Chemical exchange
Deep-learning CEST analysis
Extract exchange parameters from CEST profiles with a trained network, without hand-tuned starting values.
Conventional CEST fitting needs a starting model and reasonable initial parameters, and getting those wrong wastes time or produces a confident local minimum. A network trained on simulated profiles across the parameter space maps a profile to parameters directly, with no initialisation to choose.
It is fast enough to run across every residue as a first pass, which makes it most useful as a way to find the residues worth fitting properly and to generate the starting values that conventional fitting then needs.
What it needs
- CEST series
- Peak list or assignment
What you get
- Exchange parameters per residue
- Starting values for a conventional fit
Enter wherever your data already is
This analysis runs as a full pipeline from spectra, or picks up from work you have already done — so nothing has to be repeated to get to the next step.
- From spectra
- From a peak list
- From fitted intensities
What does the work
DNNautoCEST
Open source, redistributed under its licenceMIT-equivalent: written consent from D. Flemming HansenTrained CEST analysis
Related in Chemical exchange
- CPMG relaxation dispersionCharacterise microsecond-to-millisecond exchange and extract the populations, rates and shifts of states too sparse to see.
- Chemical Exchange Saturation Transfer (CEST)Locate and quantify sparsely populated states through saturation transfer, including DANTE and cosine-modulated variants.