LoRA-TV: read depth profile-based clustering of tumor cells in single-cell sequencing.
Brief Bioinform
; 25(4)2024 May 23.
Article
em En
| MEDLINE
| ID: mdl-38877886
ABSTRACT
Single-cell sequencing has revolutionized our ability to dissect the heterogeneity within tumor populations. In this study, we present LoRA-TV (Low Rank Approximation with Total Variation), a novel method for clustering tumor cells based on the read depth profiles derived from single-cell sequencing data. Traditional analysis pipelines process read depth profiles of each cell individually. By aggregating shared genomic signatures distributed among individual cells using low-rank optimization and robust smoothing, the proposed method enhances clustering performance. Results from analyses of both simulated and real data demonstrate its effectiveness compared with state-of-the-art alternatives, as supported by improvements in the adjusted Rand index and computational efficiency.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Análise de Célula Única
/
Neoplasias
Limite:
Humans
Idioma:
En
Ano de publicação:
2024
Tipo de documento:
Article