Sum Of Ranking Differences Research Articles

Implementation of multiobjective decision-making algorithms and image analysis in HPTLC-guided extraction optimization of natural products

A new, efficient, and low-cost approach for monitoring extraction optimization was proposed based on high-performance thin-layer chromatography (HPTLC) coupled with digital image analysis. Since HPTLC produces rich chromatographic signals corresponding to various analytes which may be differently affected by extraction conditions, four multicriteria decision-making (MCDM) techniques were compared for their ability to aggregate multiple chromatographic responses: Derringer's desirability approach, Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), Preference Ranking Organization Method for Enrichment Evaluations (PROMETHEE-2), and the Sum of ranking differences (SRD). Ultrasound-assisted extraction (UAE) of green tea leaves with ethanol-water mixtures was used as a model system. The amount of ethanol and extraction time were varied according to the central composite design. Ranking eleven extracts by Derringer's desirability approach, TOPSIS, and PROMETHEE-2 showed the same results. SRD analysis yielded slightly different results from previous methods. Response surface models based on the previous three MCDM approaches demonstrated that extraction conditions with moderate amounts of ethanol (73%) and extraction times (46 min) lead to optimal chromatographic profiles. Optimization performed on individual peaks tentatively corresponding to rutin, chlorophyll, and gallic acid may lead to different results. Aside from natural products, the proposed approach has the potential to be implemented in various extraction optimizations.

Multiobjective optimization of effect-directed planar chromatography as a promising tool for fast selection of polypotent natural products

A new method for efficiently selecting polypotent natural products is proposed in this study. The method involves using effect-directed HPTLC data and multiobjective optimization algorithms to extract chromatographic signals from HPTLC bioassay images. Three different multiobjective optimization methods, namely Derringer's desirability approach, Technique for order of preference by similarity to ideal solution (TOPSIS), and Sum of ranking differences (SRD), were applied to the chromatographic signals. In combination with jackknife cross-validation, Derringer's approach and TOPSIS demonstrated high similarity in finding the best (most polypotent), next to the best, next to the worst, and worst (least polypotent) extracts, while the SRD resulted in slightly different outcomes.Furthermore, a new method for identifying the chromatographic features that characterize the most polypotent extracts was proposed. This method is based on partial least square regression (PLS) and can be used in combination with HPTLC-chemical fingerprints to predict the desirability of new extracts. The resulting PLS models demonstrated high statistical performance with determination coefficients ranging from R2 = 0.885 in the case of Derringer's desirability, to 0.986 for TOPSIS. However, the PLS modeling of SRD values was not successful.

Alternative weighting schemes for fine‐tuned extended similarity indices

AbstractExtended similarity indices (i.e., generalization of pairwise similarity) have recently gained importance because of their simplicity, fast computation, and superiority in tasks like diversity picking. However, they operate with several meta parameters that should be optimized. Earlier, we extended the binary similarity indices to “discrete non‐binary” and “continuous” data; now we continue with introducing and comparing multiple weighting functions. As a case study, the similarity of CYP enzyme inhibitors (4016 molecules after curation) was characterized by their extended similarities, based on 2D descriptors, MACCS and Morgan fingerprints. A statistical workflow based on sum of ranking differences (SRD) and analysis of variance (ANOVA) was used for finding the optimal weight function(s). Overall, the best weighting function is the fraction (“frac”), which corresponds to the principle of parsimony. Optimal extended similarity indices were also found, and their differences are revealed across different data sets. We intend this work to be a guideline for users of extended similarity indices regarding the various weighting options available. Source code for the calculations is available at https://github.com/mqcomplab/MultipleComparisons.

Classification of colorectal primer carcinoma from normal colon with mid‐infrared spectra

AbstractIn this project, we used formalin‐fixed paraffin‐embedded (FFPE) tissue samples to measure thousands of spectra per tissue core with Fourier transform mid‐infrared spectroscopy using an FT‐IR imaging system. These cores varied between normal colon (NC) and colorectal primer carcinoma (CRC) tissues. We created a database to manage all the multivariate data obtained from the measurements. Then, we applied classifier algorithms to identify the tissue based on its yielded spectra. For classification, we used the random forest, a support vector machine, XGBoost, and linear discriminant analysis methods, as well as three deep neural networks. We compared two data manipulation techniques using these models and then applied filtering. In the end, we compared model performances via the sum of ranking differences (SRD).

Frequent Errors in Modeling by Machine Learning: A Prototype Case of Predicting the Timely Evolution of COVID-19 Pandemic

Background: The development and application of machine learning (ML) methods have become so fast that almost nobody can follow their developments in every detail. It is no wonder that numerous errors and inconsistencies in their usage have also spread with a similar speed independently from the tasks: regression and classification. This work summarizes frequent errors committed by certain authors with the aim of helping scientists to avoid them. Methods: The principle of parsimony governs the train of thought. Fair method comparison can be completed with multicriteria decision-making techniques, preferably by the sum of ranking differences (SRD). Its coupling with analysis of variance (ANOVA) decomposes the effects of several factors. Earlier findings are summarized in a review-like manner: the abuse of the correlation coefficient and proper practices for model discrimination are also outlined. Results: Using an illustrative example, the correct practice and the methodology are summarized as guidelines for model discrimination, and for minimizing the prediction errors. The following factors are all prerequisites for successful modeling: proper data preprocessing, statistical tests, suitable performance parameters, appropriate degrees of freedom, fair comparison of models, and outlier detection, just to name a few. A checklist is provided in a tutorial manner on how to present ML modeling properly. The advocated practices are reviewed shortly in the discussion. Conclusions: Many of the errors can easily be filtered out with careful reviewing. Every authors’ responsibility is to adhere to the rules of modeling and validation. A representative sampling of recent literature outlines correct practices and emphasizes that no error-free publication exists.

Audience selection for maximizing social influence

AbstractViral marketing campaigns target primarily those individuals who are central in social networks and hence have social influence. Marketing events, however, may attract diverse audience. Despite the importance of event marketing, the influence of heterogeneous target groups is not well understood yet. In this paper, we define the Audience Selection (AS) problem in which different sets of agents need to be evaluated and compared based on their social influence. A typical application of Audience selection is choosing locations for a series of marketing events. The Audience selection problem is different from the well-known Influence Maximization (IM) problem in two aspects. Firstly, it deals with sets rather than nodes. Secondly, the sets are diverse, composed by a mixture of influential and ordinary agents. Thus, Audience selection needs to assess the contribution of ordinary agents too, while IM only aims to find top spreaders. We provide a systemic test for ranking influence measures in the Audience Selection problem based on node sampling and on a novel statistical method, the Sum of Ranking Differences. Using a Linear Threshold diffusion model on two online social networks, we evaluate eight network measures of social influence. We demonstrate that the statistical assessment of these influence measures is remarkably different in the Audience Selection problem, when low-ranked individuals are present, from the IM problem, when we focus on the algorithm’s top choices exclusively.

Matrix factorization-based multi-objective ranking-What makes a good university?

Non-negative matrix factorization (NMF) efficiently reduces high dimensionality for many-objective ranking problems. In multi-objective optimization, as long as only three or four conflicting viewpoints are present, an optimal solution can be determined by finding the Pareto front. When the number of the objectives increases, the multi-objective problem evolves into a many-objective optimization task, where the Pareto front becomes oversaturated. The key idea is that NMF aggregates the objectives so that the Pareto front can be applied, while the Sum of Ranking Differences (SRD) method selects the objectives that have a detrimental effect on the aggregation, and validates the findings. The applicability of the method is illustrated by the ranking of 1176 universities based on 46 variables of the CWTS Leiden Ranking 2020 database. The performance of NMF is compared to principal component analysis (PCA) and sparse non-negative matrix factorization-based solutions. The results illustrate that PCA incorporates negatively correlated objectives into the same principal component. On the contrary, NMF only allows non-negative correlations, which enable the proper use of the Pareto front. With the combination of NMF and SRD, a non-biased ranking of the universities based on 46 criteria is established, where Harvard, Rockefeller and Stanford Universities are determined as the first three. To evaluate the ranking capabilities of the methods, measures based on Relative Entropy (RE) and Hypervolume (HV) are proposed. The results confirm that the sparse NMF method provides the most informative ranking. The results highlight that academic excellence can be improved by decreasing the proportion of unknown open-access publications and short distance collaborations. The proportion of gender indicators barely correlate with scientific impact. More authors, long-distance collaborations, publications that have more scientific impact and citations on average highly influence the university ranking in a positive direction.

Rapid identification of healthy Tegillarca granosa using laser-induced breakdown spectroscopy and fusion model

Abstract Objectives This study presents a method combining a one-class classifier and laser-induced breakdown spectrometry (LIBS) to quickly identify healthy Tegillarca granosa (T. granosa). Materials and Methods The sum of ranking differences (SRD) was used to fuse multiple anomaly detection metrics to build the one-class classifier, which was only trained with healthy T. granosa. The one-class classifier can identify healthy T. granosa to exclude non-healthy T. granosa. The proposed method calculated multiple anomaly detection metrics and standardized them to obtain a fusion matrix. Based on the fusion matrix, the samples were ranked by SRD and those ranked lowest and below the threshold were considered to be unhealthy. Results Multiple anomaly detection metrics were fused by the SRD algorithm and tested on each band, and the final fusion model achieved an accuracy rate of 98.46%, a sensitivity of 100%, and a specificity of 80%. The remaining three single classification models obtained the following results: the SVDD model achieved an accuracy rate of 87.69%, a sensitivity of 90%, and a specificity of 60%; the OCSVM model achieved an accuracy rate of 80%, a sensitivity of 76.67%, and a specificity of 60%; and the DD-SIMCA model achieved an accuracy rate of 95.38%, a sensitivity of 98.33%, and a specificity of 60%. Conclusions The experimental results showed that the proposed method achieved better results than the traditional one-class classification methods with a single metric. Therefore, the fusion method effectively improves the performance of traditional one-class classifiers when using LIBS to quickly identify healthy substances (healthy T. granosa).

Comparative Study of the Lipophilicity of Selected Anti-Androgenic and Blood Uric Acid Lowering Compounds.

This study aimed to evaluate the lipophilicity of a series substances lowering the concentration of uric acid in blood and anti-androgen drugs by thin-layer chromatography in reversed-phase systems (RP-TLC, RP-HPTLC) and computational methods. The chromatographic parameter of lipophilicity (RMW) of tested compounds was determined on three stationary phases, i.e., RP18F254, RP18WF254 and RP2F254, using ethanol-water, propan-2-ol-water and acetonitrile-water in various volume compositions as mobile phases. The chromatographic analysis led to determining the experimental value of the lipophilicity parameter for each of the tested compounds, including those for which the experimental value of the partition coefficient (logPexp) as a measure of lipophilicity is not well described in available databases, such as febuxostat, oxypurinol, ailanthone, abiraterone and teriflunomide. The chromatographic parameters of lipophilicity were compared with the logP values obtained with various software packages, such as AClogP, AlogPs, AlogP, MlogP, XlogP2, XlogP3, ACD/logP and logPKOWWIN. The obtained results indicate that, among selected chromatographic parameters of lipophilicity, both experimental and calculated logP values gave similar results, and these RP-TLC or RP-HPTLC systems can be successfully applied to estimate the lipophilicity of studied heterocyclic compounds belonging to two different pharmacological groups. This work also illustrates the similarity and difference existing between the tested compounds under study using the chemometric methods, such as principal component analysis (PCA) and cluster analysis (CA). In addition, a relatively new approach based on the sum of ranking differences (SRD) was used to compare the chromatographically obtained and theoretical lipophilicity descriptors of studied compounds.

Predicting percutaneous permeation for new succinimide derivatives by in vitro and in silico models

Percutaneous permeation of twenty-four newly synthesized succinimide derivatives was evaluated using parallel artificial membrane permeability assay (PAMPA) with 70% silicone oil and 30% isopropyl myristate. Different online tools were applied for in silico predicting of their skin permeability. According to the in silico estimation of the transdermal permeation, all compounds are expected to have relatively good ability to permeate the skin, at pH=6. However, for two compounds containing carboxylic groups, the concentration in the acceptor compartment was undetectable indicating limited permeation at pH=7.4. Statistically significant association was found between in silico predicted logKp values by the PreADMET and SwissADME online tools and the percutaneous permeability estimated from the experimental results using the artificial membranes (adj. r2 = 0.371, p = 0.00158 and adj. r2=0.232, p = 0.0135, respectively). The association between permeation through artificial membranes and the calculated logP data was also statistically significant. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) took into account in silico logKp and calculated logP data. The ranking of the lipophilicity and skin permeability parameters was conducted with sum of ranking differences (SRD) analysis which was validated. Based on the obtained results, it is predicted that lipophilicity is a pivotal physico-chemical parameter of the passive permeation of succinimide derivatives through hydrophobic barriers such as the skin.

Quantitative predictions from chemical read-across and their confidence measures

In silico modeling new approach methodologies (NAMs) are viewed as a promising starting point for filling the existing gaps in safety and ecosafety data. Read-across is one of the most widely used alternative tools for hazard assessment, aimed at filling data gaps. However, there are no systematic studies or recommendations on the measures to identify the quality of read-across predictions for the data points without any experimental response data. Recently, we have reported a new similarity-based read-across algorithm for the prediction of toxicity (biological activity in general) of untested compounds from structural analogues (the tool available from https://sites.google.com/jadavpuruniversity.in/dtc-lab-software/home). Three similarity estimation techniques such as, Euclidean distance-based similarity, Gaussian kernel function similarity, and Laplacian kernel function similarity are used in this algorithm. As the confidence of predictions for untested compounds is important information, we have addressed this issue here by consideration of several similarity and error – based criteria. The role of these measures in discriminating high and low residual query compounds is studied in three different approaches: (a) comparison of means of a measure for high and low residual groups; (b) development of classification models for absolute residuals to identify the contributing measures; (c) application of the sum of ranking differences (SRD) approach to identify the measures closer to the reference rank defined by the absolute residuals. Finally, the frequency of occurrences of different measures in the three approaches is compared. The results from three data sets with 10 divisions of source and target compounds in each case indicate that weighted standard deviation of the predicted response values appear to be the most deterministic feature for the reliability of predictions followed by different similarity-based features. The derived reliability measures will provide a greater confidence to the quality of quantitative predictions from the chemical read-across tool for new query compounds.

Multiobject Optimization of National Football League Drafts: Comparison of Teams and Experts

Predicting the success of National Football League drafts has always been an exciting issue for the teams, fans and even for scientists. Among the numerous approaches, one of the best techniques is to ask the opinion of sport experts, who have the knowledge and past experiences to rate the drafts of the teams. When asking a set of sport experts to evaluate the performances of teams, a multicriteria decision making problem arises unavoidably. The current paper uses the draft evaluations of the 32 NFL teams given by 18 experts: a novel multicriteria decision making tool has been applied: the sum of ranking differences (SRD). We introduce a quick and easy-to-follow approach on how to evaluate the performance of the teams and the experts at the same time. Our results on the 2021 NFL draft data indicate that Green Bay Packers has the most promising drafts for 2021, while the experts have been grouped into three distinct groups based on the distance to the hypothetical best evaluation. Even the coding options can be tailored according to the experts’ opinions. Statistically correct (pairwise or group) comparisons can be made using analysis of variance (ANOVA). A comparison to TOPSIS ranking revealed that SRD gives a more objective ranking due to the lack of predefined weights.

Repurposing FDA approved drugs as possible anti-SARS-CoV-2 medications using ligand-based computational approaches: sum of ranking difference-based model selection

The worldwide burden of coronavirus disease 2019 (COVID-19) is still unremittingly prevailing, with more than 440 million infections and over 5.9 million deaths documented so far since the SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) pandemic. The non-availability of treatment further aggravates the scenario, thereby demanding the exploration of pre-existing FDA-approved drugs for their effectiveness against COVID-19. The current research aims to identify potential anti-SARS-CoV-2 drugs using a computational approach and repurpose them if possible. In the present study, we have collected a set of 44 FDA-approved drugs of different classes from a previously published literature with their potential antiviral activity against COVID-19. We have employed both regression- and classification-based quantitative structure–activity relationship (QSAR) modeling to identify critical chemical features essential for anticoronaviral activity. Multiple models with the consensus algorithm were employed for the regression-based approach to improve the predictions. Additionally, we have employed a machine learning-based read-across approach using Read-Across-v3.1 available from https://sites.google.com/jadavpuruniversity.in/dtc-lab-software/home and linear discriminant analysis for the efficient prediction of potential drug candidate for COVID-19. Finally, the quantitative prediction ability of different modeling approaches was compared using the sum of ranking differences (SRD). Furthermore, we have predicted a true external set of 98 pharmaceuticals using the developed models for their probable anti-COVID activity and their prediction reliability was checked employing the “Prediction Reliability Indicator” tool available from https://dtclab.webs.com/software-tools. Though the present study does not target any protein of viral interaction, the modeling approaches developed can be helpful for identifying or screening potential anti-coronaviral drug candidates.Supplementary informationThe online version contains supplementary material available at 10.1007/s11224-022-01975-3.

Analysis and Consequences on Some Aggregation Functions of PRISM (Partial Risk Map) Risk Assessment Method

The PRISM (partial risk map) methodology is a novel risk assessment method developed as the combination of the failure mode and effect analysis and risk matrix risk assessment methods. Based on the concept of partial risks, three different aggregation functions are presented for assessing incident risks. Since the different aggregation functions give different properties to the obtained PRISM numbers and threshold surfaces (convex, concave, linear), the description of these properties is carried out. Similarity analyses based on the sum of ranking differences (SRD) method and rank correlation are performed and robustness tests are applied related to the changes of the assessment scale lengths. The PRISM method provides a solution for the systematically criticized problem of the FMEA, i.e., it is not able to deal with hidden risks behind the aggregated RPN number, while the method results in an expressive tool for risk management. Applying new aggregation functions, proactive assessment can be executed, and predictions can be given related to the incidents based on the nature of their hidden risk. The method can be suggested for safety science environments where human safety, environmental protection, sustainable production, etc., are highly required.

Comparative chemometric analysis, ranking and selection of lipophilicity parameters of 6-chloro-1,3,5-triazine derivatives with acyclic and cyclic substituents

In the present paper, the chemometric analysis, ranking and selection of the most suitable in silico lipophilicity parameters of eight alkyl and cycloalkyl s-triazine derivatives were carried out. The lipophilicity parameters were calculated using various computational approaches and computer programs. The conducted analysis is the basis for further studies aimed to define, compare and examine the influence of alkyl and cycloalkyl substituents, introduced in 6-chloro-1,3,5-triazine-2,4-diamine structure, on molecular lipophilicity and bioactivity. The chemometric methods used in the study are pattern recognition methods, such as hierarchical cluster analysis (HCA) and sum of ranking differences (SRD). The obtained ranking results indicate that the following in silico lipophilicity descriptors can be chosen as the most suitable for interpretation of lipophilicity of the studied series of s-triazine derivatives: AlogP, MlogP, WLOGP, logPKLOP and logPPHYS. The lipophilicity descriptor iLOGP was marked as the least suitable lipophilicity descriptor of the studied series of compounds. The ranking results were validated by 7-fold cross-validation approach and by comparison of ranks by random numbers (CRRN).

From Sampling to Analysis: How to Achieve the Best Sample Throughput via Sampling Optimization and Relevant Compound Analysis Using Sum of Ranking Differences Method?

The determination of an optimal volatile sampling procedure is always a key question in analytical chemistry. In this paper, we introduce the application of a novel non-parametric statistical method, the sum of ranking differences (SRD), for the quick and efficient determination of optimal sampling procedures. Different types of adsorbents (Porapak Q, HayeSep Q, and Carbotrap) and sampling times (1, 2, 4, and 6 h) were used for volatile collections of lettuce (Lactuca sativa) samples. SRD identified 6 h samplings as the optimal procedure. However, 1 or 4 h sampling with HayeSep Q and 2 h sampling with Carbotrap are still efficient enough if the aim is to reduce sampling time. Based on our results, SRD provides a novel way to not only highlight an optimal sampling procedure but also decrease evaluation time.

Effect of nitrate reduction and storage time on the antioxidative properties, biogenic amines and amino acid profile of dry fermented loins

SummaryThe aim of this work was to evaluate the effect of nitrate reduction and storage time on the content of amino acids and biogenic amines (BAs), total antioxidant capacity (TAC) and antioxidative properties of peptides isolated from dry fermented loins. The results showed that reducing the addition of nitrates increased the amount of BAs formed during storage of dry fermented loins. The lowest TAC value (tested by ABTS assay) was recorded for the sample with the highest nitrate addition (150 mg kg‐1) at beginning, while the highest value was noted for the sample without nitrate addition at 180 days of storage. The amino acid profile showed that dry fermented loin with the highest addition of nitrate was characterised by a significantly lower content of amino acids, which are precursors of key aroma compounds compared with loin samples with a lower amount of added sodium nitrate. The sum of ranking differences (SRD) indicated that loin sample with traditional addition of nitrate (150 mg kg‐1) after 120 days of storage was characterised by the lowest SRD result, which means that they are the closest to the assumed values, that is the lowest content of BAs, the highest antioxidant activity and amino acid patterns recommended by WHO/FAO/UNU Experts.

Improvement of Carrot Accelerated Solvent Extraction Efficacy Using Experimental Design and Chemometric Techniques

Human studies have demonstrated the multiple health benefits of fruits and vegetables. Due to its high fiber, mineral and antioxidant content, carrot is an ideal source for the development of nutraceuticals or functional ingredients. Current research assesses accelerated solvent extraction (ASE) traits which affect the antioxidant qualities of carrot extract using response surface methodology (RSM), hierarchical cluster analysis (HCA), and the sum of ranking differences (SRD). A mixture of organic solvents, acetone, and ethanol with or without the addition of 20% water was applied. The total carotenoid and polyphenol contents in extracts, as well as their scavenging activity and reducing power, were used as responses for the optimization of ASE extraction. RSM optimization, in the case of 20% water involvement, included 49% of acetone and 31% of ethanol (Opt1), while in the case of pure organic solvents, pure ethanol was the best choice (Opt2). The results of HCA clearly pointed out significant differences between the properties of extracts with or without water. SRD analysis confirmed ethanol to be optimal as well. RSM, HCA, and SRD analysis confirmed the same conclusion—water in the solvent mixture can significantly affect the extraction efficacy, and the optimal solvent for extracting antioxidants from carrot by ASE is pure ethanol.

Automatic food and beverage authentication and adulteration detection by classification hybrid fusion

AbstractA rising problem in the food industry is identifying the origin and/or purity of food products, and classification is often used for the identification. The process involves determining whether a food sample is similar to a collection of samples characterizing a known food product (is the food product a class member?). However, classification requires the analyst to face a myriad of complex decisions. With modern instrumentation, classification based on conventional data fusion processes increases the assortment of decisions. Typically, testing food products without data fusion involves (1) selection of an instrument or measuring device, (2) determining suitable measurement variables, for example, sensors or wavelengths for spectral data, (3) data preprocessing optimization, and (4) selection of a classification method followed by identifying the best tuning parameter setup for that classifier. If data fusion is desired, optimization of combined variations of (1)–(4) is required. This paper overviews a recent approach that simplifies data fusion decisions for food authentication and adulteration classification purposes. This unique self‐optimized fusion method avoids the confounding decisions by simultaneously evaluating any number of permutations of (1)–(3) in combination with a collection of non‐optimized classifiers based on respective tuning parameter windows for (4). Self‐optimization is obtained by using the sum of ranking differences (SRD) to form the final fused class membership decision for each new food test sample where the SRD was automatically optimized using a receiver operator characteristic (ROC) curve. The simple automatic SRD hybrid fusion/ROC curve process removes the myriad of subjective decisions imposed on the analyst and increases food classification reliability. Results are demonstrated with three datasets.

Extended similarity indices: the benefits of comparing more than two objects simultaneously. Part 1: Theory and characteristics\u2020

Quantification of the similarity of objects is a key concept in many areas of computational science. This includes cheminformatics, where molecular similarity is usually quantified based on binary fingerprints. While there is a wide selection of available molecular representations and similarity metrics, there were no previous efforts to extend the computational framework of similarity calculations to the simultaneous comparison of more than two objects (molecules) at the same time. The present study bridges this gap, by introducing a straightforward computational framework for comparing multiple objects at the same time and providing extended formulas for as many similarity metrics as possible. In the binary case (i.e. when comparing two molecules pairwise) these are naturally reduced to their well-known formulas. We provide a detailed analysis on the effects of various parameters on the similarity values calculated by the extended formulas. The extended similarity indices are entirely general and do not depend on the fingerprints used. Two types of variance analysis (ANOVA) help to understand the main features of the indices: (i) ANOVA of mean similarity indices; (ii) ANOVA of sum of ranking differences (SRD). Practical aspects and applications of the extended similarity indices are detailed in the accompanying paper: Miranda-Quintana et al. J Cheminform. 2021. https://doi.org/10.1186/s13321-021-00504-4. Python code for calculating the extended similarity metrics is freely available at: https://github.com/ramirandaq/MultipleComparisons.