Deep learning under mass‐to‐charge ratio pre‐retrieval to realize electron ionization mass spectrometry library retrieval

Liu, Miaolong; Yu, Jiancheng; Yang, Yuan; Gao, Wenqing

doi:10.1002/rcm.9398

Cited by 4 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Immunoassays are generally reliable and accurate; they are more automated and decrease the sample preparation required [68]. Considering the findings of Liu et al in particular the effects of deep learning on the computational time of the algorithm, the use of deep learning in the MS should be encouraged [69]. For the most part, MS-based methods have lower limits of quantification than immunoassays and are therefore useful for measuring very low analyte concentrations [70].…”

Section: Immunoassay or Mass Spectrometry-affordabilitymentioning

confidence: 99%

“…Additionally, they require personnel (although, the "new" MALDI-ToF does not) with specialized training, and, due to batch processing, tend to have longer turnaround times (which has been successfully reduced). In contrast, immunoassays tend to be more easily automated and require less training but are more susceptible to interference and can require higher-priced reagents, hence costing more to run [36,69,74,75]. On the other hand, the cost of running LC-MS practically does not exist, however financial considerations for purchasing an MS are substantial.…”

Section: Feasibilitymentioning

confidence: 99%

See 1 more Smart Citation

Mass Spectrometry-Based Techniques Towards OMICS 2.0

Šoša¹

2023

Preprint

View full text Add to dashboard Cite

The literature was scoped to help place mass spectrometric (MS) platforms in the spotlight of the life sciences, as a tool of OMICS and OMICS 2.0 technologies. Moreover, today’s appliances are so handy, that they literally place a whole lab on a single chip. Methods of OMICS (and the most recently developed term OMICS 2.0) are tackled, having in mind their aptness for educational purposes, as well as their feasibility. This same topic was highlighted in many reviews that have been periodically published. The author’s initial interest was the forensic application of MS, but since these interests changed, terms such as “biosensors” were also examined, so the review included means of discovery of efficient biomarkers and clinical therapeutic targets. Aside from simply reviewing the research status and the future perspectives, this article tackles terms such as Society 5.0 and OMICS 2.0. However, within the framework of this review, physical chemistry, bioinformatics, or specific software solutions were not specifically studied. Since the topic of generating permanent collections of digital content for retrospective analysis was also reviewed, the need for loads of data – cloud storage was discussed in the context of MS. These large quantities of data are easier to operate with if generated by MS, rather than by any other commercially available assay. In this manner, the review has strengthened an in-depth understanding of the applications of MS.

show abstract

Section: Immunoassay or Mass Spectrometry-affordabilitymentioning

confidence: 99%

Section: Feasibilitymentioning

confidence: 99%

Mass Spectrometry-Based Techniques Towards OMICS 2.0

Šoša¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Immunoassays are generally reliable and accurate; they are more automated and decrease the sample preparation required. Considering the findings of Liu et al and the effects of deep learning on the computational time of the algorithm, the use of deep learning in the MS should be encouraged [64]. For the most part, MS-based methods have lower limits of quantification than immunoassays and are therefore useful for measuring very low analyte concentrations [65].…”

Section: Immunoassay or Ms-affordabilitymentioning

confidence: 99%

Section: Feasibilitymentioning

confidence: 99%

“…Therefore, perhaps it is sound to expect that machine learning algorithms and deep learning could further improve the sustainability of MS since it improves library retrieval accuracy, the accuracy of spectral library retrieval, and reduces the computational time of the algorithm by more than 2 hours in the study of Liu et al [64].…”

Section: Without Actually Knowing What Sustainability Looks Like In P...mentioning

confidence: 99%

See 1 more Smart Citation

Mass Spectrometry-Based Techniques Towards OMICS 2.0

Šoša¹

2022

Preprint

View full text Add to dashboard Cite

The literature was scoped to help place mass spectrometric (MS) platforms in the spotlight of the life sciences, as a tool of OMICS and OMICS 2.0 technologies. These methods were discussed, and their feasibility was highlighted in many reviews that have been periodically published, in addition to the most recently developed term OMICS 2.0. This author’s primary interest was the forensic application of MS, but since these interests got broadened, terms such as “biosensors” were also included. So, means of discovery of efficient biomarkers and clinical therapeutic targets were also reviewed. However, within the framework of this review, physical chemistry, bioinformatics, or specific software solutions were not specifically scoped. Aside from simply reviewing the research status and the future perspectives, this article tackles terms such as Society 5.0 and OMICS 2.0. Since the topic of generating permanent collections of digital content for retrospective analysis was reviewed, what requires loads of data – cloud storage is discussed in the context of MS. In this manner, the review has strengthened an in-depth understanding of the applications of MS. These large quantities of data are easier to operate with if generated by MS, rather than by any other commercially available assay.

show abstract

SR-Unet: A Super-Resolution Algorithm for Ion Trap Mass Spectrometers Based on the Deep Neural Network

Ai,

Zhao,

et al. 2023

Anal. Chem.

View full text Add to dashboard Cite

The mass spectrometer is an important tool for modern chemical analysis and detection. Especially, the emergence of miniature mass spectrometers has provided new tools for field analysis and detection. The resolution of a mass spectrometer reflects the ability of the instrument to discriminate between adjacent mass-to-charge ratio ions, and the higher the resolution, the better the discrimination of complex mixtures. Quadrupole ion traps are generally considered as a low-resolution mass spectrometry method, but they have gained wide attention and development in recent years because of their suitability for miniaturization and high qualitative capability. For an ion trap mass spectrometer, the mass sensitivity and resolution can be mutually constrained and need to be balanced by setting an appropriate scanning speed. In this study, a super-resolution U-net algorithm (SR-Unet) is proposed for ion trap mass spectrometry, which can estimate the possible ions from the overlapping ion peaks of low-resolution spectra and improve the equivalent resolution while ensuring sufficient sensitivity and analysis speed of the instrument. By determining the mass spectra of a linear ion trap mass spectrometer (LTQ XL) in Turbo and Normal scan modes, the same unit mass resolution as that at a scan speed of 16,667 Da/s was successfully obtained at 125,000 Da/s. Also, the experiments demonstrated that the algorithm is capable of the mass-to-charge ratio and instrument migration. SR-Unet can be migrated and applied to a miniature mass spectrometer for cruise detection of volatile organic compounds (VOCs), and the identification of VOC species in Photochemical Assessment Monitoring Stations (PAMS) was improved from 31 to 50 species with the same monitoring and analysis speed requirement. Further, super-unit mass resolution peptide detection was achieved on a miniature mass spectrometer with the help of the SR-Unet algorithm, which reduced the full width at half-maxima (FWHM) of bradykinin divalent ions (m/z 531) from 0.35 to 0.15 Da at a scan speed of 375 Da/s and improved the equivalent resolution to 3540. The proposed method provides a new idea to enhance the field mixture detection capability of miniature ion trap mass spectrometers.

show abstract

Deep learning under mass‐to‐charge ratio pre‐retrieval to realize electron ionization mass spectrometry library retrieval

Cited by 4 publications

References 26 publications

Mass Spectrometry-Based Techniques Towards OMICS 2.0

Mass Spectrometry-Based Techniques Towards OMICS 2.0

Mass Spectrometry-Based Techniques Towards OMICS 2.0

SR-Unet: A Super-Resolution Algorithm for Ion Trap Mass Spectrometers Based on the Deep Neural Network

Contact Info

Product

Resources

About