SDF input file reader functional (19584163) · Commits · 钟慕尧 / deepchem

datasets/gdb1k.sdf

0 → 100644

+33910 −0

File added.

Preview size limit exceeded, changes collapsed.

datasets/gdb1k.sdf.csv

0 → 100644

+992 −0

Original line number	Diff line number	Diff line
		atomization_energy
		-596.35
		-959.62
		-2063.19
		-1241.88
		-1838.28
		-1062.9
		-1525.86
		-1521.04
		-1453.58
		-1571.76
		-994.68
		-1105.98
		-1116.89
		-1579.2
		-1774.79
		-2061.07
		-1123.24
		-1405.32
		-1554.03
		-1255.97
		-2190.06
		-2049.55
		-1477.16
		-1718.87
		-1260.78
		-1531.53
		-1370.22
		-1803.45
		-1545.31
		-1512.8
		-2051.87
		-1331.28
		-1608.25
		-1600.78
		-861.62
		-816.7
		-1751.2
		-1544.61
		-1459.54
		-1203.34
		-1788.78
		-1323.8
		-1847.46
		-1131.64
		-1215.13
		-2064.75
		-1173.81
		-1342.31
		-1223.35
		-980.76
		-1758.43
		-1316.15
		-1781.77
		-1006.46
		-1388.27
		-1063.44
		-1174.42
		-1119.26
		-1773.29
		-1600.27
		-1911.31
		-1757.3
		-861.73
		-1711.1
		-998.84
		-1058.82
		-2055.09
		-1217.33
		-1624.43
		-1920.45
		-1234.05
		-1689.49
		-1892.91
		-1672.1
		-1293.47
		-1440.44
		-1667.71
		-2047.58
		-1132.01
		-1655.54
		-1117.96
		-1367.
		-1210.47
		-1765.27
		-1646.43
		-1779.9
		-1600.11
		-1726.38
		-1395.15
		-1315.13
		-1101.34
		-1465.22
		-1416.05
		-1018.6
		-1713.92
		-1900.69
		-1770.53
		-1326.99
		-1059.31
		-1168.84
		-1425.6
		-1446.98
		-1563.08
		-1291.64
		-1549.15
		-963.04
		-1679.43
		-1325.94
		-1174.94
		-1569.44
		-1125.81
		-1270.06
		-1844.68
		-1557.43
		-1097.08
		-1455.85
		-1454.38
		-1698.66
		-1132.96
		-1551.72
		-1167.69
		-1688.27
		-1720.81
		-1527.51
		-1474.1
		-1901.45
		-1785.27
		-1471.27
		-1516.64
		-1084.82
		-1466.12
		-1413.82
		-1393.45
		-1729.65
		-803.46
		-926.22
		-1104.19
		-1131.83
		-1160.48
		-1262.44
		-1734.73
		-1152.05
		-980.82
		-1305.81
		-1418.76
		-1003.69
		-1540.62
		-1906.84
		-1617.81
		-1928.68
		-1162.03
		-1123.32
		-1332.39
		-1633.76
		-1396.44
		-1070.27
		-1915.38
		-1501.14
		-1669.35
		-1236.4
		-1574.11
		-1226.73
		-1989.7
		-1319.45
		-1466.33
		-1177.01
		-1212.42
		-1585.4
		-1938.48
		-993.7
		-1121.33
		-1018.41
		-1242.45
		-1528.92
		-1013.4
		-1610.81
		-1254.21
		-1088.85
		-1242.47
		-1763.12
		-1732.12
		-1158.53
		-1436.69
		-1364.02
		-1062.97
		-1705.49
		-1446.21
		-1092.62
		-1521.71
		-1902.7
		-1229.27
		-1662.1
		-1210.27
		-1169.19
		-1189.09
		-1479.3
		-1442.18
		-1392.3
		-1250.37
		-1797.33
		-1095.1
		-1318.51
		-1313.49
		-1527.09
		-1258.46
		-1404.09
		-1615.95
		-1170.42
		-1154.32
		-1284.37
		-1249.45
		-1328.89
		-1338.18
		-1936.69
		-1448.78
		-1160.57
		-1163.14
		-831.06
		-1253.44
		-871.19
		-1553.4
		-1120.22
		-1105.67
		-1450.54
		-1942.37
		-1910.33
		-1464.45
		-1220.93
		-1105.28
		-1763.56
		-1208.65
		-2057.64
		-1931.62
		-1727.44
		-1293.13
		-1508.99
		-1270.08
		-1906.02
		-850.55
		-1541.73
		-1602.07
		-1455.97
		-1515.17
		-1659.61
		-1770.03
		-1407.43
		-1585.07
		-1755.19
		-1450.11
		-1836.94
		-956.51
		-1318.45
		-1457.1
		-1453.52
		-1783.46
		-2191.74
		-1400.29
		-1113.95
		-1277.37
		-955.38
		-972.49
		-1081.42
		-1096.2
		-1362.56
		-944.51
		-1986.42
		-1469.08
		-725.93
		-1865.45
		-1240.08
		-1642.18
		-1926.84
		-1594.95
		-947.54
		-1286.29
		-1873.28
		-1683.09
		-1483.76
		-1472.6
		-1720.2
		-1066.53
		-1868.72
		-1118.53
		-1323.38
		-1794.58
		-1717.96
		-1814.1
		-953.49
		-1890.32
		-1988.56
		-1745.43
		-1802.28
		-1834.45
		-1200.23
		-1365.93
		-2069.4
		-1254.7
		-1759.32
		-1050.2
		-1231.52
		-2047.11
		-1749.39
		-1285.28
		-1033.09
		-1144.85
		-1263.4
		-1157.45
		-1547.55
		-1360.84
		-1009.94
		-1356.74
		-958.05
		-1632.72
		-1473.27
		-1488.23
		-1109.98
		-1664.11
		-1409.33
		-1395.52
		-1259.44
		-1120.22
		-1428.79
		-1403.68
		-1040.33
		-1693.64
		-1697.39
		-1303.56
		-1371.71
		-1161.23
		-1399.24
		-1692.04
		-1195.4
		-1792.73
		-1322.92
		-1142.8
		-1146.75
		-1309.94
		-1317.5
		-1333.46
		-1143.79
		-1614.03
		-1157.45
		-1729.98
		-1507.23
		-1531.9
		-902.44
		-1991.71
		-1704.8
		-1230.86
		-1686.99
		-1656.48
		-1199.56
		-1582.33
		-981.05
		-1739.78
		-1166.9
		-1406.47
		-1922.87
		-1391.77
		-1329.81
		-810.17
		-1251.77
		-1545.88
		-1299.08
		-1560.54
		-1573.35
		-1131.72
		-1335.4
		-1073.94
		-1257.13
		-1571.36
		-1008.49
		-1854.7
		-1622.33
		-1049.76
		-1760.86
		-1579.68
		-1749.78
		-1420.72
		-1026.2
		-1315.05
		-1029.75
		-1776.14
		-1652.25
		-1454.72
		-1183.71
		-1841.79
		-1207.59
		-1425.91
		-1457.72
		-1387.21
		-1664.72
		-1498.16
		-1018.13
		-1916.08
		-1065.62
		-1383.1
		-1576.15
		-1592.41
		-1076.42
		-1006.35
		-1599.57
		-1762.25
		-1543.15
		-1319.61
		-914.2
		-1423.73
		-1355.35
		-1130.81
		-1845.02
		-1300.91
		-1555.23
		-1855.61
		-1249.87
		-1216.27
		-1153.75
		-1311.6
		-1703.61
		-1289.94
		-1193.68
		-677.16
		-1638.72
		-1402.97
		-1849.75
		-1377.86
		-1358.14
		-1019.74
		-1648.85
		-1891.76
		-1324.08
		-1747.8
		-1112.08
		-1867.98
		-2052.19
		-1861.52
		-1145.6
		-1315.9
		-1676.62
		-1279.51
		-1899.42
		-1255.76
		-1077.68
		-1118.32
		-1179.84
		-1461.74
		-1904.2
		-1170.86
		-1014.79
		-1253.18
		-1846.69
		-1485.76
		-1894.91
		-1805.48
		-1306.67
		-1842.83
		-1754.1
		-1987.81
		-1182.59
		-1276.17
		-1619.05
		-1626.77
		-667.28
		-1267.12
		-973.32
		-1580.88
		-1858.76
		-1766.88
		-1353.07
		-1791.28
		-1159.28
		-1421.56
		-1184.76
		-1930.18
		-1346.56
		-1752.81
		-1397.5
		-1127.5
		-966.71
		-1559.65
		-1468.38
		-1160.91
		-860.33
		-1148.1
		-1458.12
		-1288.68
		-1933.2
		-1533.55
		-1010.86
		-1738.28
		-1909.06
		-925.91
		-1192.89
		-1740.7
		-1924.09
		-1324.02
		-1104.57
		-1452.21
		-1382.22
		-1707.83
		-1467.11
		-1267.25
		-1602.41
		-1331.79
		-1637.73
		-1359.16
		-1042.24
		-1131.38
		-1325.75
		-1321.07
		-796.98
		-1482.23
		-1808.45
		-1481.4
		-1275.06
		-1250.33
		-1862.52
		-1898.16
		-1360.43
		-1277.77
		-1122.73
		-1415.29
		-1485.21
		-1301.46
		-1453.11
		-1108.37
		-1227.18
		-1604.99
		-1152.68
		-1710.69
		-1937.43
		-1782.84
		-1639.14
		-1321.23
		-1247.8
		-1327.3
		-1914.48
		-1438.72
		-2045.98
		-1538.53
		-1851.53
		-1635.13
		-1459.47
		-1161.48
		-1640.49
		-1107.23
		-1248.65
		-1253.73
		-1568.34
		-1496.1
		-1018.44
		-1003.91
		-1375.68
		-1725.05
		-1660.1
		-708.37
		-1244.2
		-1507.79
		-1492.5
		-1185.51
		-1549.64
		-1673.89
		-1735.96
		-1675.41
		-1530.23
		-1607.36
		-1811.94
		-1393.65
		-1245.18
		-1684.45
		-1665.99
		-1859.41
		-1620.76
		-1723.02
		-861.3
		-1437.87
		-1561.49
		-996.47
		-1513.69
		-799.52
		-1857.18
		-1256.77
		-1635.94
		-988.51
		-1254.34
		-1275.79
		-1835.68
		-1367.87
		-1157.46
		-1799.1
		-1338.98
		-1156.77
		-1245.71
		-1804.84
		-1389.7
		-1149.68
		-1649.39
		-1025.19
		-1139.22
		-1690.79
		-1771.85
		-1653.63
		-1385.72
		-1339.
		-952.57
		-1237.38
		-1497.58
		-967.43
		-1273.24
		-1586.7
		-1741.42
		-1091.7
		-1630.09
		-1908.95
		-1113.93
		-1755.5
		-1089.61
		-2044.34
		-1789.99
		-1809.36
		-1103.89
		-1352.29
		-1558.58
		-1061.53
		-1088.23
		-1317.7
		-1472.02
		-884.77
		-1870.07
		-1623.4
		-893.41
		-1365.11
		-1270.7
		-1017.37
		-1566.95
		-1419.2
		-1297.64
		-1228.25
		-1036.5
		-1150.53
		-1455.34
		-1611.5
		-1503.72
		-1255.27
		-1137.66
		-1721.82
		-1075.22
		-1746.63
		-1256.19
		-1344.81
		-1494.99
		-953.53
		-1177.16
		-977.67
		-1017.04
		-1776.51
		-1124.15
		-1489.8
		-852.42
		-1323.74
		-1187.58
		-1476.28
		-1099.93
		-1153.43
		-1589.03
		-1239.16
		-1210.26
		-1982.75
		-1068.2
		-1597.85
		-1410.52
		-1983.95
		-1736.93
		-1102.46
		-1599.06
		-1919.22
		-1025.03
		-1627.89
		-1398.32
		-1110.11
		-1620.26
		-1522.92
		-1683.49
		-1442.33
		-1934.67
		-1186.31
		-1443.74
		-1346.82
		-862.34
		-1708.82
		-1369.28
		-1335.03
		-1115.15
		-879.38
		-1431.25
		-1792.26
		-1539.91
		-1380.61
		-1274.15
		-1306.46
		-1029.4
		-1591.64
		-1211.2
		-1801.31
		-1614.89
		-1018.01
		-1197.11
		-1282.55
		-1435.52
		-1287.53
		-1318.73
		-1551.53
		-693.01
		-1458.29
		-992.26
		-1155.53
		-1583.2
		-653.44
		-1068.82
		-1490.98
		-1702.87
		-974.5
		-1510.44
		-1428.22
		-1300.05
		-1328.7
		-1631.9
		-1535.9
		-1379.69
		-1590.5
		-972.64
		-1305.32
		-1028.25
		-1177.97
		-1849.44
		-1000.01
		-1654.94
		-1176.14
		-1254.11
		-1180.34
		-1475.84
		-1416.59
		-1169.33
		-1474.9
		-1072.55
		-1786.15
		-1053.94
		-927.43
		-1341.07
		-1125.26
		-1984.66
		-1990.67
		-1839.37
		-1455.68
		-1100.59
		-1643.94
		-1164.86
		-1577.76
		-1265.8
		-1096.09
		-1434.79
		-1645.29
		-1433.7
		-1282.77
		-1163.19
		-1714.71
		-1588.
		-1067.19
		-1259.83
		-2059.13
		-1206.6
		-1375.99
		-1033.83
		-2050.15
		-1768.2
		-1047.64
		-1866.88
		-1596.37
		-1810.76
		-1128.5
		-1268.15
		-1316.14
		-2189.38
		-1462.48
		-1093.99
		-1159.41
		-1463.15
		-1264.86
		-1248.98
		-808.87
		-949.91
		-1221.82
		-860.26
		-1657.96
		-1921.19
		-1701.34
		-1628.6
		-1325.98
		-871.86
		-1152.69
		-1472.35
		-1278.26
		-1518.14
		-1165.21
		-1326.29
		-857.15
		-1852.22
		-1276.16
		-1536.97
		-1470.79
		-1401.12
		-1271.12
		-1625.88
		-1204.42
		-1680.84
		-1924.91
		-1312.57
		-1917.92
		-1294.93
		-1744.57
		-1406.28
		-884.17
		-1070.7
		-1161.87
		-1351.03
		-1225.26
		-1280.75
		-1155.4
		-1767.82
		-1197.04
		-1062.67
		-1460.22
		-1860.2
		-2066.04
		-1799.65
		-1065.95
		-1254.62
		-1233.53
		-1605.31
		-1271.54
		-1807.35
		-1224.22
		-1322.48
		-1466.4
		-1269.63
		-1840.74
		-768.02
		-825.76
		-1505.4
		-1778.83
		-1575.44
		-785.04
		-1609.75
		-1673.08
		-1511.77
		-1412.54
		-1087.96
		-988.34
		-1743.65
		-1853.99
		-1174.66
		-1339.81
		-1018.95
		-1218.16
		-1994.55
		-1926.
		-1295.84
		-1099.75
		-2055.96
		-1298.51
		-1871.12
		-1348.1
		-1680.8
		-1136.23
		-1491.64
		-993.41
		-1354.04
		-1401.67
		-1534.19
		-1052.57
		-1304.71
		-1244.44
		-1778.55
		-1566.5
		-1716.29
		-1486.56
		-2192.
		-1430.45
		-1517.02
		-1308.78
		-1494.09
		-1306.23
		-1158.13
		-1471.15
		-1668.51
		-1647.92
		-1163.8
		-1124.79
		-1693.
		-1519.27
		-1904.48
		-1174.99
		-1032.07
		-1444.63
		-1695.85
		-1307.99
		-1995.12
		-1051.63
		-1196.17
		-1480.18
		-1349.82
		-1251.26
		-1262.45
		-1422.49
		-1020.97
		-1129.26
		-1325.85
		-1086.92
		-1384.38
		-1400.63
		-1098.8
		-1993.9
		-1677.9
		-1113.96
		-1787.65
		-1321.12
		-1724.24
		-1864.42
		-1891.5
		-1459.29
		-1391.46
		-618.72
		-1205.42
		-1258.28
		-1390.24
		-860.01
		-1593.91
		-927.78
		-1336.97
		-945.61
		-1310.13
		-872.88
		-1167.84
		-1499.73
		-1194.16
		-1686.62
		-1524.28
		-2058.97
		-1219.26
		-1002.62
		-1378.2
		-971.15
		-1564.18
		-1896.03
		-1300.09
		-1198.32
		-1374.26
		-1099.62
		-1189.89
		-1502.54
		-1643.55
		-1796.65
		-1929.11
		-1191.44
		-1321.3
		-1996.76
		-903.23
		-2062.
		-1304.31
		-1696.08
		-1023.89
		-1343.55
		-1651.31
		-1707.52
		-1713.09
		-1057.63
		-1314.1
		-1565.05
		-1934.27
		-1733.32
		-1912.68
		-1504.27
		-1086.74
		-1700.36
		-1107.82
		-1251.24
		-1026.67
		-1794.95
		-1731.09
		-1119.24
		-1236.15
		-1373.04

datasets/gdb7k.pkl.gz

deleted100644 → 0

−919 KiB

File deleted.

View file

deepchem/featurizers/init.py

+3 −1

Original line number	Diff line number	Diff line
		@@ -142,7 +142,9 @@ class Featurizer(object):
		if verbosity is not None and i % log_every_n == 0:
		log("Featurizing %d / %d" % (i, len(mols)))
		if mol is not None:
		features.append(self._featurize(mol))
		myfeatures = self._featurize(mol)
		features.append(myfeatures)
		#features.append(self._featurize(mol))
		else:
		features.append(np.array([]))

deepchem/featurizers/featurize.py

+77 −4

Original line number	Diff line number	Diff line
		@@ -38,6 +38,8 @@ def _process_field(val):
		return float(val)
		except ValueError:
		return val
		elif isinstance(val, Chem.Mol):
		return val
		else:
		raise ValueError("Field of unrecognized type: %s" % str(val))

		@@ -53,6 +55,8 @@ def _get_input_type(input_file):
		return "pandas-pickle"
		elif file_extension == ".joblib":
		return "pandas-joblib"
		elif file_extension == ".sdf":
		return "sdf"
		else:
		raise ValueError("Unrecognized extension %s" % file_extension)

		@@ -69,6 +73,12 @@ def _get_fields(input_file):
		elif input_type == "pandas-pickle":
		df = load_pickle_from_disk(input_file)
		return df.keys()
		# If SDF input, assume that .sdf.csv file contains labels
		elif input_type == "sdf":
		label_file = input_file + ".csv"
		print("Reading labels from %s" % label_file)
		with open(label_file, "rb") as inp_file_obj:
		return inp_file_obj.readline()
		else:
		raise ValueError("Unrecognized extension for %s" % input_file)

		@@ -83,7 +93,7 @@ class DataFeaturizer(object):
		def __init__(self, tasks, smiles_field, split_field=None,
		id_field=None, threshold=None, user_specified_features=None,
		protein_pdb_field=None, ligand_pdb_field=None,
		ligand_mol2_field=None,
		ligand_mol2_field=None, mol_field=None,
		compound_featurizers=[], complex_featurizers=[],
		verbosity=None, log_every_n=1000):
		"""Extracts data from input as Pandas data frame"""
		@@ -102,6 +112,7 @@ class DataFeaturizer(object):
		self.protein_pdb_field = protein_pdb_field
		self.ligand_pdb_field = ligand_pdb_field
		self.ligand_mol2_field = ligand_mol2_field
		self.mol_field = mol_field
		self.user_specified_features = user_specified_features
		self.compound_featurizers = compound_featurizers
		self.complex_featurizers = complex_featurizers
		@@ -116,13 +127,31 @@ class DataFeaturizer(object):
		or not self._shard_files_exist(feature_dir)
		or not reload)

		input_type = _get_input_type(input_file)
		read_sdf = (input_type == "sdf")

		if perform_featurization:
		if not os.path.exists(feature_dir):
		os.makedirs(feature_dir)
		input_type = _get_input_type(input_file)

		log("Loading raw samples now.", self.verbosity)

		if read_sdf:
		# Tasks are stored in .sdf.csv file
		raw_df = load_pandas_from_disk(input_file+".csv")
		# Structures are stored in .sdf file
		print("Reading structures from %s." % input_file)
		suppl = Chem.SDMolSupplier(str(input_file), removeHs=False)
		df_rows = []
		for ind, mol in enumerate(suppl):
		if mol is not None:
		smiles = Chem.MolToSmiles(mol)
		df_rows.append([ind,smiles,mol])
		mol_df = pd.DataFrame(df_rows, columns=('mol_id', 'smiles', 'mol'))
		raw_df = pd.concat([mol_df, raw_df], axis=1, join='inner')
		else:
		raw_df = load_pandas_from_disk(input_file)

		fields = raw_df.keys()
		log("Loaded raw data frame from file.", self.verbosity)
		log("About to preprocess samples.", self.verbosity)
		@@ -146,6 +175,13 @@ class DataFeaturizer(object):

		df = self._standardize_df(raw_df_shard)

		if read_sdf:
		# SDF reader compatible with compound_featurizers for now
		for compound_featurizer in self.compound_featurizers:
		log("Currently featurizing feature_type: %s"
		% compound_featurizer.__class__.__name__, self.verbosity)
		self._featurize_mol(df, compound_featurizer, worker_pool=worker_pool)
		else:
		for compound_featurizer in self.compound_featurizers:
		log("Currently featurizing feature_type: %s"
		% compound_featurizer.__class__.__name__, self.verbosity)
		@@ -183,7 +219,7 @@ class DataFeaturizer(object):
		if input_type == "csv":
		for ind, field in enumerate(fields):
		data[field] = _process_field(row[ind])
		elif input_type in ["pandas-pickle", "pandas-joblib"]:
		elif input_type in ["pandas-pickle", "pandas-joblib", "sdf"]:
		for field in fields:
		data[field] = _process_field(row[field])
		else:
		@@ -206,6 +242,8 @@ class DataFeaturizer(object):
		if self.user_specified_features is not None:
		for feature in self.user_specified_features:
		df[feature] = ori_df[[feature]]
		if self.mol_field is not None:
		df["mol"] = ori_df[[self.mol_field]]
		if self.split_field is not None:
		df["split"] = ori_df[[self.split_field]]
		if self.protein_pdb_field is not None:
		@@ -241,6 +279,41 @@ class DataFeaturizer(object):
		#features = featurize_wrapper(zip(ligand_pdbs, protein_pdbs))
		df[featurizer.__class__.__name__] = list(features)

		def _featurize_mol(self, df, featurizer, parallel=True,
		worker_pool=None):
		"""Featurize individual compounds.

		Given a featurizer that operates on individual chemical compounds
		or macromolecules, compute & add features for that compound to the
		features dataframe

		When featurizing a .sdf file, the 3-D structure should be preserved
		so we use the rdkit "mol" object created from .sdf instead of smiles
		string. Some featurizers such as CoulombMatrix also require a 3-D
		structure. Featurizing from .sdf is currently the only way to
		perform CM feautization.

		"""
		sample_mols = df["mol"].tolist()

		if worker_pool is None:
		features = []
		for ind, mol in enumerate(sample_mols):
		if ind % self.log_every_n == 0:
		log("Featurizing sample %d" % ind, self.verbosity)
		features.append(featurizer.featurize([mol], verbosity=self.verbosity))
		else:
		def featurize_wrapper(mol, dilled_featurizer):
		print("Featurizing %s" % mol)
		featurizer = dill.loads(dilled_featurizer)
		feature = featurizer.featurize([mol], verbosity=self.verbosity)
		return feature

		features = worker_pool.map_sync(featurize_wrapper,
		sample_mols)

		df[featurizer.__class__.__name__] = features

		def _featurize_compounds(self, df, featurizer, parallel=True,
		worker_pool=None):
		"""Featurize individual compounds.
		@@ -303,7 +376,7 @@ class FeaturizedSamples(object):
		"""
		# The standard columns for featurized data.
		colnames = ["mol_id", "smiles", "split"]
		optional_colnames = ["protein_pdb", "ligand_pdb", "ligand_mol2"]
		optional_colnames = ["protein_pdb", "ligand_pdb", "ligand_mol2", "mol"]

		def __init__(self, samples_dir, featurizers, dataset_files=None,
		reload=False, verbosity=None):

Admin message