A novel infrared spectroscopy marker for assessing the postoperative infection risk in patients with upper urinary tract calculus.

The aim of this study is to evaluate the ability of infrared wavenumber of calculus to predict postoperative infection in patients with upper urinary tract calculus (UUTC), and to establish a predictive model based on this. From March 2018 to March 2023, 480 UUTC patients from Fujian Provincial Hospital were included in this study. The infrared-wavenumbers related infection score (IR-infection score) was constructed by univariate analysis, multicollinearity screening, and Lasso analysis to predict postoperative infection. Continually, the Delong test was used to compare the predictive power between the IR-infection score and traditional indicators. Afterward, we performed urine metagene sequencing and stone culture to prove the correlation between calculus toxicity and IR-infection score. Finally, logistic regression was used to build a nomogram. IR-infection score composed of four independent wavenumbers could precisely predict postoperative infection (AUCvalidation cohort = 0.707) and sepsis (AUCvalidation cohort = 0.824). IR-infection score had better predictive ability than commonly used clinical indicators. Moreover, metagenomics sequencing and calculus culture confirmed the correlation between IR-infection score and calculus toxicity (all P < 0.05). The nomogram based on the IR-infection score had high predictive power (all AUCs > 0.803). Our study first developed a novel infrared spectroscopy marker and nomogram, which can help urologists better predict postoperative infection in UUTC patients.

Decoding myasthenia gravis: advanced diagnosis with infrared spectroscopy and machine learning.

Myasthenia Gravis (MG) is a rare neurological disease. Although there are intensive efforts, the underlying mechanism of MG still has not been fully elucidated, and early diagnosis is still a question mark. Diagnostic paraclinical tests are also time-consuming, burden patients financially, and sometimes all test results can be negative. Therefore, rapid, cost-effective novel methods are essential for the early accurate diagnosis of MG. Here, we aimed to determine MG-induced spectral biomarkers from blood serum using infrared spectroscopy. Furthermore, infrared spectroscopy coupled with multivariate analysis methods e.g., principal component analysis (PCA), support vector machine (SVM), discriminant analysis and Neural Network Classifier were used for rapid MG diagnosis. The detailed spectral characterization studies revealed significant increases in lipid peroxidation; saturated lipid, protein, and DNA concentrations; protein phosphorylation; PO2-asym + sym /protein and PO2-sym/lipid ratios; as well as structural changes in protein with a significant decrease in lipid dynamics. All these spectral parameters can be used as biomarkers for MG diagnosis and also in MG therapy. Furthermore, MG was diagnosed with 100% accuracy, sensitivity and specificity values by infrared spectroscopy coupled with multivariate analysis methods. In conclusion, FTIR spectroscopy coupled with machine learning technology is advancing towards clinical translation as a rapid, low-cost, sensitive novel approach for MG diagnosis.

Infrared spectral library of tooth enamel from African ungulates for accurate electron spin resonance dating.

Electron spin resonance coupled with uranium-series dating (ESR/U-series) of carbonate hydroxyapatite in tooth enamel is the main technique used to obtain age determinations from Pleistocene fossils beyond the range of radiocarbon dating. This chronological information allows to better understand diachronic change in the palaeontological record, especially with regard to the evolution of the genus Homo. Given the relative paucity of human teeth at palaeontological and archaeological localities, ESR/U-series is widely applied to the teeth of ungulate species. However, the accuracy of ESR/U-series ages is greatly affected by the incorporation of uranium in the enamel during burial in sediments. It has been shown that uranium content is positively correlated with an increased degree of atomic order in carbonate hydroxyapatite crystals, the latter determined using infrared spectroscopy. Here we present a reference infrared spectral library of tooth enamel from African ungulates, based on the grinding curve method, which serves as baseline to track the diagenetic history of carbonate hydroxyapatite in different species and thus select the best-preserved specimens for dating.

Unraveling the Structure-Spectrum Relationship of Yeast Phenylalanine Transfer RNA: Insights from Theoretical Modeling of Infrared Spectroscopy.

Yeast phenylalanine tRNA (tRNAphe) is a paradigmatic model in structural biology. In this work, we combine molecular dynamics simulations and spectroscopy modeling to establish a direct link between its structure, conformational dynamics, and infrared (IR) spectra. Employing recently developed vibrational frequency maps and coupling models, we apply a mixed quantum/classical treatment of the line shape theory to simulate the IR spectra of tRNAphe in the 1600-1800 cm-1 region across its folded and unfolded conformations and under varying concentrations of Mg2+ ions. The predicted IR spectra of folded and unfolded tRNAphe are in good agreement with experimental measurements, validating our theoretical framework. We then elucidate how the characteristic L-shaped tertiary structure of the tRNA and its modulation in response to diverse chemical environments give rise to distinct IR absorption peaks and line shapes. These calculations effectively bridge IR spectroscopy experiments and atomistic molecular simulations, unraveling the molecular origins of the observed IR spectra of tRNAphe. This work presents a robust theoretical protocol for modeling the IR spectroscopy of nucleic acids, which will facilitate its application as a sensitive probe for detecting the fluctuating secondary and tertiary structures of these essential biological macromolecules.

Exploring novel circulating biomarkers for liver cancer through extracellular vesicle characterization with infrared spectroscopy and plasmonics.

BACKGROUND: Hepatocellular carcinoma (HCC) is the most common form of liver cancer, with cirrhosis being a major risk factor. Traditional blood markers like alpha-fetoprotein (AFP) demonstrate limited efficacy in distinguishing between HCC and cirrhosis, underscoring the need for more effective diagnostic methodologies. In this context, extracellular vesicles (EVs) have emerged as promising candidates; however, their practical diagnostic application is restricted by the current lack of label-free methods to accurately profile their molecular content. To address this gap, our study explores the potential of mid-infrared (mid-IR) spectroscopy, both alone and in combination with plasmonic nanostructures, to detect and characterize circulating EVs. RESULTS: EVs were extracted from HCC and cirrhotic patients. Mid-IR spectroscopy in the Attenuated Total Reflection (ATR) mode was utilized to identify potential signatures for patient classification, highlighting significant changes in the Amide I-II region (1475-1700 cm-1). This signature demonstrated diagnostic performance comparable to AFP and surpassed it when the two markers were combined. Further investigations utilized a plasmonic metasurface suitable for ultrasensitive spectroscopy within this spectral range. This device consists of two sets of parallel rod-shaped gold nanoantennas (NAs); the longer NAs produced an intense near-field amplification in the Amide I-II bands, while the shorter NAs were utilized to provide a sharp reflectivity edge at 1800-2200 cm-1 for EV mass-sensing. A clinically relevant subpopulation of EVs was targeted by conjugating NAs with an antibody specific to Epithelial Cell Adhesion Molecule (EpCAM). This methodology enabled the detection of variations in the quantity of EpCAM-presenting EVs and revealed changes in the Amide I-II lineshape. SIGNIFICANCE: The presented results can positively impact the development of novel laboratory methods for the label-free characterization of EVs, based on the combination between mid-IR spectroscopy and plasmonics. Additionally, data obtained by using HCC and cirrhotic subjects as a model system, suggest that this approach could be adapted for monitoring these conditions.

QCL Infrared Spectroscopy Combined with Machine Learning as a Useful Tool for Classifying Acetaminophen Tablets by Brand.

The development of new methods of identification of active pharmaceutical ingredients (API) is a subject of paramount importance for research centers, the pharmaceutical industry, and law enforcement agencies. Here, a system for identifying and classifying pharmaceutical tablets containing acetaminophen (AAP) by brand has been developed. In total, 15 tablets of 11 brands for a total of 165 samples were analyzed. Mid-infrared vibrational spectroscopy with multivariate analysis was employed. Quantum cascade lasers (QCLs) were used as mid-infrared sources. IR spectra in the spectral range 980-1600 cm-1 were recorded. Five different classification methods were used. First, a spectral search through correlation indices. Second, machine learning algorithms such as principal component analysis (PCA), support vector classification (SVC), decision tree classifier (DTC), and artificial neural network (ANN) were employed to classify tablets by brands. SNV and first derivative were used as preprocessing to improve the spectral information. Precision, recall, specificity, F1-score, and accuracy were used as criteria to evaluate the best SVC, DEE, and ANN classification models obtained. The IR spectra of the tablets show characteristic vibrational signals of AAP and other APIs present. Spectral classification by spectral search and PCA showed limitations in differentiating between brands, particularly for tablets containing AAP as the only API. Machine learning models, specifically SVC, achieved high accuracy in classifying AAP tablets according to their brand, even for brands containing only AAP.

Suppressing sidechain modes and improving structural resolution for 2D IR spectroscopy via vibrational lifetimes.

Vibrational spectroscopy of protein structure often utilizes 13C18O-labeling of backbone carbonyls to further increase structural resolution. However, sidechains such as arginine, aspartate, and glutamate absorb within the same spectral region, complicating the analysis of isotope-labeled peaks. In this study, we report that the waiting time between pump and probe pulses in two-dimensional infrared spectroscopy can be used to suppress sidechain modes in favor of backbone amide I' modes based on differences in vibrational lifetimes. Furthermore, differences in the lifetimes of 13C18O-amide I' modes can aid in the assignment of secondary structure for labeled residues. Using model disordered and ß-sheet peptides, it was determined that while ß-sheets exhibit a longer lifetime than disordered structures, amide I' modes in both secondary structures exhibit longer lifetimes than sidechain modes. Overall, this work demonstrates that collecting 2D IR data at delayed waiting times, based on differences in vibrational lifetime between modes, can be used to effectively suppress interfering sidechain modes and further identify secondary structures.

SCN as a local probe of protein structural dynamics.

The dynamics of lysozyme is probed by attaching -SCN to all alanine residues. The one-dimensional infrared spectra exhibit frequency shifts in the position of the maximum absorption of 4 cm-1, which is consistent with experiments in different solvents and indicates moderately strong interactions of the vibrational probe with its environment. Isotopic substitution 12C → 13C leads to a redshift by -47 cm-1, which agrees quantitatively with experiments for CN-substituted copper complexes in solution. The low-frequency, far-infrared part of the protein spectra contains label-specific information in the difference spectra when compared with the wild type protein. Depending on the position of the labels, local structural changes are observed. For example, introducing the -SCN label at Ala129 leads to breaking of the α-helical structure with concomitant change in the far-infrared spectrum. Finally, changes in the local hydration of SCN-labeled alanine residues as a function of time can be related to the reorientation of the label. It is concluded that -SCN is potentially useful for probing protein dynamics, both in the high-frequency part (CN-stretch) and in the far-infrared part of the spectrum.

The use of vibrational spectroscopy and supervised machine learning for chemical identification of plastics ingested by seabirds.

Plastic pollution is now ubiquitous in the environment and represents a growing threat to wildlife, who can mistake plastic for food and ingest it. Tackling this problem requires reliable, consistent methods for monitoring plastic pollution ingested by seabirds and other marine fauna, including methods for identifying different types of plastic. This study presents a robust method for the rapid, reliable chemical characterisation of ingested plastics in the 1-50 mm size range using infrared and Raman spectroscopy. We analysed 246 objects ingested by Flesh-footed Shearwaters (Ardenna carneipes) from Lord Howe Island, Australia, and compared the data yielded by each technique: 92 % of ingested objects visually identified as plastic were confirmed by spectroscopy, 98 % of those were low density polymers such as polyethylene, polypropylene, or their copolymers. Ingested plastics exhibit significant spectral evidence of biological contamination compared to other reports, which hinders identification by conventional library searching. Machine learning can be used to identify ingested plastics by their vibrational spectra with up to 93 % accuracy. Overall, we find that infrared is the more effective technique for identifying ingested plastics in this size range, and that appropriately trained machine learning models can be superior to conventional library searching methods for identifying plastics.

Quantum Cascade Laser Infrared Spectroscopy for Glycan Analysis of Glycoprotein Solutions.

Glycans are oligosaccharides attached to proteins or lipids and affect their functions, such as drug efficacy, structural contribution, metabolism, immunogenicity, and molecular recognition. Conventional glycosylation analysis has relied on destructive, slow, system-sensitive methods, including enzymatic reactions, chromatography, fluorescence labeling, and mass spectrometry. Herein, we propose quantum cascade laser (QCL) infrared (IR) spectroscopy as a rapid, nondestructive method to quantify glycans and their monosaccharide composition. Previously, we demonstrated high-sensitivity IR spectroscopy of protein solution using solvent absorption compensation (SAC) and double-beam modulation (DBM) techniques. However, the SAC-DBM approach suffered a limited frequency scanning range (<400 cm-1) due to the light dispersion by acousto-optic modulators (AOMs). Here, we implemented a mirror-based double-pass AOM in the SAC-DBM scheme and successfully extended the frequency range to (970 to 1840 cm-1), which encompasses the vibrational fingerprint of biomolecules. The extended frequency range allowed the simultaneous observation of monosaccharide ring bands (1000 to 1200 cm-1) and protein amide bands (1500 to 1700 cm-1). We compared the IR spectra of six glycoproteins and two nonglycosylated proteins with the results from intact mass spectrometry. The IR absorbance ratios of the ring band to the amide band of glycoproteins in solutions showed a linear correlation with the ratios of glycan to protein backbone masses. Furthermore, a multivariate analysis produced monosaccharide compositions consistent with the reported database for the glycoproteins, and the monosaccharide compositions were used to improve the predictability of the glycan-protein mass ratio from the IR-absorbance ratio. This nondestructive, high-sensitivity QCL-IR spectroscopy could be used as a standard method to monitor batch-to-batch comparability during drug manufacturing and quantify the glycosylation and monosaccharide composition of new glycoproteins and other glycosylated biosystems.

Nanosecond Transient IR Spectroscopy of Halorhodopsin in Living Cells.

The ability to track minute changes of a single amino acid residue in a cellular environment is causing a paradigm shift in the attempt to fully understand the responses of biomolecules that are highly sensitive to their environment. Detecting early protein dynamics in living cells is crucial to understanding their mechanisms, such as those of photosynthetic proteins. Here, we elucidate the light response of the microbial chloride pump NmHR from the marine bacterium Nonlabens marinus, located in the membrane of living Escherichia coli cells, using nanosecond time-resolved UV/vis and IR absorption spectroscopy over the time range from nanoseconds to seconds. Transient structural changes of the retinal cofactor and the surrounding apoprotein are recorded using light-induced time-resolved UV/vis and IR difference spectroscopy. Of particular note, we have resolved the kinetics of the transient deprotonation of a single cysteine residue during the photocycle of NmHR out of the manifold of molecular vibrations of the cells. These findings are of high general relevance, given the successful development of optogenetic tools from photoreceptors to interfere with enzymatic and neuronal pathways in living organisms using light pulses as a noninvasive trigger.

An end-to-end approach for single-cell infrared absorption spectroscopy of bacterial inclusion bodies: from AFM-IR measurement to data interpretation of large sample sets.

BACKGROUND: Inclusion bodies (IBs) are well-known subcellular structures in bacteria where protein aggregates are collected. Various methods have probed their structure, but single-cell spectroscopy remains challenging. Atomic Force Microscopy-based Infrared Spectroscopy (AFM-IR) is a novel technology with high potential for the characterisation of biomaterials such as IBs. RESULTS: We present a detailed investigation using AFM-IR, revealing the substructure of IBs and their variation at the single-cell level, including a rigorous optimisation of data collection parameters and addressing issues such as laser power, pulse frequency, and sample drift. An analysis pipeline was developed tailored to AFM-IR image data, allowing high-throughput, label-free imaging of more than 3500 IBs in 12,000 bacterial cells. We examined IBs generated in Escherichia coli under different stress conditions. Dimensionality reduction analysis of the resulting spectra suggested distinct clustering of stress conditions, aligning with the nature and severity of the applied stresses. Correlation analyses revealed intricate relationships between the physical and morphological properties of IBs. CONCLUSIONS: Our study highlights the power and limitations of AFM-IR, revealing structural heterogeneity within and between IBs. We show that it is possible to perform quantitative analyses of AFM-IR maps over a large collection of different samples and determine how to control for various technical artefacts.

An optical photothermal infrared investigation of lymph nodal metastases of oral squamous cell carcinoma.

In this study, optical photothermal infrared (O-PTIR) spectroscopy combined with machine learning algorithms were used to evaluate 46 tissue cores of surgically resected cervical lymph nodes, some of which harboured oral squamous cell carcinoma nodal metastasis. The ratios obtained between O-PTIR chemical images at 1252 cm-1 and 1285 cm-1 were able to reveal morphological details from tissue samples that are comparable to the information achieved by a pathologist's interpretation of optical microscopy of haematoxylin and eosin (H&E) stained samples. Additionally, when used as input data for a hybrid convolutional neural network (CNN) and random forest (RF) analyses, these yielded sensitivities, specificities and precision of 98.6 ± 0.3%, 92 ± 4% and 94 ± 5%, respectively, and an area under receiver operator characteristic (AUC) of 94 ± 2%. Our findings show the potential of O-PTIR technology as a tool to study cancer on tissue samples.

Perspective: intrinsic interactions of metal ions with biological molecules as studied by threshold collision-induced dissociation and infrared multiple photon dissociation.

In this perspective, gas-phase studies of group 1 monocations and group 12 dications with amino acids and small peptides are highlighted. Although the focus is on two experimental techniques, threshold collision-induced dissociation and infrared multiple photon dissociation action spectroscopy, these methods as well as complementary approaches are summarized. The synergistic interplay with theory, made particularly powerful by the small sizes of the systems explored and the absence of solvent and support, is also elucidated. Importantly, these gas-phase methods permit quantitative insight into the structures and thermodynamics of metal cations interacting with biological molecules. Periodic trends in how these interactions vary as the metal cations get heavier are discussed as are quantitative trends with changes in the amino acid side chain and effects of hydration. Such trends allow these results to transcend the limitations associated with the biomimetic model systems.

Development of automated metabolite control using mid-infrared probe for bioprocesses and vaccine manufacturing.

Automation of metabolite control in fermenters is fundamental to develop vaccine manufacturing processes more quickly and robustly. We created an end-to-end process analytical technology and quality by design-focused process by replacing manual control of metabolites during the development of fed-batch bioprocesses with a system that is highly adaptable and automation-enabled. Mid-infrared spectroscopy with an attenuated total reflectance probe in-line, and simple linear regression using the Beer-Lambert Law, were developed to quantitate key metabolites (glucose and glutamate) from spectral data that measured complex media during fermentation. This data was digitally connected to a process information management system, to enable continuous control of feed pumps with proportional-integral-derivative controllers that maintained nutrient levels throughout fed-batch stirred-tank fermenter processes. Continuous metabolite data from mid-infrared spectra of cultures in stirred-tank reactors enabled feedback loops and control of the feed pumps in pharmaceutical development laboratories. This improved process control of nutrient levels by 20-fold and the drug substance yield by an order of magnitude. Furthermore, the method is adaptable to other systems and enables soft sensing, such as the consumption rate of metabolites. The ability to develop quantitative metabolite templates quickly and simply for changing bioprocesses was instrumental for project acceleration and heightened process control and automation. ONE-SENTENCE SUMMARY: Intelligent digital control systems using continuous in-line metabolite data enabled end-to-end automation of fed-batch processes in stirred-tank reactors.

Graphormer-IR: Graph Transformers Predict Experimental IR Spectra Using Highly Specialized Attention.

Infrared (IR) spectroscopy is an important analytical tool in various chemical and forensic domains and a great deal of effort has gone into developing in silico methods for predicting experimental spectra. A key challenge in this regard is generating highly accurate spectra quickly to enable real-time feedback between computation and experiment. Here, we employ Graphormer, a graph neural network (GNN) transformer, to predict IR spectra using only simplified molecular-input line-entry system (SMILES) strings. Our data set includes 53,528 high-quality spectra, measured in five different experimental media (i.e., phases), for molecules containing the elements H, C, N, O, F, Si, S, P, Cl, Br, and I. When using only atomic numbers for node encodings, Graphormer-IR achieved a mean test spectral information similarity (SISµ) value of 0.8449 ± 0.0012 (n = 5), which surpasses that the current state-of-the-art model Chemprop-IR (SISµ = 0.8409 ± 0.0014, n = 5) with only 36% of the encoded information. Augmenting node embeddings with additional node-level descriptors in learned embeddings generated through a multilayer perceptron improves scores to SISµ = 0.8523 ± 0.0006, a total improvement of 19.7σ (t = 19). These improved scores show how Graphormer-IR excels in capturing long-range interactions like hydrogen bonding, anharmonic peak positions in experimental spectra, and stretching frequencies of uncommon functional groups. Scaling our architecture to 210 attention heads demonstrates specialist-like behavior for distinct IR frequencies that improves model performance. Our model utilizes novel architectures, including a global node for phase encoding, learned node feature embeddings, and a one-dimensional (1D) smoothing convolutional neural network (CNN). Graphormer-IR's innovations underscore its value over traditional message-passing neural networks (MPNNs) due to its expressive embeddings and ability to capture long-range intramolecular relationships.

The secondary structure of diatom silaffin peptide R5 determined by two-dimensional infrared spectroscopy.

Diatoms, unicellular marine organisms, harness short peptide repeats of the protein silaffin to transform silicic acid into biosilica nanoparticles. This process has been a white whale for material scientists due to its potential in biomimetic applications, ranging from medical to microelectronic fields. Replicating diatom biosilicification will depend on a thorough understanding of the silaffin peptide structure during the reaction, yet existing models in the literature offer conflicting views on peptide folding during silicification. In our study, we employed two-dimensional infrared spectroscopy (2DIR) within the amide I region to determine the secondary structure of the silaffin repeat unit 5 (R5), both pre- and post-interaction with silica. The 2DIR experiments are complemented by molecular dynamics (MD) simulations of pure R5 reacting with silicate. Subsequently, theoretical 2DIR spectra calculated from these MD trajectories allowed us to compare calculated spectra with experimental data, and to determine the diverse structural poses of R5. Our findings indicate that unbound R5 predominantly forms ß-strand structures alongside various atypical secondary structures. Post-silicification, there's a noticeable shift: a decrease in ß-strands coupled with an increase in turn-type and bend-type configurations. We theorize that this structural transformation stems from silicate embedding within R5's hydrogen-bond network, prompting the peptide backbone to contract and adapt around the biosilica precursors.

Unraveling dynamic protein structures by two-dimensional infrared spectra with a pretrained machine learning model.

Dynamic protein structures are crucial for deciphering their diverse biological functions. Two-dimensional infrared (2DIR) spectroscopy stands as an ideal tool for tracing rapid conformational evolutions in proteins. However, linking spectral characteristics to dynamic structures poses a formidable challenge. Here, we present a pretrained machine learning model based on 2DIR spectra analysis. This model has learned signal features from approximately 204,300 spectra to establish a "spectrum-structure" correlation, thereby tracing the dynamic conformations of proteins. It excels in accurately predicting the dynamic content changes of various secondary structures and demonstrates universal transferability on real folding trajectories spanning timescales from microseconds to milliseconds. Beyond exceptional predictive performance, the model offers attention-based spectral explanations of dynamic conformational changes. Our 2DIR-based pretrained model is anticipated to provide unique insights into the dynamic structural information of proteins in their native environments.

Trends in authentication of edible oils using vibrational spectroscopic techniques.

The authentication of edible oils has become increasingly important for ensuring product quality, safety, and compliance with regulatory standards. Some prevalent authenticity issues found in edible oils include blending expensive oils with cheaper substitutes or lower-grade oils, incorrect labeling regarding the oil's source or type, and falsely stating the oil's origin. Vibrational spectroscopy techniques, such as infrared (IR) and Raman spectroscopy, have emerged as effective tools for rapidly and non-destructively analyzing edible oils. This review paper offers a comprehensive overview of recent advancements in using vibrational spectroscopy for authenticating edible oils. The fundamental principles underlying vibrational spectroscopy are introduced and chemometric approaches that enhance the accuracy and reliability of edible oil authentication are summarized. Recent research trends highlighted in the review include authenticating newly introduced oils, identifying oils based on their specific origins, adopting handheld/portable spectrometers and hyperspectral imaging, and integrating modern data handling techniques into the use of vibrational spectroscopic techniques for edible oil authentication. Overall, this review provides insights into the current state-of-the-art techniques and prospects for utilizing vibrational spectroscopy in the authentication of edible oils, thereby facilitating quality control and consumer protection in the food industry.

Data fusion of near-infrared and mid-infrared spectroscopy for rapid origin identification and quality evaluation of Lonicerae japonicae flos.

A data fusion strategy based on near-infrared (NIR) and mid-infrared (MIR) spectroscopy techniques were developed for rapid origin identification and quality evaluation of Lonicerae japonicae flos (LJF). A high-level data fusion for origin identification was formed using the soft voting method. This data fusion model achieved accuracy, log-loss value and Kappa value of 95.5%, 0.347 and 0.910 on the prediction set. The spectral data were converted to liquid chromatography data using a data fusion model constructed by the weighted average algorithm. The Euclidean distance and adjusted cosine similarity were used to evaluate the similarity between the converted and the real chromatographic data, with results of 247.990 and 0.996, respectively. The data fusion models all performed better than the models constructed using single data. This indicates that multispectral data fusion techniques have a wide range of application prospects and practical value in the quality control of natural products such as LJF.