Description
3D modeling programs based on artificial intelligence (AI) have revolutionized structural biology, often predicting protein structures with an unprecedented level of confidence. However, these structures remain models, and it is always interesting to compare the results of different predictors (AlphaFold3, RoseTTAFold, ESMFold…), not to limit one’s choice to the model generated with the highest confidence score, and to introduce experimental data such as known intermolecular contact regions in the selection of the best model.
We have created a web server, named “FoldScript”, to address these issues. It can be used to synthesize in 1D, 2D and 3D the multi-model information generated by the AI. We have tested this web software on different protein complexes of therapeutic targets studied by our team, for which low or high confidence scores had been obtained. We show that, while AI can provide relevant answers, a critical look remains crucial. Indeed, the “top score” solution proposed by the AI is not always the “best”.
More info on ENDscript and ESPript at https://endscript.ibcp.fr/ESPript/ENDscript/
Important information
For all those interested, Please register at: https://forms.gle/FHWjtHhgcvoXAzif8
PhD students also wishing to have this course validated by their doctoral school must register additionally on the intranet in the same way as for the other courses offered by the PhD program Plinius Cursus.
More info on ENDscript and ESPript at https://endscript.ibcp.fr/ESPript/ENDscript/