BootCellNet, a resampling-based procedure, promotes unsupervised identification of cell populations via robust inference of gene regulatory networks DOI Creative Commons
Yutaro Kumagai

PLoS Computational Biology, Journal Year: 2024, Volume and Issue: 20(9), P. e1012480 - e1012480

Published: Sept. 30, 2024

Recent advances in measurement technologies, particularly single-cell RNA sequencing (scRNA-seq), have revolutionized our ability to acquire large amounts of omics-level data on cellular states. As techniques evolve, there has been an increasing need for analysis methodologies, especially those focused cell-type identification and inference gene regulatory networks (GRNs). We developed a new method named BootCellNet, which employs smoothing resampling infer GRNs. Using the inferred GRNs, BootCellNet further infers minimum dominating set (MDS), genes that determines dynamics entire network. demonstrated robustly GRNs their MDSs from scRNA-seq facilitates unsupervised cell clusters using datasets peripheral blood mononuclear cells hematopoiesis. It also identified COVID-19 patient-specific potential transcription factors. not only identifies types explainable way but provides insights into characteristics through MDS.

Language: Английский

Emerging methods for genome-scale metabolic modeling of microbial communities DOI Creative Commons
Chaimaa Tarzi, Guido Zampieri, Neil T. Sullivan

et al.

Trends in Endocrinology and Metabolism, Journal Year: 2024, Volume and Issue: 35(6), P. 533 - 548

Published: April 3, 2024

Genome-scale metabolic models (GEMs) are consolidating as platforms for studying mixed microbial populations, by combining biological data and knowledge with mathematical rigor. However, deploying these to answer research questions can be challenging due the increasing number of available computational tools, lack universal standards, their inherent limitations. Here, we present a comprehensive overview foundational concepts building evaluating genome-scale communities. We then compare tools in terms requirements, capabilities, applications. Next, highlight current pitfalls open challenges consider when adopting existing developing new ones. Our compendium relevant expanding community modelers, both at entry experienced levels.

Language: Английский

Citations

11
A mini-review on perturbation modelling across single-cell omic modalities DOI Creative Commons
George Gavriilidis, Vasileios Vasileiou, Aspasia Orfanou

et al.

Computational and Structural Biotechnology Journal, Journal Year: 2024, Volume and Issue: 23, P. 1886 - 1896

Published: April 25, 2024

Language: Английский

Citations

10
Cross-attention enables deep learning on limited omics-imaging-clinical data of 130 lung cancer patients DOI Creative Commons
Suraj Verma, Giuseppe Magazzù,

Noushin Eftekhari

et al.

Cell Reports Methods, Journal Year: 2024, Volume and Issue: 4(7), P. 100817 - 100817

Published: July 1, 2024

Deep-learning tools that extract prognostic factors derived from multi-omics data have recently contributed to individualized predictions of survival outcomes. However, the limited size integrated omics-imaging-clinical datasets poses challenges. Here, we propose two biologically interpretable and robust deep-learning architectures for prediction non-small cell lung cancer (NSCLC) patients, learning simultaneously computed tomography (CT) scan images, gene expression data, clinical information. The proposed models integrate patient-specific clinical, transcriptomic, imaging incorporate Kyoto Encyclopedia Genes Genomes (KEGG) Reactome pathway information, adding biological knowledge within process biomarkers molecular pathways. While both accurately stratify patients in high- low-risk groups when trained on a dataset only 130 introducing cross-attention mechanism sparse autoencoder significantly improves performance, highlighting tumor regions NSCLC-related genes as potential thus offering significant methodological advancement small imaging-omics-clinical samples.

Language: Английский

Citations

2
Enhancing deep learning for demand forecasting to address large data gaps DOI Creative Commons
Chirine Riachy, Mengda He, Sina Joneidy

et al.

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: unknown, P. 126200 - 126200

Published: Dec. 1, 2024

Language: Английский

Citations

1
An Exploration on Explainable AI with Background and Motivation for XAI DOI

B. P. Sheela,

H Girisha

Algorithms for intelligent systems, Journal Year: 2024, Volume and Issue: unknown, P. 481 - 489

Published: Jan. 1, 2024

Language: Английский

Citations

0
BootCellNet, a resampling-based procedure, promotes unsupervised identification of cell populations via robust inference of gene regulatory networks DOI Creative Commons
Yutaro Kumagai

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Feb. 8, 2024

Abstract Recent advances in measurement technologies, particularly single-cell RNA sequencing (scRNA-seq), have revolutionized our ability to acquire large amounts of omics-level data on cellular states. As techniques evolve, there has been an increasing need for analysis methodologies, especially those focused cell-type identification and inference gene regulatory networks (GRNs). We developed a new method named BootCellNet, which employs smoothing resampling infer GRNs. Using the inferred GRNs, BootCellNet further infers minimum dominating set (MDS), genes that determines dynamics entire network. demonstrated robustly GRNs their MDSs from scRNA-seq facilitates unsupervised cell clusters using datasets peripheral blood mononuclear cells hematopoiesis. It also identified COVID-19 patient-specific potential transcription factors. not only identifies types explainable way but provides insights into characteristics through MDS. Author Summary Single-cell omics such as RNA-seq are instrumental identifying novel subsets involved various biological processes diseases. These however, require development analysis, areas interactions between genes. The problem essentially involves clustering, necessitates balance distinguishing different states grouping similar ones together. Current clustering methods still suffer uncertainty determining appropriate number explaining why some clustered together others separated. genes, network (GRN), remains challenging due noisy nature scRNA-seq. utilizes cluster identify types. addresses challenges GRN simultaneously will facilitate generation working hypotheses amount data.

Language: Английский

Citations

0
BootCellNet, a resampling-based procedure, promotes unsupervised identification of cell populations via robust inference of gene regulatory networks DOI Creative Commons
Yutaro Kumagai

PLoS Computational Biology, Journal Year: 2024, Volume and Issue: 20(9), P. e1012480 - e1012480

Published: Sept. 30, 2024

Recent advances in measurement technologies, particularly single-cell RNA sequencing (scRNA-seq), have revolutionized our ability to acquire large amounts of omics-level data on cellular states. As techniques evolve, there has been an increasing need for analysis methodologies, especially those focused cell-type identification and inference gene regulatory networks (GRNs). We developed a new method named BootCellNet, which employs smoothing resampling infer GRNs. Using the inferred GRNs, BootCellNet further infers minimum dominating set (MDS), genes that determines dynamics entire network. demonstrated robustly GRNs their MDSs from scRNA-seq facilitates unsupervised cell clusters using datasets peripheral blood mononuclear cells hematopoiesis. It also identified COVID-19 patient-specific potential transcription factors. not only identifies types explainable way but provides insights into characteristics through MDS.

Language: Английский

Citations

0