A cost-sensitive online learning method for peptide identification
Abstract Background Post-database search is a key procedure in peptide identification with tandem mass spectrometry (MS/MS) strategies for refining peptide-spectrum matches (PSMs) generated by database search engines. Although many statistical and machine learning-based methods have been developed t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-04-01
|
| Series: | BMC Genomics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12864-020-6693-y |
| _version_ | 1828498165800632320 |
|---|---|
| author | Xijun Liang Zhonghang Xia Ling Jian Yongxiang Wang Xinnan Niu Andrew J. Link |
| author_facet | Xijun Liang Zhonghang Xia Ling Jian Yongxiang Wang Xinnan Niu Andrew J. Link |
| author_sort | Xijun Liang |
| collection | DOAJ |
| description | Abstract Background Post-database search is a key procedure in peptide identification with tandem mass spectrometry (MS/MS) strategies for refining peptide-spectrum matches (PSMs) generated by database search engines. Although many statistical and machine learning-based methods have been developed to improve the accuracy of peptide identification, the challenge remains on large-scale datasets and datasets with a distribution of unbalanced PSMs. A more efficient learning strategy is required for improving the accuracy of peptide identification on challenging datasets. While complex learning models have larger power of classification, they may cause overfitting problems and introduce computational complexity on large-scale datasets. Kernel methods map data from the sample space to high dimensional spaces where data relationships can be simplified for modeling. Results In order to tackle the computational challenge of using the kernel-based learning model for practical peptide identification problems, we present an online learning algorithm, OLCS-Ranker, which iteratively feeds only one training sample into the learning model at each round, and, as a result, the memory requirement for computation is significantly reduced. Meanwhile, we propose a cost-sensitive learning model for OLCS-Ranker by using a larger loss of decoy PSMs than that of target PSMs in the loss function. Conclusions The new model can reduce its false discovery rate on datasets with a distribution of unbalanced PSMs. Experimental studies show that OLCS-Ranker outperforms other methods in terms of accuracy and stability, especially on datasets with a distribution of unbalanced PSMs. Furthermore, OLCS-Ranker is 15–85 times faster than CRanker. |
| first_indexed | 2024-12-11T13:02:13Z |
| format | Article |
| id | doaj.art-ae96654606ba4755a5c42eb5a1ae8ed4 |
| institution | Directory Open Access Journal |
| issn | 1471-2164 |
| language | English |
| last_indexed | 2024-12-11T13:02:13Z |
| publishDate | 2020-04-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Genomics |
| spelling | doaj.art-ae96654606ba4755a5c42eb5a1ae8ed42022-12-22T01:06:26ZengBMCBMC Genomics1471-21642020-04-0121111310.1186/s12864-020-6693-yA cost-sensitive online learning method for peptide identificationXijun Liang0Zhonghang Xia1Ling Jian2Yongxiang Wang3Xinnan Niu4Andrew J. Link5College of Science, China University of PetroleumSchool of Engineering and Applied Science, Western Kentucky UniversitySchool of Economics and Management, China University of PetroleumCollege of Science, China University of PetroleumDept. of Pathology, Microbiology and Immunology, Vanderbilt University School of MedicineDept. of Pathology, Microbiology and Immunology, Vanderbilt University School of MedicineAbstract Background Post-database search is a key procedure in peptide identification with tandem mass spectrometry (MS/MS) strategies for refining peptide-spectrum matches (PSMs) generated by database search engines. Although many statistical and machine learning-based methods have been developed to improve the accuracy of peptide identification, the challenge remains on large-scale datasets and datasets with a distribution of unbalanced PSMs. A more efficient learning strategy is required for improving the accuracy of peptide identification on challenging datasets. While complex learning models have larger power of classification, they may cause overfitting problems and introduce computational complexity on large-scale datasets. Kernel methods map data from the sample space to high dimensional spaces where data relationships can be simplified for modeling. Results In order to tackle the computational challenge of using the kernel-based learning model for practical peptide identification problems, we present an online learning algorithm, OLCS-Ranker, which iteratively feeds only one training sample into the learning model at each round, and, as a result, the memory requirement for computation is significantly reduced. Meanwhile, we propose a cost-sensitive learning model for OLCS-Ranker by using a larger loss of decoy PSMs than that of target PSMs in the loss function. Conclusions The new model can reduce its false discovery rate on datasets with a distribution of unbalanced PSMs. Experimental studies show that OLCS-Ranker outperforms other methods in terms of accuracy and stability, especially on datasets with a distribution of unbalanced PSMs. Furthermore, OLCS-Ranker is 15–85 times faster than CRanker.http://link.springer.com/article/10.1186/s12864-020-6693-yPeptide identificationMass spectrometryClassificationSupport vector machinesOnline learning |
| spellingShingle | Xijun Liang Zhonghang Xia Ling Jian Yongxiang Wang Xinnan Niu Andrew J. Link A cost-sensitive online learning method for peptide identification BMC Genomics Peptide identification Mass spectrometry Classification Support vector machines Online learning |
| title | A cost-sensitive online learning method for peptide identification |
| title_full | A cost-sensitive online learning method for peptide identification |
| title_fullStr | A cost-sensitive online learning method for peptide identification |
| title_full_unstemmed | A cost-sensitive online learning method for peptide identification |
| title_short | A cost-sensitive online learning method for peptide identification |
| title_sort | cost sensitive online learning method for peptide identification |
| topic | Peptide identification Mass spectrometry Classification Support vector machines Online learning |
| url | http://link.springer.com/article/10.1186/s12864-020-6693-y |
| work_keys_str_mv | AT xijunliang acostsensitiveonlinelearningmethodforpeptideidentification AT zhonghangxia acostsensitiveonlinelearningmethodforpeptideidentification AT lingjian acostsensitiveonlinelearningmethodforpeptideidentification AT yongxiangwang acostsensitiveonlinelearningmethodforpeptideidentification AT xinnanniu acostsensitiveonlinelearningmethodforpeptideidentification AT andrewjlink acostsensitiveonlinelearningmethodforpeptideidentification AT xijunliang costsensitiveonlinelearningmethodforpeptideidentification AT zhonghangxia costsensitiveonlinelearningmethodforpeptideidentification AT lingjian costsensitiveonlinelearningmethodforpeptideidentification AT yongxiangwang costsensitiveonlinelearningmethodforpeptideidentification AT xinnanniu costsensitiveonlinelearningmethodforpeptideidentification AT andrewjlink costsensitiveonlinelearningmethodforpeptideidentification |