GlassMol: Interpretable Molecular Property Prediction with Concept Bottleneck Models

TL;DR

Experiments across thirteen benchmarks demonstrate that GlassMol generally matches or exceeds black-box baselines, suggesting that interpretability does not sacrifice performance and challenging the commonly assumed trade-off.

Abstract

Machine learning accelerates molecular property prediction, yet state-of-the-art Large Language Models and Graph Neural Networks operate as black boxes. In drug discovery, where safety is critical, this opacity risks masking false correlations and excluding human expertise. Existing interpretability methods suffer from the effectiveness-trustworthiness trade-off: explanations may fail to reflect a model's true reasoning, degrade performance, or lack domain grounding. Concept Bottleneck Models (CBMs) offer a solution by projecting inputs to human-interpretable concepts before readout, ensuring that explanations are inherently faithful to the decision process. However, adapting CBMs to chemistry faces three challenges: the Relevance Gap (selecting task-relevant concepts from a large descriptor space), the Annotation Gap (obtaining concept supervision for molecular data), and the Capacity Gap (degrading performance due to bottleneck constraints). We introduce GlassMol, a model-agnostic CBM that addresses these gaps through automated concept curation and LLM-guided concept selection. Experiments across thirteen benchmarks demonstrate that \method generally matches or exceeds black-box baselines, suggesting that interpretability does not sacrifice performance and challenging the commonly assumed trade-off. Code is available at https://github.com/walleio/GlassMol.

Figures (5)

• Figure 1: The proposed GlassMol framework. The inputs to the encoder are the raw data, either a SMILES string or a molecular graph. The embeddings generated by the LLM or GNN are projected onto a set of task-relevant concepts selected by an LLM. The predicted concept values are then passed to a linear layer to produce the final prediction. The importance of each concept is determined by the magnitude of its contribution to the final output, computed as the product of the concept value and its weight.
• Figure 2: t-SNE visualization of learned representations on the HIA dataset.Left: The baseline shows entangled representations with no clear decision boundary. Right:GlassMol (ours) produces well-separated clusters for the two classes.
• Figure 3: Qualitative comparison of concept attribution against ground-truth structural importance. The blue highlights represent the TopoPool ground-truth importance clusters. Red circles indicate the substructures identified by GlassMol where solid lines $\xrightarrow{}$ GNN architecture and dashed lines $\xrightarrow{}$ LLM architecture.
• Figure 4: Ablation studies on critical model components for LLM (top row) and GNN (bottom row) architectures.Left: Comparison of model backbones. For LLMs, our task-specific small model (red) significantly outperforms general large models (blue/beige). For GNNs, our GINE-based architecture remains competitive. Middle: Evaluation of concept selection strategies. GPT-4 selected concepts (red) achieve the best performance, with the open-source Llama-3-70B selector (blue) serving as a strong alternative to proprietary models. Right: Robustness analysis showing that our method maintains high performance even with noisy concept labels (blue).
• Figure 5: Hyperparameter sensitivity analysis. (a) Performance vs. number of concepts ($K$). Accuracy improves rapidly and saturates around $K=40$, balancing representation power and complexity. (b) Performance vs. loss weight $\lambda$. A balanced weight of $\lambda=1$ yields optimal results, while extreme values degrade performance.