Back

Integrating multiple single-cell multi-omics samples with Smmit

Wan, C.; Ji, Z.

2023-04-06 bioinformatics
10.1101/2023.04.06.535857 bioRxiv
Show abstract

Multi-sample single-cell multi-omics datasets, which simultaneously measure multiple data modalities in the same cells across multiple samples, facilitate the study of gene expression, gene regulatory activities, and protein abundances on a population scale. We developed Smmit, a computational method for integrating data both across samples and modalities. Compared to existing methods, Smmit more effectively removes batch effects while preserving relevant biological information, resulting in superior integration outcomes. Additionally, Smmit is more computationally efficient and builds upon existing computational pipelines, requiring minimal effort for implementation. Smmit is an R software package that is freely available on Github: https://github.com/zji90/Smmit.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.