A Noisy-Label-Learning Formulation for Immune Repertoire Classification and Disease-Associated Immune Receptor Sequence Identification

TL;DR

This paper introduces a robust noisy-label-learning approach for immune repertoire classification, addressing label noise and low witness rate issues, leading to improved sequence and repertoire-level classification accuracy.

Contribution

The work proposes a novel noisy-label-learning framework with asymmetric label smoothing and co-training to enhance immune repertoire classification accuracy.

Findings

Effective in noisy label scenarios

Superior performance on CMV and Cancer datasets

Improves sequence and repertoire-level classification

Abstract

Immune repertoire classification, a typical multiple instance learning (MIL) problem, is a frontier research topic in computational biology that makes transformative contributions to new vaccines and immune therapies. However, the traditional instance-space MIL, directly assigning bag-level labels to instances, suffers from the massive amount of noisy labels and extremely low witness rate. In this work, we propose a noisy-label-learning formulation to solve the immune repertoire classification task. To remedy the inaccurate supervision of repertoire-level labels for a sequence-level classifier, we design a robust training strategy: The initial labels are smoothed to be asymmetric and are progressively corrected using the model's predictions throughout the training process. Furthermore, two models with the same architecture but different parameter initialization are co-trained simultaneously to remedy the known "confirmation bias" problem in the self-training-like schema. As a result, we obtain accurate sequence-level classification and, subsequently, repertoire-level classification. Experiments on the Cytomegalovirus (CMV) and Cancer datasets demonstrate our method's effectiveness and superior performance on sequence-level and repertoire-level tasks.