Hierarchical Generation of Molecular Graphs using Structural Motifs

Wengong Jin, Dr.Regina Barzilay, Tommi Jaakkola
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:4839-4848, 2020.

Abstract

Graph generation techniques are increasingly being adopted for drug discovery. Previous graph generation approaches have utilized relatively small molecular building blocks such as atoms or simple cycles, limiting their effectiveness to smaller molecules. Indeed, as we demonstrate, their performance degrades significantly for larger molecules. In this paper, we propose a new hierarchical graph encoder-decoder that employs significantly larger and more flexible graph motifs as basic building blocks. Our encoder produces a multi-resolution representation for each molecule in a fine-to-coarse fashion, from atoms to connected motifs. Each level integrates the encoding of constituents below with the graph at that level. Our autoregressive coarse-to-fine decoder adds one motif at a time, interleaving the decision of selecting a new motif with the process of resolving its attachments to the emerging molecule. We evaluate our model on multiple molecule generation tasks, including polymers, and show that our model significantly outperforms previous state-of-the-art baselines.

Cite this Paper


BibTeX
@InProceedings{pmlr-v119-jin20a, title = {Hierarchical Generation of Molecular Graphs using Structural Motifs}, author = {Jin, Wengong and Barzilay, Dr.Regina and Jaakkola, Tommi}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {4839--4848}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/jin20a/jin20a.pdf}, url = {http://proceedings.mlr.press/v119/jin20a.html}, abstract = {Graph generation techniques are increasingly being adopted for drug discovery. Previous graph generation approaches have utilized relatively small molecular building blocks such as atoms or simple cycles, limiting their effectiveness to smaller molecules. Indeed, as we demonstrate, their performance degrades significantly for larger molecules. In this paper, we propose a new hierarchical graph encoder-decoder that employs significantly larger and more flexible graph motifs as basic building blocks. Our encoder produces a multi-resolution representation for each molecule in a fine-to-coarse fashion, from atoms to connected motifs. Each level integrates the encoding of constituents below with the graph at that level. Our autoregressive coarse-to-fine decoder adds one motif at a time, interleaving the decision of selecting a new motif with the process of resolving its attachments to the emerging molecule. We evaluate our model on multiple molecule generation tasks, including polymers, and show that our model significantly outperforms previous state-of-the-art baselines.} }
Endnote
%0 Conference Paper %T Hierarchical Generation of Molecular Graphs using Structural Motifs %A Wengong Jin %A Dr.Regina Barzilay %A Tommi Jaakkola %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-jin20a %I PMLR %P 4839--4848 %U http://proceedings.mlr.press/v119/jin20a.html %V 119 %X Graph generation techniques are increasingly being adopted for drug discovery. Previous graph generation approaches have utilized relatively small molecular building blocks such as atoms or simple cycles, limiting their effectiveness to smaller molecules. Indeed, as we demonstrate, their performance degrades significantly for larger molecules. In this paper, we propose a new hierarchical graph encoder-decoder that employs significantly larger and more flexible graph motifs as basic building blocks. Our encoder produces a multi-resolution representation for each molecule in a fine-to-coarse fashion, from atoms to connected motifs. Each level integrates the encoding of constituents below with the graph at that level. Our autoregressive coarse-to-fine decoder adds one motif at a time, interleaving the decision of selecting a new motif with the process of resolving its attachments to the emerging molecule. We evaluate our model on multiple molecule generation tasks, including polymers, and show that our model significantly outperforms previous state-of-the-art baselines.
APA
Jin, W., Barzilay, D. & Jaakkola, T.. (2020). Hierarchical Generation of Molecular Graphs using Structural Motifs. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:4839-4848 Available from http://proceedings.mlr.press/v119/jin20a.html.

Related Material