Modified locally weighted—Partial least squares regression improving clinical predictions from infrared spectra of human serum samples

Infrared Spectroscopy for Rapid Triage of Cancer Using Blood Derivatives: A Reality Check

Infrared (IR) spectroscopy of serum/plasma represents an alluring molecular diagnostic tool, especially for cancer, as it can provide a molecular fingerprint of clinical samples based on vibrational modes of chemical bonds. However, despite the superior performance, the routine adoption of this technique for clinical settings has remained elusive. This is due to the potential confounding factors that are often overlooked and pose a significant barrier to clinical translation. In this Perspective, we summarize the concerns associated with various confounding factors, such as fluid sampling, optical effects, hemolysis, abnormal cardiovascular and/or hepatic functions, infections, alcoholism, diet style, age, and gender of a patient or normal control cohort, and improper selection of numerical methods that ultimately would lead to improper spectral diagnosis. We also propose some precautionary measures to overcome the challenges associated with these confounding factors.

Just-in-Time Learning-Integrated Partial Least-Squares Strategy for Accurately Predicting 71 Chemical Constituents in Chinese Tobacco by Near-Infrared Spectroscopy

Near-infrared spectroscopy has been widely used to characterize the chemical composition of tobacco because it is fast, economical, and nondestructive. However, few predictive models perform ideally when applied to large spectral libraries of tobacco and its various chemical indicators. In this study, the just-in-time learning-integrated partial least-squares (JIT-PLS) modeling strategy was applied for the first time to quantitatively analyze 71 chemical components in Chinese tobacco. Approximately 18000 tobacco samples from China were analyzed to find appropriately similar measurements and propose suitable and flexible similar subsets from the calibration for each test sample. In total, 879 representative aged tobacco leaf samples and 816 cigarette samples were used as external instances to evaluate the practical predicting ability of the proposed method. The most suitable similar subsets for each test sample could be selected by limiting the Euclidean distance and number of similar subsets to 0-3.0 × 10^-9 and 10-300, respectively. The majority of the JIT-PLS models performed significantly better than traditional PLS models. Specifically, using JIT-PLS instead of traditional PLS models increased the R ² values from 0.347-0.984 to 0.763-0.996, and from 0.179-0.981 to 0.506-0.989 for the prediction of 67 and 71 components in aged tobacco leaf and cigarette samples, respectively. Good prediction ability was demonstrated for routine chemical components, polyphenolic compounds, organic acids, and other compounds, with the mean ratios of prediction to deviation (RPD_mean) being 7.74, 4.39, 4.05, and 5.48, respectively). The proposed methodology could simultaneously determine 67 major components in large and complicated tobacco spectral libraries with high precision and accuracy, which will assist tobacco and cigarette quality control in collecting as well as processing stages.

ATR-IR Spectroscopy Application to Diagnostic Screening of Advanced Endometriosis

Endometriosis is one of the most common gynecological diseases among young women of reproductive age. Thus far, it has not been possible to define a parameter that is sensitive and specific enough to be a recognized biomarker for diagnosing this disease. Nonspecific symptoms of endometriosis and delayed diagnosis are impulses for researching noninvasive methods of differentiating endometriosis from other gynecological disorders. We compared three groups of individuals in our research: women with endometriosis (E), patients suffering from other gynecological disorders (nonendometriosis, NE), and healthy women from the control group (C). Partial least squares discriminant analysis (PLS-DA) models were developed based on selected serum biochemical parameters, specific regions of the serum’s infrared attenuated total reflectance (FTIR ATR) spectra, and combined data. Incorporating the spectral data into the models significantly improved differentiation among the three groups, with an overall accuracy of 87.5%, 97.3%, and 98.5%, respectively. This study shows that infrared spectroscopy and discriminant analysis can be used to differentiate serum samples among women with advanced endometriosis, women without this disease, i.e., healthy women, and, most importantly, also women with other benign gynecological disorders.

Infrared Spectroscopy of Blood

The magnitude of infectious diseases in the twenty-first century created an urgent need for point-of-care diagnostics. Critical shortages in reagents and testing kits have had a large impact on the ability to test patients with a suspected parasitic, bacteria, fungal, and viral infections. New point-of-care tests need to be highly sensitive, specific, and easy to use and provide results in rapid time. Infrared spectroscopy, coupled to multivariate and machine learning algorithms, has the potential to meet this unmet demand requiring minimal sample preparation to detect both pathogenic infectious agents and chronic disease markers in blood. This focal point article will highlight the application of Fourier transform infrared spectroscopy to detect disease markers in blood focusing principally on parasites, bacteria, viruses, cancer markers, and important analytes indicative of disease. Methodologies and state-of-the-art approaches will be reported and potential confounding variables in blood analysis identified. The article provides an up to date review of the literature on blood diagnosis using infrared spectroscopy highlighting the recent advances in this burgeoning field.

Decision Tree-PLS (DT-PLS) algorithm for the development of process: Specific local prediction models

This work presents a novel multivariate statistical algorithm, Decision Tree-PLS (DT-PLS), to improve the prediction and understanding of dynamic processes based on local partial least square regression (PLSR) models for characteristic process groups defined based on Decision Tree (DT) analysis. The DT-PLS algorithm is successfully applied to two different cell culture data sets, one obtained from bioreactors of 3.5 L lab scale and the other obtained from the 15 ml ambr microbioreactor system. Substantial improvement in the predictive capabilities of the model can be achieved based on the localization compared to the classical PLSR approach, which is implemented in the commercially available packages. Additionally, the differences in the model parameters of the local models suggest that the governing process variables vary for the different process regimes indicating the different states of the cell under different process conditions.

A possible Fourier transform infrared-based plasma fingerprint of angiotensin-converting enzyme inhibitor-induced reversal of endothelial dysfunction in diabetic mice

Angiotensin-converting enzyme inhibitors (ACE-I) display vasoprotective activity and represent the cornerstone in the treatment of cardiovascular diseases. In this study, we tested whether Fourier transform infrared (FTIR)-based analysis of blood plasma is sensitive to detect vasoprotective effects of treatment with perindopril including reversal of endothelial dysfunction in diabetes. For this purpose, plasma samples were collected from untreated db/db mice, db/db mice treated with 2 or 10 mg/kg perindopril and db+ mice. The effect of perindopril on endothelial function was examined in ex vivo aortic rings; 10 mg/kg but not 2 mg/kg of perindopril reversed endothelial dysfunction. In plasma of db/db mice, the balance between conformations of plasma proteins was noted, and treatment with perindopril at a high dose but not at a low dose reversed this effect. This was revealed by amide II/amide I ratio attributed to increased β-sheet formation. Spectral markers at 3010, 1520/1238 cm^-1 , representative for unsaturation degree of lipids and phosphorylation of tyrosine, respectively, were also affected by perindopril treatment. In conclusion, although metabolic abnormalities associated with type 2 diabetes mellitus such as hypertriglyceridemia and hyperglycemia strongly affected spectral FTIR profile of diabetic plasma, we identified FTIR features that seem to be associated with the vasoprotective activity of ACE-I.

Vibrational Spectroscopy in Body Fluids Analysis

Vibrational spectroscopy offers a unique opportunity to investigate the composition of unknown substances on a molecular basis. The spectroscopy of molecular vibrations using mid-infrared or Raman techniques has been applied to samples of body fluids. This review presents some applications related to body fluids published in the period 2005-2015.