BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260717T191436Z
UID:7336845e-69ee-403c-9278-f7abcd64f067
DTSTART:20240409T170000Z
DTEND:20240409T170000Z
DESCRIPTION:This webinar is organised by the ELIXIR 3D-BioInfo Community\n
 \n				The event is hosted by\n\n				\n					\n						\n							\n							\n			
 				\n						\n						\n							\n								Dr Vincent Zoete (Chair) \n							
 \n							\n								Dr. Gonzalo Parra\n							\n							\n								Dr Neelad
 ri Sen           \n							\n						\n						\n							\n								 Swiss
  Institute of\n\n								Bioinformatics (SIB)  \n							\n							\n				
 				Barcelona Supercomputing Center  (BSC)  \n							\n							Universi
 ty College London (UCL)\n						\n					\n				\n\n				Programme: \n			\n			
  \n		\n	\n\n\nSILVR: Conditioning Diffusion Models for Fragment-Based Sma
 ll Molecule\n	Generation\n\nDr. Antonia Mey\n	(The University of Edinburgh
 \, UK) \n\n\n\nDiffusion models have proven to be a powerful tool in imag
 e generation and\, more recently\, in small molecule generation. Broadly\,
  molecular diffusion models can generate random molecules\, however\, the 
 generation of small molecules tailored to specific protein pockets is much
  more challenging.\n	In this talk\, I will introduce Selective Iterative L
 atent Variable Refinement (SILVR)\, a novel method designed to condition e
 xisting equivariant diffusion models based on X-ray fragment hits. SILVR i
 s a conditioning method that does not require additional training. The con
 ditioning is achieved in the latent space of the trained equivariant diffu
 sion model using the SILVR rate as a parameter to vary the level of condit
 ioning.\n	This runtime modification in combination with X-ray fragments al
 lows for the generation of new molecules that fit the binding site of the 
 target protein. Furthermore\, it is possible to link\, merge\, and extend 
 fragments. I will show the capabilities of SILVR on a dataset of SARS-CoV-
 2 main protease fragments from the Diamond X-Chem COVID Moonshot dataset.\
 n	This novel method sits at the interface between experimental data and ge
 nerative models\, offering a direct tool for enhancing small molecule gene
 ration. Its advantage lies in its broad applicably to any protein target f
 or which fragment hits are available and is a promising method in the arse
 nal of tools used in fragment-based drug design.\n\n\n	\n		Two-Step Covale
 nt Docking with Attracting Cavities\n\n		Dr. Mathilde Goullieux\n			(Swiss
  Institute of Bioinformatics)\n\n		\n\n		Molecular docking is a computatio
 nal approach used to predict the most probable pose of a ligand in a prote
 in binding site. Recently\, our docking code\, Attracting Cavities1 (AC)\,
  has undergone significant enhancements aimed at improving its sampling pr
 ocedure\, robustness and flexibility2.\n\n		Given the efficacy and advanta
 ges of covalent drugs\, such as beta-lactam antibiotics or proton-pump inh
 ibitors\, understanding and predicting their interactions with biological 
 targets is of utmost importance. Consequently\, we implemented a covalent 
 docking procedure into AC. This new feature mimics the two-step process of
  covalent ligand binding. First\, non-bonded interactions drive ligand bin
 ding to the protein\, and second\, a chemical reaction leads to the format
 ion of a new covalent bond between the ligand and the protein.\n\n		AC 2.0
  was rigorously tested on 285 complexes from the PDBbind Core set (2016 ve
 rsion) and achieved a success rate of 73%\, surpassing the performance of 
 the widely used docking codes GOLD (64%) and AutoDock Vina (58%) in non-co
 valent redocking experiments. Additionally\, we evaluated the covalent doc
 king algorithm using a benchmark set of 304 experimentally resolved covale
 nt complexes. The results showed that our approach outperformed the two st
 ate-of-the-art covalent docking codes\, AutoDock4 (66%) and GOLD (35%)\, w
 ith a success rate of 78%.\n\n		In parallel\, we developed a suite of tool
 s designed to make docking calculations accessible to non-expert users. Th
 ese tools are freely accessible through two web servers. SwissParam 2023 g
 enerates force field topologies and parameters for small molecules\, both 
 for non-covalent and covalent docking3. SwissDock 2024\, which will be rel
 eased soon\, will host tools for target preparation and will enable dockin
 g with AC and Autodock Vina. Both web servers will be described during the
  present webinar.\n\n		You can find previous webinars from the 3D-BioInfo 
 Community on the Community webinars page.\n\n		 
SUMMARY:3D-BioInfo: Protein Engineering And Design 2024
URL;VALUE=URI:https://www.elixir-europe.org/events/3d-bioinfo-protein-engin
 eering-and-design-2024-0
END:VEVENT
END:VCALENDAR