Trained neural network model for parameter-less peak detection
AssigneeThermo Finnigan LLC
InventorsLinda Xueying Lin, James Timothy Dillon
Life of this patent
Estimating the term…
Abstract
Disclosed herein are scientific instrument support systems, as well as related methods, computing devices, and computer-readable media. For example, in some embodiments, a chromatography instrument support apparatus may include: first logic to receive a chromatogram data set; second logic to determine one or more peak locations for the chromatogram data set by processing the chromatogram data set through a machine-learning computational model to determine a plurality of input parameter values for a Gaussian curve fitting the chromatogram data set; and third logic to provide the one or more peak locations for further small molecule Liquid-Chromatography Mass Spectrometry (LC/MS) processing.
Claims20
A chromatography support apparatus, comprising:
- first logic to receive a chromatogram data set;
- second logic to determine one or more peak locations for the chromatogram data set by processing the chromatogram data set through a machine-learning computational model to determine a plurality of input parameter values for a Gaussian curve fitting the chromatogram data set;
- and
- third logic to provide the one or more peak locations for further small molecule Liquid-Chromatography Mass Spectrometry (LC/MS) processing.
A chromatography support apparatus, comprising:
- first logic to receive a command to train a machine-learning computational model, wherein the command includes an identification of multiple chromatogram data sets and a plurality of input parameter values for a Gaussian curve fitting each of the chromatogram data sets for training the machine-learning computational model;
- second logic to initially train the machine-learning computational model based on the multiple chromatogram data sets and the input parameter values for the Gaussian curve fitting each of the chromatogram data sets, wherein the machine-learning computational model is to output a plurality of input parameter values for a Gaussian curve fitting an input chromatogram data set;
- and
- third logic to provide, after initial training, an option to select the machine-learning computational model for application to a subsequent chromatogram data set.
A method for scientific instrument support executed by one or more processing devices, comprising:
- receiving a chromatogram data set;
- determining one or more peak locations for the chromatogram data set by processing the chromatogram data set through a machine-learning computational model to determine a plurality of input parameter values for a Gaussian curve fitting the chromatogram data set;
- and
- providing the one or more peak locations for further small molecule Liquid-Chromatography Mass Spectrometry (LC/MS) processing.
Dependencies are inferred from the claim text.