English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Predicting cross-immunity between viral strains is vital for public healthsurveillance and vaccine development. Traditional neural network methods, suchas BiLSTM, could be ineffective due to the lack of lab data for model trainingand the overshadowing of crucial features within sequence concatenation. Thecurrent work proposes a less data-consuming model incorporating a pre-trainedgene sequence model and a mutual information inference operator. Ourmethodology utilizes gene alignment and deduplication algorithms to preprocessgene sequences, enhancing the model's capacity to discern and focus ondistinctions among input gene pairs. The model, i.e., DNA PretrainedCross-Immunity Protection Inference model (DPCIPI), outperformsstate-of-the-art (SOTA) models in predicting hemagglutination inhibition titerfrom influenza viral gene sequences only. Improvement in binary cross-immunityprediction is 1.58% in F1, 2.34% in precision, 1.57% in recall, and 1.57% inAccuracy. 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 studyhighlights the potential of pre-trained gene models in revolutionizing genesequence-related prediction tasks. With more gene sequence data being harnessedand larger models trained, we foresee a significant impact of pre-trainedmodels on clinical and public health applications.

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