Fungus MALDI-TOF mass spectrum data identification method based on neural network

A technology of mass spectrometry data and neural network, which is applied in the field of identification and classification of fungal MALDI-TOF mass spectrometry data, can solve the problems of information loss, large recognition error, long process, etc., achieve high accuracy and robustness, overcome long process, The effect of mass spectrometry data enrichment on the training set

Inactive Publication Date: 2019-12-27
颐保医疗科技(上海)有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional method has a long process, and each step of the process will cause information loss, and the optimization of several parameters in the algorithm depends on historical experience. In addition, the traditional method can only count the number of characteristic peaks matched by the current mass spectrum, but in fact some content Very low fragments are still very meaningful for feature identification. At this time, artificial weight intervention adjustment is required, and the difference in artificial subjective consciousness will cause the recognition error to further increase

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fungus MALDI-TOF mass spectrum data identification method based on neural network
  • Fungus MALDI-TOF mass spectrum data identification method based on neural network
  • Fungus MALDI-TOF mass spectrum data identification method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] A method for identifying fungal MALDI-TOF mass spectrometry data based on neural network, which is characterized in that it comprises the following steps:

[0029] S1. Obtain a fungal MALDI-TOF mass spectrum data set, and classify each mass spectrum data to obtain a marked original mass spectrum data set;

[0030] S2. Perform preprocessing such as normalization on the original mass spectrum data set to obtain a preprocessed mass spectrum data set;

[0031] S3. Build a neural network;

[0032] S4. Train the constructed neural network, and obtain the trained neural network as a prediction model based on fungal MALDI-TOF mass spectrometry data;

[0033] S5. Use the above prediction model to predict the new fungus MALDI-TOF MS mass spectrum data.

[0034] Further, in the step S1, after the collection stage is completed, professionals will label the data, and take the most labeled categories as the labeling result. If the labeling results are all different, the data will be discarded a...

Embodiment 2

[0044] A method for identifying fungal MALDI-TOF mass spectrometry data based on neural network, including the following steps:

[0045] S1. Obtain a fungal MALDI-TOF mass spectrum data set, and classify each mass spectrum data to obtain a marked original mass spectrum data set;

[0046] S2. Perform preprocessing such as normalization on the original mass spectrum data set to obtain a preprocessed mass spectrum data set;

[0047] S3. Build a neural network;

[0048] S4. Train the constructed neural network, and obtain the trained neural network as a prediction model based on fungal MALDI-TOF mass spectrometry data;

[0049] S5. Use the above prediction model to predict the new fungus MALDI-TOF mass spectrum data.

[0050] Preferably, in the step S1, after the collection phase is completed, the data is marked by professionals. To ensure accuracy, three persons are separately marked, and the most marked category is taken as the marking result. If the marking results are all different, the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a fungus MALDI-TOF mass spectrum data identification method based on a neural network. The technical core of the method is that based on the neural network intelligent classification technology, the powerful operational capability of a computer is utilized, the distribution rule of the charge-to-mass ratio weights of different strains is automatically summarized based on a back propagation optimization algorithm, and then a prediction classification model of fungus MALDI-TOF mass spectrum data is constructed.

Description

Technical field [0001] The invention relates to the field of fungal MALDI-TOF mass spectrometry data identification and classification, in particular to a method for fungal MALDI-TOF mass spectrometry data identification based on neural networks. Background technique [0002] Matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) is a mass spectrometry method that can directly detect proteins from the surface of intact microbial cells. Matrix-assisted laser desorption time-of-flight mass spectrometry is widely used in many fields such as the identification of microorganisms. However, it is challenging to analyze the data obtained, because in the identification of microorganisms, different laboratory environments (changes in culture medium, culture conditions, culture time) and diversified personal operation details will cause the final mass spectrometry data. In addition, the mass spectrometry data obtained from multiple samples will have mole...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/084G06F18/241
Inventor 刘新宇徐登友许慧张群华
Owner 颐保医疗科技(上海)有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products