Abstract: An iterative process may be implemented for incrementally aggregating available batches of sample data with previously available batches to perform sequencing analysis. Genomic variant call files associated with one or more samples may be received in batches from sequencing devices and aggregated for performing sequencing analysis. The aggregated genomic variant call files may be used to generate cohort files and census files that comprise summary information related to the genomic variant call files in each batch. The census data in census files may be aggregated into a global census file that includes summary genome variant data. Multi-sample variant call files may be generated based on the global census file, cohort files, and census files. The genomic variant call files may be processed using parallel processing at multiple compute nodes. The files may be further compressed and overlapping data may be efficiently stored in buffer positions.

Abstract: The technology disclosed directly operates on sequencing data and derives its own feature filters. It processes a plurality of aligned reads that span a target base position. It combines elegant encoding of the reads with a lightweight analysis to produce good recall and precision using lightweight hardware. For instance, one million training examples of target base variant sites with 50 to 100 reads each can be trained on a single GPU card in less than 10 hours with good recall and precision. A single GPU card is desirable because it a computer with a single GPU is inexpensive, almost universally within reach for users looking at genetic data. It is readily available on could-based platforms.