Exploring Trial-and-Error in Deep Learning: Initial Application to Isotope Detection in Mass Spectrometry
Mass spectrometry plays a crucial role in biomedicine by detecting isotopes, contributing significantly to research, diagnostics, and therapy development. This study introduces IsoFusion, a deep learning model designed to address isotope detection in raw mass spectra. Rather than directly applying c...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2024-12-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2024.9020059 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850255284111409152 |
|---|---|
| author | Qihong Jiao Yuxiao Wang Yongshuai Wang Shiwei Sun Xuefeng Cui |
| author_facet | Qihong Jiao Yuxiao Wang Yongshuai Wang Shiwei Sun Xuefeng Cui |
| author_sort | Qihong Jiao |
| collection | DOAJ |
| description | Mass spectrometry plays a crucial role in biomedicine by detecting isotopes, contributing significantly to research, diagnostics, and therapy development. This study introduces IsoFusion, a deep learning model designed to address isotope detection in raw mass spectra. Rather than directly applying convolutional layers to all signal and noise peaks, IsoFusion employs a trial-and-error strategy. First, it investigates all potential charge states (trials) and collects signal peaks around expected m/z values for each trial. Then, convolutional layers extract features from each trial, which are fused to identify the correct one. Finally, the reparameterization trick predicts isotope features based on this correct trial. A key advantage of IsoFusion is shared model parameters across all trials, enhancing feature learning for less common charge states using data from prevalent ones. Our results show a significant accuracy improvement for charge state 5, reaching 99.42%, compared to DeepIso’s 43.36%. Moreover, IsoFusion achieves a 97.33% detection accuracy for isotopes, with 2.4% of detected isotopes previously unidentified by four commonly used methods. |
| format | Article |
| id | doaj-art-41e31f63e0b74fa8bbb31ac3433d7c0f |
| institution | OA Journals |
| issn | 2096-0654 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-41e31f63e0b74fa8bbb31ac3433d7c0f2025-08-20T01:56:56ZengTsinghua University PressBig Data Mining and Analytics2096-06542024-12-01741251126110.26599/BDMA.2024.9020059Exploring Trial-and-Error in Deep Learning: Initial Application to Isotope Detection in Mass SpectrometryQihong Jiao0Yuxiao Wang1Yongshuai Wang2Shiwei Sun3Xuefeng Cui4School of Computer Science and Technology, Shandong University, Qingdao 266237, ChinaSchool of Computer Science and Technology, Shandong University, Qingdao 266237, ChinaSchool of Computer Science and Technology, Shandong University, Qingdao 266237, ChinaKey Lab of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, ChinaSchool of Computer Science and Technology, Shandong University, Qingdao 266237, ChinaMass spectrometry plays a crucial role in biomedicine by detecting isotopes, contributing significantly to research, diagnostics, and therapy development. This study introduces IsoFusion, a deep learning model designed to address isotope detection in raw mass spectra. Rather than directly applying convolutional layers to all signal and noise peaks, IsoFusion employs a trial-and-error strategy. First, it investigates all potential charge states (trials) and collects signal peaks around expected m/z values for each trial. Then, convolutional layers extract features from each trial, which are fused to identify the correct one. Finally, the reparameterization trick predicts isotope features based on this correct trial. A key advantage of IsoFusion is shared model parameters across all trials, enhancing feature learning for less common charge states using data from prevalent ones. Our results show a significant accuracy improvement for charge state 5, reaching 99.42%, compared to DeepIso’s 43.36%. Moreover, IsoFusion achieves a 97.33% detection accuracy for isotopes, with 2.4% of detected isotopes previously unidentified by four commonly used methods.https://www.sciopen.com/article/10.26599/BDMA.2024.9020059liquid chromatography-mass spectrometry (lc-ms)isotope detectionretention time predictioncharge state predictiondeep learning |
| spellingShingle | Qihong Jiao Yuxiao Wang Yongshuai Wang Shiwei Sun Xuefeng Cui Exploring Trial-and-Error in Deep Learning: Initial Application to Isotope Detection in Mass Spectrometry Big Data Mining and Analytics liquid chromatography-mass spectrometry (lc-ms) isotope detection retention time prediction charge state prediction deep learning |
| title | Exploring Trial-and-Error in Deep Learning: Initial Application to Isotope Detection in Mass Spectrometry |
| title_full | Exploring Trial-and-Error in Deep Learning: Initial Application to Isotope Detection in Mass Spectrometry |
| title_fullStr | Exploring Trial-and-Error in Deep Learning: Initial Application to Isotope Detection in Mass Spectrometry |
| title_full_unstemmed | Exploring Trial-and-Error in Deep Learning: Initial Application to Isotope Detection in Mass Spectrometry |
| title_short | Exploring Trial-and-Error in Deep Learning: Initial Application to Isotope Detection in Mass Spectrometry |
| title_sort | exploring trial and error in deep learning initial application to isotope detection in mass spectrometry |
| topic | liquid chromatography-mass spectrometry (lc-ms) isotope detection retention time prediction charge state prediction deep learning |
| url | https://www.sciopen.com/article/10.26599/BDMA.2024.9020059 |
| work_keys_str_mv | AT qihongjiao exploringtrialanderrorindeeplearninginitialapplicationtoisotopedetectioninmassspectrometry AT yuxiaowang exploringtrialanderrorindeeplearninginitialapplicationtoisotopedetectioninmassspectrometry AT yongshuaiwang exploringtrialanderrorindeeplearninginitialapplicationtoisotopedetectioninmassspectrometry AT shiweisun exploringtrialanderrorindeeplearninginitialapplicationtoisotopedetectioninmassspectrometry AT xuefengcui exploringtrialanderrorindeeplearninginitialapplicationtoisotopedetectioninmassspectrometry |