M. Jusot, D. Stratmann, M. Vaisset, J. Chomilier, 8. P. Rose et al., , p.569

C. H. Christie, L. D. Costanzo, J. M. Duarte, and S. Dutta, , p.570

Z. Feng, The rcsb protein data bank: integrative 571 view of protein, gene and 3d structural information, Nucleic 572 Acids Research, vol.45, issue.D1, p.573, 2017.

M. Ignatov, C. Liu, A. Alekseenko, Z. Sun, and D. Padhorny, , p.574

S. Kotelnikov, A. Kazennov, I. Grebenkin, and Y. Kholodov, , p.575

I. Kolosvari, Monte carlo on the manifold and md 576 refinement for binding pose prediction of protein-ligand com-577 plexes: 2017 d3r grand challenge, Journal of computer-aided 578 molecular design, vol.33, issue.1, p.579, 2019.

A. Kumar and K. Y. Zhang, Shape similarity guided pose 580 prediction: lessons from d3r grand challenge 3, vol.33, p.583

P. I. Koukos, L. C. Xue, and A. M. Bonvin, Protein-584 ligand pose and affinity prediction: Lessons from d3r grand 585 challenge 3, Journal of computer-aided molecular design, vol.586, issue.1, p.587, 2019.

D. D. Nguyen, Z. Cang, K. Wu, M. Wang, Y. Cao et al., , vol.588

. Wei, Mathematical deep learning for pose and binding affin-589 ity prediction and ranking in d3r grand challenges, Journal 590 of computer-aided molecular design, vol.33, issue.1, p.592, 2019.

P. C. Lam, R. Abagyan, and M. Totrov, Hybrid recep-593 tor structure/ligand-based docking and activity prediction in 594 icm: development and evaluation in d3r grand challenge 3, 595 Journal of computer-aided molecular design, vol.33, issue.1, pp.35-46, 2019.

L. Chaput, E. Selwa, E. Elisee, and B. I. Iorga, Blinded eval-598 uation of cathepsin s inhibitors from the d3rgc3 dataset using 599 molecular docking and free energy calculations, Journal of 600 computer-aided molecular design, vol.33, issue.1, p.602, 2019.

J. Sunseri, J. E. King, P. G. Francoeur, and D. R. Koes, Convolutional neural network scoring and minimization in 604 the d3r 2017 community challenge, Journal of computer-605 aided molecular design, vol.603, issue.1, p.606, 2019.

X. He, V. H. Man, B. Ji, X. Xie, and J. Wang, Calcu-607 late protein-ligand binding affinities with the extended lin-608 ear interaction energy method: application on the cathepsin s 609 set in the d3r grand challenge 3, Journal of computer-aided 610 molecular design, vol.33, issue.1, p.611, 2019.

B. Xie and D. D. Minh, Alchemical grid dock (algdock) cal-612 culations in the d3r grand challenge 3, vol.33, p.614, 2019.

R. Vassar, D. M. Kovacs, R. Yan, and P. C. Wong, The 615 ?-secretase enzyme bace in health and alzheimer's disease: 616 regulation, cell biology, function, and therapeutic potential, 617 Journal of Neuroscience, vol.29, issue.41, p.619, 2009.

F. Prati, G. Bottegoni, M. L. Bolognesi, and A. Cavalli, Bace-1 inhibitors: From recent single-target molecules to 621 multitarget compounds for alzheimer's disease: Miniperspec-622 tive, Journal of medicinal chemistry, vol.620, issue.3, p.624, 2017.

S. Hanessian, G. Yang, J. Rondeau, and U. Neumann, , p.625

C. Betschart and M. Tintelnot-blomley, Structure-based 626 design and synthesis of macroheterocyclic peptidomimetic 627 inhibitors of the aspartic protease ?-site amyloid precursor 628 protein cleaving enzyme (bace), Journal of medicinal chem-629 istry, vol.49, issue.15, p.630, 2006.

J. B. Jordan, D. A. Whittington, M. D. Bartberger, and E. A. , , vol.631

K. Sickmier, Y. Chen, T. Cheng, and . Judd,

S. Butini, S. Brogi, E. Novellino, G. Campiani, and A. Ghosh, , p.636

M. Brindisi and S. Gemma, The structural evolution of ?-637 secretase inhibitors: a focus on the development of small-638 molecule inhibitors, Current topics in medicinal chemistry, vol.639, issue.15, pp.1787-1807, 2013.

O. Trott and A. J. Olson, AutoDock Vina: Improving the 641 speed and accuracy of docking with a new scoring func-642 tion, efficient optimization, and multithreading, J. Comput

, Chem, vol.31, issue.2, pp.455-461, 2010.

M. Kadukova and S. Grudinin, Convex-pl: a novel 645 knowledge-based potential for protein-ligand interactions de-646 duced from structural databases using convex optimization, 647 Journal of computer-aided molecular design, vol.31, issue.10, pp.943-958, 2017.

M. Kadukova and S. Grudinin, Knodle: A support vector 650 machines-based automatic perception of organic molecules 651 from 3d coordinates, J. Chem. Inf. Model, vol.56, pp.1410-1419, 2016.

G. M. Morris, R. Huey, W. Lindstrom, M. F. Sanner, and R. K. ,

D. S. Belew, A. J. Goodsell, and . Olson, Autodock4 and 655 autodocktools4: Automated docking with selective receptor 656 flexibility, J. Comput. Chem, vol.30, issue.16, pp.2785-2791, 2009.

.. Z. Liu, M. Su, L. Han, J. Liu, Q. Yang et al., Forging the basis for developing protein-ligand interaction 660 scoring functions, Accounts of chemical research, vol.659, issue.2, pp.302-309, 2017.

S. Artemova, S. Grudinin, and S. Redon, A comparison of 663 neighbor search algorithms for large rigid molecules, Journal 664 of Computational Chemistry, vol.32, issue.13, pp.2865-2877, 2011.

K. V. Klenin, F. Tristram, T. Strunk, and W. Wenzel, Derivatives of molecular surface area and volume: Simple 668 and exact analytical formulas, Journal of computational 669 chemistry, vol.667, issue.12, pp.2647-2653, 2011.

K. Klenin, F. Tristram, T. Strunk, and W. Wenzel, Achiev-671 ing numerical stability in analytical computation of the 672 molecular surface and volume, From Computational Bio-673 physics to Systems Biology, issue.CBSB11

, Scheraga's 90th Birthday, vol.8, p.75, 2012.

S. Grudinin, P. Popov, E. Neveu, and G. Cheremovskiy, Pre-676 dicting binding poses and affinities in the csar 2013-2014 677 docking exercises using the knowledge-based convex-pl po-678 tential, J. Chem. Inf. Model, vol.56, issue.6, pp.1053-1062, 2015.

S. Grudinin, M. Kadukova, A. Eisenbarth, and S. Marillet, , p.681