EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

De novo transformer modeling improves recovery of genetic cell types from sparse single-cell RNA sequencing

Jack M. Craig, M. Erfan Mowlaei, Sayaka Miura, Xinghua Shi, Sudhir Kumar

Frontiers in Bioinformatics · 19.11.2026 · 6

DOI: 10.3389/fbinf.2026.1962436 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Bioinformatics, online erschienen am 19.11.2026. Verfasst von Jack M. Craig und 4 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Single-cell RNA sequencing (scRNA-seq) simultaneously provides gene-expression profiles and genetic variants from individual cells, creating an opportunity to relate cellular phenotypes to their somatic evolutionary histories. However, delineating genetic types (GTs) from scRNA-seq remains difficult because most bases remain undetected in each cellular genome and are accompanied by false-positive and false-negative base calls.

Methods

We evaluated some existing phylogenetic and imputation methods for GT inference using one simulated and two empirical tumor datasets. We found that the extreme sparsity of cell-variant (CV) alignments produced by scRNA-seq data prevented reliable GT recovery, particularly when multiple GTs were present. This led us to explore a transformer-based genotype imputation system (STICI), which has been shown to reduce sparsity in germline genomes. However, STICI was trained on germline sequence variation in the human population, making it inapplicable for imputing idiosyncratic somatic variation in tumor genomes. We tested the hypothesis that a STICI model trained on observed bases in a given CV alignment can predict missing bases in that dataset. Results and discussion We found that sample-specific STICI (ssSTICI) models predicted many missing bases with high imputation probabilities, and the resulting CV alignments placed the constituent cells of each GT closer together in the inferred cellular phylogenies. Therefore, sample-specific deep learning models show strong potential to reduce CV alignment sparsity, paving the way for integrative studies of sequence and expression evolution using scRNA-seq and similar technologies.

Zitieren

APA

Craig, J. M., Mowlaei, M. E., Miura, S., Shi, X., & Kumar, S. (2026). De novo transformer modeling improves recovery of genetic cell types from sparse single-cell RNA sequencing. Frontiers in Bioinformatics, 6. https://doi.org/10.3389/fbinf.2026.1962436

Vancouver

Craig JM, Mowlaei ME, Miura S, Shi X, Kumar S. De novo transformer modeling improves recovery of genetic cell types from sparse single-cell RNA sequencing. Frontiers in Bioinformatics. 2026;6. doi:10.3389/fbinf.2026.1962436

BibTeX
@article{Craig2026,
  author = {Craig, Jack M. and Mowlaei, M. Erfan and Miura, Sayaka and Shi, Xinghua and Kumar, Sudhir},
  title = {De novo transformer modeling improves recovery of genetic cell types from sparse single-cell RNA sequencing},
  journal = {Frontiers in Bioinformatics},
  year = {2026},
  volume = {6},
  doi = {10.3389/fbinf.2026.1962436}
}
Kostenlos starten →