scholarly journals Comparison of species classification models of mass spectrometry data: Kernel Discriminant Analysis vs Random Forest; A case study of Afrormosia (Pericopsis elata(Harms) Meeuwen)

2017 ◽  
Vol 31 (19) ◽  
pp. 1582-1588 ◽  
Author(s):  
V. Deklerck ◽  
K. Finch ◽  
P. Gasson ◽  
J. Van den Bulcke ◽  
J. Van Acker ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Discriminant Analysis ◽  
Random Forest ◽  
Mass Spectrometry Data ◽  
Classification Models ◽  
Species Classification ◽  
Kernel Discriminant Analysis

Coupling Proton Transfer Reaction−Mass Spectrometry with Linear Discriminant Analysis:  a Case Study

2003 ◽  
Vol 51 (25) ◽  
pp. 7227-7233 ◽  
Author(s):  
Franco Biasioli ◽  
Flavia Gasperi ◽  
Eugenio Aprea ◽  
Daniela Mott ◽  
Elena Boscaini ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Discriminant Analysis ◽  
Proton Transfer ◽  
Linear Discriminant Analysis ◽  
Transfer Reaction ◽  
Proton Transfer Reaction ◽  
Reaction Mass ◽  
Linear Discriminant

scholarly journals Comparison of Computational Algorithms for the Classification of Liver Cancer using SELDI Mass Spectrometry: A Case Study

2007 ◽  
Vol 3 ◽  
pp. 117693510700300 ◽  
Author(s):  
Changyu Shen ◽  
Timothy E Breen ◽  
Lacey E Dobrolecki ◽  
C. Max Schmidt ◽  
George W. Sledge ◽  
...  
Keyword(s):  
Mass Spectrometry ◽  
Hepatocellular Carcinoma ◽  
Support Vector Machine ◽  
Random Forest ◽  
Radial Function ◽  
Support Vector ◽  
Laser Desorption Ionization ◽  
Prediction Analysis

Introduction As an alternative to DNA microarrays, mass spectrometry based analysis of proteomic patterns has shown great potential in cancer diagnosis. The ultimate application of this technique in clinical settings relies on the advancement of the technology itself and the maturity of the computational tools used to analyze the data. A number of computational algorithms constructed on different principles are available for the classification of disease status based on proteomic patterns. Nevertheless, few studies have addressed the difference in the performance of these approaches. In this report, we describe a comparative case study on the classification accuracy of hepatocellular carcinoma based on the serum proteomic pattern generated from a Surface Enhanced Laser Desorption/Ionization (SELDI) mass spectrometer. Methods Nine supervised classification algorithms are implemented in R software and compared for the classification accuracy. Results We found that the support vector machine with radial function is preferable as a tool for classification of hepatocellular carcinoma using features in SELDI mass spectra. Among the rest of the methods, random forest and prediction analysis of microarrays have better performance. A permutation-based technique reveals that the support vector machine with a radial function seems intrinsically superior in learning from the training data since it has a lower prediction error than others when there is essentially no differential signal. On the other hand, the performance of the random forest and prediction analysis of microarrays rely on their capability of capturing the signals with substantial differentiation between groups. Conclusions Our finding is similar to a previous study, where classification methods based on the Matrix Assisted Laser Desorption/Ionization (MALDI) mass spectrometry are compared for the prediction accuracy of ovarian cancer. The support vector machine, random forest and prediction analysis of microarrays provide better prediction accuracy for hepatocellular carcinoma using SELDI proteomic data than six other approaches.

154: Integration of TPSA and High-Throughput Mass Spectrometry Data Improves Prostate Cancer Prediction

2007 ◽  
Vol 177 (4S) ◽  
pp. 52-53
Author(s):  
Stefano Ongarello ◽  
Eberhard Steiner ◽  
Regina Achleitner ◽  
Isabel Feuerstein ◽  
Birgit Stenzel ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Mass Spectrometry ◽  
High Throughput ◽  
Mass Spectrometry Data ◽  
Cancer Prediction

Use of Posterior Probabilities to Evaluate Methods of Discriminant Analysis

1981 ◽  
Vol 20 (04) ◽  
pp. 207-212 ◽  
Author(s):  
J. Hermans ◽  
B. van Zomeren ◽  
J. W. Raatgever ◽  
P. J. Sterk ◽  
J. D. F. Habbema
Keyword(s):  
Experimental Data ◽  
Discriminant Analysis ◽  
Posterior Probabilities

By means of a case study the choice between several methods of discriminant analysis is presented. Experimental data of a two-groups problem with one or two variables is analysed. The different methods are compared according to posterior probabilities which can be computed for each subject and which are the basis of discriminant analysis. These posterior probabilities are analysed graphically as well as numerically.

Algorithm of combining chromatography mass spectrometry-untargeted profiling and multivariate analysis for identification of marker-substances in samples of complex composition

2020 ◽  
Vol 86 (7) ◽  
pp. 12-19
Author(s):  
I. V. Plyushchenko ◽  
D. G. Shakhmatov ◽  
I. A. Rodin
Keyword(s):  
Mass Spectrometry ◽  
Multivariate Analysis ◽  
Large Scale ◽  
Complex Composition ◽  
Unified Protocol ◽  
Chromatography Mass Spectrometry ◽  
Marker Substances ◽  
Selection Testing ◽  
Untargeted Profiling

A viral development of statistical data processing, computing capabilities, chromatography-mass spectrometry, and omics technologies (technologies based on the achievements of genomics, transcriptomics, proteomics, metabolomics) in recent decades has not led to formation of a unified protocol for untargeted profiling. Systematic errors reduce the reproducibility and reliability of the obtained results, and at the same time hinder consolidation and analysis of data gained in large-scale multi-day experiments. We propose an algorithm for conducting omics profiling to identify potential markers in the samples of complex composition and present the case study of urine samples obtained from different clinical groups of patients. Profiling was carried out by the method of liquid chromatography mass spectrometry. The markers were selected using methods of multivariate analysis including machine learning and feature selection. Testing of the approach was performed using an independent dataset by clustering and projection on principal components.

Nonparametric Pre-Processing Methods and Inference Tools for Analyzing Time-of-Flight Mass Spectrometry Data.

2007 ◽  
Vol 3 (2) ◽  
pp. 127-147 ◽  
Author(s):  
Anestis Antoniadis ◽  
Jeremie Bigot ◽  
Sophie Lambert-Lacroix ◽  
Frederique Letue
Keyword(s):  
Mass Spectrometry ◽  
Time Of Flight ◽  
Mass Spectrometry Data ◽  
Processing Methods ◽  
Flight Mass Spectrometry
Sign in / Sign up

Export Citation Format

Share Document