| //! The stringsim program prints out the trigram similarity of two strings | |
| //! using what appears to be the same algorithm used by Postgres. | |
| //! https://www.postgresql.org/docs/9.1/pgtrgm.html | |
| use std::collections::HashSet; | |
| use std::hash::Hash; | |
| fn main() { | |
| let args: Vec<String> = ::std::env::args().collect(); | |
| if args.len() != 1+2 { |
SAM and BAM filtering one-liners
@author: David Fredman, david.fredmanAAAAAA@gmail.com (sans poly-A tail)
@dependencies: http://sourceforge.net/projects/bamtools/ and http://samtools.sourceforge.net/
Please extend with additional/faster/better solutions via a pull request!
BWA mapping (using piping for minimal disk I/O)
| # len <- c(100, 120, 40, 1000, ....) | |
| len.sorted <- rev(sort(len)) | |
| N50 <- len.sorted[cumsum(len.sorted) >= sum(len.sorted)*0.5][1] | |
| N90 <- len.sorted[cumsum(len.sorted) >= sum(len.sorted)*0.9][1] |
