Skip to main content

Table 9 General shortlist of mG (top list), GB (middle list) and Ph (bottom list) sequences from the subset generated using Sezerman transformation that were consistently misclassified to a different specific sub-family

From: Using random forests for assistance in the curation of G-protein coupled receptor databases

Name

mG

mG

CS

GB

VN

Ph

Od

Ta

a8dz71_danre

0.016

0.011

0.000

0.216

0.465

0.270

0.022

a8dz72_danre

0.103

0.034

0.011

0.069

0.497

0.194

0.091

q5i5d4_9tele

0.034

0.028

0.000

0.101

0.235

0.598

0.006

q5i5c3_9tele

0.033

0.022

0.011

0.116

0.254

0.547

0.017

XP_002163014

0.119

0.017

0.028

0.435

0.294

0.079

0.028

Name

GB

mG

CS

GB

VN

Ph

Od

Ta

b3rj55_triad

0.466

0.052

0.110

0.084

0.194

0.010

0.084

XP_002738008

0.574

0.024

0.136

0.077

0.118

0.012

0.059

Name

Ph

mG

CS

GB

VN

Ph

Od

Ta

a7sdg9_nemve

0.615

0.046

0.126

0.057

0.126

0.006

0.023

a7s0d2_nemve

0.591

0.069

0.103

0.039

0.128

0.034

0.034

b3s157_triad

0.706

0.011

0.068

0.056

0.079

0.000

0.079

q4spr3_tetng

0.280

0.065

0.480

0.010

0.120

0.005

0.040

NP_001093020

0.022

0.005

0.102

0.699

0.140

0.027

0.005

b0uyj3_danre

0.870

0.005

0.041

0.010

0.073

0.000

0.000

XP_001075542

0.030

0.015

0.005

0.197

0.099

0.611

0.044

XP_001521075

0.430

0.006

0.436

0.017

0.087

0.000

0.023

  1. Values in italics are the highest for the specified sequence