BEGIN:VCALENDAR VERSION:2.0 PRODID:icalendar-ruby CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260717T142337Z UID:817707c2-2bff-478a-bfd2-af1d355cf728 DTSTART:20220621T090000Z DTEND:20220621T170000Z DESCRIPTION:This is the second webinar of the series about [the impact of A lphaFold on training and research in life sciences](https://www.ebi.ac.uk/ training/events/impact-of-alphafold-on-training-and-research-in-life-scien ces/). This webinar will focus on how AlphaFold is changing or will change the teaching/training landscape in life sciences. This will help us ident ify the gaps and opportunities for developing training materials for stude nts and researchers.\n\nTo discuss the impact of AlphaFold on teaching and training in life sciences we had the following panel of speakers:\n\n**Al exandre Bonvin** - In my short talk\, I reflected on how we have been inco rporating AlphaFold in the bachelor and master courses I am giving at Utre cht University for chemistry and molecular and cellular life sciences stud ents.\n\nI have been teaching molecular modelling for many years\, describ ing how to represent molecules and their energetics and model their struct ure and dynamics in silico. The advanced master course also has a [compute r practical in which students do homology modelling](https://www.bonvinlab .org/education/molmod_online/)\, run molecular dynamics of a peptide and u se the output for modelling a protein-peptide complex by docking. Part of this practical was [published as an educational article](https://iubmb.onl inelibrary.wiley.com/doi/10.1002/bmb.20941). This year we introduced at th e end an [AlphaFold “bonus” module](https://www.bonvinlab.org/educatio n/molmod_online/alphafold/) in which students model directly the protein- peptide complex from sequence\, something which works extremely well in th is particular case. We are also using AlphaFold this year in the context o f a second year bachelor project in which students investigate how well Al phaFold performs for the modelling of antibodies. \n\nIn both cases\, stu dents have little knowledge of the machinery under the hood\, but only som e general understanding of the role of AI in the process. Still they manag e to use this fantastic resource very efficiently. Key factors here are in my opinion: 1) the availability of [Jupyter notebooks](https://www.bonvin lab.org/education/molmod_online/alphafold/) that make using the software extremely easy\, and 2) the free computational resources of [Google Colab] (https://colab.research.google.com/). Without those it would simply be imp ossible to expose students to such methods as installing the software and more importantly the 2TB of data for the model is simply not doable on stu dent’s laptop or computer rooms managed by our university IT.\n\n**Panag iotis L. Kastritis** - AlphaFold is revolutionising structural\, molecular and even cellular biology due to its unmatched accuracy for various prote in targets. In addition\, the recent AlphaFold Structure Database and Cola bFold are fast-tracking structural biology research via models to be utili sed either as hypothesis generators or explanatory of previously perplexin g experimental data. However\, incorporating AlphaFold in teaching require s special attention because (a) fundamental understanding of machine learn ing is not trivial\; and (b) physicochemical principles of protein folding \, in the light of AlphaFold success\, must be harmonised with interpretab le machine learning\, which is presently unavailable. I conclude that prac tical aspects of AlphaFold are currently preferable for teaching both stud ents and young researchers in combination with\, e.g.\, homology modelling \, docking\, and other structure building tools. In this way\, students an d young researchers critically assess their derived models and motivate th emselves to deduce structure-function correlations while furthering workin g hypotheses on a given system.\n\n**Ezgi Karaca** - I have been teaching in molecular biology and medicine departments. My students usually come wi th a little knowledge in structural biology. Thanks to the availability of the EMBL-EBI AlphaFold (AF) Database\, I can show them the “_images_” of proteins to explain how a protein structure is related to its function . Otherwise\, we have been using AF over the ColabFold service for modelli ng disease-associated protein mutations/isoforms. The fact that AF provide s a residue-based confidence score has been very helpful to us in assessin g whether our models are biologically relevant. For large systems\, though \, a local installation of AF is required. Beyond protein structure predic tion\, the performance of AF on protein complexes are yet to be critically discussed. For this\, we should wait for the outcome of the CASP15 experi ment\, where I act as the assembly assessor.\n\n**Dina Schneidman** - I am teaching an advanced course on Structural Bioinformatics intended for Com putational Biology and Computer Science students. The course consists of l ectures\, 5 exercises\, and a 2-day hackathon. Several years ago\, the nev er-changing course part on folding began to change. We had to update the l ectures and the exercises. We have encountered several challenges. First\, we realised we have to teach deep learning to students with insufficient background. Second\, we had to make sure the homework assignments have rea sonable training time and the students have access to GPUs. Finally\, we h ad to think about hackathon projects that can be done within two days. In this webinar I described how we addressed these challenges in the webinar. \n\n  LOCATION:\, SUMMARY:Impact of AlphaFold on teaching and training in life sciences URL;VALUE=URI:https://www.ebi.ac.uk/training/events/impact-alphafold-teachi ng-and-training-life-sciences END:VEVENT END:VCALENDAR