“…One feature has an importance around 0.2 for both the approaches, being one order of magnitude larger than any other one. It is the CONSRANK score, a consensus score, which reflects the conservation (or frequency) of the inter-residue contacts featured by a given model in the whole decoys ensemble it belongs to Chermak et al (2015 ) and Oliva et al (2015 , 2013 ), widely tested on CAPRI targets ( Barradas-Bautista et al , 2020 ; Lensink et al , 2019 , 2016 ; Vangone et al , 2013 ). Among the top ten scoring functions, after CONSRANK, we find AP_GOAP_DF, CP_TD, CP_DI and CP_HLPL ( Garcia-Garcia et al , 2010 ; Pokarowski et al , 2005 ), which was interestingly also among the 10 most successful scoring functions when applied alone to DMs from three different docking software in Barradas-Bautista and Fernández-Recio (2017) , DDG_V, CP_MJ3h, pyDock_TOT, electrostatics, CP_SKOIP ( Lu et al , 2003 ), all obtained from the CCharPPI server ( Moal et al , 2015 ).…”