New instructions and own conda enviroment

elarielcl · elarielcl · commit 9fcef4453c08 · 2023-03-13T15:52:23.000+02:00
diff --git a/README.md b/README.md
@@ -1,10 +1,15 @@
 # Python scripts for running GraphChainer experiments
 
-- Use same conda enviroment as GraphChainer's
-- Modify `.env` file with the following variables `GRAPHALIGNER`, `GRAPHCHAINER`, `MINIGRAPH`, `MINICHAIN` (paths to the corresponding binaries)
+- `conda env create -f environment.yml`
+- `conda acctivate GraphChainerScripts`
+- Compile and place the aligner's binaries on the `bin/` folder (they are assumed to be called `GraphAligner, GraphChainer, minigraph, minichain` respectively)
 - Place Badread's repo in this directory `git clone https://github.com/rrwick/Badread.git`
 
-## Some instructions
+## Instructions
 
 - Every python script has its own instructions/helper
-- The scripts should be run in the order `[generate_sim_reads.py], run_experiment.py, compute_summary.py, compute_metrics.py`
+- The scripts should be run in the order `[generate_sim_reads.py], run_experiment.py, compute_summary.py, compute_metrics.py` (if real reads are used the first script is skipped)
+-- `generate_sim_reads.py` : Takes a graph as input and generates simulated reads from a random path of the graph using `GraphChainer` random path generator and `Bardread` simulator.
+-- `run_experiment.py` : Runs the four tools on the specified graph and fastq files.
+-- `compute_summary.py` : Computes csv tables with the metrics used in the paper, it receives as input the graph and the fastq file, or in the case of simulated reads, the files output by `generate_sim_reads.py`.
+-- `compute_metrics.py` : Plots a graph with the summary (csv) files output by `compute_sumary.py` 
diff --git a/compute_summary.py b/compute_summary.py
@@ -229,7 +229,7 @@ def compute_overlap(read, node):
 
 def compute_summary(args):
 
-    vertex_labels, edges = load_graph(args.gfa_graph)
+    vertex_labels, edges = load_graph(args.graph)
     reads, ref_seq, ref_seq_rev_comp, ref_path = load_reads_and_ref(args.fastq, args.fasta, args.path)
     node_limits = list(cumsum([len(vertex_labels[v]) for v in ref_path]))
 
@@ -340,7 +340,7 @@ def compute_edit_kernel(tid):
     )
 
     requiredNamed = parser.add_argument_group('required arguments')
-    requiredNamed.add_argument('-gfa', '--gfa-graph', type=str, help='Input gfa file', required=True)
+    requiredNamed.add_argument('-g', '--graph', type=str, help='Input gfa file', required=True)
     requiredNamed.add_argument('-fq', '--fastq', type=str, help='Input fastq file', required=True)
     requiredNamed.add_argument(
         '-als', '--alignments', type=str, help='Output gam/gaf files (with extension, each)', required=True, nargs='+'
diff --git a/environment.yml b/environment.yml
@@ -0,0 +1,105 @@
+name: GraphChainerScripts
+channels:
+  - anaconda
+  - conda-forge
+  - https://conda.anaconda.org/gurobi
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - brotli=1.0.9=h166bdaf_7
+  - brotli-bin=1.0.9=h166bdaf_7
+  - bzip2=1.0.8=h7b6447c_0
+  - ca-certificates=2022.12.7=ha878542_0
+  - certifi=2022.12.7=pyhd8ed1ab_0
+  - click=8.1.3=unix_pyhd8ed1ab_2
+  - contourpy=1.0.5=py310hdb19cb5_0
+  - cycler=0.11.0=pyhd8ed1ab_0
+  - dbus=1.13.18=hb2f20db_0
+  - expat=2.2.10=h9c3ff4c_0
+  - fontconfig=2.14.1=hef1e5e3_0
+  - fonttools=4.25.0=pyhd3eb1b0_0
+  - freetype=2.10.4=h0708190_1
+  - giflib=5.2.1=h36c2ea0_2
+  - glib=2.69.1=h4ff587b_1
+  - gst-plugins-base=1.14.1=h6a678d5_1
+  - gstreamer=1.14.1=h5eee18b_1
+  - icu=58.2=hf484d3e_1000
+  - joblib=1.1.1=py310h06a4308_0
+  - jpeg=9e=h166bdaf_1
+  - keyutils=1.6.1=h166bdaf_0
+  - kiwisolver=1.4.4=py310h6a678d5_0
+  - krb5=1.19.3=h3790be6_0
+  - lcms2=2.12=h3be6417_0
+  - ld_impl_linux-64=2.38=h1181459_1
+  - lerc=3.0=h295c915_0
+  - libblas=3.9.0=15_linux64_openblas
+  - libbrotlicommon=1.0.9=h166bdaf_7
+  - libbrotlidec=1.0.9=h166bdaf_7
+  - libbrotlienc=1.0.9=h166bdaf_7
+  - libcblas=3.9.0=15_linux64_openblas
+  - libclang=10.0.1=default_hb85057a_2
+  - libdeflate=1.17=h5eee18b_0
+  - libedit=3.1.20191231=he28a2e2_2
+  - libevent=2.1.12=h8f2d780_0
+  - libffi=3.3=he6710b0_2
+  - libgcc-ng=11.2.0=h1234567_1
+  - libgfortran-ng=12.2.0=h69a702a_19
+  - libgfortran5=12.2.0=h337968e_19
+  - libgomp=11.2.0=h1234567_1
+  - liblapack=3.9.0=15_linux64_openblas
+  - libllvm10=10.0.1=he513fc3_3
+  - libopenblas=0.3.20=pthreads_h78a6416_0
+  - libpng=1.6.39=h5eee18b_0
+  - libpq=12.9=h16c4e8d_3
+  - libprotobuf=3.20.3=he621ea3_0
+  - libstdcxx-ng=11.2.0=h1234567_1
+  - libtiff=4.5.0=h6a678d5_2
+  - libuuid=1.41.5=h5eee18b_0
+  - libwebp=1.2.4=h11a3e52_1
+  - libwebp-base=1.2.4=h5eee18b_1
+  - libxcb=1.15=h7f8727e_0
+  - libxkbcommon=1.0.1=hfa300c1_0
+  - libxml2=2.9.14=h74e7548_0
+  - libxslt=1.1.35=h4e12654_0
+  - lz4-c=1.9.3=h9c3ff4c_1
+  - matplotlib=3.7.0=py310h06a4308_0
+  - matplotlib-base=3.7.0=py310h1128e8f_0
+  - munkres=1.1.4=pyh9f0ad1d_0
+  - ncurses=6.4=h6a678d5_0
+  - nspr=4.33=h295c915_0
+  - nss=3.74=h0370c37_0
+  - openssl=1.1.1s=h7f8727e_0
+  - packaging=23.0=pyhd8ed1ab_0
+  - pcre=8.45=h9c3ff4c_0
+  - pillow=9.4.0=py310h6a678d5_0
+  - pip=23.0.1=py310h06a4308_0
+  - ply=3.11=py_1
+  - protobuf=3.20.3=py310h6a678d5_0
+  - pyparsing=3.0.9=pyhd8ed1ab_0
+  - pyqt=5.15.7=py310h6a678d5_1
+  - python=3.10.0=h12debd9_5
+  - python-dateutil=2.8.2=pyhd8ed1ab_0
+  - python-dotenv=1.0.0=pyhd8ed1ab_0
+  - python_abi=3.10=2_cp310
+  - qt-main=5.15.2=h327a75a_7
+  - qt-webengine=5.15.9=hd2b0992_4
+  - qtwebkit=5.212=h4eab89a_4
+  - readline=8.2=h5eee18b_0
+  - setuptools=65.6.3=py310h06a4308_0
+  - sip=6.6.2=py310h6a678d5_0
+  - six=1.16.0=pyh6c4a22f_0
+  - sqlite=3.40.1=h5082296_0
+  - tk=8.6.12=h1ccaba5_0
+  - toml=0.10.2=pyhd8ed1ab_0
+  - tornado=6.1=py310h5764c6d_3
+  - tzdata=2022g=h04d1e81_0
+  - wheel=0.38.4=py310h06a4308_0
+  - xz=5.2.10=h5eee18b_1
+  - zlib=1.2.13=h5eee18b_0
+  - zstd=1.5.2=ha4553b6_0
+  - pip:
+    - edlib==1.3.9
+    - numpy==1.24.2
+    - pyqt5-sip==12.11.0
+    - scipy==1.10.1
diff --git a/generate_sim_reads.py b/generate_sim_reads.py
@@ -11,7 +11,7 @@ def generate_sim_reads(args):
     graphchainer = getenv('GRAPHCHAINER')
 
     run(
-        f'{graphchainer} --generate-path --generate-path-seed {args.seed} -g {args.vg_graph} -f {args.fasta} -a tmp.gam'
+        f'{graphchainer} --generate-path --generate-path-seed {args.seed} -g {args.graph} -f {args.fasta} -a tmp.gam'
         .split()
     )
 
@@ -29,15 +29,15 @@ def generate_sim_reads(args):
 
     parser = ArgumentParser(
         description='''
-            Generates simulated reads from a random path of an input vg file using the Badread simulator.
+            Generates simulated reads from a random path of an input vg/gfa file using the Badread simulator.
             Badread parameters are fixed to --identity 85,95,5 --length 15000,10000 --error_model pacbio2016
             --junk_reads 0 --random_reads 0 --chimeras 0.           
         ''',
         formatter_class=RawTextHelpFormatter
     )
 
     requiredNamed = parser.add_argument_group('required arguments')
-    requiredNamed.add_argument('-vg', '--vg-graph', type=str, help='Input vg file', required=True)
+    requiredNamed.add_argument('-g', '--graph', type=str, help='Input vg/gfa file', required=True)
     requiredNamed.add_argument('-fq', '--fastq', type=str, help='Output fastq file', required=True)
 
     parser.add_argument('-s', '--seed', type=int, help='Seed for random path generator and Badread', default=0)
diff --git a/run_experiment.py b/run_experiment.py
@@ -9,25 +9,25 @@ def run_experiment(args):
 
     graphaligner = getenv('GRAPHALIGNER')
     run(
-        f'{graphaligner} -t {args.threads} -x vg -f {args.fastq} -g {args.vg_graph} '
+        f'{graphaligner} -t {args.threads} -x vg -f {args.fastq} -g {args.graph} '
         f'-a {args.alignment}_graphaligner.gam'.split()
     )
 
     graphchainer = getenv('GRAPHCHAINER')
     run(
-        f'{graphchainer} -t {args.threads} -f {args.fastq} -g {args.vg_graph} '
+        f'{graphchainer} -t {args.threads} -f {args.fastq} -g {args.graph} '
         f'-a {args.alignment}_graphchainer.gam '.split()
     )
 
     minigraph = getenv('MINIGRAPH')
     run(
-        f'{minigraph} -t {args.threads} -c {args.gfa_graph} {args.fastq}'.split(),
+        f'{minigraph} -t {args.threads} -c {args.graph} {args.fastq}'.split(),
         stdout=open(f'{args.alignment}_minigraph.gaf', 'wb')
     )
 
     minichain = getenv('MINICHAIN')
     run(
-        f'{minichain} -t {args.threads} -c {args.gfa_graph} {args.fastq}'.split(),
+        f'{minichain} -t {args.threads} -c {args.graph} {args.fastq}'.split(),
         stdout=open(f'{args.alignment}_minichain.gaf', 'wb')
     )
 
@@ -42,8 +42,7 @@ def run_experiment(args):
     )
 
     requiredNamed = parser.add_argument_group('required arguments')
-    requiredNamed.add_argument('-vg', '--vg-graph', type=str, help='Input vg file', required=True)
-    requiredNamed.add_argument('-gfa', '--gfa-graph', type=str, help='Input gfa file', required=True)
+    requiredNamed.add_argument('-g', '--graph', type=str, help='Input vg/gfa file', required=True)
     requiredNamed.add_argument('-fq', '--fastq', type=str, help='Input fastq file', required=True)
     requiredNamed.add_argument(
         '-a', '--alignment', type=str, help='Output gam/gaf files (without extension)', required=True
