RECORD
MAGNet: Motif-Agnostic Generation of Molecules from Shapes
Chemical Physics · Submitted 30 May 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Despite the added complexity of shape abstractions, MAGNet outperforms most other graph-based approaches on standard benchmarks.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Recent advances in machine learning for molecules exhibit great potential for facilitating drug discovery from in silico predictions. Most models for molecule generation rely on the decomposition of molecules into frequently occurring substructures (motifs), from which they generate novel compounds. While motif representations greatly aid in learning molecular distributions, such methods struggle to represent substructures beyond their known motif set. To alleviate this issue and increase flexibility across datasets, we propose MAGNet, a graph-based model that generates abstract shapes before allocating atom and bond types. To this end, we introduce a novel factorisation of the molecules' data distribution that accounts for the molecules' global context and facilitates learning adequate assignments of atoms and bonds onto shapes. Despite the added complexity of shape abstractions, MAGNet outperforms most other graph-based approaches on standard benchmarks. Importantly, we demonstrate that MAGNet's improved expressivity leads to molecules with more topologically distinct structures and, at the same time, diverse atom and bond assignments.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Recent advances in machine learning for molecules exhibit great potential for facilitating drug discovery from in silico predictions. | background 1.00 | 0.04 | 0.02 | asserted 0.79 |
| s1 | Most models for molecule generation rely on the decomposition of molecules into frequently occurring substructures (motifs), from which they generate novel compounds. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s2 | While motif representations greatly aid in learning molecular distributions, such methods struggle to represent substructures beyond their known motif set. | gap 0.72 | 0.07 | 0.04 | asserted 0.99 |
| s3 | To alleviate this issue and increase flexibility across datasets, we propose MAGNet, a graph-based model that generates abstract shapes before allocating atom and bond types. | contribution 0.74 | 0.89 | 0.09 | asserted 0.98 |
| s4 | To this end, we introduce a novel factorisation of the molecules' data distribution that accounts for the molecules' global context and facilitates learning adequate assignments of atoms and bonds onto shapes. | method 0.73 | 0.88 | 0.06 | asserted 0.97 |
| s5 | Despite the added complexity of shape abstractions, MAGNet outperforms most other graph-based approaches on standard benchmarks. | result 1.00 | 0.93 | 0.48 | asserted 1.00 |
| s6 | Importantly, we demonstrate that MAGNet's improved expressivity leads to molecules with more topologically distinct structures and, at the same time, diverse atom and bond assignments. | result 0.77 | 0.96 | 0.59 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Recent advances in machine learning for molecules exhibit great potential for facilitating drug discovery from in silico predictions. Most models for molecule generation rely on the decomposition of molecules into frequently occurring substructures (motifs), from which they generate novel compounds. While motif representations greatly aid in learning molecular distributions, such methods struggle to represent substructures beyond their known motif set. To alleviate this issue and increase flexibility across datasets, we propose MAGNet, a graph-based model that generates abstract shapes before allocating atom and bond types. To this end, we introduce a novel factorisation of the molecules' data distribution that accounts for the molecules' global context and facilitates learning adequate assignments of atoms and bonds onto shapes. Despite the added complexity of shape abstractions, MAGNet outperforms most other graph-based approaches on standard benchmarks. Importantly, we demonstrate that MAGNet's improved expressivity leads to molecules with more topologically distinct structures and, at the same time, diverse atom and bond assignments.
Human review
How the literature uses it
2 arXiv papers cite this in 3 sentences
Papers citing it · 2 sentences without a confident label
Cites it as background 1 paper
-
De novo molecule generation Research on de novo molecule generation focused extensively on generating molecules using their chemical graph representations [ref] .
Unified Guidance for Geometry-Conditioned Molecular Generation · Related work · 0.97
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.