Neural network prediction of peptide separation in strong anion exchange chromatography

Oh, Cheolhwan; Żak, Stanisław H.; Mirzaei, Hamid; Buck, Charles R.; Regnier, Fred E.; Zhang, Xiang

doi:10.1093/bioinformatics/btl561

Cited by 20 publications

(22 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial neural networks have been applied for predicting the separation of peptides in strong anion exchange chromatography. Such capability allows researchers to predict peptide separation and assist with required data mining steps such as protein identification [102].…”

Section: Anns Application In Proteomics and Genomicsmentioning

confidence: 99%

Artificial Neural Network in Drug Delivery and Pharmaceutical Research

Sutariya¹,

Groshev²,

Sadana³

et al. 2013

TOBIOIJ

View full text Add to dashboard Cite

Artificial neural networks (ANNs) technology models the pattern recognition capabilities of the neural networks of the brain. Similarly to a single neuron in the brain, artificial neuron unit receives inputs from many external sources, processes them, and makes decisions. Interestingly, ANN simulates the biological nervous system and draws on analogues of adaptive biological neurons. ANNs do not require rigidly structured experimental designs and can map functions using historical or incomplete data, which makes them a powerful tool for simulation of various non-linear systems.ANNs have many applications in various fields, including engineering, psychology, medicinal chemistry and pharmaceutical research. Because of their capacity for making predictions, pattern recognition, and modeling, ANNs have been very useful in many aspects of pharmaceutical research including modeling of the brain neural network, analytical data analysis, drug modeling, protein structure and function, dosage optimization and manufacturing, pharmacokinetics and pharmacodynamics modeling, and in vitro in vivo correlations. This review discusses the applications of ANNs in drug delivery and pharmacological research.

show abstract

Section: Anns Application In Proteomics and Genomicsmentioning

confidence: 99%

Artificial Neural Network in Drug Delivery and Pharmaceutical Research

Sutariya¹,

Groshev²,

Sadana³

et al. 2013

TOBIOIJ

View full text Add to dashboard Cite

show abstract

“…The effect of pH on separation ability of ion exchange chromatography has already been described. [49][50][51] Most samples before were of less complexity; therefore, careful selection of a buffer system at a fixed pH value could satisfy. Great complexity and high throughput in proteomics make comprehensive prefractionation ahead of MS absolutely necessary.…”

Section: Speculations Upon Chromatographic Behavior Of Standardmentioning

confidence: 99%

Fractionation of Complex Protein Mixture by Virtual Three-Dimensional Liquid Chromatography Based on Combined pH and Salt Steps

Ning

Dai

et al. 2008

J. Proteome Res.

View full text Add to dashboard Cite

The complexity and diversity of biological samples in proteomics require intensive fractionation ahead of mass spectrometry identification. This work developed a chromatographic method called virtual three-dimensional chromatography to fractionate complex protein mixtures. By alternate elution with different pHs and salt concentrations, we implemented pH and salt steps by turns on a single strong cation exchange column to fully exploit its chromatographic ability. Given standard proteins that were not resolved solely by pH or salt gradient elution could be successfully separated using this combined mode. With a reversed phase column tandem connected behind, we further fractionated as well as desalted proteins as the third dimension. This present strategy could readily be adapted with respect to special complexity of biological samples. Crude plasma without depleting high abundance proteins were fractionated by this three-dimensional mode and then analyzed by reversed phase liquid chromatography coupled with LTQ mass spectrometry. In total, 1933 protein groups with wide dynamic ranges were identified from a single experiment. Some characteristics that correlated to the behavior of proteins on strong cation exchange columns are also discussed.

show abstract

“…The variable selection method uninformative variable elimination by partial least squares (UVE-PLS) was employed for QSRR in Put et al (2006), to improve performance of the model. Prediction of peptide separation in a step gradient was explored by Oh et al (2007) for strong anion exchange (SAX) chromatography, where each peptide is assigned to either a 'flow-through' or 'elution' fraction. An artificial neural network based pattern classification technique was employed for the prediction and these authors extracted four significant features for analysis (sequence index, charge, molecular weight, length of amino acid residue sequence).…”

Section: Retention Time Filteringmentioning

confidence: 99%

Current Status of Computational Approaches for Protein Identification Using Tandem Mass Spectra

Zhang¹,

Oh²,

Riley³

et al. 2007

View full text Add to dashboard Cite

Proteomics is a still-evolving combination of technologies to describe and characterize all expressed proteins in a biological system. Because of upper limits on mass detection of mass spectrometers, the bottom-up approach is most widely employed in which tryptic peptides are quantified and identified from complex protein mixtures. Protein identification from tandem mass spectra is still a challenge in proteomics. Two approaches have been developed to identify proteins from tandem mass spectra, database searching and de novo sequencing. These approaches typically have positive identification rates of only ~10-20%, and exhibit high false positive identification rates. This review surveys existing algorithms developed for database searching and de novo sequencing, with a focus on recent developments for tandem mass spectrum quality assessment, peptide identification using annotated spectra libraries, statistical approaches to assess identification quality, and methods for constrained searches. We also review research comparing the performance of existing protein identification packages.

show abstract

Neural network prediction of peptide separation in strong anion exchange chromatography

Abstract: The software and testing results can be downloaded from ftp://ftp.bbc.purdue.edu.

Cited by 20 publications

References 7 publications

Artificial Neural Network in Drug Delivery and Pharmaceutical Research

Artificial Neural Network in Drug Delivery and Pharmaceutical Research

Fractionation of Complex Protein Mixture by Virtual Three-Dimensional Liquid Chromatography Based on Combined pH and Salt Steps

Current Status of Computational Approaches for Protein Identification Using Tandem Mass Spectra

Contact Info

Product

Resources

About