Scholarlink

A differentially expressed gene shows significant difference in expression levels between healthy and disease states. Thus, DEGs are a great way of identifying root cause of a disease in particular. In this paper, a novel neural network architecture is proposed to identify the differentially expressed genes (DEGs) from next generation sequencing (NGS) data. The neural network architecture is a combined network consisting convolutional layers and Long Short-Term Memory (LSTM) layers. The proposed network has been trained on NGS RNA sequence dataset. The described deep learning model takes as input RNA sequence datasets and predicts log fold change score for each gene present in the dataset. Based on the output a set of DEG is identified from the input data. The experimental results prove that the superiority of the proposed neural network architecture.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Identification of Differentially Expressed Gene from NGS RNA Seq Data Using a Neural Network Architecture

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Manan Kumar Gupta,
  • Soumen Kumar Pati

摘要

A differentially expressed gene shows significant difference in expression levels between healthy and disease states. Thus, DEGs are a great way of identifying root cause of a disease in particular. In this paper, a novel neural network architecture is proposed to identify the differentially expressed genes (DEGs) from next generation sequencing (NGS) data. The neural network architecture is a combined network consisting convolutional layers and Long Short-Term Memory (LSTM) layers. The proposed network has been trained on NGS RNA sequence dataset. The described deep learning model takes as input RNA sequence datasets and predicts log fold change score for each gene present in the dataset. Based on the output a set of DEG is identified from the input data. The experimental results prove that the superiority of the proposed neural network architecture.