Hits:

Journal:BMC supplements

Key Words:Deep neural networks; Single-cell Hi-C data; Cell type prediction; Cell classification

Abstract:Background: Cell type prediction is crucial to cell type Identification of genomics, cancer diagnosis and drug development, and it can solve the difficult and timeconsuming problem of cell classification in biological experiments. Therefore, the computational methods are urgently needed to classify and predict cell types using single-cell Hi-C data. In previous studies, there is a lack of convenient and accurate method to predict cell types based on single-cell Hi-C data. Deep neural networks
can form complex representations of single-cell Hi-C data and make it possible to handle the multidimensional and sparse biological datasets.
Results: We compare the performance of SCANN with existing methods and analyze the model by using five different evaluation metrics. When using only ML1 and ML3 datasets, in terms of the ARI and NMI values, SCANN improve 14% and
11% over the baseline approach k-means++ respectively. However, when using all six libraries of data, the ARI and NMI values of SCANN improve 63% and 88% over the baseline approach k-means++ respectively. Therefore, SCANN is highly
accurate in predicting the type of independent cell samples using single-cell Hi-C data.
Conclusions: SCANN enhances the training speed and requires fewer resources for predicting cell types. In addition, when the number of cells in different cell types was extremely unbalanced, SCANN has higher stability and flexibility in solving cell classification and cell type prediction using the single-cell Hi-C data. This predication method can assist biologists to study

All the Authors:Meili Wang,Quanzhong Liu

First Author:Bing Zhou

Indexed by:Journal paper

Correspondence Author:Hao Wu

Discipline:Engineering

First-Level Discipline:Software Engineering

Document Type:J

Volume:12

Issue:3

Page Number:1-12

Translation or Not:no

Date of Publication:2021-04-01

Included Journals:SCI