Created new mutations using mutatrix, automatized performance tests.

Martinsos · Nov 3, 2016 · 5780b72 · 5780b72
1 parent 11113e7
commit 5780b72
Show file tree

Hide file tree

Showing 65 changed files with 322 additions and 127 deletions.
diff --git a/apps/aligner/aligner.cpp b/apps/aligner/aligner.cpp
@@ -68,7 +68,7 @@ int main(int argc, char * const argv[]) {
                 " If N = 0 then all sequences will be calculated."
                 " Specifying small N can make total calculation much faster. [default: 0]\n");
         fprintf(stderr, "\t-k K  Sequences with score > K will be discarded."
-                " Smaller k, faster calculation.\n");
+                " Smaller k, faster calculation. If -1, no sequences will be discarded. [default: -1]\n");
         fprintf(stderr, "\t-p  If specified, alignment path will be found and printed. "
                 "This may significantly slow down the calculation.\n");
         fprintf(stderr, "\t-l  If specified, start locations will be found and printed. "

diff --git a/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0.fasta b/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0.fasta
diff --git a/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_10per.fa b/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_10per.fa
diff --git a/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_1per.fasta b/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_1per.fasta
diff --git a/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_25per.fa b/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_25per.fa
diff --git a/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_3per.fa b/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_3per.fa
diff --git a/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_50per.fa b/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_50per.fa
diff --git a/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_5per.fa b/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_5per.fa
diff --git a/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_65per.fa b/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_65per.fa
diff --git a/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_75per.fa b/test_data/Chromosome_2890043_3890042_0/Chromosome_2890043_3890042_0_mutated_75per.fa
diff --git a/test_data/Chromosome_2890043_3890042_0/mutated_60_perc.fasta b/test_data/Chromosome_2890043_3890042_0/mutated_60_perc.fasta
diff --git a/test_data/Chromosome_2890043_3890042_0/mutated_70_perc.fasta b/test_data/Chromosome_2890043_3890042_0/mutated_70_perc.fasta
diff --git a/test_data/Chromosome_2890043_3890042_0/mutated_80_perc.fasta b/test_data/Chromosome_2890043_3890042_0/mutated_80_perc.fasta
diff --git a/test_data/Chromosome_2890043_3890042_0/mutated_90_perc.fasta b/test_data/Chromosome_2890043_3890042_0/mutated_90_perc.fasta
diff --git a/test_data/Chromosome_2890043_3890042_0/mutated_94_perc.fasta b/test_data/Chromosome_2890043_3890042_0/mutated_94_perc.fasta
diff --git a/test_data/Chromosome_2890043_3890042_0/mutated_97_perc.fasta b/test_data/Chromosome_2890043_3890042_0/mutated_97_perc.fasta
diff --git a/test_data/Chromosome_2890043_3890042_0/mutated_99_perc.fasta b/test_data/Chromosome_2890043_3890042_0/mutated_99_perc.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_10%.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_10%.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_25%.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_25%.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_3%.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_3%.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_5%.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_5%.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_50%.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_50%.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_65%.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_65%.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_75%.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/e_coli_DH1_illumina_1x10000_mutated_75%.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_60_perc.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_60_perc.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_70_perc.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_70_perc.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_80_perc.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_80_perc.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_90_perc.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_90_perc.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_94_perc.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_94_perc.fasta
diff --git a/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_97_perc.fasta b/test_data/E_coli_DH1/mason_illumina_read_10kbp/mutated_97_perc.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline.fasta b/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_1%.fasta b/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_1%.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_10%.fasta b/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_10%.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_25%.fasta b/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_25%.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_3%.fasta b/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_3%.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_5%.fasta b/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_5%.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_50%.fasta b/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_50%.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_65%.fasta b/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_65%.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_75%.fasta b/test_data/E_coli_DH1/prefix_10kbp/e_coli_DH1_prefix10000_oneline_mutated_75%.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/mutated_60_perc.fasta b/test_data/E_coli_DH1/prefix_10kbp/mutated_60_perc.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/mutated_70_perc.fasta b/test_data/E_coli_DH1/prefix_10kbp/mutated_70_perc.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/mutated_80_perc.fasta b/test_data/E_coli_DH1/prefix_10kbp/mutated_80_perc.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/mutated_90_perc.fasta b/test_data/E_coli_DH1/prefix_10kbp/mutated_90_perc.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/mutated_94_perc.fasta b/test_data/E_coli_DH1/prefix_10kbp/mutated_94_perc.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/mutated_97_perc.fasta b/test_data/E_coli_DH1/prefix_10kbp/mutated_97_perc.fasta
diff --git a/test_data/E_coli_DH1/prefix_10kbp/mutated_99_perc.fasta b/test_data/E_coli_DH1/prefix_10kbp/mutated_99_perc.fasta
diff --git a/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1.fasta b/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1.fasta
diff --git a/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_1%.fasta b/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_1%.fasta
diff --git a/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_10%.fa b/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_10%.fa
diff --git a/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_25%.fa b/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_25%.fa
diff --git a/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_3%.fa b/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_3%.fa
diff --git a/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_5%.fa b/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_5%.fa
diff --git a/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_50%.fa b/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_50%.fa
diff --git a/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_65%.fa b/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_65%.fa
diff --git a/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_75%.fa b/test_data/Enterobacteria_Phage_1/Enterobacteria_phage_1_oneline_mutated_75%.fa
diff --git a/test_data/Enterobacteria_Phage_1/mutated_60_perc.fasta b/test_data/Enterobacteria_Phage_1/mutated_60_perc.fasta
diff --git a/test_data/Enterobacteria_Phage_1/mutated_70_perc.fasta b/test_data/Enterobacteria_Phage_1/mutated_70_perc.fasta
diff --git a/test_data/Enterobacteria_Phage_1/mutated_80_perc.fasta b/test_data/Enterobacteria_Phage_1/mutated_80_perc.fasta
diff --git a/test_data/Enterobacteria_Phage_1/mutated_90_perc.fasta b/test_data/Enterobacteria_Phage_1/mutated_90_perc.fasta
diff --git a/test_data/Enterobacteria_Phage_1/mutated_94_perc.fasta b/test_data/Enterobacteria_Phage_1/mutated_94_perc.fasta
diff --git a/test_data/Enterobacteria_Phage_1/mutated_97_perc.fasta b/test_data/Enterobacteria_Phage_1/mutated_97_perc.fasta
diff --git a/test_data/Enterobacteria_Phage_1/mutated_99_perc.fasta b/test_data/Enterobacteria_Phage_1/mutated_99_perc.fasta
diff --git a/test_data/mutator.py b/test_data/mutator.py
diff --git a/test_data/mutatrix_mutator.sh b/test_data/mutatrix_mutator.sh
@@ -0,0 +1,17 @@
+#!/usr/bin/env bash
+
+# Mutate given sequence using Mutatrix and compare it with original sequence using Edlib,
+# to see how different it is.
+
+MUTATRIX=~/git/mutatrix/mutatrix
+EDLIB=~/git/edlib/build/bin/edlib-aligner
+
+INPUT_SEQUENCE=$1
+MUTATION_PERC=$2
+
+OUTPUT_SEQUENCE="mutated_"$MUTATION_PERC"_"$INPUT_SEQUENCE
+
+$MUTATRIX -s $MUTATION_PERC -i $MUTATION_PERC -n 1 -m 0 -M 0 -P mutatrix_output $INPUT_SEQUENCE > mutation.vcf
+mv mutatrix_output* $OUTPUT_SEQUENCE
+
+$EDLIB $INPUT_SEQUENCE $OUTPUT_SEQUENCE