Modern Hopfield Networks and Attention for Immune Repertoire Classification

TL;DR

This paper introduces DeepRC, a novel deep learning method that leverages modern Hopfield networks and attention mechanisms to improve immune repertoire classification, achieving superior performance and interpretability on large-scale biological data.

Contribution

The work demonstrates that attention mechanisms are equivalent to modern Hopfield network updates and applies this insight to develop DeepRC for massive multiple instance learning in immunology.

Findings

DeepRC outperforms existing methods in predictive accuracy.

It enables extraction of biologically relevant sequence motifs.

The approach scales to extremely large datasets with many instances.

Abstract

A central mechanism in machine learning is to identify, store, and recognize patterns. How to learn, access, and retrieve such patterns is crucial in Hopfield networks and the more recent transformer architectures. We show that the attention mechanism of transformer architectures is actually the update rule of modern Hopfield networks that can store exponentially many patterns. We exploit this high storage capacity of modern Hopfield networks to solve a challenging multiple instance learning (MIL) problem in computational biology: immune repertoire classification. Accurate and interpretable machine learning methods solving this problem could pave the way towards new vaccines and therapies, which is currently a very relevant research topic intensified by the COVID-19 crisis. Immune repertoire classification based on the vast number of immunosequences of an individual is a MIL problem with an unprecedentedly massive number of instances, two orders of magnitude larger than currently considered problems, and with an extremely low witness rate. In this work, we present our novel method DeepRC that integrates transformer-like attention, or equivalently modern Hopfield networks, into deep learning architectures for massive MIL such as immune repertoire classification. We demonstrate that DeepRC outperforms all other methods with respect to predictive performance on large-scale experiments, including simulated and real-world virus infection data, and enables the extraction of sequence motifs that are connected to a given disease class. Source code and datasets: https://github.com/ml-jku/DeepRC