Structure-aware generation of drug-like molecules
By Pavol Drotár, Arian Jamasb, Ben Day, Cătălina Cangea, Pietro Lio'. 2021
21 citations recorded by the source corpus.
Structure-based drug design involves finding ligand molecules that exhibit structural and chemical complementarity to protein pockets. Deep generative methods have shown promise in proposing novel molecules from scratch (de-novo design), avoiding exhaustive virtual screening of chemical space. Most generative de-novo models fail to incorporate detailed ligand-protein interactions and 3D pocket structures. We propose a novel supervised model that generates molecular graphs jointly with 3D pose in a discretised molecular space. Molecules are built atom-by-atom inside pockets, guided by structural information from crystallographic data. We evaluate our model using a docking benchmark and find that guided generation improves predicted binding affinities by 8% and drug-likeness scores by 10% over the baseline. Furthermore, our model proposes molecules with binding scores exceeding some known ligands, which could be useful in future wet-lab studies.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Regina Barzilay
- Tommi S. Jaakkola
- Hannes Stärk
- Octavian-Eugen Ganea
- Percy Liang
- Yoshua Bengio
- Lagnajit Pattanaik
- Mohit Bansal
Citations in the corpus
- EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction (2022, methodology): “, 2020) or de novo binder generation (Masuda et al., 2020; Imrie et al., 2021; Drotár et al., 2021).”
- Structure-based drug design with equivariant diffusion models (2022, unknown): “, to generate ligands inside protein pockets atom by atom (Drotár et al., 2021; Luo et al., 2021; Li et al., 2021; Peng et al., 2022).”