Skip to main content

Table 5 LoCo vs. all-atom potentials: native recognition

From: LoCo: a novel main chain scoring function for protein structure prediction based on local coordinates

  Ranknat RMSDbest Znat CCnat FEnat (%)
LoCo 13.4 1.62 1.805 0.519 36.6
RAPDF 30.2 2.54 1.367 0.474 33.2
dDFIRE 21.2 1.89 2.019 0.556 37.3
DOPE 37.5 2.69 1.525 0.482 34.5
RF_HA_SRS 18.6 1.59 2.055 0.526 39.7
  1. LoCo native recognition performance is compared to that of four widely-used all-atom potentials. All reported measures are averages over the 77 decoy sets in the final testing group. LoCo performance is comparable to the others, placing 1st, 2nd, 3rd, 3rd and 3rd in Ranknat, RMSDbest, Znat, CCnat and FEnat, respectively. Taking the sum of all rankings among these five potentials, LoCo places 3rd overall. All metrics are defined in Performance measures at the end of Methods.