A Deep Convolutional Neural Network for Prediction of Peptide Collision Cross Sections in Ion Mobility Spectrometry
Most frequently, the identification of peptides in mass spectrometry-based proteomics is carried out using high-resolution tandem mass spectrometry. In order to increase the accuracy of analysis, additional information on the peptides such as chromatographic retention time and collision cross sectio...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Biomolecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-273X/11/12/1904 |
| _version_ | 1827673974346088448 |
|---|---|
| author | Yulia V. Samukhina Dmitriy D. Matyushin Oksana I. Grinevich Aleksey K. Buryak |
| author_facet | Yulia V. Samukhina Dmitriy D. Matyushin Oksana I. Grinevich Aleksey K. Buryak |
| author_sort | Yulia V. Samukhina |
| collection | DOAJ |
| description | Most frequently, the identification of peptides in mass spectrometry-based proteomics is carried out using high-resolution tandem mass spectrometry. In order to increase the accuracy of analysis, additional information on the peptides such as chromatographic retention time and collision cross section in ion mobility spectrometry can be used. An accurate prediction of the collision cross section values allows erroneous candidates to be rejected using a comparison of the observed values and the predictions based on the amino acids sequence. Recently, a massive high-quality data set of peptide collision cross sections was released. This opens up an opportunity to apply the most sophisticated deep learning techniques for this task. Previously, it was shown that a recurrent neural network allows for predicting these values accurately. In this work, we present a deep convolutional neural network that enables us to predict these values more accurately compared with previous studies. We use a neural network with complex architecture that contains both convolutional and fully connected layers and comprehensive methods of converting a peptide to multi-channel 1D spatial data and vector. The source code and pre-trained model are available online. |
| first_indexed | 2024-03-10T04:33:11Z |
| format | Article |
| id | doaj.art-d66d293930d24bae98900803ada12052 |
| institution | Directory Open Access Journal |
| issn | 2218-273X |
| language | English |
| last_indexed | 2024-03-10T04:33:11Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomolecules |
| spelling | doaj.art-d66d293930d24bae98900803ada120522023-11-23T04:01:03ZengMDPI AGBiomolecules2218-273X2021-12-011112190410.3390/biom11121904A Deep Convolutional Neural Network for Prediction of Peptide Collision Cross Sections in Ion Mobility SpectrometryYulia V. Samukhina0Dmitriy D. Matyushin1Oksana I. Grinevich2Aleksey K. Buryak3A.N. Frumkin Institute of Physical Chemistry and Electrochemistry, Russian Academy of Sciences, 31 Leninsky Prospect, GSP-1, 119071 Moscow, RussiaA.N. Frumkin Institute of Physical Chemistry and Electrochemistry, Russian Academy of Sciences, 31 Leninsky Prospect, GSP-1, 119071 Moscow, RussiaA.N. Frumkin Institute of Physical Chemistry and Electrochemistry, Russian Academy of Sciences, 31 Leninsky Prospect, GSP-1, 119071 Moscow, RussiaA.N. Frumkin Institute of Physical Chemistry and Electrochemistry, Russian Academy of Sciences, 31 Leninsky Prospect, GSP-1, 119071 Moscow, RussiaMost frequently, the identification of peptides in mass spectrometry-based proteomics is carried out using high-resolution tandem mass spectrometry. In order to increase the accuracy of analysis, additional information on the peptides such as chromatographic retention time and collision cross section in ion mobility spectrometry can be used. An accurate prediction of the collision cross section values allows erroneous candidates to be rejected using a comparison of the observed values and the predictions based on the amino acids sequence. Recently, a massive high-quality data set of peptide collision cross sections was released. This opens up an opportunity to apply the most sophisticated deep learning techniques for this task. Previously, it was shown that a recurrent neural network allows for predicting these values accurately. In this work, we present a deep convolutional neural network that enables us to predict these values more accurately compared with previous studies. We use a neural network with complex architecture that contains both convolutional and fully connected layers and comprehensive methods of converting a peptide to multi-channel 1D spatial data and vector. The source code and pre-trained model are available online.https://www.mdpi.com/2218-273X/11/12/1904proteomicsion mobility spectrometrydeep learningpeptides |
| spellingShingle | Yulia V. Samukhina Dmitriy D. Matyushin Oksana I. Grinevich Aleksey K. Buryak A Deep Convolutional Neural Network for Prediction of Peptide Collision Cross Sections in Ion Mobility Spectrometry Biomolecules proteomics ion mobility spectrometry deep learning peptides |
| title | A Deep Convolutional Neural Network for Prediction of Peptide Collision Cross Sections in Ion Mobility Spectrometry |
| title_full | A Deep Convolutional Neural Network for Prediction of Peptide Collision Cross Sections in Ion Mobility Spectrometry |
| title_fullStr | A Deep Convolutional Neural Network for Prediction of Peptide Collision Cross Sections in Ion Mobility Spectrometry |
| title_full_unstemmed | A Deep Convolutional Neural Network for Prediction of Peptide Collision Cross Sections in Ion Mobility Spectrometry |
| title_short | A Deep Convolutional Neural Network for Prediction of Peptide Collision Cross Sections in Ion Mobility Spectrometry |
| title_sort | deep convolutional neural network for prediction of peptide collision cross sections in ion mobility spectrometry |
| topic | proteomics ion mobility spectrometry deep learning peptides |
| url | https://www.mdpi.com/2218-273X/11/12/1904 |
| work_keys_str_mv | AT yuliavsamukhina adeepconvolutionalneuralnetworkforpredictionofpeptidecollisioncrosssectionsinionmobilityspectrometry AT dmitriydmatyushin adeepconvolutionalneuralnetworkforpredictionofpeptidecollisioncrosssectionsinionmobilityspectrometry AT oksanaigrinevich adeepconvolutionalneuralnetworkforpredictionofpeptidecollisioncrosssectionsinionmobilityspectrometry AT alekseykburyak adeepconvolutionalneuralnetworkforpredictionofpeptidecollisioncrosssectionsinionmobilityspectrometry AT yuliavsamukhina deepconvolutionalneuralnetworkforpredictionofpeptidecollisioncrosssectionsinionmobilityspectrometry AT dmitriydmatyushin deepconvolutionalneuralnetworkforpredictionofpeptidecollisioncrosssectionsinionmobilityspectrometry AT oksanaigrinevich deepconvolutionalneuralnetworkforpredictionofpeptidecollisioncrosssectionsinionmobilityspectrometry AT alekseykburyak deepconvolutionalneuralnetworkforpredictionofpeptidecollisioncrosssectionsinionmobilityspectrometry |