def test7FPS(self):
bv = DataStructs.ExplicitBitVect(32)
bv.SetBit(0)
bv.SetBit(1)
bv.SetBit(17)
bv.SetBit(23)
bv.SetBit(31)
self.assertEqual(DataStructs.BitVectToFPSText(bv), "03008280")
bv2 = DataStructs.CreateFromFPSText("03008280")
self.assertEqual(bv, bv2)
self.assertRaises(ValueError, lambda: DataStructs.CreateFromFPSText("030082801"))
bv2 = DataStructs.CreateFromFPSText("")
self.assertEqual(bv2.GetNumBits(), 0)
def testBitVectorMaxMin4(self):
# threshold tests
fname = os.path.join(RDConfig.RDBaseDir, 'Code', 'SimDivPickers',
'Wrap', 'test_data', 'chembl_cyps.head.fps')
fps = []
with open(fname) as infil:
for line in infil:
fp = DataStructs.CreateFromFPSText(line.strip())
fps.append(fp)
mmp = rdSimDivPickers.MaxMinPicker()
ids, threshold = mmp.LazyBitVectorPickWithThreshold(fps,
len(fps),
20,
-1.0,
seed=42)
self.assertEqual(list(ids), [
374, 720, 690, 339, 875, 842, 404, 725, 120, 385, 115, 868, 630,
881, 516, 497, 412, 718, 869, 407
])
self.assertAlmostEqual(threshold, 0.8977, 4)
ids, threshold = mmp.LazyBitVectorPickWithThreshold(fps,
len(fps),
20,
0.91,
seed=42)
self.assertEqual(
list(ids),
[374, 720, 690, 339, 875, 842, 404, 725, 120, 385, 115, 868, 630])
self.assertTrue(threshold >= 0.91)
def testBitVectorMaxMin3(self):
fname = os.path.join(RDConfig.RDBaseDir, 'Code', 'SimDivPickers',
'Wrap', 'test_data', 'chembl_cyps.head.fps')
fps = []
with open(fname) as infil:
for line in infil:
fp = DataStructs.CreateFromFPSText(line.strip())
fps.append(fp)
mmp = rdSimDivPickers.MaxMinPicker()
ids = list(mmp.LazyBitVectorPick(fps, len(fps), 20, seed=42))
self.assertEqual(ids, [
374, 720, 690, 339, 875, 842, 404, 725, 120, 385, 115, 868, 630,
881, 516, 497, 412, 718, 869, 407
])
ids = list(
mmp.LazyBitVectorPick(fps,
len(fps),
20,
firstPicks=[374, 720, 690, 339, 875],
seed=42))
self.assertEqual(ids, [
374, 720, 690, 339, 875, 842, 404, 725, 120, 385, 115, 868, 630,
881, 516, 497, 412, 718, 869, 407
])
def test9MultiFPBReaderEdges(self):
basen = os.path.join(RDConfig.RDBaseDir, 'Code', 'DataStructs',
'testData')
mfpbr = DataStructs.MultiFPBReader()
mfpbr.Init()
fps = "0000000000404000100000001000040000300040222000002004000240000020000000"+\
"8200010200000090000024040860070044003214820000220401054008018000226000"+\
"4800800140000042000080008008020482400000200410800000300430200800400000"+\
"0000080a0000800400010c800200648818100010880040"
ebv = DataStructs.CreateFromFPSText(fps)
bytes = DataStructs.BitVectToBinaryText(ebv)
nbrs = mfpbr.GetTanimotoNeighbors(bytes, threshold=0.6)
self.assertEqual(len(nbrs), 0)
def test8MultiFPBReaderContainsInitOnSearch(self):
basen = os.path.join(RDConfig.RDBaseDir, 'Code', 'DataStructs',
'testData')
mfpbr = DataStructs.MultiFPBReader(initOnSearch=True)
self.assertEqual(
mfpbr.AddReader(
DataStructs.FPBReader(
os.path.join(basen, "zinc_random200.1.patt.fpb"))), 1)
self.assertEqual(
mfpbr.AddReader(
DataStructs.FPBReader(
os.path.join(basen, "zinc_random200.2.patt.fpb"))), 2)
self.assertEqual(
mfpbr.AddReader(
DataStructs.FPBReader(
os.path.join(basen, "zinc_random200.3.patt.fpb"))), 3)
self.assertEqual(
mfpbr.AddReader(
DataStructs.FPBReader(
os.path.join(basen, "zinc_random200.4.patt.fpb"))), 4)
fps = "40081010824820021000500010110410003000402b20285000a4040240010030050000"+\
"080001420040009000003d04086007080c03b31d920004220400074008098010206080"+\
"00488001080000c64002a00080000200024c2000602410049200340820200002400010"+\
"02200106090401056801080182006088101000088a0048"
ebv = DataStructs.CreateFromFPSText(fps)
bytes = DataStructs.BitVectToBinaryText(ebv)
nbrs = mfpbr.GetContainingNeighbors(bytes, numThreads=4)
self.assertEqual(len(nbrs), 9)
self.assertEqual(nbrs[0][0], 160)
self.assertEqual(nbrs[0][1], 0)
self.assertEqual(nbrs[1][0], 163)
self.assertEqual(nbrs[1][1], 0)
self.assertEqual(nbrs[2][0], 170)
self.assertEqual(nbrs[2][1], 0)
self.assertEqual(nbrs[3][0], 180)
self.assertEqual(nbrs[3][1], 2)
self.assertEqual(nbrs[4][0], 182)
self.assertEqual(nbrs[4][1], 3)
self.assertEqual(nbrs[5][0], 185)
self.assertEqual(nbrs[5][1], 0)
self.assertEqual(nbrs[6][0], 189)
self.assertEqual(nbrs[6][1], 0)
self.assertEqual(nbrs[7][0], 192)
self.assertEqual(nbrs[7][1], 3)
self.assertEqual(nbrs[8][0], 193)
self.assertEqual(nbrs[8][1], 0)
def testBitVectorLeader1(self):
# threshold tests
fname = os.path.join(RDConfig.RDBaseDir, 'Code', 'SimDivPickers',
'Wrap', 'test_data', 'chembl_cyps.head.fps')
fps = []
with open(fname) as infil:
for line in infil:
fp = DataStructs.CreateFromFPSText(line.strip())
fps.append(fp)
mmp = rdSimDivPickers.LeaderPicker()
thresh = 0.8
ids = mmp.LazyBitVectorPick(fps, len(fps), thresh)
self.assertEqual(len(ids), 146)
for i in range(len(ids)):
for j in range(i):
self.assertGreaterEqual(
1 -
DataStructs.TanimotoSimilarity(fps[ids[i]], fps[ids[j]]),
thresh)
thresh = 0.9
ids = mmp.LazyBitVectorPick(fps, len(fps), thresh)
self.assertEqual(len(ids), 14)
for i in range(len(ids)):
for j in range(i):
self.assertGreaterEqual(
1 -
DataStructs.TanimotoSimilarity(fps[ids[i]], fps[ids[j]]),
thresh)
ids = mmp.LazyBitVectorPick(fps, len(fps), thresh, pickSize=10)
self.assertEqual(len(ids), 10)
for i in range(len(ids)):
for j in range(i):
self.assertGreaterEqual(
1 -
DataStructs.TanimotoSimilarity(fps[ids[i]], fps[ids[j]]),
thresh)
def test6MultiFPBReaderTani(self):
basen = os.path.join(RDConfig.RDBaseDir, 'Code', 'DataStructs',
'testData')
mfpbr = DataStructs.MultiFPBReader()
self.assertEqual(
mfpbr.AddReader(
DataStructs.FPBReader(
os.path.join(basen, "zinc_random200.1.patt.fpb"))), 1)
self.assertEqual(
mfpbr.AddReader(
DataStructs.FPBReader(
os.path.join(basen, "zinc_random200.2.patt.fpb"))), 2)
self.assertEqual(
mfpbr.AddReader(
DataStructs.FPBReader(
os.path.join(basen, "zinc_random200.3.patt.fpb"))), 3)
self.assertEqual(
mfpbr.AddReader(
DataStructs.FPBReader(
os.path.join(basen, "zinc_random200.4.patt.fpb"))), 4)
mfpbr.Init()
self.assertEqual(mfpbr.GetNumBits(), 1024)
self.assertEqual(len(mfpbr), 4)
fps = "0000000000404000100000001000040000300040222000002004000240000020000000"+\
"8200010200000090000024040860070044003214820000220401054008018000226000"+\
"4800800140000042000080008008020482400000200410800000300430200800400000"+\
"0000080a0000800400010c800200648818100010880040"
ebv = DataStructs.CreateFromFPSText(fps)
bytes = DataStructs.BitVectToBinaryText(ebv)
nbrs = mfpbr.GetTanimotoNeighbors(bytes, threshold=0.6)
self.assertEqual(len(nbrs), 6)
self.assertAlmostEqual(nbrs[0][0], 0.66412, 4)
self.assertEqual(nbrs[0][1], 0)
self.assertEqual(nbrs[0][2], 3)
self.assertAlmostEqual(nbrs[1][0], 0.65289, 4)
self.assertEqual(nbrs[1][1], 1)
self.assertEqual(nbrs[1][2], 2)
self.assertAlmostEqual(nbrs[2][0], 0.64341, 4)
self.assertEqual(nbrs[2][1], 2)
self.assertEqual(nbrs[2][2], 1)
self.assertAlmostEqual(nbrs[3][0], 0.61940, 4)
self.assertEqual(nbrs[3][1], 1)
self.assertEqual(nbrs[3][2], 0)
self.assertAlmostEqual(nbrs[4][0], 0.61905, 4)
self.assertEqual(nbrs[4][1], 0)
self.assertEqual(nbrs[4][2], 0)
self.assertAlmostEqual(nbrs[5][0], 0.61344, 4)
self.assertEqual(nbrs[5][1], 0)
self.assertEqual(nbrs[5][2], 1)
# test multi-threaded (won't do anything if the RDKit isn't compiled with threads support)
nbrs = mfpbr.GetTanimotoNeighbors(bytes, threshold=0.6, numThreads=4)
self.assertEqual(len(nbrs), 6)
self.assertAlmostEqual(nbrs[0][0], 0.66412, 4)
self.assertEqual(nbrs[0][1], 0)
self.assertEqual(nbrs[0][2], 3)
self.assertAlmostEqual(nbrs[1][0], 0.65289, 4)
self.assertEqual(nbrs[1][1], 1)
self.assertEqual(nbrs[1][2], 2)
self.assertAlmostEqual(nbrs[2][0], 0.64341, 4)
self.assertEqual(nbrs[2][1], 2)
self.assertEqual(nbrs[2][2], 1)
self.assertAlmostEqual(nbrs[3][0], 0.61940, 4)
self.assertEqual(nbrs[3][1], 1)
self.assertEqual(nbrs[3][2], 0)
self.assertAlmostEqual(nbrs[4][0], 0.61905, 4)
self.assertEqual(nbrs[4][1], 0)
self.assertEqual(nbrs[4][2], 0)
self.assertAlmostEqual(nbrs[5][0], 0.61344, 4)
self.assertEqual(nbrs[5][1], 0)
self.assertEqual(nbrs[5][2], 1)
def transform(infile, outfile, outformat, delimiter, numericID, numlines,
verbose, debug):
ins = open(infile)
outs = open(outfile, 'w')
# inform
if debug or verbose:
print(
"About to read rdkit fingerprint file {} and transform to bivector file ... {}"
.format(infile, outfile))
# run
nid = numericID
ctr = 0
# vlen = 0
for line in ins:
line.replace(r'\r', '')
# if comment line ignore
if line[0] == '#':
if debug:
print(line)
continue
# split line
chunky_line = string.split(line, delimiter)
# get rid of the newline character if it exists
if chunky_line[-1][-1] == '\n' or chunky_line[-1][-1] == '^M':
chunky_line[-1] = chunky_line[-1][:-1]
# get the fp needed
fp = DataStructs.CreateFromFPSText(chunky_line[0])
bs = fp.ToBitString()
if nid != -99999999:
pcn = nid
nid += 1
else:
try:
pcn = chunky_line[1]
except:
#raise IOError("Line " + str(ctr) + " missing id element...")
print("Line " + str(ctr) + " missing id element...")
continue
# write
if outformat:
outs.write("$SMI<C>\n")
outs.write("PCN<" + str(pcn) + ">\n")
outs.write("FPRDK<" + bs + ">\n")
outs.write("|\n")
else:
outs.write(bs + " " + str(pcn) + "\n")
if debug:
print(len(bs))
if verbose and ctr % numlines == 0:
print("Processed {} fingerprints...".format(ctr))
ctr += 1
# inform
if debug or verbose:
print("\nRead/transformed/wrote {} fingerprints.".format(ctr))
ins.close()
return
