Classification of single cell types during leukemia therapy using artificial neural networks

We trained artificial neural network (ANN) models to classify peripheral blood mononuclear cells (PBMC) in chronic lymphoid leukemia (CLL) patients. The classification task was to determine differences in gene expression profiles in PBMC pre-treatment (with ibrutinib) and on days 30, 120, 150, and 2...

Full description

Bibliographic Details
Main Authors: LYU, Minjie, Radenkovic, Milena, KESKIN, DerinB., Brusic, Vladimir
Format: Conference or Workshop Item
Language:English
Published: 2021
Subjects:
Online Access:https://eprints.nottingham.ac.uk/64683/
_version_ 1848800153809453056
author LYU, Minjie
Radenkovic, Milena
KESKIN, DerinB.
Brusic, Vladimir
author_facet LYU, Minjie
Radenkovic, Milena
KESKIN, DerinB.
Brusic, Vladimir
author_sort LYU, Minjie
building Nottingham Research Data Repository
collection Online Access
description We trained artificial neural network (ANN) models to classify peripheral blood mononuclear cells (PBMC) in chronic lymphoid leukemia (CLL) patients. The classification task was to determine differences in gene expression profiles in PBMC pre-treatment (with ibrutinib) and on days 30, 120, 150, and 280 after the start of treatment. Twelve datasets represented clinical samples containing a total 48,016 single cell profiles were used to train and test ANN models to classify the progress of therapy by gene expression changes. The accuracy of ANN classification was >92% in internal cross-validation. External cross-validation, using independent data sets for training and testing, showed the accuracy of classification of post-treatment PBMCs to more than 80%. To the best of our knowledge, this is the first study that has demonstrated the potential of ANNs with 10x single cell gene expression data for detecting the changes during treatment of CLL.
first_indexed 2025-11-14T20:47:02Z
format Conference or Workshop Item
id nottingham-64683
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:47:02Z
publishDate 2021
recordtype eprints
repository_type Digital Repository
spelling nottingham-646832021-03-10T06:23:56Z https://eprints.nottingham.ac.uk/64683/ Classification of single cell types during leukemia therapy using artificial neural networks LYU, Minjie Radenkovic, Milena KESKIN, DerinB. Brusic, Vladimir We trained artificial neural network (ANN) models to classify peripheral blood mononuclear cells (PBMC) in chronic lymphoid leukemia (CLL) patients. The classification task was to determine differences in gene expression profiles in PBMC pre-treatment (with ibrutinib) and on days 30, 120, 150, and 280 after the start of treatment. Twelve datasets represented clinical samples containing a total 48,016 single cell profiles were used to train and test ANN models to classify the progress of therapy by gene expression changes. The accuracy of ANN classification was >92% in internal cross-validation. External cross-validation, using independent data sets for training and testing, showed the accuracy of classification of post-treatment PBMCs to more than 80%. To the best of our knowledge, this is the first study that has demonstrated the potential of ANNs with 10x single cell gene expression data for detecting the changes during treatment of CLL. 2021-01-13 Conference or Workshop Item PeerReviewed application/pdf en cc_by https://eprints.nottingham.ac.uk/64683/1/Minjie_Classification%20of%20Single%20Cell%20Types%20During%20Leukemia%20Therapy%20using%20Artificial%20Neural%20Networks.pdf LYU, Minjie, Radenkovic, Milena, KESKIN, DerinB. and Brusic, Vladimir (2021) Classification of single cell types during leukemia therapy using artificial neural networks. In: 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 16-19 Dec. 2020, Seoul, Korea (South). ANN PBMC CLL ibrutinib scRNAseq Machine Learning http://dx.doi.org/10.1109/BIBM49941.2020.9313319 10.1109/BIBM49941.2020.9313319 10.1109/BIBM49941.2020.9313319 10.1109/BIBM49941.2020.9313319
spellingShingle ANN
PBMC
CLL
ibrutinib
scRNAseq
Machine Learning
LYU, Minjie
Radenkovic, Milena
KESKIN, DerinB.
Brusic, Vladimir
Classification of single cell types during leukemia therapy using artificial neural networks
title Classification of single cell types during leukemia therapy using artificial neural networks
title_full Classification of single cell types during leukemia therapy using artificial neural networks
title_fullStr Classification of single cell types during leukemia therapy using artificial neural networks
title_full_unstemmed Classification of single cell types during leukemia therapy using artificial neural networks
title_short Classification of single cell types during leukemia therapy using artificial neural networks
title_sort classification of single cell types during leukemia therapy using artificial neural networks
topic ANN
PBMC
CLL
ibrutinib
scRNAseq
Machine Learning
url https://eprints.nottingham.ac.uk/64683/
https://eprints.nottingham.ac.uk/64683/
https://eprints.nottingham.ac.uk/64683/