Filters








4,441 Hits in 5.7 sec

Improving the Results of De novo Peptide Identification via Tandem Mass Spectrometry Using a Genetic Programming-based Scoring Function for Re-ranking Peptide-Spectrum Matches [article]

Samaneh Azari, Bing Xue, Mengjie Zhang, Lifeng Peng
2019 arXiv   pre-print
A fundamental part of a quality-control method is the scoring function used to evaluate the quality of peptide-spectrum matches (PSMs).  ...  Here, we propose a genetic programming (GP) based method, called GP-PSM, to learn a PSM scoring function for improving the rate of confident peptide identification from MS/MS data.  ...  Conclusions and Future Work This work developed a genetic programming (GP) based method to automatically generate a PSM scoring function aiming at reducing the rate of false discovery peptide identification  ... 
arXiv:1908.08010v1 fatcat:rih5eyajlrgh5fnkzg76rioidm

Machine learning applications in proteomics research: How the past can boost the future

Pieter Kelchtermans, Wout Bittremieux, Kurt De Grave, Sven Degroeve, Jan Ramon, Kris Laukens, Dirk Valkenborg, Harald Barsnes, Lennart Martens
2014 Proteomics  
This ability can be used to generate a solution to a particularly intractable problem, given that enough data is available to train and subsequently evaluate an algorithm on.  ...  Machine learning is a subdiscipline within artificial intelligence that focuses on algorithms that allow computers to learn solving a (complex) problem from existing data.  ...  They selected 393 peptide properties for their initial genetic program.  ... 
doi:10.1002/pmic.201300289 pmid:24323524 fatcat:twqy6plkfvc3pcpjtc6cdif5ma

Mass spectrometry and computational proteomics [chapter]

Vineet Bafna, Knut Reinert
2004 Encyclopedia of Genetics, Genomics, Proteomics and Bioinformatics  
Mass Spectrometry is the tool of choice for Proteomics, with applications to peptide sequencing, protein structure prediction, protein-protein interactions, and many others.  ...  This overview is not intended as an introduction to the technology itself or to proteomics.  ...  Geometric matching algorithms are used to match the similar spots, and their intensities are used for normalization, sometimes with internal standards.  ... 
doi:10.1002/047001153x.g405101 fatcat:o4r5i3melng37k4aht4fnaemj4

Identifying neoantigens for cancer vaccines by personalized deep learning of individual immunopeptidomes [article]

Ngoc Hieu Tran, Rui Qiao, Lei Xin, Xin Chen, Baozhen Shan, Ming Li
2019 bioRxiv   pre-print
Our workflow trains a specific deep learning model on the immunopeptidome of an individual patient and then use it to predict mutated neoantigens of that patient.  ...  This personalized learning and mass spectrometry-based approach enables comprehensive and accurate identification of neoantigens.  ...  HLA: Human Leukocyte Antigen PSM: Peptide-Spectrum Match Underlined red letters indicate mutated amino acids.  ... 
doi:10.1101/620468 fatcat:3iwpm5dwcngtxnrifqwcmcii4a

AN ACCURATE AND EFFICIENT ALGORITHM FOR PEPTIDE AND PTM IDENTIFICATION BY TANDEM MASS SPECTROMETRY

KANG NING, KEE NG HOONG, WAI LEONG HON
2007 Genome Informatics Series  
In this paper, we strive to achieve high accuracy and efficiency for peptide identification problem, with special concern on identification of peptides with PTMs.  ...  This paper expands our previous work on PepSOM with the introduction of two accurate modified scoring functions: Sk for peptide identification and Să* for identification of peptides with PTMs.  ...  In Popitam, the scoring function is based on genetic programming (machine learning), which are quite different from our scoring function.  ... 
doi:10.11234/gi1990.19.119 fatcat:krmrlpst7faubaxog6jlmg43wu

Visualization and analysis of molecular scanner peptide mass spectra

Markus Müller, Robin Gras, Ron D. Appel, Willy V. Bienvenut, Denis F. Hochstrasser
2002 Journal of the American Society for Mass Spectrometry  
Then, the correlation between neighboring spectra is used to recalibrate the peptide masses.  ...  The molecular scanner combines protein separation using gel electrophoresis with peptide mass fingerprinting (PMF) techniques to identify proteins in a highly automated manner.  ...  The authors would like to thank Pierre-Alain Binz, Salvo Peasano, and Jean-Charles Sanchez for their very useful contributions.  ... 
doi:10.1016/s1044-0305(01)00358-0 pmid:11908802 fatcat:lm7tbw5hlvbchedosctmzxzx4i

AN ACCURATE AND EFFICIENT ALGORITHM FOR PEPTIDE AND PTM IDENTIFICATION BY TANDEM MASS SPECTROMETRY

KANG NING, HOONG KEE NG, HON WAI LEONG
2007 Genome Informatics 2007  
In this paper, we strive to achieve high accuracy and efficiency for peptide identification problem, with special concern on identification of peptides with PTMs.  ...  This paper expands our previous work on PepSOM with the introduction of two accurate modified scoring functions: Sλ for peptide identification and Sλ* for identification of peptides with PTMs.  ...  In Popitam, the scoring function is based on genetic programming (machine learning), which are quite different from our scoring function.  ... 
doi:10.1142/9781860949852_0011 fatcat:ykqfuhjr3bhrnpq3eljth3bn2a

An accurate and efficient algorithm for Peptide and ptm identification by tandem mass spectrometry

Kang Ning, Hoong Kee Ng, Hon Wai Leong
2007 Genome Informatics Series  
In this paper, we strive to achieve high accuracy and efficiency for peptide identification problem, with special concern on identification of peptides with PTMs.  ...  This paper expands our previous work on PepSOM with the introduction of two accurate modified scoring functions: Slambda for peptide identification and Slambda* for identification of peptides with PTMs  ...  In Popitam, the scoring function is based on genetic programming (machine learning), which are quite different from our scoring function.  ... 
pmid:18546510 fatcat:yjha5r4mvrdr3azn7x7i564ki4

Recent developments in quantitative proteomics

Christopher H. Becker, Marshall Bern
2011 Mutation Research. Genetic Toxicology and Environmental Mutagenesis  
Then a discussion follows on the various computational techniques used to identify peptides and proteins from LC-MS/MS data.  ...  Proteomics continues to be a rapidly expanding field, with a wealth of reports regularly appearing on technology enhancements and scientific studies using these new tools.  ...  Acknowledgments The authors are pleased to acknowledge the many contributions of Drs.  ... 
doi:10.1016/j.mrgentox.2010.06.016 pmid:20620221 pmcid:PMC2980806 fatcat:42hsowazinhb5ib3uo6h25qfqu

Pattern-based algorithm for peptide sequencing from tandem high energy collision-induced dissociation mass spectra

Wade M. Hines, Arnold M. Falick, Alma L. Burlingame, Bradford W. Gibson
1992 Journal of the American Society for Mass Spectrometry  
heights, which is then used for sequencing, The sequencing algorithm was designed to use spectral data to generate sequence fits directly rather than to use data to test the frt of series of sequence guesses  ...  The peptide sequencing algorithm uses a pattern based on the polymeric nature of peptides to classify spectral peaks into sets that are related in a sequence-independent manner, It then establishes sequence  ...  of the spectra used in this work.  ... 
doi:10.1016/1044-0305(92)87060-c pmid:24243043 fatcat:kgoeu57fcjc5hiwm75l5ijze5i

Open-pFind enables precise, comprehensive and rapid peptide identification in shotgun proteomics [article]

Hao Chi, Chao Liu, Hao Yang, Wen-Feng Zeng, Long Wu, Wen-Jing Zhou, Xiu-Nan Niu, Yue-He Ding, Yao Zhang, Rui-Min Wang, Zhao-Wei Wang, Zhen-Lin Chen (+7 others)
2018 bioRxiv   pre-print
Tested on two metabolically labeled MS/MS datasets, Open-pFind reported 50.5‒117.0% more peptide-spectrum matches (PSMs) than the seven other advanced algorithms.  ...  We have developed a novel database search algorithm, Open-pFind, to efficiently identify peptides even in an ultra-large search space which takes into account unexpected modifications, amino acid mutations  ...  The two peptides may both match the spectrum well because many fragment ions are the same for the two peptides, and then match to the same peaks in S (although they may appear to have matched different  ... 
doi:10.1101/285395 fatcat:fhbx7alh4fdw5ne3s5zcyvprru

Proteomic Cancer Classification with Mass Spectrometry Data

Jagath C Rajapakse, Kai-Bo Duan, Wee Kiang Yeo
2005 American Journal of Pharmacogenomics  
[55, 56] Some statistical and machine learning methods have been 2.3 Spectra Alignment used for peak selection purposes, for example genetic algorithm, [57] signal-to-noise ratio, [58] and ROC curve  ...  A NC-spectrum graph version of the popular SVM [73, 74] is used as the learning algorithm consists of nodes and edges.  ... 
doi:10.2165/00129785-200505050-00001 pmid:16196498 fatcat:srtqlyws5rcybi5hkjkyarojc4

Deep learning in proteomics

Bo Wen, Wenfeng Zeng, Yuxing Liao, Zhiao Shi, Sara R Savage, Wen Jiang, Bing Zhang
2020 Proteomics  
We hope this review will provide readers an overview of deep learning and how it can be used to analyze proteomics data. This article is protected by copyright. All rights reserved.  ...  Here, we provide a comprehensive overview of deep learning applications in proteomics including retention time prediction, MS/MS spectrum prediction, de novo peptide sequencing, PTM prediction, major histocompatibility  ...  By considering the predicted spectra based on deep learning, pNovo3 re-ranks the peptide candidates generated by pNovo+ (a spectrum-graph and dynamic programming based algorithm [89] ) using a learning-to-rank  ... 
doi:10.1002/pmic.201900335 pmid:32939979 fatcat:gq6yffww6reu7eqrky7u6l2454

Dereplication of microbial metabolites through database search of mass spectra

Hosein Mohimani, Alexey Gurevich, Alexander Shlemov, Alla Mikheenko, Anton Korobeynikov, Liu Cao, Egor Shcherbin, Louis-Felix Nothias, Pieter C. Dorrestein, Pavel A. Pevzner
2018 Nature Communications  
In order to clear the road toward the discovery of unknown natural products, biologists need dereplication strategies that identify known ones.  ...  Here we report DEREPLICATOR+, an algorithm that improves on the previous approaches for identifying peptidic natural products, and extends them for identification of polyketides, terpenes, benzenoids,  ...  Acknowledgements We would like to thank Dr. Hiroshi Tsugawa for providing guidelines on running MS-FINDER against custom databases. We would also like to thank Dr. Tobias Find and Dr. Oliver  ... 
doi:10.1038/s41467-018-06082-8 pmid:30279420 pmcid:PMC6168521 fatcat:lflafaoaxra3roti6jadjijdpe

Recent advances and prospects of computational methods for metabolite identification: a review with emphasis on machine learning approaches

Dai Hai Nguyen, Canh Hao Nguyen, Hiroshi Mamitsuka
2018 Briefings in Bioinformatics  
We also give an intensive discussion on advanced machine learning methods, which can lead to further improvement on this task.  ...  It is also the key to the development of many applications and areas such as biotechnology, biomedicine or pharmaceuticals.  ...  Machine Learning (ML) is to learn and predict an intermediate representation between spectra and compound structures and then use such representation for matching or retrieval.  ... 
doi:10.1093/bib/bby066 pmid:30099485 fatcat:zqdzozintjayznjctttqn3nldi
« Previous Showing results 1 — 15 out of 4,441 results