# SynthFormer: Equivariant Pharmacophore-based Generation of Synthesizable Molecules for Ligand-Based Drug Design

arXiv: https://arxiv.org/abs/2410.02718 · HTML: https://mlsanity.com/paper/2410.02718/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 52 references that are in the map.
- First posted on arXiv 3 Oct 2024.

## Builds on (most cited first, 15 of 15)

- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [MolGAN: An implicit generative model for small molecular graphs](https://mlsanity.com/paper/1805.11973/) (2018)
- [DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking](https://mlsanity.com/paper/2210.01776/) (2022)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (2018)
- [Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models](https://mlsanity.com/paper/1811.12823/) (2018)
- [Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets](https://mlsanity.com/paper/2205.07249/) (2022)
- [3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction](https://mlsanity.com/paper/2303.03543/) (2023)
- [EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction](https://mlsanity.com/paper/2202.05146/) (2022)
- [The Synthesizability of Molecules Proposed by Generative Models](https://mlsanity.com/paper/2002.07007/) (2020)
- [DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding](https://mlsanity.com/paper/2211.11214/) (2022)
- [Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design](https://mlsanity.com/paper/2110.06389/) (2021)
- [Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design](https://mlsanity.com/paper/2210.04893/) (2022)
- [Projecting Molecules into Synthesizable Chemical Spaces](https://mlsanity.com/paper/2406.04628/) (2024)
- [Activity Cliff Prediction: Dataset and Benchmark](https://mlsanity.com/paper/2302.07541/) (2023)

## Built on by (most cited first, 2 of 2)

- [Efficient and Programmable Exploration of Synthesizable Chemical Space](https://mlsanity.com/paper/2512.00384/) (2025)
- [It Takes Two to Tango: Directly Optimizing for Constrained Synthesizability in Generative Molecular Design](https://mlsanity.com/paper/2410.11527/) (2024)

## Abstract (arXiv)

Drug discovery is a complex, resource-intensive process requiring significant time and cost to bring new medicines to patients. Many generative models aim to accelerate drug discovery, but few produce synthetically accessible molecules. Conversely, synthesis-focused models do not leverage the 3D information crucial for effective drug design. We introduce SynthFormer, a novel machine learning model that generates fully synthesizable molecules, structured as synthetic trees, by introducing both 3D information and pharmacophores as input. SynthFormer features a 3D equivariant graph neural network to encode pharmacophores, followed by a Transformer-based synthesis-aware decoding mechanism for constructing synthetic trees as a sequence of tokens. It is a first-of-its-kind approach that could provide capabilities for designing active molecules based on pharmacophores, exploring the local synthesizable chemical space around hit molecules and optimizing their properties. We demonstrate its effectiveness through various challenging tasks, including designing active compounds for a range of proteins, performing hit expansion and optimizing molecular properties.