AUTHOR=Chen Yuchi , Xie Minzhu , Wen Jie 

TITLE=Predicting gene expression from histone modifications with self-attention based neural networks and transfer learning

JOURNAL=Frontiers in Genetics

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2022.1081842

DOI=10.3389/fgene.2022.1081842

ISSN=1664-8021

ABSTRACT=It is well known that histone modifications play an important part in various chromatin-dependent processes such as DNA replication, repair, and transcription. Using computational models to predict gene expression based on histone modifications has been intensively studied. However, the accuracy of the proposed models still has room for improvement, especially in cross-cell line gene expression prediction. In the work, we proposed a new model based on deep learning to predict gene expression from histone modifications called TransferChrome. The model uses a densely connected convolutional network to capture the features of histone modifications data and uses self-attention layers to aggregate global features of the data. In TransferChrome, we also used transfer learning methods for the cross-cell line gene expression prediction, the introduction of transfer learning improves the model's predict performs in new cell lines when using cross-cell information. We trained and tested our model on 56 different cell lines from REMC database, compared to existing models, our method improves the prediction performance on most cell lines. Our model also outperforms other models on cross-cell line prediction tasks. TransferChrome is an efficient model for predicting gene expression in different cell lines.