Dataset comes from prior work performed in 2016. Manual classifications of PubMed articles were performed. Our research continues this work by applying logistic regresison to the very same datset. The goal is to see if each set contains unqiue terms that would make a custom vovabulary effective at classifying Chinese hamster ovary cell articles. Work was performed on Jupyter Notebook.
Dataset can be obtained by emailing Dr. Qinghua Wang at wangq@udel.edu