Anomaly detection in genomic catalogues using unsupervised multi-view autoencoders - Archive ouverte HAL Access content directly
Journal Articles BMC Bioinformatics Year : 2021

Anomaly detection in genomic catalogues using unsupervised multi-view autoencoders

(1, 2) , (1) , (1) , (2, 3) , (1)
1
2
3

Abstract

Background: Accurate identification of Transcriptional Regulator binding locations is essential for analysis of genomic regions, including Cis Regulatory Elements. The customary NGS approaches, predominantly ChIP-Seq, can be obscured by data anomalies and biases which are difficult to detect without supervision. Results: Here, we develop a method to leverage the usual combinations between many experimental series to mark such atypical peaks. We use deep learning to perform a lossy compression of the genomic regions' representations with multiview convolutions. Using artificial data, we show that our method correctly identifies groups of correlating series and evaluates CRE according to group completeness. It is then applied to the ReMap database's large volume of curated ChIP-seq data. We show that peaks lacking known biological correlators are singled out and less confirmed in real data. We propose normalization approaches useful in interpreting black-box models. Conclusion: Our approach detects peaks that are less corroborated than average. It can be extended to other similar problems, and can be interpreted to identify correlation groups. It is implemented in an open-source tool called atyPeak.
Fichier principal
Vignette du fichier
12859_2021_Article_4359.pdf (1.82 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

inserm-03356659 , version 1 (28-09-2021)

Identifiers

Cite

Quentin Ferré, Jeanne Chèneby, Denis Puthier, Cécile Capponi, Benoît Ballester. Anomaly detection in genomic catalogues using unsupervised multi-view autoencoders. BMC Bioinformatics, 2021, 22 (1), pp.460. ⟨10.1186/s12859-021-04359-2⟩. ⟨inserm-03356659⟩
74 View
30 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More