Paper Info
Title
High-performance deep learning pipeline predicts individuals in mixtures of DNA using sequencing data
Abstract
In this study, we proposed a deep learning (DL) model for classifying individuals from mixtures of DNA samples using 27 short tandem repeats and 94 single nucleotide polymorphisms obtained through massively parallel sequencing protocol. The model was trained/tested/validated with sequenced data from 6 individuals and then evaluated using mixtures from forensic DNA samples. The model successfully identified both the major and the minor contributors with 100% accuracy for 90 DNA mixtures, that were manually prepared by mixing sequence reads of 3 individuals at different ratios. Furthermore, the model identified 100% of the major contributors and 50-80% of the minor contributors in 20 two-sample external-mixed-samples at ratios of 1:39 and 1:9, respectively. To further demonstrate the versatility and applicability of the pipeline, we tested it on whole exome sequence data to classify subtypes of 20 breast cancer patients and achieved an area under curve of 0.85. Overall, we present, for the first time, a complete pipeline, including sequencing data processing steps and DL steps, that is applicable across different NGS platforms. We also introduced a sliding window approach, to overcome the sequence length variation problem of sequencing data, and demonstrate that it improves the model performance dramatically.
Year
DOI
Venue
2021
10.1093/bib/bbab283
BRIEFINGS IN BIOINFORMATICS
Keywords
DocType
Volume
deep learning, next-generation sequencing, forensic, breast cancer, DNA mixture
Journal
22
Issue
ISSN
Citations 
6
1467-5463
0
PageRank 
References 
Authors
0.34
0
9
Name
Order
Citations
PageRank
Nam Nhut Phan100.34
Amrita Chattopadhyay201.01
Tsui-Ting Lee300.34
Hsiang-I Yin400.34
Tzu-Pin Lu575.10
Liang-Chuan Lai644.52
Hsiao-Lin Hwa7211.65
Mong-Hsun Tsai8114.97
Eric Y Chuang9186.50