Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 54 min ago
PreprintCC BYChemRxiv

Weighted Molecular Views with Global Attention Tokens

  • Muhammad Shahzeb Ali1,2
  • Shahtaj Bano1,3
  1. 1Department of Mathematics
  2. 2Ohio University
  3. 3RMIT
Open at sourceDOICite

Abstract

Accurate molecular property prediction strongly depends on the quality of molecular representations used as input to machine learning models. [1] proposed a molecular featurization method based on atomic coordinates that generates weighted views of a molecule. [2] proposedmodifications in [1] to the featurizationmethod for dimensionality reduction, which led to reduced empirical performance. In this work, we propose an alternative approach for dimensionality reduction and computational efficiency. Our proposed modifications increase the representativeness of molecular representations by generating additional molecular views, while reducing the dimensionality of these representations through the introduction of a global node into the architecture. The proposed modifications were evaluated on the QM9 dataset, where they demonstrated improved predictive performance. This work also provides a theoretical perspective to support and explain the proposed modifications.

Related

  1. Weighted Views Representation with Multi-Head Coulomb Attention for Molecular Property Prediction
    Muhammad Shahzeb Ali, Martin J. Mohlenkamp
    ACS OmegaPeer-reviewedCC BY-NC-ND 4.0Full text5 citedMedicinal chemistry & drug discoveryCrossrefOpenAlexPMC
  2. Sliding Window Attention with Auditable Chemical Sinks for Long-Sequence Molecular Transformation Modeling
    Dina Khalil, Mariam Tawfik, Sarah Farouk +2
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv
  3. Prediction of Singlet-Triplet Gaps Using Self-Attention–Based Regression with Model Integration into a Molecular Editor
    Péter Pál Fehér, András Stirling, Andras Stirling
    ChemRxivPreprintCC BY-NCFull textMaterials & polymersChemRxiv
  4. An Attention-based Architecture to Decode Chemical Transformations from Process Spectroscopic Data
    Kuldeep Singh, Vinay Prasad
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv
  5. Radial Kernel Attention for Long-Range Modeling in Polymer Machine Learning Force Fields
    Wenbo Fu, Chenghui Mao, Chengwen Hu +2
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@misc{ali2026weighted,
  title = {{Weighted Molecular Views with Global Attention Tokens}},
  author = {Muhammad Shahzeb Ali and Shahtaj Bano},
  howpublished = {ChemRxiv},
  year = {2026},
  month = may,
  doi = {10.26434/chemrxiv.15004047/v1},
  url = {https://doi.org/10.26434/chemrxiv.15004047/v1},
  note = {CC BY},
}
RIS
TY  - UNPB
TI  - Weighted Molecular Views with Global Attention Tokens
AU  - Muhammad Shahzeb Ali
AU  - Shahtaj Bano
PY  - 2026
DA  - 2026/05/29
PB  - ChemRxiv
DO  - 10.26434/chemrxiv.15004047/v1
UR  - https://doi.org/10.26434/chemrxiv.15004047/v1
AB  - Accurate molecular property prediction strongly depends on the quality of molecular representations used as input to machine learning models. [1] proposed a molecular featurization method based on atomic coordinates that generates weighted views of a molecule. [2] proposedmodifications in [1] to the featurizationmethod for dimensionality reduction, which led to reduced empirical performance. In this work, we propose an alternative approach for dimensionality reduction and computational efficiency. Our proposed modifications increase the representativeness of molecular representations by generating additional molecular views, while reducing the dimensionality of these representations through the introduction of a global node into the architecture. The proposed modifications were evaluated on the QM9 dataset, where they demonstrated improved predictive performance. This work also provides a theoretical perspective to support and explain the proposed modifications.
SN  - 2573-2293
ER  -