Multi-Hierarchical Fine-Grained Feature Mapping Driven by Feature Contribution for Molecular Odor Prediction

TL;DR

This paper introduces a hierarchical multi-feature mapping network with atomic-level feature extraction and class imbalance mitigation, significantly improving molecular odor prediction accuracy using AI models.

Contribution

The paper proposes a novel multi-hierarchical feature extraction framework with dynamic feature importance learning and imbalance-aware loss for enhanced odor prediction.

Findings

Improved prediction accuracy across multiple models

Effective atomic-level feature extraction for odors

Enhanced global feature learning from molecular graphs

Abstract

Molecular odor prediction is the process of using a molecule's structure to predict its smell. While accurate prediction remains challenging, AI models can suggest potential odors. Existing methods, however, often rely on basic descriptors or handcrafted fingerprints, which lack expressive power and hinder effective learning. Furthermore, these methods suffer from severe class imbalance, limiting the training effectiveness of AI models. To address these challenges, we propose a Feature Contribution-driven Hierarchical Multi-Feature Mapping Network (HMFNet). Specifically, we introduce a fine-grained, Local Multi-Hierarchy Feature Extraction module (LMFE) that performs deep feature extraction at the atomic level, capturing detailed features crucial for odor prediction. To enhance the extraction of discriminative atomic features, we integrate a Harmonic Modulated Feature Mapping (HMFM). This module dynamically learns feature importance and frequency modulation, improving the model's capability to capture relevant patterns. Additionally, a Global Multi-Hierarchy Feature Extraction module (GMFE) is designed to learn global features from the molecular graph topology, enabling the model to fully leverage global information and enhance its discriminative power for odor prediction. To further mitigate the issue of class imbalance, we propose a Chemically-Informed Loss (CIL). Experimental results demonstrate that our approach significantly improves performance across various deep learning models, highlighting its potential to advance molecular structure representation and accelerate the development of AI-driven technologies.