Zhiyong Lu

The paper creates a manually annotated corpus of cell phenotype mentions and shows its use in improving named entity recognition and entity linking models.

This paper develops a sequence labeling framework for drug-protein relation extraction, achieving higher performance than a text classification framework in the BioCreative VII challenge.

Deep learning rivals or beats baselines across imaging, health records, genomics and drug discovery but is not yet transformative; scarce labels, privacy and opacity remain hurdles.

The paper assesses the sustainability of expert curation in UniProtKB/Swiss-Prot by analyzing literature triage and curatorial workload.