Back

VelosGT: An App for Variant Analysis and Rare Disease Discovery

Flygare, J.; Born, A.

2023-08-12 bioinformatics
10.1101/2023.08.11.550418 bioRxiv
Show abstract

VelosGT is a MacOS application to analyze human genomes for genetic mutation and rare disease. It consumes raw read files (fasta/fastq) and returns annotated, functionally prioritized variants in a single step, while significantly out-performing standard pipelines. VelosGT ingests short-read data in all common formats (fastq, fasta, fastq.gz, and fasta.gz) as well as paired data. It can perform analyses on single genomes (proband) or trios. The underlying algorithms have been optimized to the extent that it can run directly on a personal computer, with no additional hardware required. This increases convenience and speed because no large uploads or downloads are required. All discovered variants are immediately displayed and searchable within the app. On an average* Mac laptop, VelosGT will return the results of a high-coverage 30GB read file in under an hour, and a 5GB read file in ten minutes or less. Trios can be computed using the completed child-parent analyses in a few minutes.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"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.