Nature Reviews Microbiology Article (2006) Dataset:

The dataset used to evaluate various protein localization software in the NRM 2006 article is available below in FASTA format. The dataset contains 299 Gram-negative proteins, many of which are not part of PSORTb's training dataset.

If you make use of this dataset in your research, please cite:

Jennifer L. Gardy and Fiona S.L. Brinkman (2006). Methods for predicting bacterial protein subcellular localization, Nature Reviews Microbiology 4:741-751.

NRM2006 article Gram-negative sequences:

• Cytoplasmic (145)
• Cytoplasmic Membrane (69)
• Periplasmic (29)
• Outer Membrane (38)
• Extracellular (18)