Efficient Classification of SARS-CoV-2 Spike Sequences Using Federated Learning

TL;DR

This paper introduces a federated learning approach for SARS-CoV-2 variant classification that preserves data privacy while achieving high accuracy, enabling scalable and confidential analysis of viral sequences.

Contribution

The paper develops a federated learning model for virus variant detection that maintains data privacy and demonstrates high accuracy without centralized data sharing.

Findings

Achieved 93% accuracy in variant classification.

Maintains data confidentiality across distributed sources.

Scalable to large datasets for pandemic response.

Abstract

This paper presents a federated learning (FL) approach to train an AI model for SARS-Cov-2 variant classification. We analyze the SARS-CoV-2 spike sequences in a distributed way, without data sharing, to detect different variants of this rapidly mutating coronavirus. Our method maintains the confidentiality of local data (that could be stored in different locations) yet allows us to reliably detect and identify different known and unknown variants of the novel coronavirus SARS-CoV-2. Using the proposed approach, we achieve an overall accuracy of $93\%$ on the coronavirus variant identification task. We also provide details regarding how the proposed model follows the main laws of federated learning, such as Laws of data ownership, data privacy, model aggregation, and model heterogeneity. Since the proposed model is distributed, it could scale on ``Big Data'' easily. We plan to use this proof-of-concept to implement a privacy-preserving pandemic response strategy.