A Perspective on the Prospective Use of AI in Protein Structure Prediction.

AlphaFold2 (AF2) and RoseTTaFold (RF) have revolutionized structural biology, serving as highly reliable and effective methods for predicting protein structures. This article explores their impact and limitations, focusing on their integration into experimental pipelines and their application in diverse protein classes, including membrane proteins, intrinsically disordered proteins (IDPs), and oligomers. In experimental pipelines, AF2 models help X-ray crystallography in resolving the phase problem, while complementarity with mass spectrometry and NMR data enhances structure determination and protein flexibility prediction. Predicting the structure of membrane proteins remains challenging for both AF2 and RF due to difficulties in capturing conformational ensembles and interactions with the membrane. Improvements in incorporating membrane-specific features and predicting the structural effect of mutations are crucial. For intrinsically disordered proteins, AF2's confidence score (pLDDT) serves as a competitive disorder predictor, but integrative approaches including molecular dynamics (MD) simulations or hydrophobic cluster analyses are advocated for accurate dynamics representation. AF2 and RF show promising results for oligomeric models, outperforming traditional docking methods, with AlphaFold-Multimer showing improved performance. However, some caveats remain in particular for membrane proteins. Real-life examples demonstrate AF2's predictive capabilities in unknown protein structures, but models should be evaluated for their agreement with experimental data. Furthermore, AF2 models can be used complementarily with MD simulations. In this Perspective, we propose a "wish list" for improving deep-learning-based protein folding prediction models, including using experimental data as constraints and modifying models with binding partners or post-translational modifications. Additionally, a meta-tool for ranking and suggesting composite models is suggested, driving future advancements in this rapidly evolving field.

New insights in the molecular regulation of the NADPH oxidase 2 activity: Negative modulation by Poldip2.

Poldip2 was shown to be involved in oxidative signaling to ensure certain biological functions. It was proposed that, in VSMC, by interaction with the Nox4-associated membrane protein p22phox, Poldip2 stimulates the level of reactive oxygen species (ROS) production. In vitro, with fractionated membranes from HEK393 cells over-expressing Nox4, we confirmed the up-regulation of NADPH oxidase 4 activity by the recombinant and purified Poldip2. Besides Nox4, the Nox1, Nox2, or Nox3 isoforms are also established partners of the p22phox protein raising the question of their regulation by Poldip2 and of the effect in cells expressing simultaneously different Nox isoforms. In this study, we have addressed this issue by investigating the potential regulatory role of Poldip2 on NADPH oxidase 2, present in phagocyte cells. Unexpectedly, the effect of Poldip2 on phagocyte NADPH oxidase 2 was opposite to that observed on NADPH oxidase 4. Using membranes from circulating resting neutrophils, the ROS production rate of NADPH oxidase 2 was down-regulated by Poldip2 (2.5-fold). The down-regulation effect could not be correlated to the interaction of Poldip2 with p22phox but rather, to the interaction of Poldip2 with the p47phox protein, one of the regulatory proteins of the phagocyte NADPH oxidase. Our results show that the interaction of Poldip2 with p47phox constitutes a novel regulatory mechanism that can negatively modulate the activity of NADPH oxidase 2 by trapping the so-called "adaptor" subunit of the complex. Poldip2 could act as a tunable switch capable of specifically regulating the activities of NADPH oxidases. This selective regulatory role of Poldip2, positive for Nox4 or negative for Nox2 could orchestrate the level and the type of ROS generated by Nox enzymes in the cells.