Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 52 min ago
Peer-reviewedCC BY-NC-ND 4.0ACS Omega

Weighted Views Representation with Multi-Head Coulomb Attention for Molecular Property Prediction

  • Muhammad Shahzeb Ali1
  • Martin J. Mohlenkamp1
  1. 1Ohio University , , , ,
Open at sourcePDFDOICite

Abstract

We extend the weighted-views molecular featurization framework (d’Avezac, Botts, Mohlenkamp, and Zunger, 2011) by enriching it with single-atom properties and Coulomb pair information. We use these enriched views within a machine-learning architecture incorporating shared Transformers whose attention scores directly incorporate Coulomb interactions, weighted aggregation of view outputs, and a final prediction neural network. We demonstrate performance competitive with the state-of-the-art on the QM7 atomization energy benchmark (regression), ranking enantiomers by their docking scores (trained as regression, tested by ranking), lipophilicity (regression), and blood–brain barrier penetration (classification).

Versions

Related

  1. Towards Multiscale Molecular Representation Learning through Geometry-Based Fragmentation for Polymer Property Prediction
    Makoto Takamoto, Chaitanya Sampara, Viktor Zaverkin +2
    arXivPreprintarXiv licenceFull textPhysical chemistryCondensed matterarXiv
  2. Rotamer-Dependent Amino Acid Descriptors as Protein and Peptide Representation for Reactivity and Property Prediction
    Lauriane Jacot-Descombes, Kjell Jorner
    ChemRxivPreprintCC BYGeneral chemistryChemRxiv
  3. Weighted Molecular Views with Global Attention Tokens
    Muhammad Shahzeb Ali, Shahtaj Bano
    ChemRxivPreprintCC BY5 citedMedicinal chemistry & drug discoveryOpenAlex
  4. Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements
    Jingjie Ning, Xiaochuan Li, Ji Zeng +2
    arXiv (Cornell University)PreprintLicence not statedFull text8 citedMedicinal chemistry & drug discoveryOpenAlex
  5. Topology-Guided Multi-Level Graph Learning: A Unified Framework for Molecular Property Prediction
    Hasnain Ali, Momina Arshad, Malik Ahsin Iqbal +2
    Molecules (Basel, Switzerland)Peer-reviewedCC BYFull textGeneral chemistryEurope PMC

Cite

BibTeXRIS
BibTeX
@article{ali2026weighted,
  title = {{Weighted Views Representation with Multi-Head Coulomb Attention for Molecular Property Prediction}},
  author = {Muhammad Shahzeb Ali and Martin J. Mohlenkamp},
  journal = {ACS Omega},
  year = {2026},
  month = oct,
  doi = {10.1021/acsomega.6c06094},
  url = {https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c06094/5453173/Weighted-Views-Representation-with-Multi-Head},
  note = {CC BY-NC-ND 4.0},
}
RIS
TY  - JOUR
TI  - Weighted Views Representation with Multi-Head Coulomb Attention for Molecular Property Prediction
AU  - Muhammad Shahzeb Ali
AU  - Martin J. Mohlenkamp
PY  - 2026
DA  - 2026/10/16
JO  - ACS Omega
DO  - 10.1021/acsomega.6c06094
UR  - https://pubs.acs.org/acsodf/article/doi/10.1021/acsomega.6c06094/5453173/Weighted-Views-Representation-with-Multi-Head
AB  - We extend the weighted-views molecular featurization framework (d’Avezac, Botts, Mohlenkamp, and Zunger, 2011) by enriching it with single-atom properties and Coulomb pair information. We use these enriched views within a machine-learning architecture incorporating shared Transformers whose attention scores directly incorporate Coulomb interactions, weighted aggregation of view outputs, and a final prediction neural network. We demonstrate performance competitive with the state-of-the-art on the QM7 atomization energy benchmark (regression), ranking enantiomers by their docking scores (trained as regression, tested by ranking), lipophilicity (regression), and blood–brain barrier penetration (classification).
SN  - 2470-1343
ER  -