G. Alain and Y. Bengio, What regularized auto-encoders learn from the data-generating distribution, Journal of Machine Learning Research, vol.15, issue.1, pp.3563-3593, 2014.

Y. Bengio, L. Yao, G. Alain, and P. Vincent, Generalized denoising auto-encoders as generative models, Advances in Neural Information Processing Systems, pp.899-907, 2013.

R. Samuel, L. Bowman, O. Vilnis, . Vinyals, M. Andrew et al., Generating sentences from a continuous space, 2015.

K. Cho, B. Van-merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares et al., Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint, 2014.
URL : https://hal.archives-ouvertes.fr/hal-01433235

F. Dey and A. Caflisch, Fragment-Based de Novo Ligand Design by Multiobjective Evolutionary Optimization, Journal of Chemical Information and Modeling, vol.48, issue.3, pp.679-690, 2008.
DOI : 10.1021/ci700424b

D. Douguet, G. Héì-ene-munier-lehmann, S. Labesse, and . Pochet, LEA3D: A Computer-Aided Ligand Design for Structure-Based Drug Design, Journal of Medicinal Chemistry, vol.48, issue.7, pp.2457-2468, 2005.
DOI : 10.1021/jm0492296

URL : https://hal.archives-ouvertes.fr/pasteur-00166207

P. Ertl and A. Schuffenhauer, Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions, Journal of Cheminformatics, vol.1, issue.1, p.8, 2009.
DOI : 10.1186/1758-2946-1-8

U. Fechner and G. Schneider, Flux (1):?? A Virtual Synthesis Scheme for Fragment-Based de Novo Design, Journal of Chemical Information and Modeling, vol.46, issue.2, pp.699-707, 2006.
DOI : 10.1021/ci0503560

V. Gillet, P. Peter-johnson, S. Mata, P. Sike, and . Williams, SPROUT: A program for structure generation, Journal of Computer-Aided Molecular Design, vol.28, issue.2, pp.127-153, 1993.
DOI : 10.1007/978-3-662-09438-9

R. Gómez-bombarelli, J. Aguilera-iparraguirre, D. Timothy, D. Hirzel, D. Duvenaud et al., Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach, Nature Materials, vol.5, issue.10, pp.151120-1127, 2016.
DOI : 10.1021/ct9003004

R. Gómez-bombarelli, D. Duvenaud, J. Miguel-hernández-lobato, J. Aguilera-iparraguirre, D. Timothy et al., Automatic chemical design using a data-driven continuous representation of molecules. arXiv preprint, 2016.

M. Hartenfeller and G. Schneider, design, Wiley Interdisciplinary Reviews: Computational Molecular Science, vol.3, issue.5, pp.742-759, 2011.
DOI : 10.4155/fmc.11.8

M. Hartenfeller, H. Zettl, M. Walter, M. Rupp, F. Reisen et al., DOGS: Reaction-Driven de novo Design of Bioactive Compounds, PLoS Computational Biology, vol.309, issue.2, p.1002380, 2012.
DOI : 10.1371/journal.pcbi.1002380.s001

S. Hochreiter and J. Schmidhuber, Long Short-Term Memory, Neural Computation, vol.4, issue.8, pp.1735-1780, 1997.
DOI : 10.1016/0893-6080(88)90007-X

J. John, T. Irwin, . Sterling, M. Michael, . Mysinger et al., Zinc: a free tool to discover chemistry for biology, Journal of chemical information and modeling, vol.52, issue.7, pp.1757-1768, 2012.

R. Donald, M. Jones, . Schonlau, J. William, and . Welch, Efficient global optimization of expensive black-box functions, Journal of Global optimization, vol.13, issue.4, pp.455-492, 1998.

A. Karpathy, J. Johnson, and L. Fei-fei, Visualizing and understanding recurrent networks. arXiv preprint, 2015.

S. Peter, . Kutchukian, I. Eugene, and . Shakhnovich, De novo design: balancing novelty and confined chemical space, Expert opinion on drug discovery, vol.5, issue.8, pp.789-812, 2010.

M. Alex, A. Lamb, A. Goyal, Y. Parth-goyal, S. Zhang et al., Professor forcing: A new algorithm for training recurrent networks, Advances In Neural Information Processing Systems, pp.4601-4609, 2016.

G. Landrum, Rdkit: Open-source cheminformatics. Online) http://www. rdkit. org, Accessed, vol.3, issue.04, p.2012, 2006.

Y. Li, Y. Zhao, Z. Liu, and R. Wang, Automatic Tailoring and Transplanting: A Practical Method that Makes Virtual Screening More Useful, Journal of Chemical Information and Modeling, vol.51, issue.6, 2011.
DOI : 10.1021/ci200036m

Y. Li, Z. Zhao, Z. Liu, M. Su, and R. Wang, AutoT&T v.2: An Efficient and Versatile Tool for Lead Structure Generation and Optimization, Journal of Chemical Information and Modeling, vol.56, issue.2, pp.435-453, 2016.
DOI : 10.1021/acs.jcim.5b00691

B. Brian, . Masek, S. David, . Baker, J. Roman et al., Multistep reaction based de novo drug design: Generating synthetically feasible design ideas, Journal of chemical information and modeling, vol.56, issue.4, pp.605-620, 2016.

J. Mo?kus, On bayesian methods for seeking the extremum, Optimization Techniques IFIP Technical Conference, pp.400-404, 1975.

C. Albert, G. Pierce, . Rao, W. Guy, and . Bemis, Breed: Generating novel inhibitors through hybridization of known ligands. application to cdk2, p38, and hiv protease, Journal of medicinal chemistry, issue.11, pp.472768-2775, 2004.

G. Schneider, De novo design?hop (p) ing against hope. Drug Discovery Today: Technologies, pp.453-460, 2013.

P. Schneider and G. Schneider, De Novo Design at the Edge of Chaos, Journal of Medicinal Chemistry, vol.59, issue.9, pp.4077-4086, 2016.
DOI : 10.1021/acs.jmedchem.5b01849

H. Marwin, T. Segler, C. Kogej, . Tyrchan, P. Mark et al., Generating focussed molecule libraries for drug discovery with recurrent neural networks, 2017.

T. Sterling, J. John, and . Irwin, ZINC 15 ??? Ligand Discovery for Everyone, Journal of Chemical Information and Modeling, vol.55, issue.11, 2015.
DOI : 10.1021/acs.jcim.5b00559

I. Sutskever, O. Vinyals, V. Quoc, and . Le, Sequence to sequence learning with neural networks, Advances in neural information processing systems, pp.3104-3112, 2014.

P. Vincent, H. Larochelle, Y. Bengio, and P. Manzagol, Extracting and composing robust features with denoising autoencoders, Proceedings of the 25th international conference on Machine learning, ICML '08, pp.1096-1103, 2008.
DOI : 10.1145/1390156.1390294

R. Wang, Y. Gao, and L. Lai, LigBuilder: A Multi-Purpose Program for Structure-Based Drug Design, Journal of Molecular Modeling, vol.6, issue.7-8, pp.498-516, 2000.
DOI : 10.1007/s0089400060498

D. Weininger, SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules, Journal of Chemical Information and Modeling, vol.28, issue.1, pp.31-36, 1988.
DOI : 10.1021/ci00057a005

D. White, C. Richard, and . Wilson, Generative Models for Chemical Structures, Journal of Chemical Information and Modeling, vol.50, issue.7, pp.1257-1274, 2010.
DOI : 10.1021/ci9004089

A. Scott, . Wildman, M. Gordon, and . Crippen, Prediction of physicochemical parameters by atomic contributions, Journal of chemical information and computer sciences, vol.39, issue.5, pp.868-873, 1999.

J. Ronald, D. Williams, and . Zipser, A learning algorithm for continually running fully recurrent neural networks, Neural computation, vol.1, issue.2, pp.270-280, 1989.