Spectral Similarity Measures Research Articles

TransExION: a transformer based explainable similarity metric for comparing IONS in tandem mass spectrometry

Small molecule identification is a crucial task in analytical chemistry and life sciences. One of the most commonly used technologies to elucidate small molecule structures is mass spectrometry. Spectral library search of product ion spectra (MS/MS) is a popular strategy to identify or find structural analogues. This approach relies on the assumption that spectral similarity and structural similarity are correlated. However, popular spectral similarity measures, usually calculated based on identical fragment matches between the MS/MS spectra, do not always accurately reflect the structural similarity. In this study, we propose TransExION, a Transformer based Explainable similarity metric for IONS. TransExION detects related fragments between MS/MS spectra through their mass difference and uses these to estimate spectral similarity. These related fragments can be nearly identical, but can also share a substructure. TransExION also provides a post-hoc explanation of its estimation, which can be used to support scientists in evaluating the spectral library search results and thus in structure elucidation of unknown molecules. Our model has a Transformer based architecture and it is trained on the data derived from GNPS MS/MS libraries. The experimental results show that it improves existing spectral similarity measures in searching and interpreting structural analogues as well as in molecular networking.Scientific ContributionWe propose a transformer-based spectral similarity metrics that improves the comparison of small molecule tandem mass spectra. We provide a post hoc explanation that can serve as a good starting point for unknown spectra annotation based on database spectra.

Exploring an application-oriented land-based hyperspectral target detection framework based on 3D–2D CNN and transfer learning

Target detection based on hyperspectral images refers to the integrated use of spatial information and spectral information to accomplish the task of localization and identification of targets. There are two main methods for hyperspectral target detection: supervised and unsupervised methods. Supervision method refers to the use of spectral differences between the target to be tested and the surrounding background to identify the target when the target spectrum is known. In ideal situations, supervised object detection algorithms perform better than unsupervised algorithms. However, the current supervised object detection algorithms mainly have two problems: firstly, the impact of uncertainty in the ground object spectrum, and secondly, the universality of the algorithm is poor. A hyperspectral target detection framework based on 3D–2D CNN and transfer learning was proposed to solve the problems of traditional supervised methods. This method first extracts multi-scale spectral information and then preprocesses hyperspectral images using multiple spectral similarity measures. This method not only extracts spectral features in advance, but also eliminates the influence of complex environments to a certain extent. The preprocessed feature maps are used as input for 3D–2D CNN to deeply learn the features of the target, and then, the softmax method is used to output and obtain the detection results. The framework draws on the ideas of integrated learning and transfer learning, solves the spectral uncertainty problem with the combined similarity measure and depth feature extraction network, and solves the problem of poor robustness of traditional algorithms by model migration and parameter sharing. The area under the ROC curve of the proposed method has been increased to over 0.99 in experiments on both publicly available remote sensing hyperspectral images and measured land-based hyperspectral images. The availability and stability of the proposed method have been demonstrated through experiments. A feasible approach has been provided for the development and application of specific target detection technology in hyperspectral images under different backgrounds in the future.

IMN4NPD: An Integrated Molecular Networking Workflow for Natural Product Dereplication.

Molecular networking has emerged as a standard approach for natural product (NP) discovery. However, the current pipeline based on molecular networks tends to prioritize larger clusters comprising multiple nodes. To address this issue, we present the integrated molecular networking workflow for NP dereplication (IMN4NPD). This approach not only expedites the rapid dereplication of extensive clusters within the molecular network but also places specific emphasis on self-looped or pairs of nodes, which are often overlooked by the current methods. By amalgamating the outputs from various computational tools, we efficiently dereplicate compounds falling into specific categories and provide annotations for both large cluster nodes and self-looped or pair of nodes within the molecular network. Furthermore, we have incorporated several fundamentally distinct similarity algorithms, namely, Spec2Vec and MS2DeepScore, for constructing the t-SNE network. Through comparison with modified cosine similarity, we have observed that integrating additional diverse spectral similarity measures, the resulting t-SNE network enhanced the ability to dereplicate NPs. Demonstrating the use case of an ethanol extract of Plumula nelumbinis, we illustrate that an integration of multiple computational solutions with IMN4NPD aids the dereplication, especially self-looped nodes, and in the discovery of novel compounds in NPs.

Expert Algorithm for Substance Identification Using Mass Spectrometry: Application to the Identification of Cocaine on Different Instruments Using Binary Classification Models.

This is the second of two manuscripts describing how general linear modeling (GLM) of a selection of the most abundant normalized fragment ion abundances of replicate mass spectra from one laboratory can be used in conjunction with binary classifiers to enable specific and selective identifications with reportable error rates of spectra from other laboratories. Here, the proof-of-concept uses a training set of 128 replicate cocaine spectra from one crime laboratory as the basis of GLM modeling. GLM models for the 20 most abundant fragments of cocaine were then applied to 175 additional test/validation cocaine spectra collected in more than a dozen crime laboratories and 716 known negative spectra, which included 10 spectra of three diastereomers of cocaine. Spectral similarity and dissimilarity between the measured and predicted abundances were assessed using a variety of conventional measures, including the mean absolute residual and NIST's spectral similarity score. For each spectral measure, GLM predictions were compared to the traditional exemplar approach, which used the average of the cocaine training set as the consensus spectrum for comparisons. In unsupervised models, EASI provided better than a 95% true positive rate for cocaine with a 0% false positive rate. A supervised binary logistic regression model provided 100% accuracy and no errors using EASI-predicted abundances of only four peaks at m/z 152, 198, 272, and 303. Regardless of the measure of spectral similarity, error rates for identifications using EASI were superior to the traditional exemplar/consensus approach. As a supervised binary classifier, EASI was more reliable than using Mahalanobis distances.

Spectral similarity‐based feature for hyperspectral image classification

AbstractBased on spectral similarity measure, a unified spectral similarity‐based framework is developed to generate a new series of spectral similarity‐based features for hyperspectral image classification by using classifier, such as support vector machine(SVM). First, a reference spectral signature was defined according to the original hyperspectral data. The reference spectral signature can be chosen as the uniform line or the average of the original data. Second, the proposed features were produced by calculating the spectral similarity measures between each pixel's and the reference spectral signature. The experiment result shows that these proposed features can improve hyperspectral image classification accuracies.

Spectral Similarity Measures for In Vivo Human Tissue Discrimination Based on Hyperspectral Imaging.

Similarity measures are widely used as an approved method for spectral discrimination or identification with their applications in different areas of scientific research. Even though a range of works have been presented, only a few showed slightly promising results for human tissue, and these were mostly focused on pathological and non-pathological tissue classification. In this work, several spectral similarity measures on hyperspectral (HS) images of in vivo human tissue were evaluated for tissue discrimination purposes. Moreover, we introduced two new hybrid spectral measures, called SID-JM-TAN(SAM) and SID-JM-TAN(SCA). We analyzed spectral signatures obtained from 13 different human tissue types and two different materials (gauze, instruments), collected from HS images of 100 patients during surgeries. The quantitative results showed the reliable performance of the different similarity measures and the proposed hybrid measures for tissue discrimination purposes. The latter produced higher discrimination values, up to 6.7 times more than the classical spectral similarity measures. Moreover, an application of the similarity measures was presented to support the annotations of the HS images. We showed that the automatic checking of tissue-annotated thyroid and colon tissues was successful in 73% and 60% of the total spectra, respectively. The hybrid measures showed the highest performance. Furthermore, the automatic labeling of wrongly annotated tissues was similar for all measures, with an accuracy of up to 90%. In future work, the proposed spectral similarity measures will be integrated with tools to support physicians in annotations and tissue labeling of HS images.

Adaptive Gated Graph Convolutional Network for Explainable Diagnosis of Alzheimer's Disease Using EEG Data.

Graph neural network (GNN) models are increasingly being used for the classification of electroencephalography (EEG) data. However, GNN-based diagnosis of neurological disorders, such as Alzheimer's disease (AD), remains a relatively unexplored area of research. Previous studies have relied on functional connectivity methods to infer brain graph structures and used simple GNN architectures for the diagnosis of AD. In this work, we propose a novel adaptive gated graph convolutional network (AGGCN) that can provide explainable predictions. AGGCN adaptively learns graph structures by combining convolution-based node feature enhancement with a correlation-based measure of power spectral density similarity. Furthermore, the gated graph convolution can dynamically weigh the contribution of various spatial scales. The proposed model achieves high accuracy in both eyes-closed and eyes-open conditions, indicating the stability of learned representations. Finally, we demonstrate that the proposed AGGCN model generates consistent explanations of its predictions that might be relevant for further study of AD-related alterations of brain networks.

Selection of the best hybrid spectral similarity measure for characterising marine oil spills from multi-platform hyperspectral datasets

Selection of the best hybrid spectral similarity measure for characterising marine oil spills from multi-platform hyperspectral datasets

Crop Classification Based on GDSSM-CNN Using Multi-Temporal RADARSAT-2 SAR with Limited Labeled Data

Crop classification is an important part of crop management and yield estimation. In recent years, neural networks have made great progress in synthetic aperture radar (SAR) crop classification. However, the insufficient number of labeled samples limits the classification performance of neural networks. In order to solve this problem, a new crop classification method combining geodesic distance spectral similarity measurement and a one-dimensional convolutional neural network (GDSSM-CNN) is proposed in this study. The method consisted of: (1) the geodesic distance spectral similarity method (GDSSM) for obtaining similarity and (2) the one-dimensional convolutional neural network model for crop classification. Thereinto, a large number of training data are extracted by GDSSM and the generalized volume scattering model which is based on radar vegetation index (GRVI), and then classified by 1D-CNN. In order to prove the effectiveness of the GDSSM-CNN method, the GDSSM method and 1D-CNN method are compared in the case of a limited sample. In terms of evaluation and verification of methods, the GDSSM-CNN method has the highest accuracy, with an accuracy rate of 91.2%, which is 19.94% and 23.91% higher than the GDSSM method and the 1D-CNN method, respectively. In general, the GDSSM-CNN method uses a small number of ground measurement samples, and it uses the rich polarity information in multi-temporal fully polarized SAR data to obtain a large number of training samples, which can quickly improve the accuracy of classification in a short time, which has more new inspiration for crop classification.

Mapping winter wheat in Kaifeng, China using Sentinel-1A time-series images

ABSTRACT Crop planting area mapping is essential for crop phenology monitoring, yield prediction, and disaster prevention. In this study, a winter wheat identification method combining Markov Random Field and Spectral Similarity Measure (MRF-SSM) is proposed by using Sentinel-1 A time-series images. It is found that compared with VH polarization, the backscattering coefficient of winter wheat at VV polarization fluctuates more at all growth stages and is used for winter wheat mapping. The result shows that the precision of mapping winter wheat using the MRF-SSM is 89.62% which is higher than using the support vector machine (SVM) and random forest (RF) methods. Because winter wheat near towns can be accurately identified using MRF-SSM methods. Moreover, the MRF-SSM method has the advantages of fewer winter wheat samples and less computation time. Therefore, time-series Sentinel-1A images with MRF-SSM have great potential for mapping winter wheat or other crops.

Calibr improves spectral library search for spectrum-centric analysis of data independent acquisition proteomics

Identifying peptides and proteins from mass spectrometry (MS) data, spectral library searching has emerged as a complementary approach to the conventional database searching. However, for the spectrum-centric analysis of data-independent acquisition (DIA) data, spectral library searching has not been widely exploited because existing spectral library search tools are mainly designed and optimized for the analysis of data-dependent acquisition (DDA) data. We present Calibr, a spectral library search tool for spectrum-centric DIA data analysis. Calibr optimizes spectrum preprocessing for pseudo MS2 spectra, generating an 8.11% increase in spectrum–spectrum match (SSM) number and a 7.49% increase in peptide number over the traditional preprocessing approach. When searching against the DDA-based spectral library, Calibr improves SSM number by 17.6–26.65% and peptide number by 18.45–37.31% over two state-of-the-art tools on three different data sets. Searching against the public spectral library from MassIVE, Calibr improves state-of-the-art tools in SSM and peptide numbers by more than 31.49% and 25.24%, respectively, for two data sets. Our analyses indicate higher sensitivity of Calibr results from the use of various spectral similarity measures and statistical scores, coupled with machine learning-based statistical validation for FDR control. Calibr executable files including a graphical user-interface application are available at https://ms.iis.sinica.edu.tw/COmics/Software_CalibrWizard.html and https://sourceforge.net/projects/comics-calibr.

Spectral-Spatial Boundary Detection in Hyperspectral Images.

In this paper, we propose a novel method for boundary detection in close-range hyperspectral images. This method can effectively predict the boundaries of objects of similar colour but different materials. To effectively extract the material information in the image, the spatial distribution of the spectral responses of different materials or endmembers is first estimated by hyperspectral unmixing. The resulting abundance map represents the fraction of each endmember spectra at each pixel. The abundance map is used as a supportive feature such that the spectral signature and the abundance vector for each pixel are fused to form a new spectral feature vector. Then different spectral similarity measures are adopted to construct a sparse spectral-spatial affinity matrix that characterizes the similarity between the spectral feature vectors of neighbouring pixels within a local neighborhood. After that, a spectral clustering method is adopted to produce eigenimages. Finally, the boundary map is constructed from the most informative eigenimages. We created a new HSI dataset and use it to compare the proposed method with four alternative methods, one for hyperspectral image and three for RGB image. The results exhibit that our method outperforms the alternatives and can cope with several scenarios that methods based on colour images cannot handle.

Classification of forensic hyperspectral paper data using hybrid spectral similarity algorithms

AbstractDocument forgeries that involve modification of the materials used, such as ink and paper, provide evidence of any malpractices being performed. Forensic specialists use different techniques to identify and classify these samples; however, the most preferred method is to use nondestructive techniques to avoid any potential damage to the original specimen under investigation. Hyperspectral imaging has already been explored in several application domains and used as a powerful method in forensic investigations to extract information about the materials under examination. To precisely classify the material information and utilize the hyperspectral imaging technique's potential, we probed the potential of some hybrid spectral similarity measures to classify different commonly used paper samples. A comparison of these methods is quantitatively presented in this article.

Self-Supervised Learning With Adaptive Distillation for Hyperspectral Image Classification

Hyperspectral image (HSI) classification is an important topic in the community of remote sensing, which has a wide range of applications in geoscience. Recently, deep learning-based methods have been widely used in HSI classification. However, due to the scarcity of labeled samples in HSI, the potential of deep learning-based methods has not been fully exploited. To solve this problem, a self-supervised learning (SSL) method with adaptive distillation is proposed to train the deep neural network with extensive unlabeled samples. The proposed method consists of two modules: adaptive knowledge distillation with spatial–spectral similarity and 3-D transformation on HSI cubes. The SSL with adaptive knowledge distillation uses the self-supervised information to train the network by knowledge distillation, where self-supervised knowledge is the adaptive soft label generated by spatial–spectral similarity measurement. The SSL with adaptive knowledge distillation mainly includes the following three steps. First, the similarity between unlabeled samples and object classes in HSI is generated based on the spatial–spectral joint distance (SSJD) between unlabeled samples and labeled samples. Second, the adaptive soft label of each unlabeled sample is generated to measure the probability that the unlabeled sample belongs to each object class. Third, a progressive convolutional network (PCN) is trained by minimizing the cross-entropy between the adaptive soft labels and the probabilities generated by the forward propagation of the PCN. The SSL with 3-D transformation rotates the HSI cube in both the spectral domain and the spatial domain to fully exploit the labeled samples. Experiments on three public HSI data sets have demonstrated that the proposed method can achieve better performance than existing state-of-the-art methods.

Selection of the best hybrid spectral similarity measure for characterising marine oil spills from multi-platform hyperspectral datasets

Selection of the best hybrid spectral similarity measure for characterising marine oil spills from multi-platform hyperspectral datasets

An analysis of spectral similarity measures

In this paper we analyze the most used measures for the assessment of spectral similarity of reflectance and radiance signals. First of all we divide them in five groups on the basis of the type of errors they measure. We proceed analyzing their mathematical definition to identify unintended behaviors and types of errors they are blind to. Then exploiting the Munsell atlas we analyze the correlation between metrics in terms of both Pearson's Linear Correlation Coefficient (PLCC) and Spearman's Rank Order Correlation Coefficient (SROCC). Finally we analyze the behaviour of the selected metrics with respect to two different color properties: the Chroma and the Lightness computed in the CIE L* a* b* color space. The source code of the spectral measures considered is available at the following link: <ext-link ext-link-type="url" xlink:href="https://celuigi.github.io/spectral-similarity-metrics-comparison/">https://celuigi.github.io/spectral-similarity-metrics-comparison/</ext-link>.

MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra

Mass spectrometry data is one of the key sources of information in many workflows in medicine and across the life sciences. Mass fragmentation spectra are generally considered to be characteristic signatures of the chemical compound they originate from, yet the chemical structure itself usually cannot be easily deduced from the spectrum. Often, spectral similarity measures are used as a proxy for structural similarity but this approach is strongly limited by a generally poor correlation between both metrics. Here, we propose MS2DeepScore: a novel Siamese neural network to predict the structural similarity between two chemical structures solely based on their MS/MS fragmentation spectra. Using a cleaned dataset of > 100,000 mass spectra of about 15,000 unique known compounds, we trained MS2DeepScore to predict structural similarity scores for spectrum pairs with high accuracy. In addition, sampling different model varieties through Monte-Carlo Dropout is used to further improve the predictions and assess the model’s prediction uncertainty. On 3600 spectra of 500 unseen compounds, MS2DeepScore is able to identify highly-reliable structural matches and to predict Tanimoto scores for pairs of molecules based on their fragment spectra with a root mean squared error of about 0.15. Furthermore, the prediction uncertainty estimate can be used to select a subset of predictions with a root mean squared error of about 0.1. Furthermore, we demonstrate that MS2DeepScore outperforms classical spectral similarity measures in retrieving chemically related compound pairs from large mass spectral datasets, thereby illustrating its potential for spectral library matching. Finally, MS2DeepScore can also be used to create chemically meaningful mass spectral embeddings that could be used to cluster large numbers of spectra. Added to the recently introduced unsupervised Spec2Vec metric, we believe that machine learning-supported mass spectral similarity measures have great potential for a range of metabolomics data processing pipelines.

Extraction of spatial-spectral homogeneous patches and fractional abundances for field-scale agriculture monitoring using airborne hyperspectral images

Farm scale information is crucial for large scale agricultural monitoring and policymaking. Therefore, per-field agricultural land-use statistics is more informative than per-pixel statistics. However, per-field segmentation of hyperspectral image (HSI) is challenging due to the variability in spectral responses of different spectral bands within the neighbourhood. Moreover, manual digitization and modification of the field map or field boundaries at each airborne campaign (at different spatial resolution) or each growing season is a challenging task. To overcome this challenge, we developed an unsupervised method for segmenting the spatial-spectral homogeneous pixels and its fractional abundances in airborne HSIs. In the proposed approach, morphological operations based local spectral similarity measure combined with edge detector was applied to produce edge intensity map. Watershed segmentation was applied on the binary edge map to generate the spatially homogeneous land segments in the HSI. Then, online-dictionary-learning and sparse-unmixing have been performed on the HSI to compute the fractional abundance map of vegetation, soil and crop residue and to mask the other targets. The proposed method was tested on simulated HSI, benchmark HSIs as well as the image obtained from Airborne-Visible-and-Infra-Red-Imaging-Spectrometer Next-Generation (AVIRIS-NG) sensor. Figure-of-merit, false-alarm-count and miss-count were applied to evaluate the performance of boundary detection methods. The results indicate that the fractional-spectral-similarity outperformed other distance measures in detecting spectrally homogeneous regions. It was also observed that integration of fractional-similarity with Sobel-edge-filter improved the performance of the edge detector. Edge-intensity-map generated using the fractional-similarity approach was employed as seed points for the watershed segmentation, which showed significant improvement in terms of accuracy as compared to other segmentation methods. We also demonstrated the robustness of our method on multiple HSI datasets spanning different regions. Moreover, the integration of spectral un-mixing with segmentation technique enables the identification of bare fields, harvested fields with crop-residues, and the fields with high vegetation canopy cover. The proposed method is automated with few parameters and it is operationally practical for large HSIs.

A systematic method for spatio-temporal phenology estimation of paddy rice using time series Sentinel-1 images

Spatio-temporal phenological information is essential for regional crop monitoring and accurate management. This study aimed to obtain the spatio-temporal distribution of rice phenology using time series Sentinel-1A images. In this study, a systematic method for spatial and temporal phenological estimation was developed based on multi-temporal Sentinel data. This method consisted of: (1) the Spectral Similarity Measures (SSM) approach for rice mapping, and (2) the DTHT-PF approach, which includes a dynamic threshold algorithm (DT), a hierarchical tree (HT), and a particle filter (PF) used for phenology estimation. Thereinto, a dynamic threshold algorithm for transplanting date retrieval and a hierarchical tree for obtaining an initial phenology, which is then run through a PF, are proposed based on the SAR backscatter time series. In brief, we found that the VH backscatter has the potential to provide accurate phenological estimations for paddy rice. Furthermore, rice mapping at a high accuracy level of 92.97%, transplanting date retrieval, and initial phenology estimations lay a good foundation for understanding the spatio-temporal distribution of rice phenology. A determination factor (R2) and a root mean square error (RMSE) obtained using the DTHT-PF method were much higher (approximately 0.52 in the difference) and lower (approximately 14.67 in the difference), respectively, than those obtained using the PF approach with uniform initialization. R2 and RMSE values obtained using the real-time DTHT-PF method are slightly different from those obtained using the non-real-time DTHT-PF method. Map analysis revealed that the transplanting dates and the spatial distribution phenology were larger in the west and north of the study area near the South China Sea because of higher temperatures and earlier transplanting. Altogether, our results suggest that the DTHT-PF method and the VH backscatter obtained from the Sentinel-1A images have great potential for furthering our understanding of the spatio-temporal distribution of phenology estimation. This information can greatly contribute to the improvement of precision agriculture, including crop monitoring and yield predictions.

Hyperspectral Image Classification Based on Deep Attention Graph Convolutional Network

Hyperspectral images (HSIs) have gained high spectral resolution due to recent advances in spectral imaging technologies. This incurs problems, such as an increased data scale and an increased number of bands for HSIs, which results in a complex correlation between different bands. In the applications of remote sensing and earth observation, ground objects represented by each HSI pixel are composed of physical and chemical non-Euclidean structures, and HSI classification (HIC) is becoming a more challenging task. To solve the above problems, we propose a framework based on a deep attention graph convolutional network (DAGCN). Specifically, we first integrate an attention mechanism into the spectral similarity measurement to aggregate similar spectra. Therefore, we propose a new similarity measurement method, i.e., the mixed measurement of a kernel spectral angle mapper and spectral information divergence (KSAM-SID), to aggregate similar spectra. Considering the non-Euclidean structural characteristics of HSIs, we design deep graph convolutional networks (DeepGCNs) as a feature extraction method to extract deep abstract features and explore the internal relationship between HSI data. Finally, we dynamically update the attention graph adjacency matrix to adapt to the changes in each feature graph. Experiments on three standard HSI data sets, namely, the Indian Pines, Pavia University, and Salinas data sets, demonstrate that the DAGCN outperforms the baselines in terms of various evaluation criteria. For example, on the Indian Pines data set, the overall accuracy of the proposed method achieves 98.61% when the training sample is 10%.