Session | ||
MS-73: Machine learning in biological and structural sciences
Invited: Melanie Vollmar (UK), Sergei Grudinin (France) | ||
Session Abstract | ||
Recently Machine Learning (ML), has become very popular in the fields of structural biology and chemical crystallography, throughout the pipeline from data collection and data processing through to structure solution and refinement. This technique can improve crystal structure prediction and classification, while ML and its tools (for example deep learning) have also been applied, inter alia, to drug discovery, powder diffraction and materials science. Experts in the field will discuss the background and recent advances in ML as applied to structural science. For all abstracts of the session as prepared for Acta Crystallographica see PDF in Introduction, or individual abstracts below. | ||
Introduction | ||
Presentations | ||
10:20am - 10:25am
Introduction to session 10:25am - 10:55am
Predicting experimental phasing success for data triaging 1Diamond Light Source, Didcot, United Kingdom; 2Rosalind Franklin Institute, Didcot, United Kingdom External Resource: https://www.xray.cz/iucrv/vidp.asp?id=511
10:55am - 11:25am
Deep learning entering the post-protein structure prediction era : new horizons for structural biology Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK, 38000 Grenoble, France External Resource: https://www.xray.cz/iucrv/vidp.asp?id=512
11:25am - 11:45am
How machine learning can supplement traditional quality indicators - and the human eye: A case study 1Universität Hamburg, Germany; 2Julius-Maximilians-Universität Würzburg, Germany External Resource: https://www.xray.cz/iucrv/vidp.asp?id=513
11:45am - 12:05pm
Learning structure-energy relationships for the prediction of molecular crystal structures University of Southampton, Southampton, United Kingdom External Resource: https://www.xray.cz/iucrv/vidp.asp?id=514
12:05pm - 12:25pm
New generalized crystallographic descriptors for structural machine learning University of Edinburgh, Edinburgh, United Kingdom External Resource: https://www.xray.cz/iucrv/vidp.asp?id=515
12:25pm - 12:45pm
Analysis of pre-edge XANES spectra of Fe:SiO4 system by using machine learning methods. Southern Federal University, Rostov-on-Don, Russian Federation External Resource: https://www.xray.cz/iucrv/vidp.asp?id=516
|