Identifying tumor cells at the single-cell level using machine learning

被引：33

作者：

Dohmen, Jan ^{[1
]}

Baranovskii, Artem ^{[2
,3
]}

Ronen, Jonathan ^{[1
]}

Uyar, Bora ^{[1
]}

Franke, Vedran ^{[1
]}

Akalin, Altuna ^{[1
]}

机构：

[1] Max Delbruck Ctr Mol Med Helmholtz Assoc MDC, Berlin Inst Med Syst Biol, Bioinformat & Omics Data Sci Platform, Hannoversche Str 28, D-10115 Berlin, Germany

[2] Berlin Inst Med Syst Biol, Noncoding RNAs & Mech Cytoplasm Gene Regulat Lab, Hannoversche Str 28, D-10115 Berlin, Germany

[3] Free Univ Berlin, Kaiserswerther Str 16-18, D-14195 Berlin, Germany

来源：

GENOME BIOLOGY | 2022年 / 23卷 / 01期

关键词：

Single-cell genomics; Machine learning; Cell type classification; Cancer; GENE-EXPRESSION; RNA-SEQ;

D O I：

10.1186/s13059-022-02683-1

中图分类号：

Q81 [生物工程学（生物技术）]; Q93 [微生物学];

学科分类号：

071005 ; 0836 ; 090102 ; 100705 ;

摘要：

Tumors are complex tissues of cancerous cells surrounded by a heterogeneous cellular microenvironment with which they interact. Single-cell sequencing enables molecular characterization of single cells within the tumor. However, cell annotation-the assignment of cell type or cell state to each sequenced cell-is a challenge, especially identifying tumor cells within single-cell or spatial sequencing experiments. Here, we propose ikarus, a machine learning pipeline aimed at distinguishing tumor cells from normal cells at the single-cell level. We test ikarus on multiple single-cell datasets, showing that it achieves high sensitivity and specificity in multiple experimental contexts.

引用

页数：23

共 66 条

[1] A comparison of automatic cell identification methods for single-cell RNA sequencing data [J].