Detecting retinal neural and stromal cell classes and ganglion cell subtypes based on transcriptome data with deep transfer learning.
Bioinformatics
; 38(18): 4321-4329, 2022 09 15.
Article
em En
| MEDLINE
| ID: mdl-35876552
ABSTRACT
MOTIVATION To develop and assess the accuracy of deep learning models that identify different retinal cell types, as well as different retinal ganglion cell (RGC) subtypes, based on patterns of single-cell RNA sequencing (scRNA-seq) in multiple datasets. RESULTS:
Deep domain adaptation models were developed and tested using three different datasets. The first dataset included 44â808 single retinal cells from mice (39 cell types) with 24â658 genes, the second dataset included 6225 single RGCs from mice (41 subtypes) with 13â616 genes and the third dataset included 35â699 single RGCs from mice (45 subtypes) with 18â222 genes. We used four loss functions in the learning process to align the source and target distributions, reduce misclassification errors and maximize robustness. Models were evaluated based on classification accuracy and confusion matrix. The accuracy of the model for correctly classifying 39 different retinal cell types in the first dataset was â¼92%. Accuracy in the second and third datasets reached â¼97% and 97% in correctly classifying 40 and 45 different RGCs subtypes, respectively. Across a range of seven different batches in the first dataset, the accuracy of the lead model ranged from 74% to nearly 100%. The lead model provided high accuracy in identifying retinal cell types and RGC subtypes based on scRNA-seq data. The performance was reasonable based on data from different batches as well. The validated model could be readily applied to scRNA-seq data to identify different retinal cell types and subtypes. AVAILABILITY AND IMPLEMENTATION The code and datasets are available on https//github.com/DM2LL/Detecting-Retinal-Cell-Classes-and-Ganglion-Cell-Subtypes. We have also added the class labels of all samples to the datasets. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Texto completo:
1
Base de dados:
MEDLINE
Assunto principal:
Análise de Célula Única
/
Transcriptoma
Idioma:
En
Ano de publicação:
2022
Tipo de documento:
Article