Affiliation:
1. BS Mathematics, St. Xavier's College, Mumbai, India
Abstract
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.
Reference18 articles.
1. Kinker, G.S., Greenwald, A.C., Tal, R. et al. Pan-cancer single-cell RNA-seq identifies recurring programs of cellular heterogeneity. Nat Genet 52, 1208–1218(2020).https://doi.org/10.1038/s41588-020-00726-6
2. Ghandi, M., Huang, F.W., Jané-Valbuena, J. et al. Next-generation characterization of the Cancer Cell Line Encyclopedia. Nature 569, 503–508 (2019). https://doi.org/10.1038/s41586-019-1186-315
3. Yu, C., Mannan, A., Yvone, G. et al. High-throughput identification of genotype-specific cancer vulnerabilities in mixtures of barcoded tumor cell lines. NatBiotechnol 34, 419–423 (2016) https://doi.org/10.1038/nbt.3460
4. Kang, H., Subramaniam, M., Targ, S. et al. Multiplexed droplet single-cell RNA-sequencing using natural genetic variation. Nat Biotechnol 36, 89–94 (2018). https://doi.org/10.1038/nbt.4042
5. Ainscough, B.J., Barnell, E.K., Ronning, P. et al. A deep learning approach to automate refinement of somatic variant calling from cancer sequencing data. Nat Genet 50, 1735–1743 (2018). https://doi.org/10.1038/s41588-018-0257-y