Skip to main content
. Author manuscript; available in PMC: 2020 Jan 10.
Published in final edited form as: J Comput Aided Mol Des. 2019 Jan 10;33(1):1–18. doi: 10.1007/s10822-018-0180-4

Table 5.

Top 3 submissions, based on Kendall’s τ, for each affinity ranking challenge. Submission ID in bold font indicates a method that used machine learning. See Table 3 for details.

Kendall’s Tau Software Submitter/PI Organization Submission ID
Cats Stage 1
0.45 molsoft icm 3.8–5 P. Lam/M.Totrov Molsoft vtuzm
0.36 chemminer, libsvm 3.21 A. Bonvin/A. Bonvin Utrecht University kevrd
0.35 ligprep v33013 scaffopt T. Evangelidis/T. Evangelidis Central European Institute of Technology kb2du
Cats Stage 2
0.39 molsoft icm 3.8–7 P. Lam/M.Totrov Molsoft q2k8y
0.34 ligprep v33013 scaffopt T. Evangelidis/T. Evangelidis Central European Institute of Technology m6yb2
0.32 ligprep v33013 scaffopt T. Evangelidis/T. Evangelidis Central European Institute of Technology e4emg
ABL1
0.52 rhodium 380e9–x9/openbabel 2.3.90 / pymol 1.3 J. Bohmann/Medicinal and Process Chemistry Southwest Research Institute 3o8xi
0.52 schrodinger, gold, autodock vina, r-tda, javaplex, sci kit-learn Z. Cang/W. Guo-Wei Michigan State University rdn3k
0.43 ri-score/tdl-bp/autodock vina D. Nguyen/W. Guo-Wei Michigan State University c4xt7
JAK2 SC2
0.55 docking performed with gnina commit b3fa6ae13fc6b42924f49b2d751d68f1bc14bc08 available from https//github.com/gnina/gnina, conformer generation performed with rdkit via https//github.com/dkoes/rdkit-scripts/rdconf.py, ensemble of receptors chosen via pocketome. J. Sunseri/D. Koes University of Pittsburgh zdyb5
0.36 molsoft icm 3.8–6 P. Lam/M.Totrov Molsoft 7yjh3
0.23 amber11 X.Zou/X. Zou University of Missouri-Columbia qnq6x
JAK2 SC3
0.71 itscore2 X. Zou/X. Zou University of Missouri-Columbia 87mci
0.6 docking performed with gnina commit b3fa6ae13fc6b42924f49b2d751d68f1bc14bc08 available from https//github.com/gnina/gnina, conformer generation performed with rdkit viahttps//github.com/dkoes/rdkit-scripts/rdconf.py, ensemble of receptors chosen via pocketome. J. Sunseri/D. Koes University of Pittsburgh 7bi2k
0.56 docking performed with smina static binary available at https//sourceforge.net/projects/smina/files/ with default scoring function, then rescoring performed using gnina commit b3fa6ae13fc6b42924f49b2d751d68f1bc14bc08 available from https//github.com/gnina/gnina and the default cnn affinity model, conformer generation performed with rdkit via https//github.com/dkoes/rdkit-scripts/rdconf.py, ensemble of receptors chosen via pocketome. J. Sunseri/D. Koes University of Pittsburgh yghq5
p38-α
0.21 molsoft icm 3.8–6 P. Lam/M. Totrov Molsoft 8b6kk
0.2 smina feb 28 2016, based on autodock vina 1.1.2 openbabel 2.3.2 pymol 1.8.4.2 python 2.7.11 matplotlib 1.5.1 scipy 0.17.0 click 6.6 B. Wingert/C. Camacho University of Pittsburgh u48q2
0.13 smina feb 28 2016, based on autodock vina 1.1.2 openbabel 2.3.2 pymol 1.8.4.2 python 2.7.11 matplotlib 1.5.1 scipy 0.17.0 click 6.6 B. Wingert/C. Camacho University of Pittsburgh 5vy6c
TIE2
0.57 ri-score/tdl-bp/autodock vina D. Nguyen/W. Guo-Wei Michigan State University uuihe
0.57 schrodinger, gold, autodock vina, r-tda, javaplex, scikit-learn Z. Cang/W. Guo-Wei Michigan State University y7qxv
0.5 docking performed with smina static binary available at https//sourceforge.net/projects/smina/files/ with default scoring function, then rescoring performed using gnina commit b3fa6ae13fc6b42924f49b2d751d68f1bc14bc08 available from https//github.com/gnina/gnina and the default cnn affinity model, conformer generation performed with rdkit via https//github.com/dkoes/rdkit-scripts/rdconf.py, ensemble of receptors chosen via pocketome. J. Sunseri/D. Koes University of Pittsburgh xpmn7
VEGFR2
0.43 molsoft icm 3.8–6 P. Lam/M. Totrov Molsoft y0048
0.4 itscore2 X.Zou/X. Zou University of Missouri-Columbia uv5tc
0.38 chemminer, libsvm 3.21 A. Bonvin/A. Bonvin Utrecht University 7smbe