simulations subdirectory merged in main folder

.gitignore

@@ -130,12 +130,11 @@ dmypy.json
 
 # log file directory
 logs/*
-simulations/results_*
-simulations/res_*
-simulations/configs
+results_*
+res_*
 *.snakemake
-simulations/debugging
-simulations/results
-poisson_tests_all
 *.png
-*.pdf
+*.pdf
+configs
+results
+plots

README.md

@@ -52,3 +52,24 @@ Run on a hpc cluster from the base directory:
 ```bash
 bash ./wrapper.sh -c configs/<DATASET> --profile hpc/<slurm|lsf>
 ```
+
+
+
+## How to run
+Enter the following to the command line:
+```bash
+snakemake -j 1 -s Snakefile_sim --configfile config.simulations_clock.yaml --restart-times=0
+```
+
+To run on CESGA hpc cluster
+```bash
+module load snakemake
+snakemake -j 198 -s Snakefile_sim --configfile configs/config.simulations_clock_scWGA_NGS.yaml --use-envmodules -k --profile ../hpc/slurm --scheduler greedy &> logs/snakelog.$(date +%Y-%m-%d.%H-%M-%S).out &
+```
+
+
+To run on ETHZ hpc cluster, you need a conda environment with snakemake installed. If it is called snakemake, run:
+```bash
+conda activate snakemake
+snakemake -s Snakefile_sim --configfile configs/config.simulations_clock_scWGA_NGS.yaml --use-conda -k --profile ../hpc/lsf &> logs/snakelog.$(date +%Y-%m-%d.%H-%M-%S).out &
+```

simulations/configs/config.simulations_bulk.yaml → configs/simulations/config.simulations_bulk.yaml

@@ -4,24 +4,25 @@ static:
 cellcoal:
   exe: ../../cellcoal/bin/cellcoal-1.2.0
   parameter: templates/cellcoal_parameters.template
-  no_rep: 1
+  no_rep: 10
   model:
-    no_cells: 1000
+    no_cells: 100
     no_sites: 10000
     pop_size: 10000
     no_muts:
-    mut_rate: 0.000001
+    mut_rate: 1e-6
     germline_rate: 0.0005
-    branch_rate_var:   # empty for clock, e.g. 1 for non-clock
+    branch_rate_switch:
     outgroup_branch_length: 1
+    root_branch_length: 0.5
     binary_alphabet: False
   scWGA:
     errors: False
-    ADO_rate: 0.2
+    ADO_rate: [0.2, 0.01]
     doublet_rate: [0.02, 0.01]
-    ampl_error: [0.001, 1e-8, 0]
+    ampl_error: [0.01, 1e-8, 0]
   NGS:
-    seq_cov: 0.1
+    seq_cov: 1
     errors: True
     seq_overdis: 0
     seq_error: 0.01
@@ -30,14 +31,18 @@ cellcoal:
     full_GT: False
     true_haplotypes: False
 
-monovar:
+sc_from_bulk:
   run: False
-  exe: ../../MonoVar_NB/src/monovar.py
+  subsampling: [10, 20]
+  no_rep: 2
+  errors: False
+  NGS:
+    seq_cov: 20
+    seq_overdis: 5
 
 SNP_filter:
-  depth: 10
-  quality: 5
-  singletons: False
+  depth: 5
+  quality: 1
 
 tree:
   cellcoal:
@@ -51,10 +56,11 @@ tree:
     exe: ../../cellphy/cellphy.sh
     command: FAST
 
+
 poisson:
   dispersion: True
   tree: True
-  tree_weights: [1]
+  w_max: [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000]
 
 paup:
   run: False

simulations/configs/config.simulations_clock_scWGA_NGS.yaml → configs/simulations/config.simulations_clock_scWGA_NGS.yaml

@@ -16,7 +16,7 @@ cellcoal:
     binary_alphabet: False
   scWGA:
     errors: True
-    ADO_rate: 0.2
+    ADO_rate: [0.2, 0.01]
     doublet_rate: [0.02, 0.01]
     ampl_error: [0.01, 1e-8, 0]
   NGS:
@@ -26,17 +26,21 @@ cellcoal:
     seq_error: 0.01
   output:
     tree: True
-    full_GT: True
+    full_GT: False
     true_haplotypes: False
 
-monovar:
+sc_from_bulk:
   run: False
-  exe: ../../MonoVar_NB/src/monovar.py
+  subsampling: [10, 20]
+  no_rep: 2
+  errors: False
+  NGS:
+    seq_cov: 20
+    seq_overdis: 0
 
 SNP_filter:
   depth: 5
-  quality: 0
-  singletons: True
+  quality: 1
 
 tree:
   cellcoal:
@@ -46,27 +50,18 @@ tree:
     exe: ../../infSCITE/infSCITE
     steps: 200000
   cellphy:
-    run: False
+    run: True
     exe: ../../cellphy/cellphy.sh
-    command: SEARCH
+    command: FAST
+
+poisson:
+  dispersion: True
+  tree: True
+  w_max: [1, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000]
 
-mrbayes:
-  run: False
-  exe: ../../MrBayes/src/mb
-  use_tree: True
-  ngen: [250000]
-  ss: True
 
 paup:
   run: True
-  learn_tree: False
   exe: ../../paup4a168_ubuntu64 
 
-sieve:
-  run: False
-  sciphi_exe: ../../SCIPhI/build/sciphi
-  beast_bin: ../../beast/bin
-  xml: templates/sieve_template.xml
-  steps: 100000
-
-scheduler: slurm
+scheduler:

configs/simulations/config.simulations_noClock_bulk.yaml

@@ -0,0 +1,70 @@
+static:
+  out_dir: 
+
+cellcoal:
+  exe: ../../cellcoal/bin/cellcoal-1.2.0
+  parameter: templates/cellcoal_parameters.template
+  no_rep: 5
+  model:
+    no_cells: 100
+    no_sites: 10000
+    pop_size: 10000
+    no_muts:
+    germline_rate: 0.0005
+    branch_rate_switch: 2
+    mut_rate: 8.2e-7 # 1x: 1e-6; 1.5x: 9e-7; 2x: 8.2e-7; 5x: 5.3e-7; 10x: 3.4e-7; 20x: 1.9e-7, 30x: 1.4e-7; 40x: 1.0e-7
+    outgroup_branch_length: 1
+    root_branch_length: 0.5
+    binary_alphabet: False
+  scWGA:
+    errors: False
+    ADO_rate: [0.2, 0.01]
+    doublet_rate: [0.02, 0.01]
+    ampl_error: [0.01, 1e-8, 0]
+  NGS:
+    seq_cov: 1
+    errors: True
+    seq_overdis: 0
+    seq_error: 0.01
+  output:
+    tree: True
+    full_GT: False
+    true_haplotypes: False
+
+sc_from_bulk:
+  run: True
+  subsampling: [10, 20]
+  no_rep: 2
+  errors: False
+  NGS:
+    seq_cov: 20
+    seq_overdis: 5
+
+SNP_filter:
+  depth: 5
+  quality: 1
+
+tree:
+  cellcoal:
+    run: True
+  scite:
+    run: False
+    exe: ../../infSCITE/infSCITE
+    steps: 10000
+  cellphy:
+    run: True
+    exe: ../../cellphy/cellphy.sh
+    command: FAST
+
+
+poisson:
+  dispersion: True
+  tree: True
+  w_max: [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000]
+
+paup:
+  run: False
+  learn_tree: False
+  exe: ../../paup4a168_ubuntu64
+
+scheduler:

simulations/configs/config.simulations_noClock_scWGA_NGS.yaml → configs/simulations/config.simulations_noClock_scWGA_NGS.yaml

@@ -1,17 +1,19 @@
 static:
-  out_dir: 
+  out_dir: results/
 
 cellcoal:
   exe: ../../cellcoal/bin/cellcoal-1.2.0
   parameter: templates/cellcoal_parameters.template
-  no_rep: 100
+  no_rep: 10
   model:
     no_cells: 30
     no_sites: 10000
     pop_size: 10000
     no_muts: 1000
     germline_rate: 0.0005
-    branch_rate_var: 1
+    branch_rate_var:
+    branch_rate_switch: 2
+    mut_rate: 8.2e-7 # 1x: 1e-6; 1.5x: 9e-7; 2x: 8.2e-7; 5x: 5.3e-7; 10x: 3.4e-7; 20x: 1.9e-7, 30x: 1.4e-7; 40x: 1.0e-7
     outgroup_branch_length: 1
     binary_alphabet: False
   scWGA:
@@ -29,14 +31,9 @@ cellcoal:
     full_GT: False
     true_haplotypes: False
 
-monovar:
-  run: False
-  exe: ../../MonoVar_NB/src/monovar.py
-
 SNP_filter:
   depth: 5
-  quality: 0
-  singletons: True
+  quality: 1
 
 tree:
   cellcoal:
@@ -50,23 +47,14 @@ tree:
     exe: ../../cellphy/cellphy.sh
     command: SEARCH
 
-mrbayes:
-  run: False
-  exe: ../../MrBayes/src/mb
-  use_tree: True
-  ngen: [250000]
-  ss: True
-
 paup:
-  run: True
+  run: False
   learn_tree: False
   exe: ../../paup4a168_ubuntu64 
 
-sieve:
-  run: False
-  sciphi_exe: ../../SCIPhI/build/sciphi
-  beast_bin: ../../beast/bin
-  xml: templates/sieve_template.xml
-  steps: 100000
+poisson:
+  dispersion: True
+  tree: True
+  w_max: [100, 200, 300, 400, 500, 600, 700, 800, 900, 1000]
 
 scheduler: slurm