PROFOUND
predicting PROtein FOldability owing to mUlti poiNt Deletions

PROFOUND uses positive-unlabeled classifiers utilizing fold level attributes, environment-specific properties, and deletion site-specific properties to predict the change in foldability owing to contiguous multi-point deletion (MPD) of amino acids in protein structures. PROFOUND is a first of its kind prediction system that reports a recall of 82.2% (86.6%) and a fall out rate of 14.2% (20.6%) corresponding to MPDs in the loop (non-loop) region.


Upload PDB file (format) (<2MB): (Sample)
Chain id:
In the uploaed file, place only the ATOM records of a single model corresponding to a single chain ID without any backbone discontinuity. The residues shouldn't have multiple occupancies with chain ID placed in the relevant location.

Currently, PROFOUND supports the deletion of non-terminal residues (min 2, max 15), but does not support the deletion of an entire loop. PROFOUND selects the separate classifier for the loop and non-loop region.
Deletion from: to:


Email (optional):


Download PROFOUND Supporting Data



How to cite:
1. Anupam Banerjee, Pralay Mitra (2020) Estimating Change in Foldability Due to Multipoint Deletions in Protein Structures Journal of Chemical Information and Modeling 60(12):6679-6690 [DOI] [PubMed].


Other servers: ProMoCell ProDeMo PPSBoost