cnv code

Landrylab · May 20, 2020 · 1beed9a · 1beed9a
1 parent 3b34b74
commit 1beed9a
Show file tree

Hide file tree

Showing 17 changed files with 53,534 additions and 2 deletions.
diff --git a/03_relatedness_to_beer_strains/README b/03_relatedness_to_beer_strains/README
@@ -1,6 +1,7 @@
 # Analyses related to estimating relatedness of the Jean-Talon strain to other beer strains (Figure 3)
 
 
+
 ## Calculating IBS, IBD and plotting figures in Figure 3 
 ### Complete vcf file for these analyses can be downloaded from figshare as File S4
 
@@ -11,6 +12,7 @@ calculate_IBS_IBD.R
 
 ./input_files/sample_VarFiltr.vcf.gz	# complete vcf file can be downloaded from figshare as File S4
 ./input_files/table_S2.csv		# metadata for all strains
+
 ./output/sample_VarFiltr_ibs.nwk	# tree based on IBS matrix
 genotypes_allsamples_VarFiltr.gds	# temporary file
 
@@ -32,7 +34,7 @@ genotypes_allsamples_VarFiltr.gds			# temporary file
 
 
 
-# Manipulating fasta files
+## Manipulating fasta files
 ### Selecting non-overlapping and single exon genes; 
 ### if vcf with genotypes of relatives is present (can be downloaded from figshare - File S5), 
 ### after running several bcftools and seqtk commands one can generate msa of concatenated genes
@@ -47,7 +49,7 @@ manipulateFasta.ipynb
 
 
 
-# Calculating divergence time between Jean-Talon and relatives using S. cerevisiae S288C as an outgroup
+## Calculating divergence time between Jean-Talon and relatives using S. cerevisiae S288C as an outgroup
 
 calcRelativeTime_Scer.ipynb
 

diff --git a/04_copy_number_variation/README b/04_copy_number_variation/README
@@ -0,0 +1,42 @@
+# Code for analyses of copy number variation (CNVs) (Figure 4 & Figure S3)
+
+
+
+## Plotting CNVs and aneuploidies in Jean-Talon and its close relatives (Figure 4)
+
+plotCNP.R
+
+input_files/getCNVIntervals_all.tab	# List of CNVs > 10 kb
+
+output/plotCNP.pdf
+
+
+
+## Analysisng CNVs (Figure S3)
+## - filtering for poor quality coverage
+## - subsampling unrelated strains within groups
+## - calculating frequencies of CNVs in groups & plotting heatmaps (this only after running some bash scripts)
+
+### Complete file with coverage estimates can be downloaded from figshare as File S6.
+
+manageCNVs.ipynb
+
+./input_files/sample_FileS6.txt.gz		# coverage in 250 bp windows for all strains
+./input_files/FileS7.txt.gz			# gain and loss variants for all strains
+./input_files/table_S2.csv			# metadata for all strains
+./input_files/IBDKINGmethod_kinship_matrix.out	# kinship coefficient between all samples
+./input_files/chromLengthConvertion.fai		# genome fasta fai file
+./input_files/genome_windows_250.bed		# bed file with 250 bp windows
+./input_files/cnv_beer_bb_gains.bed		# coordinates of gains in Beer/baking group
+./input_files/cnv_beer_bb_losses.bed		# coordinates of losses in Beer/baking group
+
+
+
+## Plotting heatmap of coverage in maltose metabolism genes (Figure S3)
+
+plotMaltoseCNV.ipynb
+
+./input_files/maltoseGenes_CNV.tab
+./input_files/table_S2.csv
+
+./output/figure_heatmap_maltose.pdf
diff --git a/04_copy_number_variation/input_files/FileS7.txt.gz b/04_copy_number_variation/input_files/FileS7.txt.gz
diff --git a/04_copy_number_variation/input_files/IBDKINGmethod_kinship_matrix.out b/04_copy_number_variation/input_files/IBDKINGmethod_kinship_matrix.out
diff --git a/04_copy_number_variation/input_files/chromLengthConvertion.fai b/04_copy_number_variation/input_files/chromLengthConvertion.fai
@@ -0,0 +1,16 @@
+ref|NC_001133|	230218
+ref|NC_001134|	813184
+ref|NC_001135|	316620
+ref|NC_001136|	1531933
+ref|NC_001137|	576874
+ref|NC_001138|	270161
+ref|NC_001139|	1090940
+ref|NC_001140|	562643
+ref|NC_001141|	439888
+ref|NC_001142|	745751
+ref|NC_001143|	666816
+ref|NC_001144|	1078177
+ref|NC_001145|	924431
+ref|NC_001146|	784333
+ref|NC_001147|	1091291
+ref|NC_001148|	948066
diff --git a/04_copy_number_variation/input_files/cnv_beer_bb_gains.bed b/04_copy_number_variation/input_files/cnv_beer_bb_gains.bed
@@ -0,0 +1,18 @@
+ref|NC_001133|	27000	160750
+ref|NC_001134|	35500	222750
+ref|NC_001134|	265000	793750
+ref|NC_001135|	14250	82750
+ref|NC_001135|	90000	290250
+ref|NC_001136|	437500	514250
+ref|NC_001137|	23000	184250
+ref|NC_001138|	30000	139250
+ref|NC_001138|	143000	270161
+ref|NC_001140|	0	85250
+ref|NC_001141|	38750	205250
+ref|NC_001141|	210500	439888
+ref|NC_001143|	517750	666816
+ref|NC_001147|	709000	1057000
+ref|NC_001148|	0	56500
+ref|NC_001148|	62500	436750
+ref|NC_001148|	443000	804500
+ref|NC_001148|	856500	931250
diff --git a/04_copy_number_variation/input_files/cnv_beer_bb_losses.bed b/04_copy_number_variation/input_files/cnv_beer_bb_losses.bed
@@ -0,0 +1,9 @@
+ref|NC_001136|	1472750	1526250
+ref|NC_001139|	7000	74750
+ref|NC_001139|	319750	402000
+ref|NC_001141|	39250	105250
+ref|NC_001141|	105500	163000
+ref|NC_001141|	210500	272750
+ref|NC_001141|	336500	433750
+ref|NC_001146|	11500	97000
+ref|NC_001146|	101000	155750