Skip to main content

Table 1 Detailed Contact Prediction Results on 48 Test Proteins for Sequence Separation >= 6, 12, and 24 respectively.

From: Improved residue contact prediction using support vector machines and a large feature set

Protein type

Len

Type

Separation >= 6

Separation >= 12

Separation >= 12

   

Acc(corr/pred)

Cov(corr/tot)

Acc(corr/pred)

Cov(corr/tot)

Acc(corr/pred)

Cov(corr/tot)

1IG5A

75

alpha

0.333 (25/75)

0.446 (25/56)

0.240 (18/75)

0.486 (18/37)

0.273 (9/33)

0.346 (9/26)

1HXIA

112

alpha

0.304 (34/112)

0.270 (34/126)

0.214 (24/112)

0.238 (24/101)

0.015 (1/67)

0.018 (1/55)

1SKNP

74

alpha

0.093 (4/43)

0.133 (4/30)

0.000 (0/18)

0.000 (0/24)

0.000 (0/6)

0.000 (0/20)

1ELRA

128

alpha

0.406 (52/128)

0.327 (52/159)

0.384 (33/86)

0.264 (33/125)

0.227 (5/22)

0.085 (5/59)

1E29A

135

alpha

0.289 (39/135)

0.193 (39/202)

0.111 (15/135

0.112 (15/134)

0.103 (7/68)

0.071 (7/99)

1CTJA

89

alpha

0.157 (14/89)

0.147 (14/95)

0.112 (10/89

0.204 (10/49)

0.090 (8/89)

0.190 (8/42)

1J75A

57

alpha

0.474 (27/57)

0.466 (27/58)

0.250 (7/28)

0.206 (7/34)

0.500 (1/2)

0.038 (1/26)

1ECAA

136

alpha

0.103 (14/136)

0.156 (14/90)

0.063 (5/79)

0.064 (5/78)

0.070 (3/43)

0.041 (3/74)

1FIOA

190

alpha

0.143 (19/133)

0.161 (19/118)

0.153 (11/72)

0.113 (11/97)

0.140 (8/57)

0.110 (8/73)

1C75A

71

alpha

0.282 (20/71)

0.211 (20/95)

0.099 (7/71)

0.127 (7/55)

0.087 (4/46)

0.089 (4/45)

1HCRA

52

alpha

0.058 (3/52)

0.231 (3/13)

0.056 (1/18)

0.167 (1/6)

0.000 (0/0)

0.000 (0/3)

1QJPA

137

beta

0.518 (71/137)

0.183 (71/389)

0.489 (67/137)

0.215 (67/312)

0.350(48/137)

0.300 (48/160)

1D2SA

170

beta

0.482 (82/170)

0.180 (82/455)

0.341 (58/170)

0.150 (58/386)

0.165 (28/170)

0.096 (28/293)

1CQYA

99

beta

0.182 (18/99)

0.080 (18/225)

0.172 (17/99)

0.094 (17/180)

0.273 (27/99)

0.197 (27/137)

1BMGA

98

beta

0.398 (39/98)

0.177 (39/220)

0.398 (39/98)

0.211 (39/185)

0.429 (42/98)

0.323 (42/130)

1MAIA

119

beta

0.538 (64/119)

0.298 (64/215)

0.361 (43/119)

0.250 (43/172)

0.034 (4/119)

0.048 (4/83)

1AMXA

150

beta

0.387 (58/150)

0.162 (58/357)

0.300 (45/150)

0.148 (45/304)

0.220 (33/150)

0.141 (33/234)

1G3PA

192

beta

0.042 (8/192)

0.019 (8/420)

0.042 (8/192

0.023 (8/342)

0.036 (7/192)

0.026 (7/273)

1RSYA

135

beta

0.578 (78/135)

0.259 (78/301)

0.459 (62/135)

0.240 (62/258)

0.230 (31/135)

0.177 (31/175)

1WHIA

122

beta

0.492 (60/122)

0.201 (60/298)

0.459 (56/122

0.226 (56/248)

0.295 (36/122)

0.303 (36/119)

1HE7A

107

beta

0.280 (30/107)

0.183 (30/164)

0.327 (35/107)

0.254 (35/138)

0.346 (37/107)

0.394 (37/94)

1MWPA

96

a+b

0.365 (35/96)

0.178 (35/197)

0.385 (37/96)

0.236 (37/157)

0.292 (28/96)

0.311 (28/90)

1QGVA

130

a+b

0.338 (44/130)

0.198 (44/222)

0.338 (44/130)

0.221 (44/199)

0.385 (50/130)

0.279 (50/179)

1DBUA

152

a+b

0.434 (66/152)

0.208 (66/317)

0.276 (42/152)

0.162 (42/260)

0.151 (23/152)

0.111 (23/207)

1XERA

103

a+b

0.466 (48/103)

0.219 (48/219)

0.330 (34/103)

0.214 (34/159)

0.204 (21/103)

0.193 (21/109)

1JSFA

130

a+b

0.500 (65/130)

0.316 (65/206)

0.385 (50/130)

0.345 (50/145)

0.154 (20/130)

0.235 (20/85)

1DZOA

120

a+b

0.608 (73/120)

0.330 (73/221)

0.500 (60/120)

0.351 (60/171)

0.083 (10/120)

0.139 (10/72)

1GRJA

151

a+b

0.318 (48/151)

0.209 (48/230)

0.225 (34/151)

0.186 (34/183)

0.066 (10/151)

0.084 (10/119)

1MSCA

129

a+b

0.620 (80/129)

0.421 (80/190)

0.512 (66/129)

0.524 (66/126)

0.225 (29/129)

0.644 (29/45)

1CEWI

108

a+b

0.528 (57/108)

0.300 (57/190)

0.454 (49/108)

0.310 (49/158)

0.278 (30/108)

0.316 (30/95)

1VHHA

157

a+b

0.414 (65/157)

0.206 (65/316)

0.338 (53/157

0.201 (53/264)

0.223 (35/157)

0.174 (35/201)

1BUOA

121

a+b

0.298 (36/121)

0.300 (36/120)

0.207 (25/121)

0.291 (25/86)

0.140 (17/121)

0.309 (17/55)

1G2RA

94

a+b

0.340 (32/94)

0.254 (32/126)

0.309 (29/94)

0.309 (29/94)

0.234 (22/94)

0.400 (22/55)

1E9MA

106

a+b

0.387 (41/106)

0.186 (41/220)

0.358 (38/106)

0.200 (38/190)

0.311 (33/106)

0.210 (33/157)

1E87A

117

a+b

0.470 (55/117)

0.239 (55/230)

0.299 (35/117)

0.193 (35/181)

0.291 (34/117)

0.227 (34/150)

1H9OA

108

a+b

0.630 (68/108)

0.354 (68/192)

0.352 (38/108)

0.299 (38/127)

0.148 (16/108)

0.302 (16/53)

1IDOA

184

a/b

0.402 (74/184)

0.223 (74/332)

0.402 (74/184)

0.250 (74/296)

0.402 (74/184)

0.277 (74/267)

1CHDA

198

a/b

0.429 (85/198)

0.175 (85/487)

0.384 (76/198)

0.170 (76/447)

0.338 (67/198)

0.181 (67/370)

1FUEA

163

a/b

0.374 (61/163)

0.185 (61/330)

0.374 (61/163)

0.206 (61/296)

0.399 (65/163)

0.251 (65/259)

1CXQA

143

a/b

0.448 (64/143)

0.303 (64/211)

0.350 (50/143)

0.276 (50/181)

0.091 (13/143)

0.115 (13/113)

1F4PA

147

a/b

0.442 (65/147)

0.222 (65/293)

0.361 (53/147)

0.205 (53/258)

0.354 (52/147)

0.223 (52/233)

1ES8A

196

a/b

0.240 (47/196)

0.130 (47/361)

0.153 (30/196)

0.100 (30/300)

0.189 (37/196)

0.160 (37/231)

1DMGA

172

a/b

0.302 (52/172)

0.176 (52/296)

0.273 (47/172)

0.175 (47/269)

0.192 (33/172)

0.155 (33/213)

1A1HA

85

small

0.424 (36/85)

0.424 (36/85)

0.129 (11/85)

0.262 (11/42)

0.000 (0/85)

0.000 (0/0)

9WGAB

171

small

0.415 (71/171)

0.188 (71/378)

0.357 (61/171)

0.268 (61/228)

0.041 (7/171)

0.175 (7/40)

2MADL

124

small

0.274 (34/124)

0.106 (34/321)

0.226 (28/124)

0.106 (28/263)

0.218 (27/124)

0.116 (27/232)

1EJGA

46

small

0.261 (12/46)

0.203 (12/59)

0.419 (13/31

0.271 (13/48)

0.458 (11/24

0.306 (11/36)

1AAOA

113

coil-coil

0.221 (25/113)

0.397 (25/63)

0.031 (3/97)

0.158 (3/19)

0.000 (0/35)

0.000 (0/0)

  1. Column 1 lists the protein name (PDB code + chain id). The chain id of a single-chain protein is denoted by "A" instead of "-". Column 2 lists chain lengths, ranging from 46 to 198. Column 3 lists the SCOP structure class, alpha, beta, a+b, a/b, small, and coil-coil represent six SCOP protein classess (all alpha helix, all beta sheet, alpha helix + beta sheet, alpha helix alternating beta sheet, small protein, and coil-coil), respectively. Columns 4 and 5 report the prediction accuracy (specificity) and coverage (sensitivity) for each protein. Accuracy is the number of correct predictions divided by the total number of predictions. Coverage is the number of correct predictions divided by the total number of true contacts. The raw number of correct preditions, all predictions, and true contacts are also reported in the brackets.