mlsanityData to 7 Oct 2026

Drug Discovery SMILES-to-Pharmacokinetics Diffusion Models with Deep Molecular Understanding

arXiv 2408.07636 ↗First posted 14 Aug 2024q-bio.QM cs.AI cs.LGcited by 0

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

Abstract (arXiv)

Artificial intelligence (AI) is increasingly used in every stage of drug development. One challenge facing drug discovery AI is that drug pharmacokinetic (PK) datasets are often collected independently from each other, often with limited overlap, creating data overlap sparsity. Data sparsity makes data curation difficult for researchers looking to answer research questions in poly-pharmacy, drug combination research, and high-throughput screening. We propose Imagand, a novel SMILES-to-Pharmacokinetic (S2PK) diffusion model capable of generating an array of PK target properties conditioned on SMILES inputs. We show that Imagand-generated synthetic PK data closely resembles real data univariate and bivariate distributions, and improves performance for downstream tasks. Imagand is a promising solution for data overlap sparsity and allows researchers to efficiently generate ligand PK data for drug discovery research. Code is available at https://github.com/bing1100/Imagand.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 22 of its 59 references that are in the map. First posted on arXiv 14 Aug 2024.

Builds on

22 of 59 references.

References · 22

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2022Classifier-Free Diffusion Guidancecited by 5,717
  7. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  8. 2014Conditional Generative Adversarial Netscited by 2,152
  9. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  10. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  11. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  12. 2020A Generalization of Transformer Networks to Graphscited by 653
10 more
  1. 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptionscited by 440
  2. 2020ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Predictioncited by 332
  3. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 326
  4. 2018GuacaMol: Benchmarking Models for De Novo Molecular Designcited by 294
  5. 2022Language Models are Realistic Tabular Data Generatorscited by 290
  6. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 258
  7. 2022ChemBERTa-2: Towards Chemical Foundation Modelscited by 123
  8. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  9. 2023Conditional Diffusion Based on Discrete Graph Structures for Molecular Graph Generationcited by 46
  10. 2020Network Medicine Framework for Identifying Drug Repurposing Opportunities for COVID-19cited by 38

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Synthetic Data from Diffusion Models Improve Drug Discovery Prediction
  2. 2024SMILES-Mamba: Chemical Mamba Foundation Models for Drug ADMET Prediction
  3. 2026Physiologically Informed Deep Learning: A Multi-Scale Framework for Next-Generation PBPK Modeling
  4. 2025Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides
  5. 2026Genotype-Conditioned Molecular Generation via Evidence-Grounded Multi-Objective Latent Perturbation in Diffusion Models
  6. 2025Pharmacophore-Conditioned Diffusion Model for Ligand-Based De Novo Drug Design
  7. 2024DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration
  8. 2024Guided Multi-objective Generative AI to Enhance Structure-based Drug Design