mlsanityData to 14 Oct 2026

SOLD: SELFIES-based Objective-driven Latent Diffusion

arXiv 2509.25198 ↗First posted 3 Sep 2025cs.LGcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Recently, machine learning has made a significant impact on de novo drug design. However, current approaches to creating novel molecules conditioned on a target protein typically rely on generating molecules directly in the 3D conformational space, which are often slow and overly complex. In this work, we propose SOLD (SELFIES-based Objective-driven Latent Diffusion), a novel latent diffusion model that generates molecules in a latent space derived from 1D SELFIES strings and conditioned on a target protein. In the process, we also train an innovative SELFIES transformer and propose a new way to balance losses when training multi-task machine learning models.Our model generates high-affinity molecules for the target protein in a simple and efficient way, while also leaving room for future improvements through the addition of more data.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 17 of its 36 references that are in the map. First posted on arXiv 3 Sep 2025.

Builds on

17 of 36 references.

References · 17

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  7. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  8. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
  9. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 183
  10. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 177
  11. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 172
  12. 2022A 3D Generative Model for Structure-Based Drug Designcited by 149
5 more
  1. 2017Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Modelscited by 117
  2. 2020Molecular representation learning with language models and domain-relevant auxiliary taskscited by 94
  3. 2019SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discoverycited by 90
  4. 2019Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representationcited by 23
  5. 2017In silico generation of novel, drug-like chemical matter using the LSTM neural networkcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation
  2. 2023A Latent Diffusion Model for Protein Structure Generation
  3. 2025Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides
  4. 2026SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles
  5. 2023Geometric Latent Diffusion Models for 3D Molecule Generation
  6. 2025From thermodynamics to protein design: Diffusion models for biomolecule generation towards autonomous protein engineering
  7. 2023Accelerating Inference in Molecular Diffusion Models with Latent Representations of Protein Structure
  8. 2025Discriminative protein sequence modelling with Latent Space Diffusion