Deep feature selection for Identification of Essential Proteins of Learning and Memory in Mouse Model of Down Syndrome

Abstract

Down syndrome is a chromosomal abnormality related to intellectual disabilities that affects 0.1% of live births worldwide. It occurs when an individual has a full or partial extra copy of chromosome 21. This chromosome trisomy results in the overexpression of genes that is believed to be sufficient to interfere normal pathways and normal responses to stimulation, causing learning and memory deficiency. Therefore, by studying these proteins and the disturbance in pathways that are involved in learning and memory, we can consider drugs that would correct the observed perturbations, and therefore assist in enhancing the memory and learning. Here, from genes based on an earlier study that identified 77 proteins differentially expressed in normal and trisomic wild mice exposed to context fear conditioning (CFC), we provide a quantitative protein selection based on different feature selection techniques to select the most important proteins related to learning and memory. These techniques include Fisher score, Chi score, and correlation-based subset. In addition, a deep feature selection is utilized to extract high order proteins using deep neural networks. Three main experiments are carried out:studying the control mice's response, studying the trisomy mice's response, and studying the control-trisomy mice's response. In each experiment, support vector machine classifier is used to assess these selected proteins ability to distinguish between learned and not-learned mice to the fear conditioning event. By applying the deep feature selection, fifteen proteins were selected in control mice, nine in trisomy mice, and seven in control-trisomy mice achieving distinguishing accuracies of 93%, 99%, 84% respectively compared to 74%, 78%, and 71% average accuracies of other selection methods. Some of these proteins have important biological function in learning such as CaNA, NUMb, and NOS. 2 deficiency [1]. There are around 3,000 to 5,000 children born annually with down 3 syndrome [2]. DS is usually related to intellectual disability, and physical growth 4 delays [3]. It is a chromosomal anomaly caused by the presence of a third copy, full or 5 partial, of chromosome 21 (Hsa21). This can be due to an error in cell division, 6 non-disjunction, in which a pair of 21st chromosomes fail to separate, resulting in an 7 additional chromosome called trisomy 21 [2]. This Hsa21 encodes more than 500 gene 8 models [4], where an unknown subset of these genes contributes in the learning 9 PLOS1/14 deficit [5]. Overexpression of these genes may affect different biological processes and 10 pathways, including brain development and function [6]. 11Along the past decades, the interest in the identification of DS learning deficits has 12 been raised [7][8][9][10][11][12][13]. However, because of the lack of enough information about Hsa21 13 encoded genes, where functional information is available for less their half [5], it is 14 logical to look for a disturbance in pathways that are critical to learning and memory, 15 and then to consider dr...

Verification of foetal Down syndrome biomarker proteins in maternal plasma and applications in prenatal screening for Down syndrome

“…These data will allow for the early diagnosis of DS. Absolutely, there are many popular molecular techniques that can be used to detect prenatal diagnostic markers such as Fisher score, Chi score, and correlation-based subset [12]. We will consider using these molecular techniques for further research.…”

“…At present, many studies have studied the relationship between proteome and DS by various molecular techniques. Abdeldayem et al [12]. used Fisher score, Chi score, and correlation-based subset to select the most important proteins related to learning and memory from mouse model of DS.…”

Discovering critical proteins in the learning process in a Down Syndrome model of mouse through machine learning

“…Sara et al 27 proposed a quantitative approach to investigate protein expression in order to identify important differences in protein levels in mice exposed to CFC by using machine learning feature selection algorithms. Four different selection models are used such as Fisher score, Chi score, correlation-based approach and Deep feature selection (D-DFS) proposed by Yifeng et al 28 .…”

“…An increment of accuracy with their reduced protein subset (98% by applying Random Forest) was shown compared to the previous models built from the original protein data-sets.On the other hand, Kulan et al 24 argues that Naïve Bayes feature selection method could provide a better protein subset rather than AdaBoost used by B.Feng et al Same as the previous work, they reduced the dataset from 77 proteins to 30 and applied Random Forest, Deep Neural Network, and SVM for classification. They compared their results with B. Feng et al, and showed that their method gives a higher accuracy, by reaching 99% accuracy using DNN.Sara et al 27 proposed a quantitative approach to investigate protein expression in order to identify important differences in protein levels in mice exposed to CFC by using machine learning feature selection algorithms. Four different selection models are used such as Fisher score, Chi score, correlation-based approach and Deep feature selection (D-DFS) proposed by Yifeng et al 28 .…”