期刊
GENOME BIOLOGY
卷 22, 期 1, 页码 -出版社
BMC
DOI: 10.1186/s13059-021-02452-6
关键词
Single-cell genomics; Data zoo; Model zoo
资金
- German Research Foundation (DFG) fellowship through the Graduate School of Quantitative Biosciences Munich (QBM) [GSC 1006]
- Joachim Herz Foundation
- BMBF [01IS18036B, 01IS18053A, 01ZX1711A]
- Chan Zuckerberg Initiative [2019-207271, 2019-002438]
- Helmholtz Association's Initiative and Networking Fund through Helmholtz AI [ZT-I-PF-5-01]
- Bavarian Ministry of Science and the Arts of the Bavarian Research Association ForInter
- Chan Zuckerberg Initiative DAF, an advised fund of Silicon Valley Community Foundation [2021-230826]
- Projekt DEAL
sfaira is a single-cell data zoo paired with executable pre-trained models for public datasets, addressing issues with independent analysis and contextualization in single-cell RNA-seq datasets. We propose an adaptation of cross-entropy loss for cell type classification tailored to datasets annotated at different levels of coarseness.
Single-cell RNA-seq datasets are often first analyzed independently without harnessing model fits from previous studies, and are then contextualized with public data sets, requiring time-consuming data wrangling. We address these issues with sfaira, a single-cell data zoo for public data sets paired with a model zoo for executable pre-trained models. The data zoo is designed to facilitate contribution of data sets using ontologies for metadata. We propose an adaption of cross-entropy loss for cell type classification tailored to datasets annotated at different levels of coarseness. We demonstrate the utility of sfaira by training models across anatomic data partitions on 8 million cells.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据