nuc ups

Author: Fxe

modelseedpy/core/msbuilder.py

@@ -287,7 +287,7 @@ def build_gpr(cpx_gene_role):
 
 class MSBuilder:
     def __init__(
-        self, genome, template=None, name=None, ontology_term="RAST", index="0"
+        self, genome, template=None, name=None, ontology_term="RAST", index="0", template_core=None,
     ):
         """
 
@@ -303,7 +303,7 @@ def __init__(
         self.name = name
         self.genome = genome
         self.template = template
-        self.template_core = None
+        self.template_core = template_core
         self.genome_class = None
         self.search_name_to_genes, self.search_name_to_original = _aaaa(
             genome, ontology_term

modelseedpy/core/msgenome.py

@@ -1,24 +1,53 @@
 # -*- coding: utf-8 -*-
 import logging
 import re
+from typing import Iterable
 from cobra.core.dictlist import DictList
 
 logger = logging.getLogger(__name__)
 
 DEFAULT_SPLIT = " "
 
 
-def to_fasta(features, filename, line_size=80, fn_header=None):
+class MSFeature:
+    def __init__(self, feature_id, sequence, description=None, aliases=None):
+        """
+
+        @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 = 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)
+
+
+def to_fasta(features: Iterable[MSFeature], filename, line_size=80, fn_header=None):
     with open(filename, "w") as fh:
         for feature in features:
             if feature.seq:
-                h = f">{feature.id}\n"
+                h = f">{feature.id}{DEFAULT_SPLIT}{feature.description}\n"
                 if fn_header:
                     h = fn_header(feature)
                 fh.write(h)
                 _seq = feature.seq
                 lines = [
-                    _seq[i : i + line_size] + "\n"
+                    _seq[i: i + line_size] + "\n"
                     for i in range(0, len(_seq), line_size)
                 ]
                 for line in lines:
@@ -134,34 +163,6 @@ def extract_features(faa_str, split=DEFAULT_SPLIT, h_func=None):
     return features
 
 
-class MSFeature:
-    def __init__(self, feature_id, sequence, description=None, aliases=None):
-        """
-
-        @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 = 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()

modelseedpy/core/rast_client.py

@@ -100,7 +100,7 @@ def annotate_protein_sequence(self, protein_id: str, protein_seq: str):
     def annotate_protein_batch(self, protein_batch: dict):
         protein_annotations = {}
         features = [
-            {"id": id, "protein_translation": seq} for id, seq in protein_batch.items()
+            {"id": _id, "protein_translation": seq} for _id, seq in protein_batch.items()
         ]
         params = [{"features": features}, {"stages": self.stages}]
         result = self.rpc_client.call("GenomeAnnotation.run_pipeline", params)