Unlock instant, AI-driven research and patent intelligence for your innovation.

Feature cross fusion time sequence peak cluster accurate positioning method

A cross-fusion and precise positioning technology, applied in the field of biological information/signal processing, can solve the problem of inaccurate peak cluster positioning, and achieve the effects of avoiding falling into local minimum, facilitating rapid convergence, and avoiding insufficient consideration

Inactive Publication Date: 2021-06-04
NORTHWEST UNIV(CN)
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the deficiencies in the prior art, the purpose of the present invention is to provide a time series peak cluster accurate positioning method of feature cross fusion to solve the technical problem of inaccurate peak cluster positioning in the prior art

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
  • Feature cross fusion time sequence peak cluster accurate positioning method
  • Feature cross fusion time sequence peak cluster accurate positioning method
  • Feature cross fusion time sequence peak cluster accurate positioning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0114] This embodiment provides a method for precise positioning of time series peak clusters based on feature cross fusion, which is carried out according to the following steps:

[0115] Step 1, identifying the glycopeptide mass spectrum data set to obtain the identification result data set;

[0116] The glycopeptide mass spectrum data set is multiple original mass spectrum files;

[0117] The identification result data set includes repeated identification ion data set r-Set and unmatched ion data set;

[0118] The repeated identification ion data set r-Set includes glycopeptide mass, charge, secondary spectrum number, sugar structure number and peptide chain composition; the unmatched ion data set includes glycopeptide mass, charge, secondary mass spectrum number, glycopeptide structure Numbering and peptide chain composition;

[0119] In this example, the glycopeptide mass spectrum data set of the pGlyco2.0 method was used for identification, and two original mass spectr...

example 1

[0257] Following the above-mentioned technical scheme, this practical example presents a time-series peak cluster precise positioning method based on feature cross-fusion, which is carried out through the above-mentioned steps 1 to 2, and the following is obtained: Figure 4 , where the abscissa represents the error range of the rough calibration, and the ordinate represents the true positive rate. The curve in the figure shows the change of the true positive rate under different error ranges, from Figure 4 It can be seen from the figure that as the error range increases, the true positive rate of the method of the present application is significantly higher than that of the traditional OLS method. Therefore, compared with the traditional method, the method of the present application has better overall stability.

example 2

[0259] Following the above-mentioned technical scheme, this actual measurement example provides a time-series peak cluster precise positioning method based on feature cross fusion, which uses the above-mentioned steps 1 to 3. The method Mine of this application is compatible with traditional PTW, DTW, and SFA-MS methods in The effects on the four evaluation indicators are as follows: Figure 5 As can be seen from the figure, the present invention is significantly better than the other three methods on the evaluation indicators of output result rate, true positive rate, positive result rate and harmonic mean, and compared to other three methods. The best method among these methods, the present invention improves the result rate, true positive rate, positive result rate and harmonic average by 0.4%, 5.7%, 4.3%, and 5.4% respectively. Therefore, it can be seen that the precise positioning of the present application Compared with the traditional method, the positioning accuracy of...

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 discloses a feature cross fusion time sequence peak cluster accurate positioning method, which is carried out according to the following steps: identifying a glycopeptide mass spectrum data set to obtain an identification result data set; establishing a random disturbance-based time-weighted global coarse calibration model among the original mass spectrum data, and carrying out model parameter training by using the repeated identification ion data set r-Set to obtain a random disturbance-based time-weighted global coarse calibration model; and using a time weighting coarse calibration model based on random disturbance for completing coarse calibration on an unmatched ion data set to obtain a coarse calibration result, and obtaining an optimal matching peak cluster CPeak-b according to the coarse calibration result. A random disturbance function used by the model is beneficial to rapid convergence of the model, and the model is prevented from falling into local minimum; and a peak feature cross fusion formula is constructed for correlation value calculation, an optimal matching peak cluster is obtained, accurate positioning of the peak cluster is completed, and the problem that in the prior art, peak cluster positioning is not accurate enough is solved.

Description

technical field [0001] The invention belongs to the field of biological information / signal processing, relates to the precise positioning of peak clusters in mass spectrometry, and in particular to a time series peak cluster precise positioning method for feature cross fusion. Background technique [0002] In the analysis and research of mass spectrometry data, there are usually gas chromatography, liquid chromatography LC and so on. These instruments and methods are capable of performing biological mass spectrometry to generate rich spectral information. Therefore, the acquisition of high-quality data is the key to practical applications, but this step is often affected by changes in instrument conditions and manual operations. In order to better apply the data, problems such as peak cluster drift caused by instrument drift, temperature and pressure fluctuations, injection delays, and aging of isolates in the data must be dealt with. Therefore, in the follow-up analysis a...

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): G16C20/30G01N30/86G06N3/12
CPCG16C20/30G01N30/8679G01N30/8696G06N3/126
Inventor 冯筠陆柯迪孙士生胡陟
Owner NORTHWEST UNIV(CN)