PuSH - Publication Server of Helmholtz Zentrum München

Lambourne, L.* ; Yadav, A.* ; Wang, Y.* ; Desbuleux, A.* ; Kim, D.K.* ; Laval, F.* ; Spirohn-Fitzgerald, K.* ; Cafarelli, T.* ; Pons, C.* ; Kovács, I.A.* ; Jailkhani, N.* ; Schlabach, S.* ; De Ridder, D.* ; Luck, K.* ; Botchkarev, V.V.* ; Debnath, O.* ; Bian, W.* ; Shen, Y.* ; Yang, Z.* ; Mee, M.W.* ; Helmy, M.* ; Jacob, Y.* ; Lemmens, I.* ; Rolland, T.* ; McClain, G.G.* ; Coté, A.G.* ; Gebbia, M.* ; Kishore, N.* ; Knapp, J.J.* ; Mellor, J.C.* ; Memisoglu, G.* ; Reimand, J.* ; Tavernier, J.* ; Cusick, M.E.* ; Zhong, Q.* ; Aloy, P.* ; Hao, T.* ; Charloteaux, B.* ; Roth, F.P.* ; De Las Rivas, J.* ; Falter-Braun, P. ; Hill, D.E.* ; Calderwood, M.A.* ; Twizere, J.C.* ; Vidal, M.*

Experimental assessment of AI-based interactome mapping.

Nat. Commun., DOI: 10.1038/s41467-026-70942-x (2026)
DOI PMC
Genotype-phenotype relationships are mediated through intricate networks of physical and functional interactions among macromolecules. Knowledge of the interactome is vital to understand and model genetics and cellular biology. Recent advances in accurately predicting tertiary protein structures using artificial intelligence (AI) approaches such as AlphaFold1 have revived the vision that the protein-protein interactome might be fully predictable through computational modeling of quaternary structures. Here we present a comprehensive experimental framework to systematically assess the impact of AI-driven interactome predictions for yeast2 and human3. We find that the quality of high-confidence predictions is on par with established experimental approaches. However, in proteome-wide screening, the tested AI approaches underperform in the discovery of strictly novel protein-protein interactions (PPIs) compared to experimental reference interactome maps. In particular, the yeast interactome map described here identifies >40-fold more novel PPIs than its AI counterpart. Strikingly, AlphaFold provides structural models for a substantial number of experimentally identified PPIs missed by the virtual screens. Our results suggest that, at this stage, the main contribution of AI predictions is to provide quaternary structure models for experimentally identified PPIs.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
ISSN (print) / ISBN 2041-1723
e-ISSN 2041-1723
Journal Nature Communications
Publisher Springer
Publishing Place London
Reviewing status Peer reviewed
Institute(s) Institute of Network Biology (INET)