An open-source solution for advanced imaging flow cytometry data analysis using machine learning

详细信息    查看全文

• 作者：Holger Hennig^a ; ^b ; ^c ; Paul Rees^a ; ^c ; Thomas Blasi^d ; Lee Kamentsky^a ; ¹ ; Jane Hung^a ; David Dao^a ; Anne E. Carpenter^a ; Andrew Filby^e ; ^{Andrew.Filby@newcastle.ac.uk}
• 关键词：IFC ; imaging flow cytometry
• 刊名：Methods
• 出版年：2017
• 出版时间：1 January 2017
• 年：2017
• 卷：112
• 期：Complete
• 页码：201-210
• 全文大小：2090 K
• 卷排序：112

文摘

Imaging flow cytometry enables potentially powerful, multiplexed single-cell analysis. Data analysis techniques for imaging flow cytometry are largely manual and subjective. Our machine learning workflow identifies phenotypes in imaging flow cytometry. The workflow uses open-source software and does not require computational expertise.