15th Community Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction
`
Menu
#
GR code
GR name
Domains Count
SUM Zscore (>-2.0)
Rank SUM Zscore (>-2.0)
AVG Zscore (>-2.0)
Rank AVG Zscore (>-2.0)
SUM Zscore (>0.0)
Rank SUM Zscore (>0.0)
AVG Zscore (>0.0)
Rank AVG Zscore (>0.0)
1
229
Yang-Server
108
82.5877
2
0.7832
2
92.5982
1
0.8574
1
2
162
UM-TBM
109
87.6934
1
0.8045
1
91.8410
2
0.8426
2
3
035
Manifold-E
109
46.3607
5
0.4253
7
63.2197
3
0.5800
4
4
475
MULTICOM_refine
109
47.7746
3
0.4383
5
54.8979
4
0.5037
6
5
120
MULTICOM_egnn
109
47.1138
4
0.4322
6
52.8480
5
0.4848
7
6
158
MULTICOM_deep
109
45.4041
6
0.4166
8
51.0686
6
0.4685
8
7
288
DFolding-server
109
34.0187
8
0.3121
11
49.9465
7
0.4582
10
8
086
MULTICOM_qa
109
43.1930
7
0.3963
9
49.4940
8
0.4541
11
9
462
MultiFOLD
109
31.6482
10
0.2904
13
47.2831
9
0.4338
12
10
446
ColabFold
109
26.8437
12
0.2463
15
46.8624
10
0.4299
13
11
166
RaptorX
109
33.5969
9
0.3082
12
45.8090
11
0.4203
14
12
125
UltraFold_Server
109
26.4331
13
0.2425
16
40.3241
12
0.3699
15
13
298
MUFold
109
28.7393
11
0.2637
14
39.7967
13
0.3651
16
14
131
Kiharalab_Server
109
10.7099
25
0.0983
29
39.5082
14
0.3625
17
15
098
GuijunLab-Assembly
109
21.7402
15
0.1995
19
36.6711
15
0.3364
19
16
188
GuijunLab-DeepDA
109
26.3224
14
0.2415
17
36.5916
16
0.3357
20
17
466
Shennong
105
13.6144
21
0.2059
18
35.9139
17
0.3420
18
18
383
server_124
109
17.0985
19
0.1569
24
35.5967
18
0.3266
21
19
403
server_126
109
19.5558
17
0.1794
21
35.5320
19
0.3260
22
20
270
NBIS-AF2-standard
109
21.4961
16
0.1972
20
34.1607
20
0.3134
24
21
245
FoldEver
109
15.2209
20
0.1396
26
33.8134
21
0.3102
25
22
353
hFold
106
12.9372
22
0.1787
22
33.3984
22
0.3151
23
23
151
IntFOLD7
109
6.2485
28
0.0573
33
32.9872
23
0.3026
26
24
018
server_123
109
9.5672
27
0.0878
31
31.1801
24
0.2861
28
25
261
server_122
109
10.9444
24
0.1004
28
30.8276
25
0.2828
29
26
264
server_125
109
10.3617
26
0.0951
30
30.2311
26
0.2773
30
27
481
GuijunLab-Meta
107
11.8944
23
0.1485
25
29.1492
27
0.2724
31
28
282
GuijunLab-Threader
109
17.2316
18
0.1581
23
28.1772
28
0.2585
32
29
239
Yang-Multimer
45
-102.7890
37
0.5602
3
27.4611
29
0.6102
3
30
089
GuijunLab-RocketX
108
5.8266
29
0.0725
32
27.3532
30
0.2533
33
31
073
DFolding-refine
106
-36.3592
34
-0.2864
39
25.3667
31
0.2393
35
32
133
ShanghaiTech-TS-SER
105
-13.0873
32
-0.0485
36
25.2661
32
0.2406
34
33
011
GinobiFold-SER
105
-11.1661
31
-0.0302
35
24.6080
33
0.2344
36
34
215
XRC_VU
80
-46.9128
35
0.1386
27
23.5756
34
0.2947
27
35
071
RaptorX-Multimer
45
-106.6032
38
0.4755
4
23.4830
35
0.5218
5
36
450
ManiFold-serv
109
-0.0786
30
-0.0007
34
23.0836
36
0.2118
37
37
390
NBIS-AF2-multimer
50
-98.9688
36
0.3806
10
23.0656
37
0.4613
9
38
443
BAKER-SERVER
109
-20.7476
33
-0.1903
37
20.9480
38
0.1922
38
39
427
MESHI_server
76
-117.1133
39
-0.6725
40
8.6120
39
0.1133
40
40
219
Pan_Server
104
-135.0695
40
-1.2026
41
4.7695
40
0.0459
41
41
315
Cerebra
109
-197.2832
46
-1.8099
46
2.9270
41
0.0269
43
42
370
wuqi
87
-153.9438
41
-1.2637
42
2.7157
42
0.0312
42
43
046
Manifold-LC-E
15
-191.8055
45
-0.2537
38
2.4712
43
0.1647
39
44
368
FALCON2
107
-171.3804
42
-1.5643
43
2.3896
44
0.0223
44
45
333
FALCON0
107
-171.3804
42
-1.5643
43
2.3896
44
0.0223
44
46
212
BhageerathH-Pro
103
-180.8593
44
-1.6394
45
1.2395
46
0.0120
46
47
280
ACOMPMOD
78
-210.5824
47
-1.9049
47
0.1265
47
0.0016
47
The cummulative z-scores in this table are calculated according to the following procedure (example for the "first" models):
1. Calculate z-scores from the raw scores for all "first" models (corresponding values from the main result table);
2. Remove outliers - models with zscores below the tolerance threshold (set to -2.0);
3. Recalculate z-scores on the reduced dataset;
4. Assign z-scores below the penalty threshold (either -2.0 or 0.0) to the value of this threshold.