CSV-Filter: a deep learning-based comprehensive structural variant filtering method for both short and long reads

• Published in: Bioinformatics (Oxford, England) Vol. 40; no. 9
• Main Authors: Xia, Zeyu, Xiang, Weiming, Wang, Qingzhe, Li, Xingze, Li, Yilin, Gao, Junyu, Tang, Tao, Yang, Canqun, Cui, Yingbo
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 02.09.2024; Oxford Publishing Limited (England)
• Subjects: Algorithms; Deep Learning; Feature extraction; Genomic Structural Variation; High-Throughput Nucleotide Sequencing - methods; Humans; Image filters; Machine learning; Original Paper; Precision medicine; Self-supervised learning; Sequence Analysis, DNA - methods; Software; Transfer learning
• ISSN: 1367-4811; 1367-4803; 1367-4811
• DOI: 10.1093/bioinformatics/btae539

Abstract Motivation Structural variants (SVs) play an important role in genetic research and precision medicine. As existing SV detection methods usually contain a substantial number of false positive calls, approaches to filter the detection results are needed. Results We developed a novel deep learning-based SV filtering tool, CSV-Filter, for both short and long reads. CSV-Filter uses a novel multi-level grayscale image encoding method based on CIGAR strings of the alignment results and employs image augmentation techniques to improve SV feature extraction. CSV-Filter also utilizes self-supervised learning networks for transfer as classification models, and employs mixed-precision operations to accelerate training. The experiments showed that the integration of CSV-Filter with popular SV detection tools could considerably reduce false positive SVs for short and long reads, while maintaining true positive SVs almost unchanged. Compared with DeepSVFilter, a SV filtering tool for short reads, CSV-Filter could recognize more false positive calls and support long reads as an additional feature. Availability and implementation https://github.com/xzyschumacher/CSV-Filter