lh3

#include <math.h>
#include <stdio.h>
#include <stdlib.h>

#define RADIX 2.0

/*************************
 * balance a real matrix *
 *************************/

lh3

Original link: http://www.concentric.net/~Ttwang/tech/inthash.htm
Taken from: http://web.archive.org/web/20071223173210/http://www.concentric.net/~Ttwang/tech/inthash.htm
Reformatted using pandoc

Integer Hash Function

Thomas Wang, Jan 1997

last update Mar 2007

lh3

References:

• https://support.basespace.illumina.com/knowledgebase/articles/403618-python-run-downloader
• https://developer.basespace.illumina.com/docs/content/documentation/rest-api/api-reference

Steps:

1. Follow steps 1-5 in the first link above to acquire access_token. This will take a while, but you only need to do this once. Never share this token!!
2. Find the file you want to download. Copy the link, which looks something like: https://basespace.illumina.com/sample/9804795/files/tree/NA12878-L1_S1_L001_R1_001.fastq.gz?id=515013503. The "id" is the unique file identifier.
3. Download the file with: wget -O filename 'https://api.basespace.illumina.com/v1pre3/files/{id}/content?access_token={token}', where {token} is from step 1 and {id} from step 2.

lh3

/*
  For any 1<k<=64, let mask=(1<<k)-1. hash_64() is a bijection on [0,1<<k), which means
  hash_64(x, mask)==hash_64(y, mask) if and only if x==y. hash_64i() is the inversion of
  hash_64(): hash_64i(hash_64(x, mask), mask) == hash_64(hash_64i(x, mask), mask) == x.
*/

// Thomas Wang's integer hash functions. See <https://gist.github.com/lh3/59882d6b96166dfc3d8d> for a snapshot.
uint64_t hash_64(uint64_t key, uint64_t mask)
{
	key = (~key + (key << 21)) & mask; // key = (key << 21) - key - 1;

lh3

#include <stddef.h>
#include <stdio.h>
#include <string.h>
#include "getopt.h"

char *optarg;
int optind=1, opterr=1, optopt, __optpos, optreset=0;

#define optpos __optpos

lh3

This is a small experiment on the alignment of ~50bp INDELs. The query sequences are shown in 0.01.fq below, where seq_ori is a 204bp sequence extracted from the human reference genome, seq_del54 contains a 54bp deletion in the middle, seq_del84 contains a 84bp deletion in a 120bp read, and seq_ins40 contains a 40bp insertion in a 140bp read. These four short sequences were mapped to the human reference genome with Bowtie2, BWA-MEM, LAST, Novoalign, SNAP and Stampy with default settings. Non-default scoring functions were also tested for Bowtie2 (--rdg 5,1 --rfg 5,1), BWA-MEM (-A2 -E1) and LAST (-r2 -q4). The output by various mappers/settings can be found in this gist. The following table gives my summary:

Mapper	Setting	-84bp	-54bp	+40bp
BBMAP	default	Yes	Yes	Yes
Bowtie2	default	No	No	No
Bowtie2	--rdg 5,1 --rfg 5,1	as insertion	as insertion	Yes
BWA-MEM	default	as split	Yes	Yes
BWA-MEM	-A2 -E1	Yes	Yes	Yes
LAST	default	as split	as split

lh3

#
# generate 01compositional.bed.gz
#

# low-complexity by mDUST
mdust hs37d5.fa -c -w7 -v28 \
  | hs37d5.mdust-w7-v28.txt \
  | cut -f1,3,4 \
  | gawk -vOFS="\t" '{--$2;print}' \
  | bgzip > 01compositional/hs37d5.mdust-w7-v28.bed.gz

lh3

• https://www.pacb.com/smrt-science/smrt-resources/datasets/
• https://github.com/PacificBiosciences/DevNet/wiki/Datasets

lh3

#include <zlib.h>
#include <fcntl.h>
#include <stdio.h>

#define BUF_LEN 0x100000

int main(int argc, char *argv[])
{
	uLong crc = crc32(0L, Z_NULL, 0);
	unsigned char buf[BUF_LEN];

lh3

#creates a base image from condo
FROM continuumio/miniconda3
SHELL ["/bin/bash", "-c"]

COPY environment.yml .

#run environment
#RUN conda env create -f environment.yml

RUN conda init bash