updated bio3graph library and package data

workflows/bio3graph/library.py

@@ -5,7 +5,7 @@ Bio3graph triplet extractor.
 """
 
 
-def bio3graph_create_document(input_dict):
+def bio3graph_create_document_from_file(input_dict):
     from triplet_extractor import data_structures as ds
     fn = input_dict['docfile']
     doc = ds.Document()
@@ -13,6 +13,16 @@ def bio3graph_create_document(input_dict):
     return {'document': doc}
 
 
+def bio3graph_create_document_from_string(input_dict):
+    from triplet_extractor import data_structures as ds
+    from unidecode import unidecode
+
+    docstr = input_dict['docstr']
+    doc = ds.Document()
+    doc.loadString(unidecode(docstr))
+    return {'document': doc}
+
+
 def bio3graph_split_sentences(input_dict):
     from triplet_extractor import data_structures as ds
     doc = input_dict['document']
@@ -62,6 +72,29 @@ def bio3graph_build_default_vocabulary(input_dict):
     return {'vocabulary': voc}
 
 
+def bio3graph_build_default_vocabulary_custom_compounds(input_dict):
+    from triplet_extractor import tripletExtraction as te
+    from os.path import normpath, join, dirname
+    from StringIO import StringIO
+
+    comp = input_dict['compounds']
+
+    dname = normpath(dirname(__file__))
+    voc = te.Vocabulary()
+    s = StringIO()
+    s.write(comp)
+    s.flush()
+    voc.loadCompounds_file(s)
+    voc.loadPredicates_files(activationFname=join(dname, 'triplet_extractor/vocabulary/activation.lst'),
+                             activations_rotate=join(dname, 'triplet_extractor/vocabulary/activation_rotate.lst'),
+                             inhibitionFname=join(dname, 'triplet_extractor/vocabulary/inhibition.lst'),
+                             bindingFname=join(dname, 'triplet_extractor/vocabulary/binding.lst'),
+                             activationFname_passive=join(dname, 'triplet_extractor/vocabulary/activation_pas.lst'),
+                             inhibitionFname_passive=join(dname, 'triplet_extractor/vocabulary/inhibition_pas.lst'),
+                             bindingFname_passive=join(dname, 'triplet_extractor/vocabulary/binding_pas.lst'))
+    return {'vocabulary': voc}
+
+
 def bio3graph_extract_triplets(input_dict):
     from triplet_extractor import tripletExtraction as te
     voc = input_dict['vocabulary']
@@ -152,3 +185,124 @@ def bio3graph_reset_colours(input_dict):
     nwx = copy.deepcopy(input_dict['network'])
     gop.reset_edge_colors(nwx)
     return {'network': nwx}
+
+
+def bio3graph_search_pubmed(input_dict):
+    from NCBI import NCBI_Extractor
+
+    q = input_dict['query']
+    if not q:
+        raise ValueError('Empty PubMed query!')
+
+    nhits = input_dict['maxHits']
+    maxHits = int(nhits) if nhits else 0
+
+    ex = NCBI_Extractor()
+    ids = ex.query(q, maxHits=maxHits)
+    return {'pmids': ids}
+
+
+def bio3graph_filter_open_access(input_dict):
+    import cPickle
+    from os.path import normpath, join, dirname
+
+    oa = cPickle.load(open(normpath(join(dirname(__file__), 'data/OA_dict.pickle')), 'rb'))
+    ids = input_dict['ids']
+    result = filter(lambda(x): True if x in oa else False, ids)
+    return {'oa_ids': result}
+
+
+def bio3graph_get_xmls(input_dict):
+    from NCBI import NCBI_Extractor
+
+    ids = input_dict['id_list']
+    if not isinstance(ids, list):
+        ids = list(ids)
+
+    result = []
+    a = NCBI_Extractor()
+    for did in ids:
+        result.append(a.getXML(did))
+    return {'xmls': result}
+
+
+def bio3graph_get_fulltexts(input_dict):
+    from NCBI import NCBI_Extractor
+
+    ids = input_dict['id_list']
+    if not isinstance(ids, list):
+        ids = list(ids)
+
+    result = []
+    a = NCBI_Extractor()
+    for did in ids:
+        doc = a.getFulltext(did)
+        ft = '%s\n%s\n%s\n' % (doc.title, doc.abstract, doc.body)
+        result.append(ft)
+    return {'fulltexts': result}
+
+
+def bio3graph_map_entrez_to_ncbi_symbol(input_dict):
+    import cPickle
+    from os.path import normpath, join, dirname
+
+    e2symb = cPickle.load(open(normpath(join(dirname(__file__), 'data/entrez2symbol.pickle')), 'rb'))
+    glist = input_dict['genes']
+    result = []
+    for g in glist:
+        g = g.replace('EntrezGene:', '')
+        g = int(g)
+        symb = e2symb.get(g)
+        if symb:
+            result.append(symb)
+    return {'gene_symbols': result}
+
+
+def bio3graph_get_gene_synonyms_from_GPSDB(input_dict):
+    from GPSDB_synonyms import Synonym_extractor
+
+    glist = input_dict['gene_symbols']
+    a = Synonym_extractor()
+    result = a.get_geneset_synonyms(glist)
+    return {'gene_synonyms': result}
+
+
+def bio3graph_construct_compounds_from_gene_synonyms(input_dict):
+    import csv
+    from StringIO import StringIO
+
+    syns = input_dict['gene_synonyms']
+    s = StringIO()
+    w = csv.writer(s)
+    for g in syns:
+        elts = [g] + syns[g]
+        w.writerow(elts)
+    s.flush()
+    result = s.getvalue()
+    return {'compounds_csv': result}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

workflows/bio3graph/triplet_extractor/tripletExtraction.py

@@ -49,8 +49,11 @@ def readEntitiesLnDoc_csv(fname):
     Each line is either empty, or contains synonym(s) for some entity.
     Returns a dictionary where keys are base names and values are synonyms.
     '''
+    if isinstance(fname, StringIO.StringIO):
+        reader = csv.reader(fname, skipinitialspace=True)
+    else:
+        reader = csv.reader(open(fname), skipinitialspace=True)
 
-    reader = csv.reader(open(fname), skipinitialspace=True)
     entities = {}
     for row in reader:
         if len(row) == 0:
@@ -590,7 +593,8 @@ class Vocabulary(object):
 
 
     def loadCompounds_stringIO(self, compString):
-        compounds = readEntitiesLnDoc_stringIO(compString)
+#        compounds = readEntitiesLnDoc_stringIO(com
+        compounds = readEntitiesLnDoc_csv(compString)
         self._buildCompoundsStructures(compounds)
     #end