Skip to content
DraconiticResearch
Search Sources API
186,546 studies31 sourcesUpdated 23 min ago
PreprintCC BY-NC-NDChemRxiv

ChemEidos: Synthesis-Aware Multimodal Foundation Models for Domain-Specific Generative Design

  • Jacob M. Remington
  • Elizabeth H. Frush
  • David A. Pardoe
  • William R. Pitt
  • Irene Pitard
  • Laetitia Breuil
Open at sourcePDFDOICite

Abstract

Generative artificial intelligence models for de novo drug discovery often suffer synthetic tractability issues and lack fidelity in underrepresented chemical domains. This white paper highlights ChemEidos, a novel multimodal generative design platform that utilizes the underlying patterns, forms, and organizing principles of chemical space (eidos) by incorporating expert domain knowledge in focused training sets and at inference time.

Related

  1. Generative and Foundation-Model Artificial Intelligence in Food Safety Analysis, Authenticity Identification, and Quality Control: A Systematic Review of Validation and Decision Readiness.
    Zied Bahroun, Mohamed Amine Abdeljaouad
    Foods (Basel, Switzerland)Peer-reviewedCC BYFull textAnalytical chemistryEurope PMC
  2. Domain-Informed AI Multimodal Foundation Model for Materials Science
    Carine de Menezes Rebello, Erick Giovani Sperandio Nascimento, Idelfonso B. R. Nogueira
    ChemRxivPreprintCC BYMaterials & polymersChemRxiv
  3. A Full-Spectrum Generative Lead Discovery (FSGLD) pipeline via DRUG-GAN: A multiscale method for drug-like/target-specific compound library generation
    Beihong Ji, Matthew Brock, Yuhui Wu +6
    Science AdvancesPeer-reviewedPublisher termsFull textGeneral chemistrySci. Adv.CrossrefEurope PMCPMC
  4. Multimodal LLM-Assisted Diagnosis of Cryptic Failure Modes in High-Throughput Experimentation: A Case Study in Gold Nanorod Synthesis
    Riya Patel, Gabriela Briceno, Amirali Aghazadeh +1
    ChemRxivPreprintCC BY-NC-NDFull textMaterials & polymersChemRxiv
  5. Adaptation of a retrosynthetic tool to project-specific chemistry: oligomer synthesis case study
    Almaz Gilmullin, Tagir Akhmetshin, Olga Klimchuk +6
    ChemRxivPreprintCC BYFull textGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@misc{remington2026chemeidos,
  title = {{ChemEidos: Synthesis-Aware Multimodal Foundation Models for Domain-Specific Generative Design}},
  author = {Jacob M. Remington and Elizabeth H. Frush and David A. Pardoe and William R. Pitt and Irene Pitard and Laetitia Breuil},
  howpublished = {ChemRxiv},
  year = {2026},
  month = oct,
  doi = {10.26434/chemrxiv.15010851/v1},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010851/v1},
  note = {CC BY-NC-ND},
}
RIS
TY  - UNPB
TI  - ChemEidos: Synthesis-Aware Multimodal Foundation Models for Domain-Specific Generative Design
AU  - Jacob M. Remington
AU  - Elizabeth H. Frush
AU  - David A. Pardoe
AU  - William R. Pitt
AU  - Irene Pitard
AU  - Laetitia Breuil
PY  - 2026
DA  - 2026/10/22
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15010851/v1
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010851/v1
AB  - Generative artificial intelligence models for de novo drug discovery often suffer synthetic tractability issues and lack fidelity in underrepresented chemical domains. This white paper highlights ChemEidos, a novel multimodal generative design platform that utilizes the underlying patterns, forms, and organizing principles of chemical space (eidos) by incorporating expert domain knowledge in focused training sets and at inference time.
ER  -