add pipeline for demographic inference and simulation

README.md

@@ -29,6 +29,8 @@ This repository includes data and scripts to analyze structural variations of 25
 - [SVTK](https://github.com/talkowski-lab/svtk)
 - [ANNOTSV](https://github.com/lgmgeo/AnnotSV)
 - [Paragraph](https://github.com/Illumina/paragraph)
+- [vcftools](http://vcftools.sourceforge.net/man_latest.html)
+- [bcftools](http://samtools.github.io/bcftools)
 - python3
 - numpy
 
@@ -52,11 +54,24 @@ In the bash file ```pipeline.sv-calling.sh```, we use sample data to demonstrate
 
 
 -------
-## Sample and Variant quality control
 
-### Script: pipeline.sv-calling.sh
+## Pipeline for Demographic inference and simulation
+
+### Script: pipeline.demographic_inference.sh
 
 ### Requirements
+- [easySFS](https://github.com/isaacovercast/easySFS)
+- [dadi](https://dadi.readthedocs.io/en/latest/)
+- [msprime](https://github.com/tskit-dev/tutorials)
+
+
+### Summary
+In the bash file ```pipeline.demographic_inference.sh```, we use sample data to demonstrate the complete process of detecting and annotating structural variations based on nanopore sequencing technology.
+
+1. Firstly, long reads were mapped to GRCh37 human reference from NCBI without alternate sequences. Mapping was performed with NGMLR with ONT default parameters.
+
+2. Then SV calling was performed on each sample using Sniffles, NanoSV, and SVIM. These tools have been reported to be compatible with NGMLR and show better accuracy and sensitivity than others. Five minimum supporting reads with at least 50 bp length was required. The insertion sequence and read ID was required for each method, and the rest are all default parameters.
+
 
 -------
 ## Visualization for chracteristics of SVs

example/samples.YRIandTIBandHAN.clust

@@ -0,0 +1,272 @@
+NA18508	YRI
+NA18510	YRI
+NA18522	YRI
+NA18488	YRI
+NA18868	YRI
+NA18870	YRI
+NA18499	YRI
+NA18856	YRI
+NA18502	YRI
+NA18507	YRI
+NA18519	YRI
+NA18933	YRI
+NA18907	YRI
+NA18867	YRI
+NA18874	YRI
+NA19102	YRI
+NA19107	YRI
+NA19114	YRI
+NA19119	YRI
+NA19121	YRI
+NA18879	YRI
+NA18881	YRI
+NA19099	YRI
+NA19239	YRI
+NA19138	YRI
+NA19118	YRI
+NA19137	YRI
+NA19210	YRI
+NA19093	YRI
+NA19098	YRI
+NA19190	YRI
+NA19113	YRI
+NA19152	YRI
+NA19171	YRI
+NA19222	YRI
+NA19238	YRI
+NA19257	YRI
+NA19207	YRI
+NA19214	YRI
+NA19144	YRI
+NA19149	YRI
+NA19175	YRI
+NA18505	YRI
+NA18517	YRI
+NA18853	YRI
+NA18858	YRI
+NA18916	YRI
+NA18923	YRI
+NA18865	YRI
+NA18877	YRI
+NA18909	YRI
+NA19096	YRI
+NA19159	YRI
+NA19116	YRI
+NA19130	YRI
+NA19197	YRI
+NA19200	YRI
+NA19236	YRI
+NA19248	YRI
+NA19147	YRI
+NA19185	YRI
+NA18511	YRI
+NA18516	YRI
+NA18523	YRI
+NA18489	YRI
+NA18504	YRI
+NA18934	YRI
+NA18871	YRI
+NA18876	YRI
+NA18908	YRI
+NA18910	YRI
+NA18864	YRI
+NA18915	YRI
+NA19095	YRI
+NA19184	YRI
+NA19189	YRI
+NA19153	YRI
+NA19160	YRI
+NA19172	YRI
+NA19223	YRI
+NA19235	YRI
+NA19141	YRI
+NA19146	YRI
+NA19108	YRI
+NA19247	YRI
+NA19204	YRI
+NA19209	YRI
+NA18486	YRI
+NA18498	YRI
+NA18501	YRI
+NA18520	YRI
+NA18912	YRI
+NA18917	YRI
+NA18861	YRI
+NA18873	YRI
+NA18924	YRI
+NA18878	YRI
+NA19198	YRI
+NA19201	YRI
+NA19206	YRI
+NA19117	YRI
+NA19129	YRI
+NA19131	YRI
+NA19143	YRI
+NA19092	YRI
+NA19213	YRI
+NA19225	YRI
+NA19256	YRI
+SAMC006354	TIB
+SAMC006367	TIB
+SAMC006368	TIB
+SAMC006369	TIB
+SAMC006370	TIB
+SAMC006371	TIB
+SAMC006374	TIB
+SAMC006375	TIB
+SAMC006376	TIB
+SAMC006377	TIB
+SAMC006378	TIB
+SAMC006379	TIB
+SAMC006380	TIB
+SAMC006381	TIB
+SAMC006382	TIB
+SAMC006385	TIB
+SAMC006386	TIB
+SAMC006387	TIB
+SAMC006389	TIB
+WGC025285D	TIB
+WGC025288D	TIB
+WGC025289D	TIB
+WGC025290D	TIB
+WGC025291D	TIB
+WGC025292D	TIB
+WGC025294D	TIB
+WGC025295D	TIB
+WGC025296D	TIB
+WGC025297D	TIB
+WGC025298D	TIB
+WGC025299D	TIB
+WGC025300D	TIB
+WGC025301D	TIB
+WGC025302D	TIB
+WGC025304D	TIB
+WGC025307D	TIB
+SAMC006353	TIB
+SAMC006355	TIB
+SAMC006356	TIB
+SAMC006357	TIB
+SAMC006358	TIB
+SAMC006359	TIB
+SAMC006360	TIB
+SAMC006361	TIB
+SAMC006362	TIB
+SAMC006363	TIB
+SAMC006364	TIB
+SAMC006365	TIB
+SAMC006366	TIB
+SAMC006372	TIB
+SAMC006373	TIB
+SAMC006383	TIB
+SAMC006384	TIB
+SAMC006388	TIB
+WGC025265D	TIB
+WGC025267D	TIB
+WGC025268D	TIB
+WGC025269D	TIB
+WGC025270D	TIB
+WGC025271D	TIB
+WGC025274D	TIB
+WGC025275D	TIB
+WGC025276D	TIB
+WGC025277D	TIB
+WGC025278D	TIB
+WGC025279D	TIB
+WGC025280D	TIB
+WGC025281D	TIB
+WGC025282D	TIB
+WGC025283D	TIB
+WGC025284D	TIB
+WGC025286D	TIB
+WGC025287D	TIB
+WGC025308D	TIB
+WGC025309D	TIB
+WGC025310D	TIB
+WGC025311D	TIB
+WGC025312D	TIB
+WGC025313D	TIB
+WGC025314D	TIB
+WGC025215D	HAN
+WGC025216D	HAN
+WGC025222D	HAN
+WGC025223D	HAN
+WGC025224D	HAN
+WGC025225D	HAN
+WGC025226D	HAN
+WGC025229D	HAN
+WGC025230D	HAN
+WGC025231D	HAN
+WGC025232D	HAN
+WGC025234D	HAN
+WGC025235D	HAN
+WGC025241D	HAN
+WGC025242D	HAN
+WGC025243D	HAN
+WGC025244D	HAN
+WGC025245D	HAN
+WGC025246D	HAN
+WGC025247D	HAN
+WGC025248D	HAN
+WGC025249D	HAN
+WGC025250D	HAN
+WGC025251D	HAN
+WGC025252D	HAN
+WGC025255D	HAN
+WGC025256D	HAN
+WGC025257D	HAN
+WGC025258D	HAN
+WGC025259D	HAN
+WGC025260D	HAN
+WGC025261D	HAN
+WGC025262D	HAN
+WGC025263D	HAN
+WGC026449D	HAN
+WGC026450D	HAN
+WGC026451D	HAN
+WGC026453D	HAN
+WGC026454D	HAN
+WGC026456D	HAN
+WGC026457D	HAN
+WGC026460D	HAN
+WGC029399D	HAN
+WGC029400D	HAN
+WGC029402D	HAN
+WGC029411D	HAN
+SAMC006391	HAN
+SAMC006392	HAN
+SAMC006393	HAN
+SAMC006394	HAN
+SAMC006395	HAN
+SAMC006396	HAN
+SAMC006397	HAN
+SAMC006398	HAN
+SAMC006399	HAN
+SAMC006400	HAN
+SAMC006401	HAN
+SAMC006402	HAN
+SAMC006403	HAN
+SAMC006404	HAN
+SAMC006405	HAN
+SAMC006406	HAN
+SAMC006407	HAN
+SAMC006408	HAN
+SAMC006409	HAN
+SAMC006410	HAN
+SAMC006411	HAN
+SAMC006412	HAN
+SAMC006413	HAN
+SAMC006414	HAN
+SAMC006415	HAN
+SAMC006416	HAN
+SAMC006417	HAN
+SAMC006418	HAN
+SAMC006419	HAN
+SAMC006421	HAN
+SAMC006422	HAN
+SAMC006423	HAN
+SAMC006424	HAN
+SAMC006425	HAN
+SAMC006426	HAN
+SAMC006427	HAN
+SAMC006428	HAN
+SAMC006429	HAN

pipeline.demographic_inference.sh

@@ -0,0 +1,56 @@
+# pipeline for demographic inference and simulation
+
+path_software_easySFS=easySFS.py
+path_vcf_include_YRI=example/merge.genotypes.corrected.delCHR.svtk.chr1.vcf
+path_samples_cluster=example/samples.YRIandTIBandHAN.clust
+root_script=scripts
+
+# 1. construct sfs and proj to a smaller set
+$path_software_easySFS \
+-p $path_samples_cluster \
+-i $path_vcf_include_YRI \
+-a -f \
+-o YRI_TIB_HAN/sfs.pruned \
+--proj 50,40,40 \
+--unfolded
+
+# 2. generate bootstrap dataset and calculate GIM
+arry_trio=('YRI_TIB_HAN')
+arry_model=("sfs.pruned")
+
+for trio in ${arry_trio[@]};do
+    echo $trio
+    fname_fs=$(echo $trio | sed 's/_/-/g');
+    poplist=$(echo $trio | sed 's/_/,/g');
+    proj='50,40,40'
+    echo $poplist
+    echo $proj
+    for model in ${arry_model[@]};do
+        echo $model
+        python $root_script/run_generate_sfs_segments.py \
+        -d $trio/$model/datadict.txt \
+        -p $trio/$model/bootstrap \
+        -l $poplist -u --random \
+        --projections $proj
+    done;
+done;
+
+# 3. demographic inference
+model_list=('split_symmig_all')
+for model in ${model_list[@]};do
+  python $root_script/run_inference.py \
+  -s YRI_TIB_HAN/YRI-TIB-HAN.sfs \
+  -p YRI_TIB_HAN/YRI-TIB-HAN -m $model \
+  --unfolded
+done
+
+# 4. simulation
+model='sfs.pruned'
+path_hapmap=example/hapmap
+for label_simulate in `seq 1 1000`; do
+  for ((i=22;i>=1;i--));do
+          chrom='chr'$i
+    echo $chrom
+    python $root_script/run_simulate_pipeline.py $chrom $label_simulate YRI_TIB_HAN/YRI-TIB-HAN.sfs YRI_TIB_HAN/$model/segments 'split_symmig_all' YRI_TIB_HAN/$model/ normal $path_hapmap
+  done;
+done;