16th Community Wide Experiment on the
Critical Assessment of Techniques for Protein Structure Prediction
`
Menu
TS Analysis : Z-score based relative group performance
Results Home Table Browser
  GDT_TS   Assessor's formula

    Models:

    • Ranking on the models designated as "1"
    • Ranking on the models with the best scores

    Groups:

    • All groups on 'all groups' targets
    • Server groups on 'all groups' + 'server only' targets

    Formula and Domains:

      The ranking of groups is based on the analysis of zscores for GDT_TS.
    • easy
    • medium
    • hard
    #     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)
1 052 Yang-Server 74 36.4436 1 0.4925 6 40.8978 1 0.5527 4
2 022 Yang 74 32.9468 2 0.4452 10 39.0158 2 0.5272 7
3 456 Yang-Multimer 74 31.1402 3 0.4208 13 36.3137 3 0.4907 11
4 051 MULTICOM 74 23.0815 5 0.3119 18 33.3714 4 0.4510 14
5 208 falcon2 73 21.7877 7 0.3259 16 33.3229 5 0.4565 13
6 465 Wallner 74 7.4037 28 0.1001 57 33.2892 6 0.4499 15
7 019 Zheng-Server 74 25.5830 4 0.3457 15 31.7675 7 0.4293 19
8 028 NKRNA-s 60 -1.2319 34 0.4461 9 31.6574 8 0.5276 6
9 287 plmfold 74 18.7256 12 0.2530 28 31.1692 9 0.4212 21
10 110 MIEnsembles-Server 74 23.0680 6 0.3117 19 30.1535 10 0.4075 25
11 319 MULTICOM_LLM 74 19.2839 11 0.2606 27 29.8795 11 0.4038 27
12 075 GHZ-ISM 70 12.6455 24 0.2949 21 29.8002 12 0.4257 20
13 284 Unicorn 70 12.1924 26 0.2885 22 29.3472 13 0.4192 22
14 294 KiharaLab 74 14.6986 17 0.1986 41 29.3153 14 0.3962 30
15 462 Zheng 74 19.6521 10 0.2656 26 29.0969 15 0.3932 31
16 301 GHZ-MAN 73 16.2558 15 0.2501 29 29.0668 16 0.3982 28
17 015 PEZYFoldings 74 0.5862 33 0.0079 62 28.6854 17 0.3876 33
18 147 Zheng-Multimer 74 21.1799 8 0.2862 23 28.3640 18 0.3833 35
19 331 MULTICOM_AI 74 15.7602 16 0.2130 38 28.1391 19 0.3803 37
20 163 MultiFOLD2 74 12.2650 25 0.1657 48 27.5408 20 0.3722 40
21 241 elofsson 74 21.0431 9 0.2844 24 27.5200 21 0.3719 41
22 345 MULTICOM_human 74 14.5853 18 0.1971 42 27.2515 22 0.3683 42
23 304 AF3-server 73 18.5462 13 0.2815 25 26.3829 23 0.3614 44
24 293 MRAH 74 13.3799 20 0.1808 43 26.3215 24 0.3557 48
25 079 MRAFold 74 13.0197 22 0.1759 46 26.1474 25 0.3533 49
26 122 MQA_server 64 -6.6338 39 0.2088 39 26.0332 26 0.4068 26
27 267 kiharalab_server 74 5.6004 29 0.0757 60 25.8154 27 0.3489 50
28 164 McGuffin 74 13.2313 21 0.1788 44 25.7782 28 0.3484 51
29 425 MULTICOM_GATE 74 16.5382 14 0.2235 34 25.6706 29 0.3469 53
30 475 ptq 67 2.2492 30 0.2425 31 25.5626 30 0.3815 36
31 264 GuijunLab-Human 73 14.1266 19 0.2209 35 25.1359 31 0.3443 54
32 148 Guijunlab-Complex 74 12.8969 23 0.1743 47 23.7760 32 0.3213 61
33 031 MassiveFold 66 -7.5043 40 0.1287 55 23.6643 33 0.3586 46
34 312 GuijunLab-Assembly 73 8.4045 27 0.1425 50 23.3636 34 0.3200 62
35 196 HYU_MLLAB 74 -2.0933 35 -0.0283 68 22.0040 35 0.2974 65
36 269 CSSB_server 60 -17.3287 45 0.1779 45 21.8527 36 0.3642 43
37 375 milliseconds 60 -14.0776 43 0.2320 33 21.5140 37 0.3586 45
38 272 GromihaLab 70 -29.1484 50 -0.3021 89 21.3057 38 0.3044 63
39 388 DeepFold-server 74 -14.1654 44 -0.1914 84 20.9061 39 0.2825 67
40 298 ShanghaiTech-human 62 -18.2179 46 0.0933 59 20.8692 40 0.3366 57
41 314 GuijunLab-PAthreader 71 0.8022 32 0.0958 58 20.5574 41 0.2895 66
42 145 colabfold_baseline 59 -30.4079 51 -0.0069 65 20.4677 42 0.3469 52
43 235 isyslab-hust 72 -3.9046 36 0.0013 64 19.9934 43 0.2777 69
44 369 Bhattacharya 66 -9.1693 42 0.1035 56 19.8223 44 0.3003 64
45 091 Huang-HUST 56 -28.5669 49 0.1327 53 19.1094 45 0.3412 56
46 262 CoDock 57 -36.7950 54 -0.0490 71 18.5368 46 0.3252 59
47 286 CSSB_experimental 72 -6.1763 38 -0.0302 69 18.2555 47 0.2535 76
48 014 Cool-PSP 74 -4.6634 37 -0.0630 72 18.0803 48 0.2443 78
49 274 kozakovvajda 36 -59.1262 58 0.4687 7 17.9896 49 0.4997 10
50 419 CSSB-Human 74 1.2122 31 0.0164 61 17.6264 50 0.2382 79
51 494 ClusPro 36 -59.7497 59 0.4514 8 17.3660 51 0.4824 12
52 198 colabfold 59 -40.0905 55 -0.1710 83 16.1454 52 0.2737 70
53 059 DeepFold 74 -20.4987 47 -0.2770 88 15.4688 53 0.2090 80
54 112 Seder2024easy 57 -41.5587 56 -0.1326 77 15.4348 54 0.2708 71
55 423 ShanghaiTech-server 59 -30.8715 52 -0.0148 67 15.3531 55 0.2602 74
56 322 XGroup 37 -61.0130 60 0.3510 14 15.2823 56 0.4130 23
57 311 RAGfold_Prot1 57 -35.9928 53 -0.0350 70 15.0121 57 0.2634 73
58 221 CSSB_FAKER 74 -7.9686 41 -0.1077 75 14.7065 58 0.1987 81
59 204 Zou 36 -67.5299 61 0.2353 32 14.0764 59 0.3910 32
60 017 Seder2024hard 56 -43.6414 57 -0.1365 78 13.9688 60 0.2494 77
61 212 PIEFold_human 74 -25.2276 48 -0.3409 90 12.8418 61 0.1735 86
62 489 Fernandez-Recio 36 -76.4868 65 -0.0135 66 11.9104 62 0.3308 58
63 219 XGroup-server 31 -78.3749 66 0.2460 30 11.6982 63 0.3774 38
64 323 Yan 31 -79.2777 67 0.2168 37 11.5501 64 0.3726 39
65 290 Pierce 27 -85.4034 72 0.3184 17 11.0192 65 0.4081 24
66 358 PerezLab_Gators 34 -79.7986 70 0.0059 63 11.0041 66 0.3237 60
67 023 FTBiot0119 39 -75.8093 63 -0.1490 81 10.9797 67 0.2815 68
68 171 ChaePred 23 -94.9038 75 0.3085 20 9.9156 68 0.4311 18
69 450 OpenComplex_Server 73 -84.6331 71 -1.1320 97 9.4718 69 0.1298 91
70 218 HIT-LinYang 21 -97.0635 77 0.4255 12 9.3384 70 0.4447 16
71 167 OpenComplex 74 -86.5112 73 -1.1691 98 9.1292 71 0.1234 92
72 085 Bates 25 -94.7330 74 0.1307 54 8.8977 72 0.3559 47
73 397 smg_ulaval 15 -109.7757 79 0.5483 3 8.7961 73 0.5864 2
74 393 GuijunLab-QA 32 -79.3386 68 0.1457 49 8.4761 74 0.2649 72
75 481 Vfold 20 -103.8950 78 0.2052 40 7.7067 75 0.3853 34
76 261 UNRES 53 -75.8895 64 -0.6394 93 7.6152 76 0.1437 90
77 191 Schneidman 24 -96.6145 76 0.1411 51 6.2023 77 0.2584 75
78 033 Diff 10 -125.8177 83 0.2182 36 5.1670 78 0.5167 8
79 187 Ayush 24 -115.3152 80 -0.6381 92 4.5323 79 0.1888 82
80 189 LCBio 11 -124.4557 82 0.1404 52 4.3787 80 0.3981 29
81 120 Cerebra 67 -129.4933 86 -1.7238 106 4.2334 81 0.0632 95
82 139 DeepFold-refine 74 -75.3857 62 -1.0187 96 4.0469 82 0.0547 96
83 376 OFsingleseq 11 -133.6958 92 -0.6996 94 3.7815 83 0.3438 55
84 040 DELCLAB 67 -79.6389 69 -0.9797 95 3.5515 84 0.0530 97
85 361 Cerebra_server 71 -129.9739 88 -1.7461 107 2.8241 85 0.0398 98
86 380 mialab_prediction 15 -119.7928 81 -0.1195 76 2.7671 86 0.1845 85
87 338 GeneSilico 12 -126.7163 84 -0.2264 87 2.0526 87 0.1711 87
88 231 B-LAB 10 -128.6611 85 -0.0661 73 1.8858 88 0.1886 83
89 325 405 9 -131.2340 89 -0.1371 79 1.6644 89 0.1849 84
90 276 FrederickFolding 3 -140.4545 97 0.5152 5 1.5455 90 0.5152 9
91 159 406 9 -131.4360 90 -0.1596 82 1.4624 91 0.1625 88
92 337 APOLLO 15 -135.7437 93 -1.1829 99 1.4246 92 0.0950 93
93 008 HADDOCK 9 -131.7999 91 -0.2000 86 1.3913 93 0.1546 89
94 117 Vakser 25 -139.1272 96 -1.6451 105 0.9288 94 0.0372 99
95 468 MIALAB_gong 10 -129.9421 87 -0.1942 85 0.8312 95 0.0831 94
96 174 colabfold_foldseek 1 -145.3207 100 0.6793 1 0.6793 96 0.6793 1
97 049 UTMB 1 -145.4224 101 0.5776 2 0.5776 97 0.5776 3
98 143 dMNAfold 1 -145.4663 102 0.5337 4 0.5337 98 0.5337 5
99 271 mialab_prediction2 1 -145.5678 104 0.4322 11 0.4322 99 0.4322 17
100 300 ARC 15 -137.4534 94 -1.2969 100 0.2904 100 0.0194 102
101 132 profold2 6 -145.0381 99 -1.5064 103 0.1580 101 0.0263 101
102 114 COAST 15 -138.3052 95 -1.3537 101 0.1574 102 0.0105 104
103 351 digiwiser-ensemble 4 -145.5539 103 -1.3885 102 0.1394 103 0.0348 100
104 400 OmniFold 2 -144.7457 98 -0.3728 91 0.0289 104 0.0145 103
105 355 CMOD 1 -146.1001 105 -0.1001 74 0.0000 105 0.0000 105
106 197 D3D 1 -146.1432 106 -0.1432 80 0.0000 105 0.0000 105
107 357 UTAustin 2 -147.2183 108 -1.6091 104 0.0000 105 0.0000 105
108 105 PFSC-PFVM 41 -146.8286 107 -1.9714 108 0.0000 105 0.0000 105
109 138 Shengyi 2 -148.0000 109 -2.0000 109 0.0000 105 0.0000 105
110 281 T2DUCC 1 -148.0000 109 -2.0000 109 0.0000 105 0.0000 105
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.
Protein Structure Prediction Center
Sponsored by the US National Institute of General Medical Sciences (NIH/NIGMS)
Please address any questions or queries to:
© 2007-2024, University of California, Davis
Terms of Use