Logistic Regression Analysis of LC-MS/MS Data of Monomers Eluted from Aged Dental Composites: A Supervised Machine-Learning Approach

Abstract

Compound identification by database searching that matches experimental with library mass spectra is commonly used in mass spectrometric (MS) data analysis. Vendor software often outputs scores that represent the quality of each spectral match for the identified compounds. However, software-generated identification results can differ drastically depending on the initial search parameters. Machine learning is applied here to provide a statistical evaluation of software-generated compound identification results from experimental tandem MS data. This task was accomplished using the logistic regression algorithm to assign an identification probability value to each identified compound. Logistic regression is usually used for classification, but here it is used to generate identification probabilities without setting a threshold for classification. Liquid chromatography coupled with quadrupole-time-of-flight tandem MS was used to analyze the organic monomers leached from resinbased dental composites in a simulated oral environment. The collected tandem MS data were processed with vendor software, followed by statistical evaluation of these results using logistic regression. The assigned identification probability to each compound provides more confidence in identification beyond solely by database matching. A total of 21 distinct monomers were identified among all samples, including five intact monomers and chemical degradation products of bisphenol A glycidyl methacrylate (BisGMA), oligomers of bisphenol-A ethoxylate methacrylate (BisEMA), triethylene glycol dimethacrylate (TEGDMA), and urethane dimethacrylate (UDMA). The logistic regression model can be used to evaluate any database-matched liquid chromatography-tandem MS result by training a new model using analytical standards of compounds present in a chosen database and then generating identification probabilities for candidates from unknown data using the new model.

Blinking characteristics of organic fluorophores for blink-based multiplexing

“…When the default classification threshold is applied (i.e., P A > 0.5 is automatically classified as emitter A), a minimum classification accuracy of 86.4% is observed, corresponding to a high true positive rate (TPR) of 0.86 and modest false positive rate (FPR) of 0.13. However, prior studies have shown that the classification threshold can be increased to maximize model accuracy 14 , 60 , 61 . Figure 2D demonstrates this principle for 5ROX versus R6G.…”

Biotecnologia: Fonte De Novas Moléculas Antimicrobianas Para O Tratamento De Infecções Bacterianas Multirresistentes

“…Constraints on ML models are not specific to instrument, sample type, or data analysis software (Chen et al 2023). In this study, the observed limitations associated with the quality of the models and data resulted in the need for adjustments for a better model performance.…”

Advancements and Practical Considerations for Biophysical Research: Navigating the Challenges and Future of Super-resolution Microscopy

“…68−70 Highlighting the power of single-molecule approaches in dynamic studies, our work contributes two new methodologies: single-molecule fluorescence anisotropy (smFA) and the single-molecule neighboring density (smND) assay. 15,16 smFA brings a new dimension to SRM by enabling the observation of intracellular viscosity through the measurement of rotational mobility of fluorescent proteins. On the other hand, the smND assay quantifies protein oligomeric states directly within cells by analyzing the spatial distribution and density of individual protein molecules.…”