Merge pull request #97 from cdanielmachado/development

Latest development changes

.gitignore

@@ -8,4 +8,6 @@ docs/_build/*
 Dockerfile
 .idea/*
 *.DS_Store
-.vscode/*
+.vscode/*
+carveme/universe/download bigg fasta.ipynb
+carveme/data/generated/bigg_proteins.dmnd

carveme/__init__.py

@@ -4,7 +4,7 @@
 from reframed import set_default_solver
 from reframed.solvers.solver import default_parameters, Parameter
 
-__version__ = '1.3.0'
+__version__ = '1.4.1'
 
 project_dir = os.path.abspath(os.path.dirname(__file__)) + '/'
 

carveme/cli/carve.py

@@ -11,9 +11,26 @@
 from reframed.io.sbml import sanitize_id
 import argparse
 import os
+import os.path
 import pandas as pd
 from multiprocessing import Pool
 from glob import glob
+import subprocess
+
+
+def first_run_check():
+    diamond_db = project_dir + config.get('generated', 'diamond_db')
+    if not os.path.exists(diamond_db):
+        print("Running diamond for the first time, please wait while we build the internal database...")
+        fasta_file = project_dir + config.get('input', 'fasta_file')
+        cmd = ['diamond', 'makedb', '--in', fasta_file, '-d', diamond_db[:-5]]
+        try:
+            exit_code = subprocess.call(cmd)
+        except OSError:
+            print('Unable to run diamond (make sure diamond is available in your PATH).')
+        else:
+            if exit_code != 0:
+                print('Failed to run diamond (wrong arguments).')
 
 
 def build_model_id(name):
@@ -87,7 +104,7 @@ def maincall(inputfile, input_type='protein', outputfile=None, diamond_args=None
     if input_type == 'protein' or input_type == 'dna':
         if verbose:
             print('Running diamond...')
-        diamond_db = project_dir + config.get('input', 'diamond_db')
+        diamond_db = project_dir + config.get('generated', 'diamond_db')
         blast_output = os.path.splitext(inputfile)[0] + '.tsv'
         exit_code = run_blast(inputfile, input_type, blast_output, diamond_db, diamond_args, verbose)
 
@@ -230,7 +247,7 @@ def maincall(inputfile, input_type='protein', outputfile=None, diamond_args=None
             m2, n2 = len(model.metabolites), len(model.reactions)
             print('Added {} reactions and {} metabolites'.format((n2 - n1), (m2 - m1)))
 
-        if init_env:  #Should initialize enviroment again as new exchange reactions can be acquired during gap-filling
+        if init_env:  # Initializes environment again as new exchange reactions can be acquired during gap-filling
             init_env.apply(model, inplace=True, warning=False)
 
         save_cbmodel(model, outputfile, flavor=flavor)
@@ -328,7 +345,9 @@ def main():
     elif args.cobra:
         flavor = 'cobra'
     else:
-        flavor = None
+        flavor = config.get('sbml', 'default_flavor')
+
+    first_run_check()
 
     if not args.recursive:
         if len(args.input) > 1:
@@ -390,4 +409,4 @@ def f(x):
 
 
 if __name__ == '__main__':
-    main()
+    main()

carveme/cli/gapfill.py

@@ -38,7 +38,7 @@ def maincall(inputfile, media, mediadb=None, universe=None, universe_file=None,
             universe_file = project_dir + config.get('generated', 'default_universe')
 
     try:
-        universe_model = load_cbmodel(universe_file)
+        universe_model = load_cbmodel(universe_file, flavor='cobra')
     except IOError:
         if universe:
             raise IOError('Failed to load universe "{0}". Please run build_universe.py --{0}.'.format(universe))
@@ -113,7 +113,7 @@ def main():
     elif args.cobra:
         flavor = 'cobra'
     else:
-        flavor = None
+        flavor = config.get('sbml', 'default_flavor')
 
     maincall(inputfile=args.input,
          media=args.media.split(','),

carveme/cli/merge_community.py

@@ -5,7 +5,7 @@
 from carveme.reconstruction.utils import load_media_db
 
 
-def maincall(inputfiles, flavor=None, split_pool=False, no_biomass=False, init=None, mediadb=None, ext_comp_id=None, outputfile=None):
+def maincall(inputfiles, flavor=None, init=None, mediadb=None,  outputfile=None):
 
     if not flavor:
         flavor = config.get('sbml', 'default_flavor')
@@ -16,17 +16,9 @@ def maincall(inputfiles, flavor=None, split_pool=False, no_biomass=False, init=N
         model_id = 'community'
         outputfile = 'community.xml'
 
-    if ext_comp_id is None:
-        ext_comp_id = 'C_e'
-
     models = [load_cbmodel(inputfile, flavor=flavor) for inputfile in inputfiles]
-
-    community = Community(model_id, models,
-                          extracellular_compartment_id=ext_comp_id,
-                          merge_extracellular_compartments=(not split_pool),
-                          create_biomass=(not no_biomass))
-
-    merged = community.generate_merged_model()
+    community = Community(model_id, models)
+    model = community.merged_model
 
     if init:
         if not mediadb:
@@ -37,14 +29,10 @@ def maincall(inputfiles, flavor=None, split_pool=False, no_biomass=False, init=N
         except IOError:
             raise IOError('Failed to load media library:' + mediadb)
 
-        if split_pool:
-            fmt_func = lambda x: f"R_EX_M_{x}_e_pool"
-        else:
-            fmt_func = lambda x: f"R_EX_{x}_e"
-        init_env = Environment.from_compounds(media_db[init], fmt_func=fmt_func)
-        init_env.apply(merged, inplace=True)
+        init_env = Environment.from_compounds(media_db[init])
+        init_env.apply(model, inplace=True)
 
-    save_cbmodel(merged, outputfile, flavor=flavor)
+    save_cbmodel(model, outputfile, flavor=flavor)
 
 
 def main():
@@ -54,17 +42,10 @@ def main():
 
     parser.add_argument('-o', '--output', dest='output', help="SBML output file (community)")
 
-    parser.add_argument('--split-pool', action='store_true', dest='split_pool',
-                        help='Keep individual extracellular compartments separated from common metabolite pool.')
-
-    parser.add_argument('--no-community-biomass', action='store_true', dest='no_biomass',
-                        help='Do not create a common community biomass equation.')
-
     parser.add_argument('-i', '--init', dest='init',
                         help="Initialize model with given medium")
 
     parser.add_argument('--mediadb', help="Media database file")
-    parser.add_argument('--ext', help="Extracellular compartment identifier in the models (default 'C_e').")
 
     sbml = parser.add_mutually_exclusive_group()
     sbml.add_argument('--cobra', action='store_true', help="SBML input/output in old cobra format")
@@ -81,15 +62,12 @@ def main():
     elif args.cobra:
         flavor = 'cobra'
     else:
-        flavor = None
+        flavor = config.get('sbml', 'default_flavor')
 
     maincall(inputfiles=args.input,
          flavor=flavor,
-         split_pool=args.split_pool,
-         no_biomass=args.no_biomass,
          init=args.init,
          mediadb=args.mediadb,
-         ext_comp_id=args.ext,
          outputfile=args.output)
 
 

carveme/config.cfg

@@ -8,7 +8,6 @@ unbalanced_metabolites = data/input/unbalanced_metabolites.csv
 manually_curated = data/input/manually_curated.csv
 refseq = data/input/refseq_release_201.tsv.gz
 fasta_file = data/input/bigg_proteins.faa
-diamond_db = data/input/bigg_proteins.dmnd
 
 [generated]
 folder = data/generated/
@@ -17,6 +16,7 @@ model_specific_data = data/generated/model_specific_data.csv.gz
 universe_draft = data/generated/universe_draft.xml.gz
 default_universe = data/generated/universe_bacteria.xml.gz
 bigg_gibbs = data/generated/bigg_gibbs.csv
+diamond_db = data/generated/bigg_proteins.dmnd
 
 
 [solver]

setup.py

@@ -24,7 +24,6 @@
         'data/input/metabolomics_park2016.csv',
         'data/input/unbalanced_metabolites.csv',
         'data/input/bigg_proteins.faa',
-        'data/input/bigg_proteins.dmnd',
         'data/input/equilibrator_compounds.tsv.gz',
         'data/input/refseq_release_201.tsv.gz',
         'data/generated/bigg_gibbs.csv',
@@ -35,13 +34,48 @@
         'data/generated/universe_grampos.xml.gz',
         'data/generated/universe_gramneg.xml.gz',
         'data/generated/universe_archaea.xml.gz',
+        'data/benchmark/media_db.tsv',
+        'data/benchmark/biolog/bsub/biolog_carbon.tsv',
+        'data/benchmark/biolog/bsub/biolog_phosphorus.tsv',
+        'data/benchmark/biolog/bsub/biolog_nitrogen.tsv',
+        'data/benchmark/biolog/bsub/biolog_sulfur.tsv',
+        'data/benchmark/biolog/ecol/biolog_carbon.tsv',
+        'data/benchmark/biolog/ecol/biolog_phosphorus.tsv',
+        'data/benchmark/biolog/ecol/biolog_nitrogen.tsv',
+        'data/benchmark/biolog/ecol/biolog_sulfur.tsv',
+        'data/benchmark/biolog/paer/biolog_carbon.tsv',
+        'data/benchmark/biolog/rsol/biolog_carbon.tsv',
+        'data/benchmark/biolog/rsol/biolog_phosphorus.tsv',
+        'data/benchmark/biolog/rsol/biolog_nitrogen.tsv',
+        'data/benchmark/biolog/rsol/biolog_sulfur.tsv',
+        'data/benchmark/biolog/sone/biolog_carbon.tsv',
+        'data/benchmark/biolog/sone/biolog_nitrogen.tsv',
+        'data/benchmark/essentiality/bsub.tsv',
+        'data/benchmark/essentiality/ecol.tsv',
+        'data/benchmark/essentiality/mgen.tsv',
+        'data/benchmark/essentiality/paer.tsv',
+        'data/benchmark/essentiality/sone.tsv',
+        'data/benchmark/fasta/Bsubtilis_168.faa',
+        'data/benchmark/fasta/Paeruginosa_PAO1.faa',
+        'data/benchmark/fasta/Ecoli_K12_MG1655.faa',
+        'data/benchmark/fasta/M_genitalium_G37.faa',
+        'data/benchmark/fasta/Rsolanacearum_GMI1000.faa',
+        'data/benchmark/fasta/Soneidensis_MR1.faa',
+        'data/benchmark/models/bsub.xml',
+        'data/benchmark/models/rsol.xml',
+        'data/benchmark/models/ecol.xml',
+        'data/benchmark/models/paer.xml',
+        'data/benchmark/models/sone.xml',
+        'data/benchmark/models/mgen.xml',
+        'data/benchmark/results/biolog.tsv',
+        'data/benchmark/results/essentiality.tsv',
     ]
 }
 
 
 setup(
     name='carveme',
-    version='1.3.0',
+    version='1.4.1',
     description="CarveMe: automated metabolic model reconstruction",
     long_description=readme,
     author="Daniel Machado",