p04 / Conference
An Extensive Overview of Feature Representation Techniques for Molecule Classification
Pan-Hellenic Conference on Progress in Computing and Informatics (PCI 2023), 156-162 · 2023 · Online 2024
In plain language
This study examines how representing a molecule affects classification performance and computational efficiency.
Research context
It offers an empirical basis for choosing molecular representations for downstream predictive tasks.
Approach
Ten molecular featurizers are compared with five machine-learning models, including graph and linear representations.
Findings
The accessible abstract excerpt describes the evaluation but does not provide a complete result ranking.
Summary based on abstract. Conference citation year is 2023; online publication is February 2024. The retrieved Scholar abstract is truncated before the complete findings; no specific ranking is asserted.