Machine Learning in Computer-Aided Drug Design

Drug discovery is a long and expensive process. Currently, pharmaceutical companies begin to acknowledge the potential of machine learning methods. These methods enable the effective exploration of the chemical space and the rapid identification of promising chemical compounds. During the presentation, I will discuss the possibilities of employing deep learning models in drug design. I will focus mainly on the models predicting molecular properties [2, 3] and generative models that are used to create new drug candidates and optimize chemical properties [4]. I am also going to describe some approaches that strive to improve these methods by making use of chemical simulations, which I am researching in my current projects [1].

 

[1] Cieplinski, T., Danel, T., Podlewska, S., & Jastrzebski, S.
(2020). We should at least be able to Design Molecules that Dock Well.
arXiv preprint arXiv:2006.16955.
[2] Danel, T., Spurek, P., Tabor, J., Śmieja, M., Struski, Ł., Słowik,
A., & Maziarka, Ł. (2019). Spatial Graph Convolutional Networks. arXiv
preprint arXiv:1909.05310.
[3] Maziarka, Ł., Danel, T., Mucha, S., Rataj, K., Tabor, J., &
Jastrzębski, S. (2020). Molecule Attention Transformer. arXiv preprint
arXiv:2002.08264.
[4] Maziarka, Ł., Pocha, A., Kaczmarczyk, J., Rataj, K., Danel, T., &
Warchoł, M. (2020). Mol-CycleGAN: a generative model for molecular
optimization. Journal of Cheminformatics, 12(1), 1-18.