Enhancing protein inter-residue real distance prediction by scrutinising deep learning models

Abstract

Protein structure prediction (PSP) has achieved significant progress lately via prediction of inter-residue distances using deep learning models and exploitation of the predictions during conformational search. In this context, prediction of large inter-residue distances and also prediction of distances between residues separated largely in the protein sequence remain challenging. To deal with these challenges, state-of-the-art inter-residue distance prediction algorithms have used large sets of coevolutionary and non-coevolutionary features. In this paper, we argue that the more the types of features used, the more the kinds of noises introduced and then the deep learning model has to overcome the noises to improve the accuracy of the predictions. Also, multiple features capturing similar underlying characteristics might not necessarily have significantly better cumulative effect. So we scrutinise the feature space to reduce the types of features to be used, but at the same time, we strive to improve the prediction accuracy. Consequently, for inter-residue real distance prediction, in this paper, we propose a deep learning model named scrutinised distance predictor (SDP), which uses only 2 coevolutionary and 3 non-coevolutionary features. On several sets of benchmark proteins, our proposed SDP method improves mean Local Distance Different Test (LDDT) scores at least by 10% over existing state-of-the-art methods. The SDP program along with its data is available from the website https://gitlab.com/mahnewton/sdp.

Distance plus attention for binding affinity prediction

“…The seven physicochemical properties [ 14 , 29 ] for each amino acid residue are steric parameter (graph shape index), hydrophobicity, volume, polarisability, isoelectric point, helix probability, and sheet probability. When extracting these three features for protein residues, we focused exclusively on the 20 standard amino acid residues.…”

“…Inspired by the use of distance measures in protein structure prediction [ 14 , 28 , 29 ], in this work, we employ distance-based input features in protein-ligand binding affinity prediction. To be more specific, we use distances between donor-acceptor [ 30 ], hydrophobic [ 31 , 32 ], and -stacking [ 31 , 32 ] atoms as interactions between such atoms play crucial roles in protein-ligand binding.…”

Learning to discover medicines

“…To balance between 3D structural information and simplicity, 2D representation via an attributed graph can be used. For example, in the case of protein, the distance/contact between residues can be predicted [ 42 , 43 ] to form the contact/distance map. The contact/distance map is then used as an adjacency matrix of an attributed graph where each node represents a residue and edges represent the contact/distance between residues.…”

Freeprotmap: waiting-free prediction method for protein distance map

“…The widespread application of distance map prediction has attracted extensive attention from researchers. Barger et al [26] and Rahman et al [27] develop extended 1 Helices can be identified by thickening of the diagonal line on the distance map, while parallel and antiparallel β-folds can be characterized by lines parallel or orthogonal to the diagonal line of the distance map, respectively. 2 Two or more secondary structural units are connected by a connecting polypeptide (loop) to form further a local spatial structure with a special geometric arrangement.…”