Skip to content
DraconiticResearch
Search Sources API
201,818 studies31 sourcesUpdated 35 min ago
PreprintCC BYChemRxiv

DeNoMAP: An Interactive Web Application for Multi-Criteria Prioritization of De Novo Designed Compounds

  • Francisco L. Feitosa1,2,3,4,5,6
  • Erik D. Díaz-Dionisio3,4
  • Juan F. Avellaneda-Tamayo3,4
  • Carolina Horta Andrade1,2,5,6
  • José L. Medina-Franco3,4
6 affiliations
  1. 1Laboratory for Molecular Modeling and Drug Design (LabMol), Faculdade de Farmácia
  2. 2Universidade Federal de Goiás
  3. 3DIFACQUIM Research Group, Department of Pharmacy, School of Chemistry
  4. 4Universidad Nacional Autónoma de México
  5. 5Center for Research and Advancement in Fragments and Molecular Targets (CRAFT), School of Pharmaceutical Sciences at Ribeirao Preto
  6. 6University of São Paulo
Open at sourcePDFDOICite

Abstract

De novo molecular generation is increasingly used in drug discovery, yet deciding which generated structures merit follow-up remains difficult, because established benchmarking metrics primarily characterize generative models rather than individual compounds. We present DeNoMAP, a general multi-criteria prioritization framework implemented as an interactive, open-access web application, which positions de novo-generated molecules in a normalized three-dimensional space defined by novelty, synthesizability and drug-likeness. A user-defined desirability zone enables transparent and reproducible candidate selection. Novelty is computed against ZINC20 as an external reference collection using the SmallWorld search engine, rather than against the generative model’s training set. Applied to a published library of 8,066 DNMT1 candidates, the web application identified 15 prioritized compounds among 852 successfully evaluated cluster representatives. DeNoMAP is publicly available at https://denomap.streamlit.app/ and its source code at https://github.com/flfeitosa/DeNoMAP.

Related

  1. ADMET-Informed Machine Learning Prioritization of Hydrogel-Associated Compounds for Nanocarrier Evaluation
    Zeinab Hosseinyazdi, Seyed Majid Hashemianzadeh
    ChemRxivPreprintCC BY-NC-NDFull textGeneral chemistryChemRxiv
  2. N-Alkylpyridinium sulfonates as versatile scout compounds for multi-mode highly targeted metabolomics: Application to Gammarus fossarum
    Remy de Boni, Delphine Arquier, Sophie Ayciriex +4
    Journal of Chromatography B - Analytical Technologies in the Biomedical and Life SciencesPeer-reviewedLicence not statedAnalytical chemistryHAL
  3. Unbundling the magnetic interactions in 3d/4f oxides: application to Ba2LnFeO5 compounds
    V. Hardy, V. Caignaert, F. Veillon +3
    Journal of Magnetism and Magnetic MaterialsPeer-reviewedCC BYFull textMaterials & polymersGeneral physicsHAL
  4. Application-Specific Multi-Criteria Decision Analysis of Source-Optimized Nanoparticle Textile Formulations: Trade-offs in Washing Durability, Antibacterial Performance, and Laboratory-Scale Raw-Material Cost
    Yunfei Li
    ChemRxivPreprintCC BY-NC-NDFull textGeneral chemistryChemRxiv
  5. Conserved recognition and divergent peripheral dynamics of designed statin analogues at human HMG-CoA reductase: ensemble docking and replicated molecular dynamics
    Tyrell Towle
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@misc{feitosa2026denomap,
  title = {{DeNoMAP: An Interactive Web Application for Multi-Criteria Prioritization of De Novo Designed Compounds}},
  author = {Francisco L. Feitosa and Erik D. Díaz-Dionisio and Juan F. Avellaneda-Tamayo and Carolina Horta Andrade and José L. Medina-Franco},
  howpublished = {ChemRxiv},
  year = {2026},
  month = oct,
  doi = {10.26434/chemrxiv.15010444/v1},
  url = {https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010444/v1},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - DeNoMAP: An Interactive Web Application for Multi-Criteria Prioritization of De Novo Designed Compounds
AU  - Francisco L. Feitosa
AU  - Erik D. Díaz-Dionisio
AU  - Juan F. Avellaneda-Tamayo
AU  - Carolina Horta Andrade
AU  - José L. Medina-Franco
PY  - 2026
DA  - 2026/10/14
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15010444/v1
UR  - https://chemrxiv.org/doi/full/10.26434/chemrxiv.15010444/v1
AB  - De novo molecular generation is increasingly used in drug discovery, yet deciding which generated structures merit follow-up remains difficult, because established benchmarking metrics primarily characterize generative models rather than individual compounds. We present DeNoMAP, a general multi-criteria prioritization framework implemented as an interactive, open-access web application, which positions de novo-generated molecules in a normalized three-dimensional space defined by novelty, synthesizability and drug-likeness. A user-defined desirability zone enables transparent and reproducible candidate selection. Novelty is computed against ZINC20 as an external reference collection using the SmallWorld search engine, rather than against the generative model’s training set. Applied to a published library of 8,066 DNMT1 candidates, the web application identified 15 prioritized compounds among 852 successfully evaluated cluster representatives. DeNoMAP is publicly available at https://denomap.streamlit.app/ and its source code at https://github.com/flfeitosa/DeNoMAP.
ER  -