An imputation method for single‐cell RNA sequencing data based on a parallel gated recurrent unit neural network

Shuang Xu, Xiangtao Li, Jingsong Li, Yu Jiang · 2026

Read An imputation method for single‐cell RNA sequencing data based on a parallel gated recurrent unit neural network by Shuang Xu, Xiangtao Li, Jingsong Li, Yu Jiang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13642110.txt.

Description

Shuang Xu and three colleagues present a neural network method, IPGRU, for filling in missing values in single-cell RNA sequencing data. Dropout events hide many true gene readings, which biases later analysis and weakens conclusions about cell identity.

The method recasts the filling task as many single-gene predictions handled by parallel gated recurrent units, a network type that learns patterns across genes. Tests showed accurate recovery of missing values and cleaner data for cell clustering and for tracing how cells change type over time. The authors offer the approach as a sturdy preprocessing step for single-cell studies and precision medicine.

Catalog record

CREATORShuang Xu, Xiangtao Li, Jingsong Li, Yu Jiang
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE34 KB
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13642110

Browse the full library · About the Tower of Babel