Item

Continual learning approaches for single cell RNA sequencing data

Saygili,Görkem
; 
Özgöde Yigin,Büşra
Abstract
Single-cell RNA sequencing data is among the most interesting and impactful data of today and the sizes of the available datasets are increasing drastically. There is a substantial need for learning from large datasets, causing nontrivial challenges, especially in hardware. Loading even a single dataset into the memory of an ordinary, off-the-shelf computer can be infeasible, and using computing servers might not always be an option. This paper presents continual learning as a solution to such hardware bottlenecks. The findings of cell-type classification demonstrate that XGBoost and Catboost algorithms, when implemented in a continual learning framework, exhibit superior performance compared to the best-performing static classifier. We achieved up to 10% higher median F1 scores than the state-of-the-art on the most challenging datasets. On the other hand, these algorithms can suffer from variations in data characteristics across diverse datasets, pointing out indications of the catastrophic forgetting problem.
Description
Publisher Copyright: © 2023, Springer Nature Limited.
Date
2023-09-15
Journal Title
Journal ISSN
Volume Title
Publisher
Collections
Tilburg University Research Output Collection
Load more
Show all metadata
Research Projects
Organizational Units
Journal Issue
Keywords
Single-cell RNA sequencing data
Citation
Saygili, G & Özgöde Yigin, B 2023, 'Continual learning approaches for single cell RNA sequencing data', Scientific Reports, vol. 13, 15286. https://doi.org/10.1038/s41598-023-42482-7
URI
https://hdl.handle.net/20.500.14602/80297
Embedded videos