Calibration transfer via filter learning.

BACKGROUND: Calibration transfer is an essential activity in analytical chemistry in order to avoid a complete recalibration. Currently, the most popular calibration transfer methods, such as piecewise direct standardization and dynamic orthogonal projection, require a certain amount of standard or reference samples to guarantee their effectiveness. To achieve higher efficiency, it is desirable to perform the transfer with as few reference samples as possible. RESULTS: To this end, we propose a new calibration transfer method by using a calibration database from a master instrument (source domain) and only one spectrum with known properties from a slave instrument (target domain). We first generate a counterpart of this spectrum in the source domain by a multivariate Gaussian kernel. Then, we train a filter to make the response function of the slave instrument equivalent to that of the master instrument. To avoid the need for labels from the target domain, we also propose an unsupervised way to implement our method. Compared with several state-of-the-art methods, the results on one simulated dataset and two real-world datasets demonstrate the effectiveness of our method. SIGNIFICANCE: Traditionally, the demand for certain amounts of reference samples during calibration transfer is cumbersome. Our approach, which requires only one reference sample, makes the transfer process simple and fast. In addition, we provide an alternative for performing unsupervised calibration transfer. As such, the proposed method is a promising tool for calibration transfer.

Identification of near-infrared characteristic bands of small bowel necrosis based on cellwise detection algorithm.

The near-infrared spectroscopy is often used to distinguish small bowel necrosis due to necrotizing enterocolitis (NEC). The characteristic bands of small bowel necrosis, as an important basis for evaluating the confidence of the differentiation results, are challenging to identify quickly. In this study, we proposed to identify characteristic bands of lesion samples based on hyperspectral imaging (HSI) and cellwise outlier detection. Rabbits were used as an animal model to simulate the clinical symptoms of NEC. The rabbits were detected at intervals of 10, 30, 60, and 90 min. The characteristic bands were identified within the same rabbit, between different rabbits and at different times. The result showed the bands near 763 nm, corresponding to the absorption peak of deoxyhemoglobin, were the characteristic bands separating samples with NEC. The identification result was plausible because hypoxia was the main cause of NEC. The method was easy to perform.

Automatic detection of ischemic necrotic sites in small intestinal tissue using hyperspectral imaging and transfer learning.

Acquiring large amounts of hyperspectral data of small intestinal tissue with real labels in the clinic is difficult, and the data shows inter-patient variability. Building an automatic identification model using a small dataset presents a crucial challenge in obtaining a strong generalization of the model. This study aimed to explore the performance of hyperspectral imaging and transfer learning techniques in the automatic identification of normal and ischemic necrotic sites in small intestinal tissue. Hyperspectral data of small intestinal tissues were collected from eight white rabbit samples. The transfer component analysis (TCA) method was performed to transfer learning on hyperspectral data between different samples and the variability of data distribution between samples was reduced. The results showed that the TCA transfer learning method improved the accuracy of the classification model with less training data. This study provided a reliable method for single-sample modelling to detect necrotic sites in small intestinal tissue .

A robust method to improve the regression accuracy of LIBS data: determination of heavy metal Cu in Tegillarca granosa.

Tegillarca granosa (T. granosa) is susceptible to contamination by heavy metals, which poses potential health risks for consumers. Laser-induced breakdown spectroscopy (LIBS) combined with the classical partial least squares (PLS) model has shown promise in determining heavy metal concentrations in T. granosa. However, the presence of outliers during calibration can compromise the model's integrity and diminish its predictive capabilities. To address this issue, we propose using a robust method for partial least squares, RSIMPLS, to improve the accuracy of Cu prediction in T. granosa. The RSIMPLS algorithm was employed to analyze and process the high-dimensional LIBS data and utilized diagnostic plots to identify various types of outliers. By selectively eliminating certain outliers, a robust calibration method was achieved. The results showed that LIBS spectroscopy has the potential to predict Cu in T. granosa, with a coefficient of determination (Rp2) of 0.79 and a root mean square error of prediction (RMSEP) of 11.28. RSIMPLS significantly improved the prediction accuracy of Cu concentrations with a 43% decrease in RMSEP compared to the PLS. These findings validated the effectiveness of combining LIBS data with the RSIMPLS algorithm for the prediction of Cu concentrations in T. granosa.

Discrimination between normal and necrotic small intestinal tissue using hyperspectral imaging and unsupervised classification.

Objective and automatic clinical discrimination of normal and necrotic sites of small intestinal tissue remains challenging. In this study, hyperspectral imaging (HSI) and unsupervised classification techniques were used to distinguish normal and necrotic sites of small intestinal tissues. Small intestinal tissue hyperspectral images of eight Japanese large-eared white rabbits were acquired using a visible near-infrared hyperspectral camera, and K-means and density peaks (DP) clustering algorithms were used to differentiate between normal and necrotic tissue. The three cases in this study showed that the average clustering purity of the DP clustering algorithm reached 92.07% when the two band combinations of 500-622 and 700-858 nm were selected. The results of this study suggest that HSI and DP clustering can assist physicians in distinguishing between normal and necrotic sites in the small intestine in vivo.

Non-Destructive Measurement of Egg's Haugh Unit by Vis-NIR with iPLS-Lasso Selection.

Egg freshness is of great importance to daily nutrition and food consumption. In this work, visible near-infrared (vis-NIR) spectroscopy combined with the sparsity of interval partial least square regression (iPLS) were carried out to measure the egg's freshness by semi-transmittance spectral acquisition. A fiber spectrometer with a spectral range of 550-985 nm was embedded in the developed spectral scanner, which was designed with rich light irradiation mode from another two reflective surfaces. The semi-transmittance spectra were collected from the waist of eggs and monitored every two days. Haugh unit (HU) is a key indicator of egg's freshness, and ranged 56-91 in 14 days after delivery. The profile of spectra was analyzed the relation to the changes of egg's freshness. A series of iPLS models were constructed on the basis of spectral intervals at different divisions of the spectral region to predict the egg's HU, and then the least absolute shrinkage and selection operator (Lasso) was used to sparse the number of iPLS member models acting as a role of model selection and fusion regression. By optimization of the number of spectral intervals in the range of 1 to 40, the 26th fusion model obtained the best performance with the minimum root mean of squared error of prediction (RMSEP) of 5.161, and performed the best among the general PLS model and other intervals-combined PLS models. This study provided a new, rapid, and reliable method for the non-destructive and in-site determination of egg's freshness.

Recent Advances in Silver and Gold Nanoparticles-Based Colorimetric Sensors for Heavy Metal Ions Detection: A Review.

Silvetr and gold nanoparticles-based colorimetric sensors (Ag/Au-NPs-CSns) allow potential prospects for the development of efficient sensors owing to their unique shape- and size-dependent optical properties. In this review, recent (2020) advances in morphology-controllable synthesis, shape/size-dependent performance, sensing mechanism, challenges and prospects of Ag/Au-NPs-CSns for the detection of heavy metals are discussed. The size/shape-controlled synthesis of innovative Ag/Au-NPs-CSns is reviewed critically and the possible role of different parameters like temperature, time, pH, stabilizing/capping agents, reducing agents and concentration/nature of precursors are discussed. Then, we highlighted how the shape, size, optimum composition, functionalization, stabilizing/capping agents, surface structure and synergism influence the optical properties and sensing efficiency of Ag/Au-NPs-CSns. This review attempted to accentuate the efficiency of novel multimetallic Ag/AuNPs-CSns as compare to their monometallic counterparts and explained how the incorporation of multi-metals affects their performance. Besides, the sensing mechanisms of Ag/Au-NPs-CSns with special reference to recently published studies are discussed. Finally, challenges and prospects in the controllable-synthesis and practical applications of these sensors are studied. This mechanistic approach and timely review can be promisingly considered as a valuable reference and will help fuel new ideas for the development of novel colorimetric sensors. HighlightsA review of recent advances in Ag/Au-NPs-CSns for heavy metal ions detectionMorphology of Ag/Au-NPs-CSns regulate their optical properties/sensing efficiencyPromising Ag/Au-NPs-CSns can be synthesized by adjusting experimental parametersHybrid and functionalized Ag/Au-NPs-CSns have superior sensing performanceSize/shape transformation, aggregation/anti- and oxidation are sensing mechanisms.

Consensual Regression of Soluble Solids Content in Peach by Near Infrared Spectrocopy.

In order to reduce the uncertainty of the genetic algorithm (GA) in optimizing the near-infrared spectral calibration model and avoid the loss of spectral information of the unselected variables, a strategy of fusing consensus models is proposed to measure the soluble solids content (SSC) in peaches. A total of 266 peach samples were collected at four arrivals, and their interactance spectra were scanned by an integrated analyzer prototype, and then an internal index of SSC was destructively measured by the standard refractometry method. The near-infrared spectra were pre-processed with mean centering and were selected successively with a genetic algorithm (GA) to construct the consensus model, which was integrated with two member models with optimized weightings. One was the conventional partial least square (PLS) optimized with GA selected variables (PLSGA), and the other one was the derived PLS developed with residual variables after GA selections (PLSRV). The performance of PLSRV models showed some useful spectral information related to peaches' SSC and someone performed close to the full-spectral-based PLS model. Among these 10 runs, consensus models obtained a lower root mean squared errors of prediction (RMSEP), with an average of 1.106% and standard deviation (SD) of 0.0068, and performed better than that of the optimized PLSGA models, which achieved a RMSEP of average 1.116% with SD of 0.0097. It can be concluded that the application of fusion strategy can reduce the fluctuation uncertainty of a model optimized by genetic algorithm, fulfill the utilization of the spectral information amount, and realize the rapid detection of the internal quality of the peach.

Using one-class autoencoder for adulteration detection of milk powder by infrared spectrum.

Food adulteration detection requires quick and simple methods. Spectral detection can significantly reduce the analysis time, but it needs to construct a detection model. In this study, a one-class classification method based on an autoencoder is proposed for the detection of food adulteration by spectroscopy. In the proposed method, the autoencoder is constructed to extract low-dimensional features from high-dimensional spectral data and reconstruct the original spectrum. Then the coding error and reconstruction error are used to determine the food sample is adulterated or not. The infrared spectral data of milk powder and its adulterated forms are used to verify the performance of the proposed model. Experimental results show that the proposed method has similar effects to soft independent modeling of class analogy and one-class partial least squares, and is significantly better than support vector data description. The proposed method can be flexibly applied to the spectral detection of food adulteration.

Characterization and source analysis of heavy metals contamination in microplastics by Laser-Induced Breakdown Spectroscopy.

The increasing presence of microplastics in marine environment is a critical issue and the plastic-metal contamination has received much attention. However, conventional methods for heavy metal determination are time-consuming, need sample pretreatments, require a strict operation environment, or have high limits of detection. In this study, heavy metals contaminated microplastics samples collected from a remote coral island were quantified and analyzed by using Laser-Induced Breakdown Spectroscopy (LIBS). The characters of the trace metals in microplastics were used to determine the sources of the contaminants, and the potential origins of the metals were demonstrated from the statistical analysis. LIBS is a facile and non-destructive trace analysis technique and the strategy led to rapid and multi-metals detection of individual samples. Heavy metals such as copper (Cu), lead (Pb), iron (Fe), cadmium (Cd), zinc (Zn), manganese (Mn), chromium (Cr) were detected and quantified in the individual microplastics samples. The findings showed that LIBS is a promising strategy for the characterization of microplastics and for the analysis of the source of heavy metals contaminants present in the microplastics particles.

Visible near-infrared hyperspectral imaging and supervised classification for the detection of small intestinal necrosis tissue in vivo.

Complete recognition of necrotic areas during small bowel tissue resection remains challenging due to the lack of optimal intraoperative aid identification techniques. This research utilizes hyperspectral imaging techniques to automatically distinguish normal and necrotic areas of small intestinal tissue. Sample data were obtained from the animal model of small intestinal tissue of eight Japanese large-eared white rabbits developed by experienced physicians. A spectral library of normal and necrotic regions of small intestinal tissue was created and processed using six different supervised classification algorithms. The results show that hyperspectral imaging combined with supervised classification algorithms can be a suitable technique to automatically distinguish between normal and necrotic areas of small intestinal tissue. This new technique could aid physicians in objectively identify normal and necrotic areas of small intestinal tissue.

SERS-based lateral flow immunoassay for sensitive and simultaneous detection of anti-SARS-CoV-2 IgM and IgG antibodies by using gap-enhanced Raman nanotags.

The lateral flow immunoassay (LFIA) has played a crucial role in early diagnosis during the current COVID-19 pandemic owing to its simplicity, speed and affordability for coronavirus antibody detection. However, the sensitivity of the commercially available LFIAs needs to be improved to better prevent the spread of the infection. Here, we developed an ultra-sensitive surface-enhanced Raman scattering-based lateral flow immunoassay (SERS-based LFIA) strip for simultaneous detection of anti-SARS-CoV-2 IgM and IgG by using gap-enhanced Raman nanotags (GERTs). The GERTs with a 1 nm gap between the core and shell were used to produce the "hot spots", which provided about 30-fold enhancement as compared to conventional nanotags. The COVID-19 recombinant antigens were conjugated on GERTs surfaces and replaced the traditional colloidal gold for the Raman sensitive detection of human IgM and IgG. The LODs of IgM and IgG were found to be 1 ng/mL and 0.1 ng/mL (about 100 times decrease was observed as compared to commercially available LFIA strips), respectively. Moreover, under the condition of common nano-surface antigen, precise SERS signals proved the unreliability of quantitation because of the interference effect of IgM on IgG.

Degradation degree analysis of environmental microplastics by micro FT-IR imaging technology.

The degradation potential of microplastics remains a critical issue for researching marine litter, and it is one of the most important factors that can be used for calculating the persistence time of microplastics in certain conditions. However, there are lack of standard or approved methods for estimating the ageing stage of environmental microplastics. In this study, the potential of spectral-image fusion strategy was investigated to analyze the degradation degree of polyethylene microplastics in natural exposure of coastline. The proposed spectral-image fusion linear model showed a significant ability to classify the degradation degree of environmental microplastics samples with the best accuracy of 97.1% as compared to two single-sensing information-based linear models (with one spectral wavelength of the carbonyl index at 1720 cm-1 or three-channel components from LAB color-space). This is the first attempt to qualitatively measure the degradation degree of the naturally exposed microplastics based on spectral-image fusion model. The proposed fusion model based strategy is an effective tool for predicting the degradation degree of the field exposed microplastics.

Simultaneously and quantitatively analyze the heavy metals in Sargassum fusiforme by laser-induced breakdown spectroscopy.

As a nutritious and popular seafood among consumers, Sargassum fusiforme is susceptible to the toxic heavy metals because of its strong adsorption properties. In this study, laser-induced breakdown spectroscopy (LIBS) coupled with a simple framework (only remove some noise and low-intensity variables, and then combine with PLS algorithm) was used to establish the detection models to simultaneously and quantitatively analyze the content of heavy metals arsenic (As), chromium (Cd), cadmium (Cr), copper (Cu), mercury (Hg), lead (Pb) and zinc (Zn) in Sargassum fusiforme. As comparisons, three classic variable methods of successive projections algorithm (SPA), uninformative variable elimination (UVE) and variable importance in projection (VIP) were adopted. The final results showed that six of seven heavy metal models from the TV-PLSR model were optimal. These results demonstrate that the TV-PLSR framework combined with LIBS technique is an effective framework for quantitatively analyzing the heavy metals in Sargassum fusiforme.

Synthetic spectra generated by boundary equilibrium generative adversarial networks and their applications with consensus algorithms.

One of the major restrictions in spectroscopic analysis is the limited number of calibrations, especially for biological samples. Meanwhile, there is a lack of effective algorithms to simulate synthetic spectra from the real spectra of limited samples. Thus in this work, a boundary equilibrium generative adversarial network (BEGAN) was proposed to automatically generate synthetic spectra and successfully produce spectra from two datasets. Then, the impact of the diversity ratio was estimated in the aspect of the quality and diversity of the generated spectra by BEGAN, and a negative correlation was found between quality and diversity. Finally, these synthetic spectra are applied in a consensus algorithm named creating diversity partial least squares (CDPLS) to replenish virtual samples in every iteration. Results show that the synthetic spectra generated by BEGAN are of high quality and improve the predictive performance of CDPLS. It can concluded that BEGAN has the potential to generate derived homologous spectra and expand the number of spectra in some small sample sets.

Overdispersed gene expression in schizophrenia.

Schizophrenia (SCZ) is a severe, highly heterogeneous psychiatric disorder with varied clinical presentations. The polygenic genetic architecture of SCZ makes identification of causal variants a daunting task. Gene expression analyses hold the promise of revealing connections between dysregulated transcription and underlying variants in SCZ. However, the most commonly used differential expression analysis often assumes grouped samples are from homogeneous populations and thus cannot be used to detect expression variance differences between samples. Here, we applied the test for equality of variances to normalized expression data, generated by the CommonMind Consortium (CMC), from brains of 212 SCZ and 214 unaffected control (CTL) samples. We identified 87 genes, including VEGFA (vascular endothelial growth factor) and BDNF (brain-derived neurotrophic factor), that showed a significantly higher expression variance among SCZ samples than CTL samples. In contrast, only one gene showed the opposite pattern. To extend our analysis to gene sets, we proposed a Mahalanobis distance-based test for multivariate homogeneity of group dispersions, with which we identified 110 gene sets with a significantly higher expression variability in SCZ, including sets of genes encoding phosphatidylinositol 3-kinase (PI3K) complex and several others involved in cerebellar cortex morphogenesis, neuromuscular junction development, and cerebellar Purkinje cell layer development. Taken together, our results suggest that SCZ brains are characterized by overdispersed gene expression-overall gene expression variability among SCZ samples is significantly higher than that among CTL samples. Our study showcases the application of variability-centric analyses in SCZ research.

Using Class-Specific Feature Selection for Cancer Detection with Gene Expression Profile Data of Platelets.

A novel multi-classification method, which integrates the elastic net and probabilistic support vector machine, was proposed to solve this problem in cancer detection with gene expression profile data of platelets, whose problems mainly are a kind of multi-class classification problem with high dimension, small samples, and collinear data. The strategy of one-against-all (OVA) was employed to decompose the multi-classification problem into a series of binary classification problems. The elastic net was used to select class-specific features for the binary classification problems, and the probabilistic support vector machine was used to make the outputs of the binary classifiers with class-specific features comparable. Simulation data and gene expression profile data were intended to verify the effectiveness of the proposed method. Results indicate that the proposed method can automatically select class-specific features and obtain better performance of classification than that of the conventional multi-class classification methods, which are mainly based on global feature selection methods. This study indicates the proposed method is suitable for general multi-classification problems featured with high-dimension, small samples, and collinear data.

AStrap: identification of alternative splicing from transcript sequences without a reference genome.

SUMMARY: Alternative splicing (AS) is a well-established mechanism for increasing transcriptome and proteome diversity, however, detecting AS events and distinguishing among AS types in organisms without available reference genomes remains challenging. We developed a de novo approach called AStrap for AS analysis without using a reference genome. AStrap identifies AS events by extensive pair-wise alignments of transcript sequences and predicts AS types by a machine-learning model integrating more than 500 assembled features. We evaluated AStrap using collected AS events from reference genomes of rice and human as well as single-molecule real-time sequencing data from Amborella trichopoda. Results show that AStrap can identify much more AS events with comparable or higher accuracy than the competing method. AStrap also possesses a unique feature of predicting AS types, which achieves an overall accuracy of ∼0.87 for different species. Extensive evaluation of AStrap using different parameters, sample sizes and machine-learning models on different species also demonstrates the robustness and flexibility of AStrap. AStrap could be a valuable addition to the community for the study of AS in non-model organisms with limited genetic resources. AVAILABILITY AND IMPLEMENTATION: AStrap is available for download at https://github.com/BMILAB/AStrap. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A novel feature selection method to predict protein structural class.

Integrating various features from different protein properties helps to improve the prediction accuracy of protein structural class but need to deal with the corresponding integrated high-dimensional data. Thus, the feature selection process used to select the informative features from the integrated features also becomes an indispensable key step. This paper proposes a novel feature selection method, Partial-Maximum-Correlation-Information based Recursive Feature Elimination (PMCI-RFE), to quickly select the best feature subset from the integrated high-dimensional protein features set to improve the prediction performance of protein structural class. PMCI-RFE can also be used to find different types of informative features to further analyze some biological relationships. The proposed PMCI-RFE method uses the correlation information between the feature space and class encoding space to select informative features based on the idea of orthogonal component projection in the feature space. The experimental results on six widely used benchmark datasets show that PMCI-RFE is a fast and effective method compare to other four state-of-the-art feature selection methods, which indeed can make full use of different protein property information and improve the predictability of protein structural class.

Integrating multiple fitting regression and Bayes decision for cancer diagnosis with transcriptomic data from tumor-educated blood platelets.

The application of machine learning in cancer diagnostics has shown great promise and is of importance in clinic settings. Here we consider applying machine learning methods to transcriptomic data derived from tumor-educated platelets (TEPs) from individuals with different types of cancer. We aim to define a reliability measure for diagnostic purposes to increase the potential for facilitating personalized treatments. To this end, we present a novel classification method called MFRB (for Multiple Fitting Regression and Bayes decision), which integrates the process of multiple fitting regression (MFR) with Bayes decision theory. MFR is first used to map multidimensional features of the transcriptomic data into a one-dimensional feature. The probability density function of each class in the mapped space is then adjusted using the Gaussian probability density function. Finally, the Bayes decision theory is used to build a probabilistic classifier with the estimated probability density functions. The output of MFRB can be used to determine which class a sample belongs to, as well as to assign a reliability measure for a given class. The classical support vector machine (SVM) and probabilistic SVM (PSVM) are used to evaluate the performance of the proposed method with simulated and real TEP datasets. Our results indicate that the proposed MFRB method achieves the best performance compared to SVM and PSVM, mainly due to its strong generalization ability for limited, imbalanced, and noisy data.