ipTM scores are on the higher side for interactors and noninteractors

Hi,

I am observing higher ipTM scores for both known interactors and noninteractors when protenix was tried on a couple of examples mentioned in this paper https://pubs.acs.org/doi/10.1021/acs.jcim.3c01805.

Ideally for most interacting proteins the ipTM scores should be > 0.5 and < 0.5 for noninteracting ones. I have observed this for AF2.3 and Chai1 for the examples mentioned in the paper whereas for protenix the scores are always >0.5.

I was wondering if there is any difference in the way the ipTM confidence head has been trained for protenix vs others and this is always leading to higher ipTM scores. Would appreciate your comments on this observation.

Regards
Rakesh

Start by reproducing the reported Protenix scores on the interacting and noninteracting examples from the linked paper, then compare them with the AF2.3 and Chai1 results described in the issue. Review how Protenix's ipTM confidence head is trained and determine whether the consistently higher scores are expected or indicate a problem; document the comparison and explanation as the completion criteria.

Written by the indexing model from the issue text.