DPCIPI: A pre-trained deep learning model for predicting cross-immunity between drifted strains of Influenza A/H3N2

TL;DR

This paper introduces DPCIPI, a pre-trained deep learning model that predicts cross-immunity between drifted Influenza A/H3N2 strains using gene sequences, outperforming existing methods with less data.

Contribution

The work presents a novel pre-trained gene sequence model combined with mutual information inference for improved cross-immunity prediction from gene sequences.

Findings

DPCIPI outperforms SOTA models in predicting hemagglutination inhibition titer.

Binary cross-immunity prediction accuracy improved by 1.57%.

Multilevel cross-immunity prediction accuracy improved by 2.19%.

Abstract

Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development. Traditional neural network methods, such as BiLSTM, could be ineffective due to the lack of lab data for model training and the overshadowing of crucial features within sequence concatenation. The current work proposes a less data-consuming model incorporating a pre-trained gene sequence model and a mutual information inference operator. Our methodology utilizes gene alignment and deduplication algorithms to preprocess gene sequences, enhancing the model's capacity to discern and focus on distinctions among input gene pairs. The model, i.e., DNA Pretrained Cross-Immunity Protection Inference model (DPCIPI), outperforms state-of-the-art (SOTA) models in predicting hemagglutination inhibition titer from influenza viral gene sequences only. Improvement in binary cross-immunity prediction is 1.58% in F1, 2.34% in precision, 1.57% in recall, and 1.57% in Accuracy. For multilevel cross-immunity improvements, the improvement is 2.12% in F1, 3.50% in precision, 2.19% in recall, and 2.19% in Accuracy. Our study highlights the potential of pre-trained gene models in revolutionizing gene sequence-related prediction tasks. With more gene sequence data being harnessed and larger models trained, we foresee a significant impact of pre-trained models on clinical and public health applications.