Sara’s paper IDPpub: Illuminating the Dark Phosphoproteome Through PubMed Mining has been published in...

Sara’s paper IDPpub: Illuminating the Dark Phosphoproteome Through PubMed Mining has been published in Molecular & Cellular Proteomics. Phosphorylation is an essential component of cellular signaling, and phosphoproteomics enables global identification and quantification of phosphosites from biological samples. However, interpretation of phosphoproteomic findings is hindered by our limited knowledge on functions, phenotype associations, and regulating enzymes of the phosphosites. We developed a computational pipeline that uses BioBERT to extract phosphorylation sites from biomedical abstracts. The pipeline further aligns the sites to human and mouse reference sequences to facilitate computational applications and intersection with mass spectrometry experiments. The extracted evidence sentences can be used to identify regulating enzymes and biological functions. We made all data available in the IDPpub web portal for easy exploration.