Liam Brierley

This paper uses graph neural networks to predict host origins from paramyxovirus sequences, showing improved performance over traditional methods, especially with sparse data.

This study uses machine learning to predict avian influenza zoonosis risk based on viral genome sequence features, finding that a multi-model approach outperforms individual models.

The paper evaluates kmer-based representations of TCR repertoires for classification, showing that reduced amino acid alphabets improve performance and interpretability in autoimmune disease classification.

The paper uses machine learning to model the spread of H5N1 avian influenza in Europe, finding that ecological factors refine risk predictions beyond climate alone.

The paper develops a machine learning model to predict zoonotic potential of avian influenza viruses using genomic data, achieving high accuracy in distinguishing zoonotic from non-zoonotic strains.

This study uses machine learning to predict coronavirus animal hosts from spike protein and whole genome sequence composition biases, achieving 73% accuracy in cross-validation.