Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 May;107(5):333-343.
doi: 10.1002/cyto.a.24934. Epub 2025 Apr 17.

BL-FlowSOM: Consistent and Highly Accelerated FlowSOM Based on Parallelized Batch Learning

Fumitaka Otsuka  1   2 , Kenji Yamane  1 , Koji Futamura  2 , Junichiro Enoki  2 , Yuji Nishimaki  3 , Yoshiki Tanaka  3 , Akihide Higuchi  4 , Motohiro Furuki  1   2
Affiliations

BL-FlowSOM: Consistent and Highly Accelerated FlowSOM Based on Parallelized Batch Learning

Fumitaka Otsuka et al. Cytometry A. 2025 May.

Abstract

The recent increase in the dimensionality of cytometry data has led to the development of various computational analysis methods. FlowSOM is one of the best-performing clustering methods but has room for improvement in terms of the consistency and speed of the clustering process. Here, we introduce Batch Learning FlowSOM (BL-FlowSOM), which is a consistent and highly accelerated FlowSOM based on parallelized batch learning. The change of the learning algorithm from online learning to batch learning with principal component analysis initialization improves consistency and eliminates randomness in the clustering process. It also enables the parallelization of the learning process, leading to significant acceleration of the clustering process with clustering quality equivalent to that of FlowSOM. BL-FlowSOM is available on Sony's Spectral Flow Analysis (SFA)-Life sciences Cloud Platform (https://www.sonybiotechnology.com/us/instruments/sfa-cloud-platform/).

Keywords: batch learning; computational cytometry; high‐dimensional flow cytometry; parallelization; self‐organizing map; spectral flow cytometry; unsupervised clustering.

PubMed Disclaimer

Similar articles

See all similar articles

References

    1. S. C. DeRosa, L. A. Herzenberg, L. A. Herzenberg, and M. Roderer, “11‐Color, 13‐Parameter Flow Cytometry: Identification of Human Naive T Cells by Phenotype, Function, and T‐Cell Receptor Diversity,” Nature Medicine 7, no. 2 (2001): 245–248, https://doi.org/10.1038/84701.
    1. S. P. Perfetto, P. K. Chattopadhyay, and M. Roederer, “Seventeen‐Colour Flow Cytometry: Unravelling the Immune System,” Nature Reviews Immunology 4 (2004): 648–655.
    1. D. R. Bandura, V. I. Baranov, O. I. Ornatsky, et al., “Mass Cytometry: Technique for Real Time Single Cell Multitarget Immunoassay Based on Inductively Coupled Plasma Time‐Of‐Flight Mass Spectrometry,” Analytical Chemistry 81 (2009): 6813–6822.
    1. J. P. Nolan, “The Evolution of Spectral Flow Cytometry,” Cytometry, Part A 101, no. 10 (2022): 812–817.
    1. K. Futamura, M. Sekino, A. Hata, et al., “Novel Full‐Spectral Flow Cytometry With Multiple Spectrally‐Adjacent Fluorescent Proteins and Fluorochromes and Visualization of In Vivo Cellular Movement,” Cytometry, Part A 87, no. 9 (2015): 830–842.

LinkOut - more resources