# Learning to Extend Molecular Scaffolds with Structural Motifs

arXiv: https://arxiv.org/abs/2103.03864 · HTML: https://mlsanity.com/paper/2103.03864/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 60 references that are in the map.
- First posted on arXiv 5 Mar 2021.

## Builds on (most cited first, 30 of 34)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [MolGAN: An implicit generative model for small molecular graphs](https://mlsanity.com/paper/1805.11973/) (2018)
- [GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders](https://mlsanity.com/paper/1802.03480/) (2018)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (2018)
- [Efficient Graph Generation with Graph Recurrent Attention Networks](https://mlsanity.com/paper/1910.00760/) (2019)
- [Learning Deep Generative Models of Graphs](https://mlsanity.com/paper/1803.03324/) (2018)
- [Hierarchical Generation of Molecular Graphs using Structural Motifs](https://mlsanity.com/paper/2002.03230/) (2020)
- [Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discovery](https://mlsanity.com/paper/1803.09518/) (2018)
- [Constrained Graph Variational Autoencoders for Molecule Design](https://mlsanity.com/paper/1805.09076/) (2018)
- [Multi-Objective De Novo Drug Design with Conditional Graph Generative Model](https://mlsanity.com/paper/1801.07299/) (2018)
- [Molecule Edit Graph Attention Network: Modeling Chemical Reactions as Sequences of Graph Edits](https://mlsanity.com/paper/2006.15426/) (2020)
- [GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation](https://mlsanity.com/paper/1906.12192/) (2019)
- [Guiding Deep Molecular Optimization with Genetic Exploration](https://mlsanity.com/paper/2007.04897/) (2020)
- [Barking up the right tree: an approach to search over molecule synthesis DAGs](https://mlsanity.com/paper/2012.11522/) (2020)
- [DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation](https://mlsanity.com/paper/1811.09766/) (2018)
- [Scaffold-constrained molecular generation](https://mlsanity.com/paper/2009.07778/) (2020)
- [DeepScaffold: a comprehensive tool for scaffold-based de novo drug discovery using deep learning](https://mlsanity.com/paper/1908.07209/) (2019)

## Built on by (most cited first, 30 of 71)

- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation](https://mlsanity.com/paper/2302.09048/) (2023)
- [Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation](https://mlsanity.com/paper/2110.01219/) (2021)
- [Graph-based Molecular Representation Learning](https://mlsanity.com/paper/2207.04869/) (2022)
- [Regression Transformer: Concurrent sequence regression and generation for molecular language modeling](https://mlsanity.com/paper/2202.01338/) (2022)
- [GenMol: A Drug Discovery Generalist with Discrete Diffusion](https://mlsanity.com/paper/2501.06158/) (2025)
- [Gotta be SAFE: A New Framework for Molecular Design](https://mlsanity.com/paper/2310.10773/) (2023)
- [De Novo Molecular Generation via Connection-aware Motif Mining](https://mlsanity.com/paper/2302.01129/) (2023)
- [Retrieval-based Controllable Molecule Generation](https://mlsanity.com/paper/2208.11126/) (2022)
- [LIMO: Latent Inceptionism for Targeted Molecule Generation](https://mlsanity.com/paper/2206.09010/) (2022)
- [Re-evaluating Retrosynthesis Algorithms with Syntheseus](https://mlsanity.com/paper/2310.19796/) (2023)
- [Sparse Training of Discrete Diffusion Models for Graph Generation](https://mlsanity.com/paper/2311.02142/) (2023)
- [DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization](https://mlsanity.com/paper/2403.13829/) (2024)
- [Molecule Generation with Fragment Retrieval Augmentation](https://mlsanity.com/paper/2411.12078/) (2024)
- [Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design](https://mlsanity.com/paper/2210.04893/) (2022)
- [Drug Discovery with Dynamic Goal-aware Fragments](https://mlsanity.com/paper/2310.00841/) (2023)
- [De novo Drug Design using Reinforcement Learning with Multiple GPT Agents](https://mlsanity.com/paper/2401.06155/) (2023)
- [C5T5: Controllable Generation of Organic Molecules with Transformers](https://mlsanity.com/paper/2108.10307/) (2021)
- [Accelerating Material Design with the Generative Toolkit for Scientific Discovery](https://mlsanity.com/paper/2207.03928/) (2022)
- [DrugLLM: Open Large Language Model for Few-shot Molecule Generation](https://mlsanity.com/paper/2405.06690/) (2024)
- [Saturn: Sample-efficient Generative Molecular Design using Memory Manipulation](https://mlsanity.com/paper/2405.17066/) (2024)
- [t-SMILES: A Scalable Fragment-based Molecular Representation Framework for De Novo Molecule Generation](https://mlsanity.com/paper/2301.01829/) (2023)
- [Molecule Generation for Drug Design: a Graph Learning Perspective](https://mlsanity.com/paper/2202.09212/) (2022)
- [ToDD: Topological Compound Fingerprinting in Computer-Aided Drug Discovery](https://mlsanity.com/paper/2211.03808/) (2022)
- [Flatten Graphs as Sequences: Transformers are Scalable Graph Generators](https://mlsanity.com/paper/2502.02216/) (2025)
- [RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNets](https://mlsanity.com/paper/2406.18739/) (2024)
- [Deep Learning Methods for Small Molecule Drug Discovery: A Survey](https://mlsanity.com/paper/2303.00313/) (2023)
- [Expressivity and Generalization: Fragment-Biases for Molecular GNNs](https://mlsanity.com/paper/2406.08210/) (2024)
- [Unified Guidance for Geometry-Conditioned Molecular Generation](https://mlsanity.com/paper/2501.02526/) (2025)
- [Molecule Design by Latent Prompt Transformer](https://mlsanity.com/paper/2310.03253/) (2023)

## Abstract (arXiv)

Recent advancements in deep learning-based modeling of molecules promise to accelerate in silico drug discovery. A plethora of generative models is available, building molecules either atom-by-atom and bond-by-bond or fragment-by-fragment. However, many drug discovery projects require a fixed scaffold to be present in the generated molecule, and incorporating that constraint has only recently been explored. Here, we propose MoLeR, a graph-based model that naturally supports scaffolds as initial seed of the generative procedure, which is possible because it is not conditioned on the generation history. Our experiments show that MoLeR performs comparably to state-of-the-art methods on unconstrained molecular optimization tasks, and outperforms them on scaffold-based tasks, while being an order of magnitude faster to train and sample from than existing approaches. Furthermore, we show the influence of a number of seemingly minor design choices on the overall performance.