Optimized preprocessing and machine learning for quantitative Raman spectroscopy in biology

Abstract

Raman spectroscopy's capability to provide meaningful composition predictions is heavily reliant on a preprocessing step to remove insignificant spectral variation. This is crucial in biofluid analysis. Widespread adoption of diagnostics using Raman requires a robust model that can withstand routine spectra discrepancies due to unavoidable variations such as age, diet, and medical background. A wealth of preprocessing methods are available, and it is often up to trial-and-error or user experience to select the method that gives the best results. This process can be incredibly time consuming and inconsistent for multiple operators. In this study, we detail a method to analyze the statistical variability within a set of training spectra and determine suitability to form a robust model. This allows us to selectively qualify or exclude a preprocessing method, predetermine robustness, and simultaneously identify the number of components that will form the best predictive model. We demonstrate the ability of this technique to improve predictive models of two artificial biological fluids. Raman spectroscopy is ideal for noninvasive, nondestructive analysis. Routine health monitoring that maximizes comfort is increasingly crucial, particularly in epidemic-level diabetes diagnoses. High variability in spectra of biological samples can hinder Raman's adoption for these methods. Our technique allows the decision of optimal pretreatment method to be determined for the operator; model performance is no longer a function of user experience. We foresee this statistical technique being an instrumental element to widening the adoption of Raman as a monitoring tool in a field of biofluid analysis. KEYWORDS chemometrics, machine learning, preprocessing methods, quantiative biological analysis, Raman spectroscopy 958

Enhanced Sensitivity for Quantifying Disease Markers via Raman and Machine-Learning of Circulating Biofluids in Optofluidic Chips

“…To achieve reliable automated diagnostics from Raman spectra, we have previously introduced a machine-learning algorithm to optimize spectrum processing for analysis [19].…”

“…An F-test (significance level α = 0.05) assesses the variability in this matrix to determine if improvement in prediction is statistically significant or due to sampling. This process rejects preprocessing methods which demonstrate chance correlation and is presented in figure 2 [19].…”

Towards a widespread adoption of metabolic modeling tools in biopharmaceutical industry: a process systems biology engineering perspective

“…It is worth to highlight that spectroscopic sensors can in this sense be embedded in the concept of soft sensor 22 as they are used to compensate the lack of specific measurement by reconstructing the missing signals based on available measurements using data analysis models 23 . This type of hybrid approach will therefore continue to greatly benefit from the flourishing evolution of artificial intelligence tools and certainly allows to overcome the current limitations of spectroscopic monitoring methods 24 .…”

Recent advances in linear and nonlinear Raman spectroscopy. Part XIV

“…She finds that her measurements represent direct evidence regarding cisplatin interactions with selected model media that are widely used in biochemistry and biophysics and that these interactions could influence the effectiveness of cisplatin as a drug. Storey and Helmy [ 57 ] reported on the optimization of preprocessing and machine learning for the use of quantitative Raman spectroscopy in biology. Their technique allows the decision of the optimal pretreatment method to be determined for the operator and that model performance is no longer a function of user decisions.…”