1 - 14 of 14 results

Cyscon

A disulfide bond predictor. The most confident disulfide bonds are first identified and bonding prediction is then focused on the remaining cysteine residues based on SVR training. Compared to purely machine learning-based approaches, Cyscon improved the average accuracy of connectivity pattern prediction by 21.9%. For proteins with more than 5 disulfide bonds, Cyscon improved the accuracy by 585% on the benchmark set of PDBCYS. When applied to 158 non-redundant cysteine-rich proteins, Cyscon predictions helped increase (or decrease) the TM-score (or RMSD) of the ab initio QUARK modeling by 12.1% (or 14.4%). This result demonstrates a new avenue to improve the ab initio structure modeling for cysteine-rich proteins.

DIpro / DIsulphide bridge prediction

A framework for disulphide bridge predictions. DIpro provides graphical models and recursive neural networks to predict the bonding probability of each pair of cysteines, leveraging in addition secondary structure and relative solvent accessibility information. DIpro infers the disulphide bridge connectivity of each protein chain, which in turn yields a solution for both the bridge and residue classification problems, even in the case where the bonding state of individual cysteines is not known.

SCRATCH

Offers a platform for determining protein structural features and tertiary structures. SCRATCH is a web application including ten modules for determining three and eight class: (1) secondary structure, (2) relative solvent accessibility, (3) domain boundaries, (4) disordered regions, (5) disulfide bridges, (6) the effect of single amino acid mutation on stability, (7) residue-residue contact maps, and (8) tertiary structures as well as contacts with other residues compared to average.