Proteome Profiling without Selection Bias

Barla, Annalisa; Irler, B.; Merler, Stefano; Jurman, Giuseppe; Paoli, Silvano; Furlanello, Cesare

doi:10.1109/cbms.2006.134

Cited by 4 publications

(2 citation statements)

References 17 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Precise visual inspection of Fig.3 gives us useful information about the spectrum. Without any pre-processing and analysis, it can obviously be seen that: l. In last third of the MSII, there are no valuable information (this result is previously reported using complicated feature extraction and selection procedures [17,5,15,16,22]). 2.…”

Section: A a Novel Data Representation/or Msdmentioning

confidence: 65%

See 1 more Smart Citation

A novel method for mass spectrometry data representation and analysis

Alipoor¹,

Haddadnia²

2010

2010 17th Iranian Conference of Biomedical Engineering (ICBME)

View full text Add to dashboard Cite

In this paper a novel representation/analysis method on high throughput SELDI-TOF mass-spectroscopy data is developed. To avoid complexity of conventional methods, mass spectrum is converted to an intensity image and then image processing techniques is implemented to solve the cancer classification problem.The proposed system benefits a thoroughly novel and efficient idea to design an image-based pattern recognition system for cancer classification. The system is successfully validated using a well-known ovarian cancer proteomic dataset. Results of applying the method are comparable to state of the art methods in proteomic pattern recognition.

show abstract

Section: A a Novel Data Representation/or Msdmentioning

confidence: 65%

“…They achieved accuracy of 100% using these 10 features. There are some other works that all of them didn't reach perfect classification [16][17][18][19][20][21][22].…”

Section: Dataset and Related Workmentioning

confidence: 99%

A novel method for mass spectrometry data representation and analysis

Alipoor¹,

Haddadnia²

2010

2010 17th Iranian Conference of Biomedical Engineering (ICBME)

View full text Add to dashboard Cite

show abstract

Machine learning methods for predictive proteomics

Barla

Jurman²,

Riccadonna³

et al. 2007

Briefings in Bioinformatics

View full text Add to dashboard Cite

The search for predictive biomarkers of disease from high-throughput mass spectrometry (MS) data requires a complex analysis path. Preprocessing and machine-learning modules are pipelined, starting from raw spectra, to set up a predictive classifier based on a shortlist of candidate features. As a machine-learning problem, proteomic profiling on MS data needs caution like the microarray case. The risk of overfitting and of selection bias effects is pervasive: not only potential features easily outnumber samples by 10(3) times, but it is easy to neglect information-leakage effects during preprocessing from spectra to peaks. The aim of this review is to explain how to build a general purpose design analysis protocol (DAP) for predictive proteomic profiling: we show how to limit leakage due to parameter tuning and how to organize classification and ranking on large numbers of replicate versions of the original data to avoid selection bias. The DAP can be used with alternative components, i.e. with different preprocessing methods (peak clustering or wavelet based), classifiers e.g. Support Vector Machine (SVM) or feature ranking methods (recursive feature elimination or I-Relief). A procedure for assessing stability and predictive value of the resulting biomarkers' list is also provided. The approach is exemplified with experiments on synthetic datasets (from the Cromwell MS simulator) and with publicly available datasets from cancer studies.

show abstract

A Grid Environment for High-Throughput Proteomics

Cannataro

Barla

Flor³

et al. 2007

IEEE Trans.on Nanobioscience

View full text Add to dashboard Cite

We connect in a grid-enabled pipeline an ontology-based environment for proteomics spectra management with a machine learning platform for unbiased predictive analysis. We exploit two existing software platforms (MS-Analyzer and BioDCV), the emerging proteomics standards, and the middleware and computing resources of the EGEE Biomed VO grid infrastructure. In the setup, BioDCV is accessed by the MS-Analyzer workflow as a Web service, thus providing a complete grid environment for proteomics data analysis. Predictive classification studies on MALDI-TOF data based on this environment are presented.

show abstract

Proteome Profiling without Selection Bias

Cited by 4 publications

References 17 publications

A novel method for mass spectrometry data representation and analysis

A novel method for mass spectrometry data representation and analysis

Machine learning methods for predictive proteomics

A Grid Environment for High-Throughput Proteomics

Contact Info

Product

Resources

About