PlasmoFAB

PlasmoFAB is a curated dataset containing amino acid sequences of proteins expressed by Plasmodium falciparum (Pf). Sequences are separated into antigen candidates and intracellular proteins. PlasmoFAB is created to provide a high-quality trainings set for machine learning models that will be used for Pf antigen exploration. We provide PlasmoFAB in form of two separate csv files. One file, named <em>PlasmoFAB_pos.csv</em>, contains the positive set, i.e., all protein sequences that are antigen candidates. The other file, named <em>PlasmoFAB_neg.csv</em>, contains the negative set, i.e., all protein sequences that are intracellular proteins. Each sequence has a flag in the datafield "test" that indicates whether or not the sequence was used in the test set of machine learning experiments performed in the corresponding manuscript. Additionally, the file <em>PlasmoFAB_datasheet.md</em> contains a datasheet for PlasmoFAB as introduced in Gebru, Timnit, et al. "Datasheets for datasets." <em>Communications of the ACM</em> 64.12 (2021): 86-92.