Dataset Information

Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis.

ABSTRACT: Clustering and cell type classification are important steps in single-cell RNA-seq (scRNA-seq) analysis. As more and more scRNA-seq data are becoming available, supervised cell type classification methods that utilize external well-annotated source data start to gain popularity over unsupervised clustering algorithms. However, the performance of existing supervised methods is highly dependent on source data quality, and they often have limited accuracy to classify cell types that are missing in the source data. To overcome these limitations, we developed ItClust, a transfer learning algorithm that borrows idea from supervised cell type classification algorithms, but also leverages information in target data to ensure sensitivity in classifying cells that are only present in the target data. Through extensive evaluations using data from different species and tissues generated with diverse scRNA-seq protocols, we show that ItClust significantly improves clustering and cell type classification accuracy over popular unsupervised clustering and supervised cell type classification algorithms.

SUBMITTER: Hu J

PROVIDER: S-EPMC8009055 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis.

Hu Jian J Li Xiangjie X Hu Gang G Lyu Yafei Y Susztak Katalin K Li Mingyao M

Nature machine intelligence 20201005 10

Clustering and cell type classification are important steps in single-cell RNA-seq (scRNA-seq) analysis. As more and more scRNA-seq data are becoming available, supervised cell type classification methods that utilize external well-annotated source data start to gain popularity over unsupervised clustering algorithms. However, the performance of existing supervised methods is highly dependent on source data quality, and they often have limited accuracy to classify cell types that are missing in ...[more]

PMID: 33817554

Similar Datasets

Project description:BackgroundA limitation of traditional differential expression analysis on small datasets involves the possibility of false positives and false negatives due to sample variation. Considering the recent advances in deep learning (DL) based models, we wanted to expand the state-of-the-art in disease biomarker prediction from RNA-seq data using DL. However, application of DL to RNA-seq data is challenging due to absence of appropriate labels and smaller sample size as compared to number of genes. Deep learning coupled with transfer learning can improve prediction performance on novel data by incorporating patterns learned from other related data. With the emergence of new disease datasets, biomarker prediction would be facilitated by having a generalized model that can transfer the knowledge of trained feature maps to the new dataset. To the best of our knowledge, there is no Convolutional Neural Network (CNN)-based model coupled with transfer learning to predict the significant upregulating (UR) and downregulating (DR) genes from both trained and untrained datasets.ResultsWe implemented a CNN model, DEGnext, to predict UR and DR genes from gene expression data obtained from The Cancer Genome Atlas database. DEGnext uses biologically validated data along with logarithmic fold change values to classify differentially expressed genes (DEGs) as UR and DR genes. We applied transfer learning to our model to leverage the knowledge of trained feature maps to untrained cancer datasets. DEGnext's results were competitive (ROC scores between 88 and 99[Formula: see text]) with those of five traditional machine learning methods: Decision Tree, K-Nearest Neighbors, Random Forest, Support Vector Machine, and XGBoost. DEGnext was robust and effective in terms of transferring learned feature maps to facilitate classification of unseen datasets. Additionally, we validated that the predicted DEGs from DEGnext were mapped to significant Gene Ontology terms and pathways related to cancer.ConclusionsDEGnext can classify DEGs into UR and DR genes from RNA-seq cancer datasets with high performance. This type of analysis, using biologically relevant fine-tuning data, may aid in the exploration of potential biomarkers and can be adapted for other disease datasets.

Dataset Information

Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis.

Publications

Iterative transfer learning with neural network for clustering and cell type classification in single-cell RNA-seq analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets