Alessandro Muscoloni

Network shape intelligence outperforms AlphaFold2 intelligence in vanilla protein interaction prediction.

This paper introduces Network Shape Intelligence (NSI) and shows it outperforms AlphaFold2 in predicting protein interactions using only local network information without training.

Local-community network automata modelling based on length-three-paths for prediction of complex network structures in protein interactomes, food webs and more

The paper introduces a network automaton rule, CH2-L3, to predict complex network structures across different domains like protein interactomes and food webs by maximizing internal links in local communities.