A Contrastive Learning Pre-Training Method for Motif Occupancy Identification.
Int J Mol Sci
; 23(9)2022 Apr 24.
Article
em En
| MEDLINE
| ID: mdl-35563090
ABSTRACT
Motif occupancy identification is a binary classification task predicting the binding of DNA motif instances to transcription factors, for which several sequence-based methods have been proposed. However, through direct training, these end-to-end methods are lack of biological interpretability within their sequence representations. In this work, we propose a contrastive learning method to pre-train interpretable and robust DNA encoding for motif occupancy identification. We construct two alternative models to pre-train DNA sequential encoder, respectively a self-supervised model and a supervised model. We augment the original sequences for contrastive learning with edit operations defined in edit distance. Specifically, we propose a sequence similarity criterion based on the Needleman-Wunsch algorithm to discriminate positive and negative sample pairs in self-supervised learning. Finally, a DNN classifier is fine-tuned along with the pre-trained encoder to predict the results of motif occupancy identification. Both proposed contrastive learning models outperform the baseline end-to-end CNN model and SimCLR method, reaching AUC of 0.811 and 0.823, respectively. Compared with the baseline method, our models show better robustness for small samples. Specifically, the self-supervised model is proved to be practicable in transfer learning.
Palavras-chave
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Algoritmos
Tipo de estudo:
Diagnostic_studies
/
Prognostic_studies
Idioma:
En
Revista:
Int J Mol Sci
Ano de publicação:
2022
Tipo de documento:
Article
País de afiliação:
China