Insights into the Unknown: Federated Data Diversity Analysis on Molecular Data

TL;DR

This paper evaluates federated clustering methods for analyzing the diversity of distributed molecular data in pharmaceutical research, emphasizing the importance of domain knowledge and explainability.

Contribution

It benchmarks federated clustering approaches against centralized methods on molecular datasets and introduces chemistry-informed evaluation metrics.

Findings

Federated clustering methods can effectively analyze distributed molecular data.

Incorporating domain knowledge improves diversity assessment accuracy.

Explainability analyses highlight the importance of chemistry-informed metrics.

Abstract

AI methods are increasingly shaping pharmaceutical drug discovery. However, their translation to industrial applications remains limited due to their reliance on public datasets, lacking scale and diversity of proprietary pharmaceutical data. Federated learning (FL) offers a promising approach to integrate private data into privacy-preserving, collaborative model training across data silos. This federated data access complicates important data-centric tasks such as estimating dataset diversity, performing informed data splits, and understanding the structure of the combined chemical space. To address this gap, we investigate how well federated clustering methods can disentangle and represent distributed molecular data. We benchmark three approaches, Federated kMeans (Fed-kMeans), Federated Principal Component Analysis combined with Fed-kMeans (Fed-PCA+Fed-kMeans), and Federated Locality-Sensitive Hashing (Fed-LSH), against their centralized counterparts on eight diverse molecular datasets. Our evaluation utilizes both, standard mathematical and a chemistry-informed evaluation metrics, SF-ICF, that we introduce in this work. The large-scale benchmarking combined with an in-depth explainability analysis shows the importance of incorporating domain knowledge through chemistry-informed metrics, and on-client explainability analyses for federated diversity analysis on molecular data.