adding some code

Author: Naozumi Hiranuma

data/analysis_list.npy

@@ -0,0 +1,4 @@
+ver1: 4000 datasets
+ver2: expansion to 800 datasets
+ver3: trimmed homology to refinment sets
+ver4: trimmed post casp13 released targets

data/readme.txt

@@ -0,0 +1,8 @@
+from .dataProcessingUtils import *
+from .pyprotein import *
+from .featurize import *
+from .resnet import *
+from .model import *
+from .model2 import *
+from .utils import *
+from .dataset import *

data/test_proteins2.npy

@@ -0,0 +1,17 @@
+import numpy as np
+
+# 3LAA to tip atom conversion.
+dict_3LAA_to_tip = {"ALA":"CB", "CYS":"SG", "ASP":"CG", "ASN":"CG", "GLU":"CD",
+                "GLN":"CD", "PHE":"CZ", "HIS":"NE2", "ILE":"CD1", "GLY":"CA",
+                "LEU":"CG", "MET":"SD", "ARG":"CZ", "LYS":"NZ", "PRO":"CG",
+                "VAL":"CB", "TYR":"OH", "TRP":"CH2", "SER":"OG", "THR":"OG1"}
+
+# 1LAA to number conversion.
+aas = "ACDEFGHIKLMNPQRSTVWY-"
+dict_1LAA_to_num = dict([(aas[a], a) for a in range(len(aas))])
+
+# 3LAA to 1LAA conversion.
+dict_3LAA_to_1LAA = {"ALA":"A", "CYS":"C", "ASP":"D", "ASN":"N", "GLU":"E",
+                 "GLN":"Q", "PHE":"F", "HIS":"H", "ILE":"I", "GLY":"G",
+                 "LEU":"L", "MET":"M", "ARG":"R", "LYS":"K", "PRO":"P",
+                 "VAL":"V", "TYR":"Y", "TRP":"W", "SER":"S", "THR":"T"}

data/test_proteins3.npy

@@ -0,0 +1,25 @@
+   A  R  N  D  C  Q  E  G  H  I  L  K  M  F  P  S  T  W  Y  V  B  Z  X  *
+A  4 -1 -2 -2  0 -1 -1  0 -2 -1 -1 -1 -1 -2 -1  1  0 -3 -2  0 -2 -1  0 -4 
+R -1  5  0 -2 -3  1  0 -2  0 -3 -2  2 -1 -3 -2 -1 -1 -3 -2 -3 -1  0 -1 -4 
+N -2  0  6  1 -3  0  0  0  1 -3 -3  0 -2 -3 -2  1  0 -4 -2 -3  3  0 -1 -4 
+D -2 -2  1  6 -3  0  2 -1 -1 -3 -4 -1 -3 -3 -1  0 -1 -4 -3 -3  4  1 -1 -4 
+C  0 -3 -3 -3  9 -3 -4 -3 -3 -1 -1 -3 -1 -2 -3 -1 -1 -2 -2 -1 -3 -3 -2 -4 
+Q -1  1  0  0 -3  5  2 -2  0 -3 -2  1  0 -3 -1  0 -1 -2 -1 -2  0  3 -1 -4 
+E -1  0  0  2 -4  2  5 -2  0 -3 -3  1 -2 -3 -1  0 -1 -3 -2 -2  1  4 -1 -4 
+G  0 -2  0 -1 -3 -2 -2  6 -2 -4 -4 -2 -3 -3 -2  0 -2 -2 -3 -3 -1 -2 -1 -4 
+H -2  0  1 -1 -3  0  0 -2  8 -3 -3 -1 -2 -1 -2 -1 -2 -2  2 -3  0  0 -1 -4 
+I -1 -3 -3 -3 -1 -3 -3 -4 -3  4  2 -3  1  0 -3 -2 -1 -3 -1  3 -3 -3 -1 -4 
+L -1 -2 -3 -4 -1 -2 -3 -4 -3  2  4 -2  2  0 -3 -2 -1 -2 -1  1 -4 -3 -1 -4 
+K -1  2  0 -1 -3  1  1 -2 -1 -3 -2  5 -1 -3 -1  0 -1 -3 -2 -2  0  1 -1 -4 
+M -1 -1 -2 -3 -1  0 -2 -3 -2  1  2 -1  5  0 -2 -1 -1 -1 -1  1 -3 -1 -1 -4 
+F -2 -3 -3 -3 -2 -3 -3 -3 -1  0  0 -3  0  6 -4 -2 -2  1  3 -1 -3 -3 -1 -4 
+P -1 -2 -2 -1 -3 -1 -1 -2 -2 -3 -3 -1 -2 -4  7 -1 -1 -4 -3 -2 -2 -1 -2 -4 
+S  1 -1  1  0 -1  0  0  0 -1 -2 -2  0 -1 -2 -1  4  1 -3 -2 -2  0  0  0 -4 
+T  0 -1  0 -1 -1 -1 -1 -2 -2 -1 -1 -1 -1 -2 -1  1  5 -2 -2  0 -1 -1  0 -4 
+W -3 -3 -4 -4 -2 -2 -3 -2 -2 -3 -2 -3 -1  1 -4 -3 -2 11  2 -3 -4 -3 -2 -4 
+Y -2 -2 -2 -3 -2 -1 -2 -3  2 -1 -1 -2 -1  3 -3 -2 -2  2  7 -1 -3 -2 -1 -4 
+V  0 -3 -3 -3 -1 -2 -2 -3 -3  3  1 -2  1 -1 -2 -2  0 -3 -1  4 -3 -2 -1 -4 
+B -2 -1  3  4 -3  0  1 -1  0 -3 -4  0 -3 -3 -2  0 -1 -4 -3 -3  4  1 -1 -4 
+Z -1  0  0  1 -3  3  4 -2  0 -3 -3  1 -1 -3 -1  0 -1 -3 -2 -2  1  4 -1 -4 
+X  0 -1 -1 -1 -2 -1 -1 -1 -1 -1 -1 -1 -1 -1 -2  0  0 -2 -1 -1 -1 -1 -1 -4 
+* -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4  1 

data/test_proteins4.npy

@@ -0,0 +1,99 @@
+ALA_CA CAbb
+ALA_CB CH3
+ALA_C CObb
+ALA_N Nbb
+ALA_O OCbb
+ARG_CA CAbb
+ARG_CB CH2
+ARG_C CObb
+ARG_N Nbb
+ARG_O OCbb
+ASN_CA CAbb
+ASN_CB CH2
+ASN_C CObb
+ASN_N Nbb
+ASN_O OCbb
+ASP_CA CAbb
+ASP_CB CH2
+ASP_C CObb
+ASP_N Nbb
+ASP_O OCbb
+CYS_CA CAbb
+CYS_CB CH2
+CYS_C CObb
+CYS_N Nbb
+CYS_O OCbb
+GLN_CA CAbb
+GLN_CB CH2
+GLN_C CObb
+GLN_N Nbb
+GLN_O OCbb
+GLU_CA CAbb
+GLU_CB CH2
+GLU_C CObb
+GLU_N Nbb
+GLU_O OCbb
+GLY_CA CAbb
+GLY_C CObb
+GLY_N Nbb
+GLY_O OCbb
+HIS_CA CAbb
+HIS_CB CH2
+HIS_C CObb
+HIS_N Nbb
+HIS_O OCbb
+ILE_CA CAbb
+ILE_CB CH1
+ILE_C CObb
+ILE_N Nbb
+ILE_O OCbb
+LEU_CA CAbb
+LEU_CB CH2
+LEU_C CObb
+LEU_N Nbb
+LEU_O OCbb
+LYS_CA CAbb
+LYS_CB CH2
+LYS_C CObb
+LYS_N Nbb
+LYS_O OCbb
+MET_CA CAbb
+MET_CB CH2
+MET_C CObb
+MET_N Nbb
+MET_O OCbb
+PHE_CA CAbb
+PHE_CB CH2
+PHE_C CObb
+PHE_N Nbb
+PHE_O OCbb
+PRO_CA CAbb
+PRO_CB CH2
+PRO_C CObb
+PRO_N Npro
+PRO_O OCbb
+SER_CA CAbb
+SER_CB CH2
+SER_C CObb
+SER_N Nbb
+SER_O OCbb
+THR_CA CAbb
+THR_CB CH1
+THR_C CObb
+THR_N Nbb
+THR_O OCbb
+TRP_CA CAbb
+TRP_CB CH2
+TRP_C CObb
+TRP_N Nbb
+TRP_O OCbb
+TYR_CA CAbb
+TYR_CB CH2
+TYR_C CObb
+TYR_N Nbb
+TYR_O OCbb
+VAL_CA CAbb
+VAL_CB CH1
+VAL_C CObb
+VAL_N Nbb
+VAL_O OCbb

data/train_proteins2.npy

@@ -0,0 +1,167 @@
+ALA_CA CAbb
+ALA_CB CH3
+ALA_C CObb
+ALA_N Nbb
+ALA_O OCbb
+ARG_CA CAbb
+ARG_CB CH2
+ARG_C CObb
+ARG_CD CH2
+ARG_CG CH2
+ARG_CZ aroC
+ARG_NE Narg
+ARG_NH1 Narg
+ARG_NH2 Narg
+ARG_N Nbb
+ARG_O OCbb
+ASN_CA CAbb
+ASN_CB CH2
+ASN_C CObb
+ASN_CG CNH2
+ASN_ND2 NH2O
+ASN_N Nbb
+ASN_OD1 ONH2
+ASN_O OCbb
+ASP_CA CAbb
+ASP_CB CH2
+ASP_C CObb
+ASP_CG COO
+ASP_N Nbb
+ASP_OD1 OOC
+ASP_OD2 OOC
+ASP_O OCbb
+CYS_CA CAbb
+CYS_CB CH2
+CYS_C CObb
+CYS_N Nbb
+CYS_O OCbb
+CYS_SG S
+GLN_CA CAbb
+GLN_CB CH2
+GLN_C CObb
+GLN_CD CNH2
+GLN_CG CH2
+GLN_NE2 NH2O
+GLN_N Nbb
+GLN_OE1 ONH2
+GLN_O OCbb
+GLU_CA CAbb
+GLU_CB CH2
+GLU_C CObb
+GLU_CD COO
+GLU_CG CH2
+GLU_N Nbb
+GLU_OE1 OOC
+GLU_OE2 OOC
+GLU_O OCbb
+GLY_CA CAbb
+GLY_C CObb
+GLY_N Nbb
+GLY_O OCbb
+HIS_CA CAbb
+HIS_CB CH2
+HIS_C CObb
+HIS_CD2 aroC
+HIS_CE1 aroC
+HIS_CG aroC
+HIS_ND1 Nhis
+HIS_NE2 Ntrp
+HIS_N Nbb
+HIS_O OCbb
+ILE_CA CAbb
+ILE_CB CH1
+ILE_C CObb
+ILE_CD1 CH3
+ILE_CG1 CH2
+ILE_CG2 CH3
+ILE_N Nbb
+ILE_O OCbb
+LEU_CA CAbb
+LEU_CB CH2
+LEU_C CObb
+LEU_CD1 CH3
+LEU_CD2 CH3
+LEU_CG CH1
+LEU_N Nbb
+LEU_O OCbb
+LYS_CA CAbb
+LYS_CB CH2
+LYS_C CObb
+LYS_CD CH2
+LYS_CE CH2
+LYS_CG CH2
+LYS_N Nbb
+LYS_NZ Nlys
+LYS_O OCbb
+MET_CA CAbb
+MET_CB CH2
+MET_C CObb
+MET_CE CH3
+MET_CG CH2
+MET_N Nbb
+MET_O OCbb
+MET_SD S
+PHE_CA CAbb
+PHE_CB CH2
+PHE_C CObb
+PHE_CD1 aroC
+PHE_CD2 aroC
+PHE_CE1 aroC
+PHE_CE2 aroC
+PHE_CG aroC
+PHE_CZ aroC
+PHE_N Nbb
+PHE_O OCbb
+PRO_CA CAbb
+PRO_CB CH2
+PRO_C CObb
+PRO_CD CH2
+PRO_CG CH2
+PRO_N Npro
+PRO_O OCbb
+SER_CA CAbb
+SER_CB CH2
+SER_C CObb
+SER_N Nbb
+SER_OG OH
+SER_O OCbb
+THR_CA CAbb
+THR_CB CH1
+THR_C CObb
+THR_CG2 CH3
+THR_N Nbb
+THR_OG1 OH
+THR_O OCbb
+TRP_CA CAbb
+TRP_CB CH2
+TRP_C CObb
+TRP_CD1 aroC
+TRP_CD2 aroC
+TRP_CE2 aroC
+TRP_CE3 aroC
+TRP_CG aroC
+TRP_CH2 aroC
+TRP_CZ2 aroC
+TRP_CZ3 aroC
+TRP_NE1 Ntrp
+TRP_N Nbb
+TRP_O OCbb
+TYR_CA CAbb
+TYR_CB CH2
+TYR_C CObb
+TYR_CD1 aroC
+TYR_CD2 aroC
+TYR_CE1 aroC
+TYR_CE2 aroC
+TYR_CG aroC
+TYR_CZ aroC
+TYR_N Nbb
+TYR_OH OH
+TYR_O OCbb
+VAL_CA CAbb
+VAL_CB CH1
+VAL_C CObb
+VAL_CG1 CH3
+VAL_CG2 CH3
+VAL_N Nbb
+VAL_O OCbb

data/train_proteins3.npy

@@ -0,0 +1,21 @@
+residue,steric_parameter,polarizability,volume,hydrophobicity,isoelectric_pt,helix_prob,sheet_prob
+ALA,1.28,0.05,1.00,0.31,6.11,0.42,0.23
+GLY,0.00,0.00,0.00,0.00,6.07,0.13,0.15
+VAL,3.67,0.14,3.00,1.22,6.02,0.27,0.49
+LEU,2.59,0.19,4.00,1.70,6.04,0.39,0.31
+ILE,4.19,0.19,4.00,1.80,6.04,0.30,0.45
+PHE,2.94,0.29,5.89,1.79,5.67,0.30,0.38
+TYR,2.94,0.30,6.47,0.96,5.66,0.25,0.41
+TRP,3.21,0.41,8.08,2.25,5.94,0.32,0.42
+THR,3.03,0.11,2.60,0.26,5.60,0.21,0.36
+SER,1.31,0.06,1.60,-0.04,5.70,0.20,0.28
+ARG,2.34,0.29,6.13,-1.01,10.74,0.36,0.25
+LYS,1.89,0.22,4.77,-0.99,9.99,0.32,0.27
+HIS,2.99,0.23,4.66,0.13,7.69,0.27,0.30
+ASP,1.60,0.11,2.78,-0.77,2.95,0.25,0.20
+GLU,1.56,0.15,3.78,-0.64,3.09,0.42,0.21
+ASN,1.60,0.13,2.95,-0.60,6.52,0.21,0.22
+GLN,1.56,0.18,3.95,-0.22,5.65,0.36,0.25
+MET,2.35,0.22,4.43,1.23,5.71,0.38,0.32
+PRO,2.67,0.00,2.72,0.72,6.80,0.13,0.34
+CYS,1.77,0.13,2.43,1.54,6.35,0.17,0.41