DeepTrio: Variant Calling in Families Using Deep Learning
Kolesnikov, A.; Goel, S.; Nattestad, M.; Yun, T.; Baid, G.; Yang, H.; McLean, C.; Chang, P.-C.; Carroll, A.
Show abstract
Every human inherits one copy of the genome from their mother and another from their father. Parental inheritance helps us understand the transmission of traits and genetic diseases, which often involve de novo variants and rare recessive alleles. Here we present DeepTrio, which learns to analyze child-mother-father trios from the joint sequence information, without explicit encoding of inheritance priors. DeepTrio learns how to weigh sequencing error, mapping error, and de novo rates and genome context directly from the sequence data. DeepTrio has higher accuracy on both Illumina and PacBio HiFi data when compared to DeepVariant. Improvements are especially pronounced at lower coverages (with 20x DeepTrio roughly equivalent to 30x DeepVariant). As DeepTrio learns directly from data, we also demonstrate extensions to exome calling solely by changing the training data. DeepTrio includes pre-trained models for Illumina WGS, Illumina exome, and PacBio HiFi.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Haplotype-aware variant calling enables high accuracy in nanopore long-reads using deep neural networks 97%
- Merfin: improved variant filtering and polishing via k-mer validation 96%
- Multiscale Analysis of Pangenome Enables Improved Representation of Genomic Diversity For Repetitive And Clinical Relevant Genes 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.