Begin test for issue 256: How to get most recent common ancesters and…

… shortest path distance between two terms?

#256

tests/i148_semsim_lin.py

@@ -2,30 +2,35 @@
 """Test for issue 148, Lin Similarity if a term has no annotations"""
 
 
-import os
-import sys
+from os.path import join
+from os.path import dirname
+from os.path import abspath
+from sys import stdout
+
 from itertools import combinations_with_replacement as combo_w_rplc
+
 from goatools.base import get_godag
 from goatools.associations import dnld_annofile
 from goatools.anno.gpad_reader import GpadReader
 #### from goatools.semantic import semantic_similarity
 from goatools.semantic import TermCounts
 #### from goatools.semantic import get_info_content
 #### from goatools.semantic import deepest_common_ancestor
-from goatools.semantic import resnik_sim
+#### from goatools.semantic import resnik_sim
 from goatools.semantic import lin_sim
 #### from goatools.godag.consts import NS2GO
 
-REPO = os.path.join(os.path.dirname(os.path.abspath(__file__)), "..")
+REPO = join(dirname(abspath(__file__)), "..")
 
-def test_i148_semsim_lin(prt=sys.stdout):
+def test_i148_semsim_lin(prt=stdout):
     """Test for issue 148, Lin Similarity if a term has no annotations"""
-    fin_gpad = os.path.join(REPO, 'goa_human.gpad')
+    fin_gpad = join(REPO, 'goa_human.gpad')
     dnld_annofile(fin_gpad, 'gpad')
 
-    godag = get_godag(os.path.join(REPO, "go-basic.obo"), loading_bar=None)
+    godag = get_godag(join(REPO, "go-basic.obo"), loading_bar=None)
     annoobj = GpadReader(fin_gpad, godag=godag)
 
+    # Researcher-provided GO IDs
     goids = [
         'GO:0042581',
         'GO:0101002',
@@ -40,19 +45,20 @@ def test_i148_semsim_lin(prt=sys.stdout):
 
     # Calculate Lin values
     p2v = {frozenset([a, b]): lin_sim(a, b, godag, termcounts) for a, b in combo_w_rplc(goids, 2)}
-    _prt_values(goids, p2v, prt=sys.stdout)
+    _prt_lins_similarity(goids, p2v, prt)
 
 
-def _prt_values(goids, p2v, prt=sys.stdout):
-    """Print values"""
-    prt.write('           {HDR}\n'.format(HDR=' '.join(goids)))
+def _prt_lins_similarity(goids, p2v, prt):
+    """Print Lin's semantic similarity between all researcher provided GO IDs (goids)"""
+    prt.write("\nLin's semantic similarity between researcher-provided GO IDs:\n")
+    prt.write(f'           {" ".join(goids)}\n')
     none = 'None     '
     for go_row in goids:
-        prt.write('{GO} '.format(GO=go_row))
+        prt.write(f'{go_row} ')
         for go_col in goids:
-            val = p2v[frozenset([go_row, go_col])]
-            txt = '{L:<9.6} '.format(L=val) if val is not None else none
-            prt.write('{T:10} '.format(T=txt))
+            lins_val = p2v[frozenset([go_row, go_col])]
+            lins_str = f'{lins_val:<9.6} ' if lins_val is not None else none
+            prt.write(f'{lins_str:10} ')
         prt.write('\n')
 
 

tests/test_i256_mca_dist.py

@@ -0,0 +1,57 @@
+#!/usr/bin/env python
+"""Test Yang's RWC measure added to other semantic similariy measures"""
+
+
+from os.path import join
+from os.path import dirname
+from os.path import abspath
+from os.path import exists
+import collections as cx
+from goatools.obo_parser import GODag
+from goatools.utils import get_b2aset
+from goatools.anno.idtogos_reader import IdToGosReader
+from goatools.semantic import TermCounts
+
+
+REPO = join(dirname(abspath(__file__)), "..")
+
+def test_semantic_similarity():
+    """Test faster version of sematic similarity"""
+    godag = GODag(join(REPO, 'tests/data/yangRWC/fig1b.obo'))
+    name2go = {o.name: o.item_id for o in godag.values()}
+    assoc = _get_id2gos(join(REPO, 'tests/data/yangRWC/fig1b.anno'), godag, name2go)
+    tcntobj = TermCounts(godag, assoc)
+    assert tcntobj.gocnts[name2go['I']] == 20
+    assert tcntobj.gocnts[name2go['L']] == 21
+    assert tcntobj.gocnts[name2go['M']] == 20
+    assert tcntobj.gocnts[name2go['N']] == 20
+
+def _get_id2gos(file_id2gos, godag, name2go):
+    """Get annotations"""
+    if exists(file_id2gos):
+        return IdToGosReader(file_id2gos, godag=godag).get_id2gos('CC')
+    id2num = {
+        name2go['A']:  1,
+        name2go['B']:  1,
+        name2go['C']: 10,
+        name2go['D']: 10,
+        name2go['E']: 10,
+        name2go['F']: 10,
+        name2go['G']: 10,
+        name2go['H']: 10,
+        name2go['I']: 18,
+    }
+    go2genes = cx.defaultdict(set)
+    genenum = 0
+    for goid, qty in id2num.items():
+        for _ in range(qty):
+            go2genes[goid].add(genenum)
+            genenum += 1
+    id2gos = get_b2aset(go2genes)
+    IdToGosReader.wr_id2gos(file_id2gos, id2gos)
+    return id2gos
+
+
+
+if __name__ == '__main__':
+    test_semantic_similarity()

tests/test_yang_fig1b.py

@@ -2,21 +2,24 @@
 """Test Yang's RWC measure added to other semantic similariy measures"""
 
 
-import os
+from os.path import join
+from os.path import dirname
+from os.path import abspath
+from os.path import exists
 import collections as cx
 from goatools.obo_parser import GODag
 from goatools.utils import get_b2aset
 from goatools.anno.idtogos_reader import IdToGosReader
 from goatools.semantic import TermCounts
 
 
-REPO = os.path.join(os.path.dirname(os.path.abspath(__file__)), "..")
+REPO = join(dirname(abspath(__file__)), "..")
 
 def test_semantic_similarity():
     """Test faster version of sematic similarity"""
-    godag = GODag(os.path.join(REPO, 'tests/data/yangRWC/fig1b.obo'))
+    godag = GODag(join(REPO, 'tests/data/yangRWC/fig1b.obo'))
     name2go = {o.name: o.item_id for o in godag.values()}
-    assoc = _get_id2gos(os.path.join(REPO, 'tests/data/yangRWC/fig1b.anno'), godag, name2go)
+    assoc = _get_id2gos(join(REPO, 'tests/data/yangRWC/fig1b.anno'), godag, name2go)
     tcntobj = TermCounts(godag, assoc)
     assert tcntobj.gocnts[name2go['I']] == 20
     assert tcntobj.gocnts[name2go['L']] == 21
@@ -25,7 +28,7 @@ def test_semantic_similarity():
 
 def _get_id2gos(file_id2gos, godag, name2go):
     """Get annotations"""
-    if os.path.exists(file_id2gos):
+    if exists(file_id2gos):
         return IdToGosReader(file_id2gos, godag=godag).get_id2gos('CC')
     id2num = {
         name2go['A']:  1,