Accurate prediction of solvent accessibility using neural networks–based regression

By Rafal Adamczak, Aleksey A. Porollo, Jaroslaw Meller. Proteins: Structure, Function, and Bioinformatics, 2004

298 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Combining prediction of secondary structure and solvent accessibility in proteins (2005, methodology): “18 Such independently predicted RSA values, or alternatively, their 2-class projections, with a threshold of 25% RSA separating the class of “buried” from the class of “exposed” residues, were subsequently used as additional features describing local environments of amino acid residues for the…”
rawMSA: End-to-end Deep Learning Makes Protein Sequence Profiles and Feature Extraction obsolete (2018, methodology): “…methods have been developed to predict a number of structural properties of proteins: secondary structure (SS) [9–14], relative solvent accessibility (RSA) [14–17], backbone dihedrals [18], disorder [14,19,20], disorder-to-order transition [21,22],contact maps [23–26], and model quality [27–30].”
Prediction‐based fingerprints of protein–protein interactions (2006, methodology): “35 In two state projections (e.g., using 25% RSA as a threshold between buried and exposed residues), regression-based methods outperformed current state-of-the-art clas-sification-based approaches.”