Msatpcorrection

.gitignore

@@ -1,4 +1,5 @@
 .DS_Store
+@eaDir
 
 # Byte-compiled / optimized / DLL files
 __pycache__/

modelseedpy/__init__.py

@@ -27,7 +27,7 @@
 c_handler.setFormatter(c_format)
 logger.addHandler(c_handler)
 if config.get("logging","log_file") == "yes":
-    f_handler = logging.FileHandler(config.get("logging","filename"),mode="w")
+    f_handler = logging.FileHandler(config.get("logging","filename"), mode="a")
     f_handler.setLevel(logging_hash[config.get("logging","file_level")])
     f_format = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
     f_handler.setFormatter(f_format)

modelseedpy/core/msgenome.py

@@ -1,10 +1,9 @@
 import logging
-logger = logging.getLogger(__name__)
-
 import re
 import copy  # !!! the import is never used
 from cobra.core.dictlist import DictList
 
+logger = logging.getLogger(__name__)
 
 
 def normalize_role(s):
@@ -13,15 +12,12 @@ def normalize_role(s):
     s = re.sub('[\W_]+', '', s)
     return s
 
-#Static factory functions:
-
-#def build_from_kbase_gto:
-
 
 def read_fasta(f, split='|', h_func=None):
     with open(f, 'r') as fh:
         return parse_fasta_str(fh.read(), split, h_func)
 
+
 def parse_fasta_str(faa_str, split='|', h_func=None):
     features = []
     seq = None
@@ -48,23 +44,54 @@ def parse_fasta_str(faa_str, split='|', h_func=None):
 
 
 class MSFeature:
+
     def __init__(self, feature_id, sequence, description=None):
-        self.id = feature_id; self.seq = sequence
+        """
+
+        @param feature_id: identifier for the protein coding feature
+        @param sequence: protein sequence
+        @param description: description of the feature
+        """
+
+        self.id = feature_id
+        self.seq = sequence
         self.description = description  # temporary replace with proper parsing
         self.ontology_terms = {}
         self.aliases = []
 
     def add_ontology_term(self, ontology_term, value):
+        """
+        Add functional term to the feature
+
+        @param ontology_term: type of the ontology (e.g., RAST, EC)
+        @param value: value for the ontology (e.g., pyruvate kinase)
+        """
         if ontology_term not in self.ontology_terms:
             self.ontology_terms[ontology_term] = []
         if value not in self.ontology_terms[ontology_term]:
             self.ontology_terms[ontology_term].append(value)
 
 
 class MSGenome:
+
     def __init__(self):
         self.features = DictList()
 
+    def add_features(self, feature_list: list):
+        """
+
+        :param feature_list:
+        :return:
+        """
+        duplicates = list(filter(lambda o: o.id in self.features, feature_list))
+        if len(duplicates) > 0:
+            raise ValueError(f"unable to add features {duplicates} already present in the genome")
+
+        for f in feature_list:
+            f._genome = self
+
+        self.features += feature_list
+
     @staticmethod
     def from_fasta(filename, contigs=0, split='|', h_func=None):  # !!! the contigs argument is never used
         genome = MSGenome()
@@ -83,10 +110,10 @@ def from_protein_sequences_hash(sequences):
         return genome
 
     def alias_hash(self):
-        return {alias:gene for gene in self.features for alias in gene.aliases}
+        return {alias: gene for gene in self.features for alias in gene.aliases}
 
-    def search_for_gene(self,query):
+    def search_for_gene(self, query):
         if query in self.features:
             return self.features.get_by_id(query)
         aliases = self.alias_hash()
-        return aliases[query] if query in aliases else None
+        return aliases[query] if query in aliases else None

modelseedpy/core/msgenomeclassifier.py

@@ -1,4 +1,5 @@
 from modelseedpy.ml.predict_phenotype import create_indicator_matrix
+from modelseedpy.core.msgenome import MSGenome
 
 
 class MSGenomeClassifier:
@@ -22,7 +23,10 @@ def extract_features_from_genome(genome, ontology_term):
         return {'genome': list(features)}
 
     def classify(self, genome_or_roles, ontology_term='RAST'):
-        if isinstance(genome_or_roles,"MSGenome"):
+        """
+        param genome_or_roles:
+        """
+        if isinstance(genome_or_roles, MSGenome):
             genome_or_roles = self.extract_features_from_genome(genome_or_roles, ontology_term)
         indicator_df, master_role_list = create_indicator_matrix(genome_or_roles, self.features)
         predictions_numerical = self.model.predict(indicator_df[master_role_list].values)

modelseedpy/core/msmedia.py

@@ -3,6 +3,7 @@
 
 logger = logging.getLogger(__name__)
 
+
 class MediaCompound:
 
     def __init__(self, compound_id, lower_bound, upper_bound, concentration=None):
@@ -23,16 +24,18 @@ def minFlux(self):
 
 
 class MSMedia:
-    def __init__(self, media_id):
+
+    def __init__(self, media_id, name=""):
         self.id = media_id
+        self.name = name
         self.mediacompounds = DictList()
 
     @staticmethod
     def from_dict(media_dict):
         """
         Either dict with exchange bounds (example: {'cpd00027': (-10, 1000)}) or
         just absolute value of uptake (example: {''cpd00027': 10})
-        :param d:
+        :param media_dict:
         :return:
         """
         media = MSMedia('media')

modelseedpy/fbapkg/gapfillingpkg.py

@@ -285,7 +285,8 @@ def extend_model_with_template_metabolites(self, template, index='0'):
         for template_compound in template.compcompounds:
             compartment = template_compound.compartment
             compartment_index = "0" if compartment == 'e' else index
-            cobra_metabolite = self.convert_template_compound(template_compound, compartment_index, template)  # TODO: move function out
+            cobra_metabolite = template_compound.to_metabolite(compartment_index)
+            #cobra_metabolite = self.convert_template_compound(template_compound, compartment_index, template)  # TODO: move function out
             if cobra_metabolite.id not in self.model.metabolites and cobra_metabolite.id not in new_metabolites:
                 new_metabolites[cobra_metabolite.id] = cobra_metabolite
                 #self.model.add_metabolites([cobra_metabolite])
@@ -302,6 +303,8 @@ def extend_model_with_template_metabolites(self, template, index='0'):
 
     # Possible new function to add to the KBaseFBAModelToCobraBuilder to extend a model with a template for gapfilling for a specific index
     def extend_model_with_template_for_gapfilling(self, template, index):
+        logger.debug(f'extend model with template: {template}, index: {index}')
+
         new_reactions = {}
         new_penalties = dict()
 

setup.py

@@ -31,6 +31,9 @@
         "matplotlib >= 3.0.0",
         "pyeda"
     ],
+    tests_require=[
+        "pytest",
+    ],
     project_urls={
         'Documentation': 'https://modelseedpy.readthedocs.io/en/stable/',
         'Issues': 'https://github.com/ModelSEED/ModelSEEDpy/issues',