Open AccessDeep Learning model to Automate the process of mapping Cancer Cells to Cell Lines & Cancer Types from Single Cell RNA-Seq Data
Author(s) -
Vatsal Patel
Publication year - 2021
Publication title -
international journal of scientific research in computer science, engineering and information technology
Language(s) - English
Resource type - Journals
ISSN - 2456-3307
DOI - 10.32628/cseit21741
Subject(s) - computer science , cancer , cancer cell , rna seq , process (computing) , cancer cell lines , computational biology , artificial neural network , deep learning , cell culture , artificial intelligence , biology , genetics , gene expression , gene , transcriptome , operating system
Single Cell RNA Sequencing has given us a broad domain to study heterogeneity & expression profiles of cells. Downstream analysis of such data has led us to important observation and classification of cell types. However, these approaches demand great exertion and effort added that it seems the only way to proceed ahead for the first time. Results of such verified analysis have led us to create labels from our dataset. We can use the same labeled data as an input to a neural network and this way we would be able to automate the tedious & time-consuming process of downstream analysis. In this paper, we have automated the process of mapping cancer cells to cancer cell lines & cancer types. For the same, we have used pan-cancer single cell sequencing data of 53513 cells from 198 cell lines reflecting 22 cancer types.