Skip to main content

Table 5 Performance on CASP10 targets with clustering and neighbourhoods (δ = 2)

From: A study and benchmark of DNcon: a method for protein residue-residue contact prediction using deep networks

 

Top L/10 long range

Top L/5 long range

Method

Acc. (SE)

Cluster

count

Acc. (SE)

Cluster

count

DNcon(222)

0.583(0.030)

666

0.520(0.025)

1018

RaptorX-Roll(358)

0.524(0.030)

596

0.476(0.027)

917

IBGteam [DL] (305)

0.503(0.037)

408

0.391(0.034)

662

RandomForest (396)

0.477(0.035)

577

0.441(0.031)

895

RandomForest(257)

0.455(0.034)

627

0.415(0.030)

907

SVM(81)

0.416(0.034)

596

0.345(0.027)

936

  1. Accuracies for the top L/10, L/5 and L medium and long range contact predictions for 96 CASP10 targets. L is the length of the protein. Estimates for standard error are provided in parenthesises. δ is the size of the neighbourhood. Cluster count is the number of clusters identified by the method.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us