Hierarchical Clustering Approach Research Articles

SHCF: A supervised hierarchical clustering approach to remove high density salt and pepper noise from black and white content digital images

SHCF: A supervised hierarchical clustering approach to remove high density salt and pepper noise from black and white content digital images

Optimization of virtual machines performance using fuzzy hashing and genetic algorithm-based memory deduplication of static pages

The demand for memory capacity has increased, and cloud energy usage has soared. The performance and scalability of virtualization interfaces in cloud computing are hampered by a lack of sufficient memory. To figure out this problem, a technique defined as memory deduplication is widely used to reduce memory consumption utilizing the page-sharing method. However, this method of memory deduplication using KSM has significant drawbacks, such as overhead owing to many online comparisons, which will consume so many CPU resources. In this research, a modified approach of Memory Deduplication of Static Memory Pages (mSMD), which is based on the identification of similar applications by Fuzzy hashing and clustering them using the Hierarchical Agglomerative Clustering approach, followed by similarity detection between static memory pages based on Genetic Algorithm and details stored in Multilevel shared page table, both operations performed in offline and final memory deduplication is carried out during online, is proposed for achieving performance optimization in virtual machines by reducing memory capacity requirements. When compared to existing techniques, the simulation results indicate that the proposed approach mSMD efficaciously minimizes the memory capacity required while improving performance.

A hierarchical cluster approach toward understanding the regional variable in country conflict modeling

PurposeThis paper aims to examine how the regional variable in country conflict modeling affects forecast accuracy and identifies a methodology to further improve the predictions.Design/methodology/approachThis paper uses statistical learning methods to both evaluate the quantity of data for clustering countries along with quantifying accuracy according to the number of clusters used.FindingsThis study demonstrates that increasing the number of clusters for modeling improves the ability to predict conflict as long as the models are robust.Originality/valueThis study investigates the quantity of clusters used in conflict modeling, while previous research assumes a specific quantity before modeling.

Parea: Multi-view ensemble clustering for cancer subtype discovery

Multi-view clustering methods are essential for the stratification of patients into sub-groups of similar molecular characteristics. In recent years, a wide range of methods have been developed for this purpose. However, due to the high diversity of cancer-related data, a single method may not perform sufficiently well in all cases. We present Parea, a multi-view hierarchical ensemble clustering approach for disease subtype discovery. We demonstrate its performance on several machine learning benchmark datasets. We apply and validate our methodology on real-world multi-view patient data, comprising seven types of cancer. Parea outperforms the current state-of-the-art on six out of seven analysed cancer types. We have integrated the Parea method into our Python package Pyrea (https://github.com/mdbloice/Pyrea), which enables the effortless and flexible design of ensemble workflows while incorporating a wide range of fusion and clustering algorithms.

An agglomerative hierarchical clustering approach to identify coexisting bacteria in groups of bacterial vaginosis patients

Polymicrobial syndromes such as Bacterial Vaginosis (BV), where there is a great diversity of microorganisms and causal connotations, turn it into a disease with complex dynamics in the bacteria’s coexistence in groups of patients. The main aim of this study was to explore a dataset of patients with BV to determine a more informed number of groups to create for further analysis of bacteria’s coexistence. The Agglomerative Hierarchical Clustering (AHC) algorithm was applied to a BV dataset from an urban population in southeastern Mexico consisting of 201 patient records with 59 patient attributes and three classes (BV-positive, BV-negative, BV-indeterminate). In the clustering results obtained, it is possible to identify different remarkable groups of patients. The most prevalent coexisting bacteria among patients with BV were Atopobium + Gardnerella vaginalis with 37.50%, Atopobium + Megasphaera with 15.68% in the first experiment. Whereas, in the second experiment, the coexisting bacteria were Atopobium + Megasphaera + Mycoplasma hominis with 33.33% and Atopobium + Gardnerella vaginalis + Mycoplasma hominis with 25%. Finally, we provided evidence that via the AHC algorithm, it was possible to identify an optimal number of clusters with high intra-similarity and inter-dissimilarity. Furthermore, this approach allowed us to create a clustering model that helps analyze the complex dynamics between bacteria in groups of patients with BV.

A hierarchical clustering approach for colorectal cancer molecular subtypes identification from gene expression data

BackgroundColorectal cancer (CRC) is the second leading cause of cancer fatalities and the third most common human disease. Identifying molecular subgroups of CRC and treating patients accordingly could result in better therapeutic success compared with treating all CRC patients similarly. Studies have highlighted the significance of CRC as a major cause of mortality worldwide and the potential benefits of identifying molecular subtypes to tailor treatment strategies and improve patient outcomes. MethodsThis study proposed an unsupervised learning approach using hierarchical clustering and feature selection to identify molecular subtypes and compares its performance with that of conventional methods. The proposed model contained gene expression data from CRC patients obtained from Kaggle and used dimension reduction techniques followed by Z-score-based outlier removal. Agglomerative hierarchy clustering was used to identify molecular subtypes, with a P-value-based approach for feature selection. The performance of the model was evaluated using various classifiers including multilayer perceptron (MLP). ResultsThe proposed methodology outperformed conventional methods, with the MLP classifier achieving the highest accuracy of 89% after feature selection. The model successfully identified molecular subtypes of CRC and differentiated between different subtypes based on their gene expression profiles. ConclusionThis method could aid in developing tailored therapeutic strategies for CRC patients, although there is a need for further validation and evaluation of its clinical significance.

HLA-Clus: HLA class I clustering based on 3D structure

BackgroundIn a previous paper, we classified populated HLA class I alleles into supertypes and subtypes based on the similarity of 3D landscape of peptide binding grooves, using newly defined structure distance metric and hierarchical clustering approach. Compared to other approaches, our method achieves higher correlation with peptide binding specificity, intra-cluster similarity (cohesion), and robustness. Here we introduce HLA-Clus, a Python package for clustering HLA Class I alleles using the method we developed recently and describe additional features including a new nearest neighbor clustering method that facilitates clustering based on user-defined criteria.ResultsThe HLA-Clus pipeline includes three stages: First, HLA Class I structural models are coarse grained and transformed into clouds of labeled points. Second, similarities between alleles are determined using a newly defined structure distance metric that accounts for spatial and physicochemical similarities. Finally, alleles are clustered via hierarchical or nearest-neighbor approaches. We also interfaced HLA-Clus with the peptide:HLA affinity predictor MHCnuggets. By using the nearest neighbor clustering method to select optimal allele-specific deep learning models in MHCnuggets, the average accuracy of peptide binding prediction of rare alleles was improved.ConclusionsThe HLA-Clus package offers a solution for characterizing the peptide binding specificities of a large number of HLA alleles. This method can be applied in HLA functional studies, such as the development of peptide affinity predictors, disease association studies, and HLA matching for grafting. HLA-Clus is freely available at our GitHub repository (https://github.com/yshen25/HLA-Clus).

The Impact of Socioeconomic and Demographic Factors on COVID-19 Forecasting Model

Background: COVID-19 has become a primary public health issue in various countries across the world. The main difficulty in managing outbreaks of infectious diseases is due to the difference in geographical, demographic, economic inequalities and people's behavior in each region. The spread of disease acts like a series of diverse regional outbreaks; each part has its disease transmission pattern. Objective: This study aims to assess the association of socioeconomic and demographic factors to COVID-19 cases through cluster analysis and forecast the daily cases of COVID-19 in each cluster using a predictive modeling technique. Methods: This study applies a hierarchical clustering approach to group regencies and cities based on their socioeconomic and demographic similarities. After that, a time-series forecasting model, Facebook Prophet, is developed in each cluster to assess the transmissibility risk of COVID-19 over a short period of time. Results: A high incidence of COVID-19 was found in clusters with better socioeconomic conditions and densely populated. The Prophet model forecasted the daily cases of COVID-19 in each cluster, with Mean Absolute Percentage Error (MAPE) of 0.0869; 0.1513; and 0.1040, respectively, for cluster 1, cluster 2, and cluster 3. Conclusion: Socioeconomic and demographic factors were associated with different COVID-19 waves in a region. From the study, we found that considering socioeconomic and demographic factors to forecast COVID-19 cases played a crucial role in determining the risk in that area. Keywords: COVID-19, Facebook Prophet , Hierarchical clustering, Socioeconomic and demographic

Reducing waste management scenario space for developing countries: A hierarchical clustering on principal components approach.

The complexity of waste management (WM) problems resulted in the explosion of scenarios that challenge focused discussion among stakeholders and hinder the integrity of policy responses in developing countries. Hence, drawing similarities is essential to reduce the number of scenarios to simplify the WM efforts. To extract similarities, measuring WM performance is not enough, but the background factors related to this performance should be incorporated. These factors form a unique system characteristic that facilitates or hinders WM functions. Thus, this study applied multivariate statistical analysis to clarify underlying characteristics that facilitate efficient WM scenario developments for developing countries. The study first analysed drivers associated with improved WM system performance using bivariate correlation analysis. As a result, twelve significant drivers associated with controlled solid waste were identified. Then, it mapped the countries based on their WM system characteristics using the combined principal component analysis and hierarchical clustering approach. Thirteen variables were examined to extract similarities between the countries. The results identified three homogenous clusters. The clusters were found considerably parallel to the global classifications based on income and human development index. Hence, the presented approach is efficient in explaining similarities that reduce WM scenarios and favours cooperation among countries.

Application of Hierarchical Clustering Approach for Prediction of Grain Size in Heat-Treated EN9 Steel

One of the simplest, most popular, and productive ways to conduct research and testing in the field of materials science is through the use of metallographic study. Technological boon in the field of metallographic study, opens new gateway for materials characterization through image processing technologies. Image segmentation, edge detection, and roughly estimating grain size are the three main goals of metallographic image processing. The objective of this paper was to determine the grain size of EN9 steel by applying different clustering techniques to the image textured data, collected from EN9 steel metallographic specimens in normalized and annealed condition. In order to determine the average grain size in EN9 steel specimens when seen with a metallurgical microscope, this article blends the ideas of image processing with various hierarchical clustering methodologies to study material characteristics.

Efficient Trajectory Clustering with Road Network Constraints Based on Spatiotemporal Buffering

The analysis of individuals’ movement behaviors is an important area of research in geographic information sciences, with broad applications in smart mobility and transportation systems. Recent advances in information and communication technologies have enabled the collection of vast amounts of mobility data for investigating movement behaviors using trajectory data mining techniques. Trajectory clustering is one commonly used method, but most existing methods require a complete similarity matrix to quantify the similarities among users’ trajectories in the dataset. This creates a significant computational overhead for large datasets with many user trajectories. To address this complexity, an efficient clustering-based method for network constraint trajectories is proposed, which can help with transportation planning and reduce traffic congestion on roads. The proposed algorithm is based on spatiotemporal buffering and overlapping operations and involves the following steps: (i) Trajectory preprocessing, which uses an efficient map-matching algorithm to match trajectory points to the road network. (ii) Trajectory segmentation, where a Compressed Linear Reference (CLR) technique is used to convert the discrete 3D trajectories to 2D CLR space. (iii) Spatiotemporal proximity analysis, which calculates a partial similarity matrix using the Longest Common Subsequence similarity indicator in CLR space. (iv) Trajectory clustering, which uses density-based and hierarchical clustering approaches to cluster the trajectories. To verify the proposed clustering-based method, a case study is carried out using real trajectories from the GeoLife project of Microsoft Research Asia. The case study results demonstrate the effectiveness and efficiency of the proposed method compared with other state-of-the-art clustering-based methods.

Abstract PD16-07: Association of MRI morphologic phenotype from unsupervised learning with breast cancer subtypes and treatment response

Abstract Background Breast cancer is a heterogeneous disease and can be categorized into clinically or biologically meaningful subtypes. Predictive models built by MRI biomarkers performed better when they are optimized by breast cancer subtype than models optimized in the full cohort [1]. Functional tumor volume (FTV) measured from breast MRI has been used to assess tumor response to neoadjuvant therapy longitudinally in the I-SPY 2 TRIAL. Tumors show distinct morphological patterns, or phenotypes, on MRI. Previous studies demonstrated that either qualitative or quantitative measurements characterizing these phenotypes may provide additional information about treatment response [2,3]. In this study, we investigated if MRI morphologic phenotypes defined by unsupervised clustering is associated with breast cancer subtype and pathologic complete response (pCR) after neoadjuvant chemotherapy (NAC). Methods A cohort of 990 patients enrolled in the I-SPY 2 TRIAL were included in this retrospective analysis. Patients were randomized to one of nine experimental drug arms or standard NAC, and pCR was assessed at surgery. DCE-MRI data acquired at pretreatment (T0) and early treatment (T1) were analyzed. Four subtypes of breast cancer were defined by immunohistochemistry (IHC) based on hormone receptor (HR) and HER2 status. Radiomic features were extracted by PyRadiomics [4] using FTV masks from DCE-MRI. MRI morphologic phenotypes were determined based on unsupervised hierarchical clustering approach on extracted radiomic shape features plus FTV using Pearson correlation with agglomerative ward linkage. The associations between the unsupervised clusters of radiomic features and FTV with four IHC subtypes and pCR were evaluated using χ2 test of independence. Cramer’s V [5] were computed to measure the strength of association (higher Cramer’s V means stronger association). P-value < 0.05 was considered statistically significant. Results Three clusters were generated by unsupervised hierarchical clustering in a population of 910 patients included in our analysis (80 patients excluded due to missing pCR or DCE-MRIs). At T0, the unsupervised clusters showed statistically significant but weak association with pCR (Cramer’s V = 0.088, p = 0.029), but the association between the clusters and HR/HER2 subtypes did not reach significance (Cramer’s V = 0.055, p = 0.48). The unsupervised clusters based on T1 shape radiomic features showed statistically significant association with both pCR and HR/HER2 subtypes (p < 0.001 for both) with Cramer’s V of 0.231 and 0.154, respectively. Our results showed stronger association between pCR and cancer subtypes with MRI shape radiomic features at T1 than at T0. Various pCR rates were observed in MRI clusters at T1. They were 56%, 36%, and 23% in Cluster 1, 2, 3, respectively. Table 1 shows pCR rates by HR/HER2 subtype in each cluster. In all sub-cohorts, pCR rate was highest in Cluster 1 and lowest in Cluster 3. In HR+/HER2-, the pCR rate in Cluster 1 was 2-fold of the pCR rates in Clusters 2 and 3-fold of Cluster 3. pCR rate was statistically significantly different depending on the MRI clusters in the sub-cohorts except for the HR/HER2+ sub-cohort: HR+/HER2-, p< 0.001; HR+/HER2+, p=0.021; HR-/HER2+, p=0.083; HR-/HER2-, p< 0.001. Conclusion MRI phenotype generated by unsupervised clustering using radiomic shape features at both pretreatment and early-treatment time points was associated with pCR outcome. Stronger association was observed at early-treatment time point. The association differed by subtype, with the strongest observed in HR+/HER2- and triple negative subtypes. Our results suggest that radiomic shape features derived from DCE-MRI may be helpful for early prediction of tumor response to NAC. Citations 1. npj Breast Cancer 6, (2020). 2. Tomography 6, (2020). 3. Annals of Surgical Oncology 20, 3823–3830 (2013). 4. Cancer Research 77, e104–e107 (2017). 5. Korean Stat Soc 42, 323–328 (2013). Table 1. pCR rate by HR/HER2 subtype in each MRI cluster at T1 Citation Format: Nu N. Le, Natsuko Onishi, David C. Newitt, Jessica E. Gibbs, Lisa J. Wilmes, Efstathios Gennatas, Barbara LeStage, Laura J. Esserman, Nola M. Hylton, Wen Li. Association of MRI morphologic phenotype from unsupervised learning with breast cancer subtypes and treatment response [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr PD16-07.

Prioritized Mapping in Bali: Multi-View Hierarchical Agglomerative Clustering (MVHAC) Approach

This study aims to determine which sectors and areas should be prioritized in development in BalI. The data used is panel data from 2010 – 2022 for all districts/cities in Bali. The data analysis technique for mapping sectors and regions is Multi-View Hierarchical Agglomerative Clustering (MVHAC). The results of the analysis of Location Quotient and Dyanmic Location Quotient show that the SARBAGITA area (Denpasar, Badung, Gianyar, and Tabanan) has potential in the secondary and tertiary sectors, while other areas are in the primary sector. MVHAC analysis shows that in quadrant 1 (cluster 1), namely Badung and Denpasar, the sectors that can be developed are agriculture, forestry and fisheries; real estate; manufacturing industry; water supply, waste management and waste recycling and mining and excavation, the area of quadrant 3 (cluster 2) of Tabanan and Gianyar is almost similar to Badung and Tabanan, but the potential sector is also transportation and warehousing, while quadrant 4 (cluster 2) is more on the information and communication; real estate; educational services; health services and social activities.

A Functional Trait-Based Approach to Evaluate the Resilience of Key Ecosystem Functions of Tropical Savannas

The persistence of the woody vegetation of the Sahelian savannas, and their supported ecosystem functions, have been questioned since the great drought of 1970s–1980s. To assess the resilience of this vegetation to drought and grazing, we undertook a trait-based approach using field inventory, historical survey databases, and traits data literature. Using a hierarchical clustering approach, we gathered the species present from 1970 to 2015 into functional groups according to their effect traits related to primary productivity and biogeochemical cycles. First, we studied the evolution of functional redundancy (FRe) and response diversity (RDiv) of the functional effect groups to drought and grazing, two indicators of resilience, since the 1970s. Second, we looked at the spatial variation of these two indices in 2015, according to local topography. FRe and RDiv of 80% of the functional groups examined declined since 1970, endangering the persistence of the studied functions. Local topography strongly influenced current FRe and RDiv, with depressions presenting higher values. Finally, by examining species’ abundances, their regeneration, and the functional group to which they belong, we determined some key species that could benefit from protection to ensure the persistence of the ecosystem functions supported by the woody vegetation. This study has expanded knowledge about the savanna’s response to pressures and has shown how a functional traits-based approach could be an effective tool to guide the management of tropical savannas.

Abstract WMP29: Sex Differences On The Importance Of Multimorbidity In Post-stroke Disability:the Taiwan Stroke Registry

Background: Experiencing a clinical stroke may further aggravate the clinical condition of patients with multimorbidity and pose significant challenges regarding recommended poststroke therapies. However, there is limited evidence regarding the impact of multimorbidity on long-term disability in stroke patients, or whether any associations differ by sex. Hypotheses: Clusters of multimorbidity are associated with post-stroke disability. The association may depend on sex membership. Methods: In the Taiwan Stroke Registry study, 9818 patients with their first-ever recorded ischemic stroke were examined. Employing a hierarchical clustering approach, clusters of multimorbidity were generated based on 16 risk factors and were characterized using the observed/expected prevalence ratio ≥1.5 and the prevalence exclusivity measure ≥25%. Post-stroke disability was assessed using the mRS and categorized into less (mRS <3) vs. more disability (mRS ≥3) over 12 months. The association between clusters of multimorbidity and post-stroke disability adjusted for age, sex, education, and stroke severity (NIHSS) was determined using logistic regression models, overall and stratified by sex. Results: Patients with a cluster profile of diabetes, peripheral artery disease and uremia had more disability than patients with a healthier cluster profile (Table 1). The association only remained significant in males, who had a higher multimorbidity burden, but not in females who more frequently had more severe strokes and more severe post-stroke disability. Conclusion: Patients with multimorbidity involving diabetes, peripheral artery disease and uremia have greater post-stroke disability and may require a more targeted rehabilitative approach. Certain clusters of multimorbidity may be more important for long-term post-stroke disability outcomes in males than in females.

The cellular basis of mechanosensation in mammalian tongue.

Mechanosensory neurons that innervate the tongue provide essential information to guide feeding, speech, and social grooming. We use invivo calcium imaging of mouse trigeminal ganglion neurons to identify functional groups of mechanosensory neurons innervating the anterior tongue. These sensory neurons respond to thermal and mechanical stimulation. Analysis of neuronal activity patterns reveal that most mechanosensory trigeminal neurons are tuned to detect moving stimuli across the tongue. Using an unbiased, multilayer hierarchical clustering approach to classify pressure-evoked activity based on temporal response dynamics, we identify five functional classes of mechanosensory neurons with distinct force-response relations and adaptation profiles. These populations are tuned to detect different features of touch. Molecular markers of functionally distinct clusters are identified by analyzing cluster representation in genetically marked neuronal subsets. Collectively, these studies provide a platform for defining the contributions of functionally distinct mechanosensory neurons to oral behaviors crucial for survival in mammals.

A PCA-AHC Approach to Provenance Studies of Non-Ferrous Metals with Combined Pb Isotope and Chemistry Data

This paper discusses the applicability of the Principal Component Analysis-Agglomerative Hierarchical Clustering (PCA-AHC) approach to provenance studies of non-ferrous metals using combined Pb isotope and chemistry data. Pb isotopic ratios were converted to the natural abundance of individual isotopes and then to weight units. Next, all relevant variables (Pb isotopes and trace elements) were processed with PCA and AHC to examine the relationships between observations. The method is first verified on three literature-based case studies (1, 2, and 3). It is argued that, as is the case in archaeological iron provenance studies, the PCA-AHC method is also viable for non-ferrous metals. This method can greatly facilitate research, compared to conventional biplots with ratios of Pb isotopes and trace elements. Additionally, PCA-AHC can become part of the initial deposit selection process, and it can help clarify less obvious classification cases. The main problem with a practical application of this approach is insufficient deposit datasets with complete Pb isotopic and chemistry data. In such cases, it is possible to use the PCA-AHC method separately on Pb isotopic and chemistry data and then to compare and contrast results. Alternatively, the proposed approach can be used solely with Pb isotopic data. This application is shown in two additional case studies (4 and 5), which demonstrate the method’s application for tracing artefacts to their parent ores using datasets with a few thousand observations.

A Comparative Study of Collaborative Filtering and Content-Based Approaches for Improving the Accuracy of Travel Recommender Systems for Malayalam Language

In this paper, we present a personalized travel recommender system in the Malayalam language using artificial intelligence techniques. The study focuses on the use of travelogues and travel reviews written by travellers on social media as the primary source of data. A dataset of 11000 posts from 6444 travellers was collected from Facebook and other online platforms during 2020-2023. The data was pre-processed to extract relevant information such as travel mode, type of travel, location visited, and climate. Two approaches were used to build the recommender system: collaborative filtering-based K-means clustering and content-based hierarchical agglomerative clustering. The results of the study showed that the clustering approach significantly improved the efficiency and accuracy of the recommender system. K-means clustering achieved an accuracy of 91% and an F1 score of 85%, while the agglomerative hierarchical clustering approach achieved an accuracy of 85% and an F1 score of 84.25%. The results of this study demonstrate the potential of using travelogues and travel reviews to construct a personalized travel recommender system in regional languages.

Big data analysis using a parallel ensemble clustering architecture and an unsupervised feature selection approach

Ensemble clustering is known as a challenging research direction in data mining. The results of several individual clustering methods are combined to produce higher quality final clusters. This study introduces a parallel hierarchical clustering approach based on the divide-and-conquer strategy, which is an attempt to realize faster and more efficient ensemble clustering. Here, we propose a cluster consensus selection approach that selects a subset of meriting primary clusters to participate in the final consensus. Considering the sample-cluster and cluster–cluster similarity on the selected primary clusters, we form the final clusters based on the clusters clustering technique as a consensus function. In addition, the proposed scheme is equipped with an unsupervised feature selection approach to remove features that do not contribute significantly to clustering. Extensive evaluations have been performed on datasets of different dimensions from the University of California Irvine (UCI) machine learning repository. The simulation results guarantee the efficiency of the proposed scheme and improves the average performance between 6% and 24% compared to the state-of-the-art clustering methods.

Profiling of pyrrolizidine alkaloids using a retronecine-based untargeted metabolomics approach coupled to the quantitation of the retronecine-core in medicinal plants using UHPLC-QTOF

Pyrrolizidine alkaloids (PA) are secondary metabolites of high toxicological relevance. Several PA quantitative methodologies were developed based on a limited number of certified standards, including time consuming solid phase extraction (SPE) purification steps. Herein, we shed light on the variability of PA in herbal extracts and propose a quantification methodology based on ultra-high-performance liquid chromatography high-resolution mass spectrometry (UHPLC-HRMS) for the evaluation of the total PA content as retronecine-equivalents (RE) directly from crude matrices. Particularly in the focus of the investigation were Alkanna spp. (Boraginaceae), which possess a wide range of pharmaceutical properties. In addition, a comparative PA screening of crude and SPE enriched extracts was performed and PA-containing plants from Fabaceae and Compositae families were included to demonstrate universal applicability. In total, 105 PA were identified using HRMSe experiments, specific MS/MS fragmentation PA patterns, a customized in-house library and literature data. Among them, 18 glycosidic PA derivatives were reported for the first time in literature. Using a hierarchical clustering approach, PA distribution in herbal extracts was shown to be family-dependent and significantly different among species. This was further supported by the results of the total PA concentrations, obtained using a retronecine/heliotridine/internal standard-based targeted UHPLC-HRMS quantification method, which varied from 8.64 ± 0.08–3096.28 ± 273.72 μg RE/g extract dry weight in shoots extracts of Alkanna spp. and leaves extracts of Crotalaria retusa L. respectively. Worth mentioning is that the procedure allowed to quantify PA in Alkanna spp. If the procedure based on 35 specific PA recommended by European regulations had been used, results would have been equal to zero for the four species since none were observed in Alkanna spp. Finally, by combining the RE results with the corresponding dereplication results, a customized correction factor for each extract (ranging from 2.12 to 2.48) was assessed leading to a more accurate estimate of the PA content regardless of the molecular weight of each PA. The present methodology will facilitate PA quantification directly from crude extracts and avoid the underestimation the real PA content due to limited availabilty of authentic reference compounds in botanical extracts used in phytomedicines or food supplements/cosmetics.