Molecular Odor Prediction with Harmonic Modulated Feature Mapping and Chemically-Informed Loss

TL;DR

This paper introduces a novel feature mapping and loss function for molecular odor prediction, effectively handling complex features and severe label imbalance to improve model accuracy in chemoinformatics.

Contribution

It proposes a chemically-informed feature mapping and an ensemble optimization loss to address non-smooth objectives and label imbalance in odor prediction models.

Findings

Significant accuracy improvements across multiple deep learning models.

Effective handling of label imbalance and feature complexity.

Enhanced molecular structure representation for odor prediction.

Abstract

Molecular odor prediction has great potential across diverse fields such as chemistry, pharmaceuticals, and environmental science, enabling the rapid design of new materials and enhancing environmental monitoring. However, current methods face two main challenges: First, existing models struggle with non-smooth objective functions and the complexity of mixed feature dimensions; Second, datasets suffer from severe label imbalance, which hampers model training, particularly in learning minority class labels. To address these issues, we introduce a novel feature mapping method and a molecular ensemble optimization loss function. By incorporating feature importance learning and frequency modulation, our model adaptively adjusts the contribution of each feature, efficiently capturing the intricate relationship between molecular structures and odor descriptors. Our feature mapping preserves feature independence while enhancing the model's efficiency in utilizing molecular features through frequency modulation. Furthermore, the proposed loss function dynamically adjusts label weights, improves structural consistency, and strengthens label correlations, effectively addressing data imbalance and label co-occurrence challenges. Experimental results show that our method significantly can improves the accuracy of molecular odor prediction across various deep learning models, demonstrating its promising potential in molecular structure representation and chemoinformatics.