based on a hierarchical Bayesian model, where dataset dimensionality, percentage of significant variables, and substructure via dependency vary. Selection efficacy is measured through false-discovery and missed-discovery rates. In all scenarios, the S-CART method is seen to consistently outperform SSVS and RF in both speed and detection accuracy. We demonstrate the utility of the S-CART technique both on simulated data and in a control-treatment mouse study. We show that the network analysis based on the S-CART-selected gene subset in essence recapitulates the biological findings of the study using only a fraction of the original set of genes considered in the study's analysis.ConclusionsThe relatively simple-minded gene selection algorithms like S-CART may often in practical circumstances be preferred over much more sophisticated ones. The advantage of the "greedy" selection methods utilized by S-CART and the likes is that they scale well with the problem size and require virtually no tuning or training while remaining efficient in extracting the relevant information from microarray-like datasets containing large number of redundant or irrelevant variables.AvailabilityThe MATLAB 7.4b code for the S-CART implementation is available for download from https://neyman.mcg.edu/posts/scart.zip.

Dataset Information

A Three-Stage Teacher, Student Neural Networks and Sequential Feed Forward Selection-Based Feature Selection Approach for the Classification of Autism Spectrum Disorder.

Publications

A Three-Stage Teacher, Student Neural Networks and Sequential Feed Forward Selection-Based Feature Selection Approach for the Classification of Autism Spectrum Disorder.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets