Search

Information about the species composition of a forest is necessary for assessing biodiversity in a particular region and making economic decisions on the management of forest resources. Recognition of the species composition, according to the Earth’s remote sensing data, greatly simplifies the work and reduces time and labor costs in comparison with a traditional inventory of the forest, conducted through ground-based observations. This study analyzes the possibilities of tree species discrimination in coniferous–deciduous forests according to Sentinel-2 data using two automated recognition methods: random forest (RF) and generative topographic mapping (GTM). As remote sensing data, Sentinel-2 images of the Raifa section of Volga-Kama State Reserve in the Tatarstan Republic, Russia used: six images for the vegetation period of 2020. The analysis was carried out for the main forest-forming species. The training sample was created based on the cadastral data of the forest fund. The recognition quality was assessed using the F1-score, precision, recall, and accuracy metrics. The RF method showed a higher recognition accuracy. The accuracy of correct recognition by the RF method on the training sample reaches 0.987, F1-score = 0.976, on the control sample, accuracy = 0.764, F1-score = 0.709.

The flock structures produced by individuals, e.g., animals, self-organize and change their complexity over time. Although flock structures are often characterized by the spatial alignment of each element, this study focuses on their dynamic and hierarchical nature, temporal variations, and meta-structures. In hierarchical systems, sometimes, the upper structure is unchanged, whereas the lower components change constantly over time. Current clustering methods aim to capture the static and mono-layer features of complex patterning. To detect and track dynamic and hierarchical objects, a new clustering technique is required. Hence, in this study, we improve the generative topographic mapping (GTM) method to visualize such dynamic hierarchical structures as they continuously change over time. Using examples from our recent studies on the large-scale Boids model, we confirm that the newly developed method can capture the complex flocking objects as well as track the merging and collapsing events of objects.

The intrinsic nature of noisy and complex data sets is often concealed in low-dimensional structures embedded in a higher dimensional space. Number of methodologies have been developed to extract and represent such structures in the form of manifolds (i.e. geometric structures that locally resemble continuously deformable intervals of R-j1). Usually apriori knowledge of the manifold's intrinsic dimensionality is required. Additionally, their performance can often be hampered by the presence of a significant high-dimensional noise aligned along the low-dimensional core manifold. In real-world applications, the data can contain several low-dimensional structures of different dimensionalities. We propose a framework for dimensionality estimation and reconstruction of multiple noisy manifolds embedded in a noisy environment. To the best of our knowledge, this work represents the first attempt at detection and modelling of a set of coexisting general noisy manifolds by uniting two aspects of multi-manifold learning: the recovery and approximation of core noiseless manifolds and the construction of their probabilistic models. The easy-to-understand hyper-parameters can be manipulated to obtain an emerging picture of the multi-manifold structure of the data. We demonstrate the workings of the framework on two synthetic data sets, presenting challenging features for state-of-the-art techniques in Multi-Manifold learning. The first data set consists of multiple sampled noisy manifolds of different intrinsic dimensionalities, such as Mobius strip, toroid and spiral arm. The second one is a topologically complex set of three interlocked toroids. Given the absence of such unified methodologies in the literature, the comparison with existing techniques is organized along the two separate aspects of our approach mentioned above, namely manifold approximation and probabilistic modelling. The framework is then applied to a complex data set containing simulated gas volume particles from a particle simulation of a dwarf galaxy interacting with its host galaxy cluster. Detailed analysis of the recovered 1D and 2D manifolds can help us to understand the nature of Star Formation in such complex systems. (C) 2021 The Author(s). Published by Elsevier B.V.

This is a review article of Generative Topographic Mapping (GTM) – a non-linear dimensionality reduction technique producing generative 2D maps of high-dimensional vector spaces – and its specific applications in Drug Design (chemical space cartography, compound library design and analysis, virtual screening, pharmacological profiling, de novo drug design, conformational space & docking interaction cartography, etc.) Written by chemoinformaticians for potential users among medicinal chemists and biologists, the article purposely avoids all underlying mathematics. First, the GTM concept is intuitively explained, based on the strong analogies with the rather popular Self-Organizing Maps (SOMs), which are well established library analysis tools. GTM is basically a fuzzy-logics-based generalization of SOMs. The second part of the review, some of published GTM applications in drug design are briefly revisited.

Functioning of rotary machines is based on the rolling element of bearings, as the rolling element of bearings is the crucial component of rotary machines. The entire operation of rotating machines may terminate after the failure of rolling element of bearings. Hence, the failure of rotating machine is mainly dependent on rolling element of bearings, as it may break down an entire process. Thus, to avoid the sudden breakdown of rotary machines, it is essential to develop the diagnostics and prognostics methodology of rolling element of bearings. In the rolling element of bearings, the assessment of bearing degradation and fault diagnostics is essential to establish the methodology. Therefore, this article proposes a methodology to diagnose the fault of bearing and to assess bearing degradation. Envelope spectra and generative topographic mapping are used together in the methodology proposed. Selection of frequency band based on encompasses one or more resonance of spectrum of signal. Envelope spectrum is determined to pick up the peak of the characteristic fault frequencies of the bearing. Extraction of features from time and frequency domains is used in the generative topographic mapping. Health degradation index, an index termed as evolution of bearing degradation, is obtained from the classifier of generative topographic mapping. Experiments were conducted on the bearings to verify the proposed methodology. On interpreting the obtained results, it was found that the proficiency of proposed methodology is most appropriate for detecting the fault in bearing and tracking the degradation evolution in bearings.

Prediction of molecular properties plays a critical role towards rational drug design. In this study, the Molecular Topographic Map (MTM) is proposed, which is a two-dimensional (2D) map that can be used to represent a molecule. An MTM is generated from the atomic features set of a molecule using generative topographic mapping and is then used as input data for analyzing structure-property/activity relationships. In the visualization and classification of 20 amino acids, differences of the amino acids can be visually confirmed from and revealed by hierarchical clustering with a similarity matrix of their MTMs. The prediction of molecular properties was performed on the basis of convolutional neural networks using MTMs as input data. The performance of the predictive models using MTM was found to be equal to or better than that using Morgan fingerprint or MACCS keys. Furthermore, data augmentation of MTMs using mixup has improved the prediction performance. Since molecules converted to MTMs can be treated like 2D images, they can be easily used with existing neural networks for image recognition and related technologies. MTM can be effectively utilized to predict molecular properties of small molecules to aid drug discovery research.

This paper is devoted to the analysis of available experimental data and preparation of predictive models for binding affinity of molecules with respect to two nuclear receptors involved in endocrine disruption (ED): the oestrogen (ER) and the androgen (AR) receptors. The ED-relevant data were retrieved from multiple sources, including the CERAPP, CoMPARA, and the Tox21 projects as well as ChEMBL and PubChem databases. Data analysis performed with the help of generative topographic mapping revealed the problem of low agreement between experimental values from different sources. Collected data were used to train both classification models for ER and AR binding activities and regression models for relative binding affinity (RBA) and median inhibition concentration (IC50). These models displayed relatively poor performance in classification (sensitivities ER = 0.34, AR = 0.49) and in regression (determination coefficient r2 for the RBA and IC50 models in external validation varied from 0.44 to 0.76). Our analysis demonstrates that low models’ performance resulted from misinterpreted experimental endpoints or wrongly reported values, thus confirming the observations reported in CERAPP and CoMPARA studies. Developed models and collected data sets included of 6215 (ER) and 3789 (AR) unique compounds, which are freely available.

Summary One of the major objectives of seismic interpretation is to effectively predict the distribution of reservoir facies away from well control. With the advent of increasing number of meaningful seismic attributes, it is time consuming and laborious to analyze them through conventional analytical methods. Machine learning techniques analyze higher dimensional data points faster and effectively. Automated seismic facies classification techniques are increasingly becoming important in identifying the potential hydrocarbon bearing zone and favorable facies. Such facies classification techniques, or, automated clustering algorithms, help arrange similar seismic traces based on the waveform shape, amplitude, phase, frequency, and other relevant seismic attributes. The main objective of automated facies classification using machine learning techniques is to perform facies classification fast and efficiently using several relevant seismic attributes for mapping the facies distribution and effective identification of the sweet spots. The automated clustering algorithms fall into two categories – supervised and unsupervised algorithms. Unsupervised machine learning algorithms are purely data driven and help in recognizing and classifying the patterns from a dataset without any a priori information. A posteriori information such as well data, is integrated into the results for recognizing the facies classification and calibrating the interpretation. Unsupervised learning methods also help to highlight subtle stratigraphic features that might otherwise be unnoticed using conventional analytical methods. In this study, we adopted a recent unsupervised classification technique called, generative topographic mapping (GTM). We applied this technique to a dataset from Offshore Nova Scotia, to extract the natural clusters from the seismic data for facies classification. Using the GTM technique applied to seismic data, we were able to map the distribution of different facies and potential sweet spots in the study area.

In the framework of REACH (Registration Evaluation Authorization and restriction of Chemicals) regulation, industries have generated and reported a huge amount of (eco)toxicological data on substance produced or imported in Europe. The registration procedure initiated the creation of a large REACH database of well defined (eco)toxicological properties. Here, the data distribution in the REACH chemical space was analyzed with the help of the Generative Topographic Mapping (GTM) approach. GTM generates 2-dimensional maps on which each compound is represented as a data point. The 3rd dimension can be used in order to display a distribution of the given (eco)toxicological property, which can further be used for property assessment of new compounds projected on the map. We report the "Universal REACH map" which accommodates 11 endpoints, covering environmental fate and (eco)toxicological properties. This map demonstrates acceptable predictive performance: in cross-validation, balanced accuracy ranges from 0.60 to 0.78. The 11 endpoints profile has been computed for each REACH-registered substance. Some concerns related to acute aquatic toxicity have been identified, whereas for environmental fate and human health endpoints the amount of compounds predicted as of concern was much smaller. It has been demonstrated that superposition of several class landscapes allows to select the zones in the chemical space populated by compounds with a given (eco)toxicological profile.

International audience; Here we report a new predictive model for autoignition temperature (AIT), an important physical parameter widely used to assess potential safety hazards of combustible materials. Available structure -AIT data extracted from different sources were critically analysed. Support vector regression (SVR) models on different data subsets were built in order to identify a reliable compound set on which a realistic model could be built. This led to a selection of the dataset containing 875 compounds annotated with AIT values. The thereupon-based SVR model performs reasonably well in cross-validation with the determination coefficient r 2 = 0.77 and mean absolute error MAE = 37.8°C. External validation on 20 industrial compounds missing in the training set confirmed its good predic-tive power (MAE = 28.7°C). ARTICLE HISTORY

Discovery of drugs against newly emerged pathogenic agents like the SARS-CoV-2 coronavirus (CoV) must be based on previous research against related species. Scientists need to get acquainted with and develop a global oversight over so-far tested molecules. Chemography (herein used Generative Topographic Mapping, in particular) places structures on a human-readable 2D map (obtained by dimensionality reduction of the chemical space of molecular descriptors) and is thus well suited for such an audit. The goal is to map medicinal chemistry efforts so far targeted against CoVs. This includes comparing libraries tested against various virus species/genera, predicting their polypharmacological profiles and highlighting often encountered chemotypes. Maps are challenged to provide predictive activity landscapes against viral proteins. Definition of “anti-CoV” map zones led to selection of therein residing 380 potential anti-CoV agents, out of a vast pool of 800M organic compounds.

DNA-Encoded Library (DEL) technology has emerged as an alternative method for bioactive molecules discovery in medicinal chemistry. It enables the simple synthesis and screening of compound libraries of enormous size. Even though it gains more and more popularity each day, there are almost no reports of chemoinformatics analysis of DEL chemical space. Therefore, in this project, we aimed to generate and analyze the ultra-large chemical space of DEL. Around 2500 DELs were designed using commercially available building blocks resulting in 2,5B DEL compounds that were compared to biologically relevant compounds from ChEMBL using Generative Topographic Mapping. This allowed to choose several optimal DELs covering the chemical space of ChEMBL to the highest extent and thus containing the maximum possible percentage of biologically relevant chemotypes. Different combinations of DELs were also analyzed to identify a set of mutually complementary libraries allowing to attain even higher coverage of ChEMBL than it is possible with one single DEL.

Generative topographic mapping (GTM) approach is used to visualize the chemical space of organic molecules (L) with respect to binding a wide range of 41 different metal cations (M) and also to build predictive models for stability constants (logK) of 1:1 (M:L) complexes using “density maps,” “activity landscapes,” and “selectivity landscapes” techniques. A two-dimensional map describing the entire set of 2962 metal binders reveals the selectivity and promiscuity zones with respect to individual metals or groups of metals with similar chemical properties (lanthanides, transition metals, etc). The GTM-based global (for entire set) and local (for selected subsets) models demonstrate a good predictive performance in the cross-validation procedure. It is also shown that the data likelihood could be used as a definition of the applicability domain of GTM-based models. Thus, the GTM approach represents an efficient tool for the predictive cartography of metal binders, which can both visualize their chemical space and predict the affinity profile of metals for new ligands.

Generative topographic mapping (GTM) has been used to visualize and analyze the chemical space of antimalarial compounds as well as to build predictive models linking structure of molecules with their antimalarial activity. For this, a database, including ~3000 molecules tested in one or several of 17 anti-Plasmodium activity assessment protocols, has been compiled by assembling experimental data from in-house and ChEMBL databases. GTM classification models built on subsets corresponding to individual bioassays perform similarly to the earlier reported SVM models. Zones preferentially populated by active and inactive molecules, respectively, clearly emerge in the class landscapes supported by the GTM model. Their analysis resulted in identification of privileged structural motifs of potential antimalarial compounds. Projection of marketed antimalarial drugs on this map allowed us to delineate several areas in the chemical space corresponding to different mechanisms of antimalarial activity. This helped us to make a suggestion about the mode of action of the molecules populating these zones.

In this paper, a new model for voice morphing is proposed. The spectral characteristics of a source speaker’s speech have been transferred to speech as it was spoken by another designated target speaker. The proposed model performs a phoneme segmentation of the voice signal and then transforms the spectral characteristics of each segment using a Linear Prediction model. The spectral features extracted using the Linear Prediction Coding (LPC) technique are aligned using the Dynamic Time Wrapping (DTW). The Generative Topographic Mapping (GTM) method was used for modeling the LPC features. Then, the transformation is achieved using the Gaussian Mixture Model (GMM). The transformed code-books are finally converted to prediction coefficients, and the excitation signal is filtered in order to synthesis the speech. A correlation test is performed between the source, and target signals showed a high correlation. The results reveal that the proposed model is promising in terms of recognizing full sentences in addition to individual words.

International audience; Generative topographic mapping was used to investigate the possibility to diversify the in-house compounds collection of Boehringer Ingelheim (BI). For this purpose, a 2D map covering the relevant chemical space was trained, and the BI compound library was compared to the Aldrich-Market Select (AMS) database of more than 8M purchasable compounds. In order to discover new (sub)structures, the “AutoZoom” tool was developed and applied in order to analyze chemotypes of molecules residing in heavily populated zones of a map and to extract the corresponding maximum common substructures. A set of 401K new structures from the AMS database was retrieved and checked for drug-likeness and biological activity.

Following previous efforts to render the Conformational Space (CS) of flexible compounds by Generative Topographic Mapping (GTM), this polyvalent mapping technique is here adapted to the docking problem. Contact fingerprints (CF) characterize ligands from the perspective of the binding site by monitoring protein atoms that are &ldquo, touched&rdquo, by those of the ligand. A &ldquo, Contact&rdquo, (CF) map was built by GTM-driven dimensionality reduction of the CF vector space. Alternatively, a &ldquo, Hybrid&rdquo, (Hy) map used a composite descriptor of CFs concatenated with ligand fragment descriptors. These maps indirectly represent the active site and integrate the binding information of multiple ligands. The concept is illustrated by a docking study into the ATP-binding site of CDK2, using the S4MPLE program to generate thousands of poses for each ligand. Both maps were challenged to (1) Discriminate native from non-native ligand poses, e.g., create RMSD-landscapes &ldquo, colored&rdquo, by the conformer ensemble of ligands of known binding modes in order to highlight &ldquo, native&rdquo, map zones (poses with RMSD to PDB structures &lt, 2&Aring, ). Then, projection of poses of other ligands on such landscapes might serve to predict those falling in native zones as being well-docked. (2) Distinguish ligands&ndash, characterized by their ensemble of conformers&ndash, by their potency, e.g., testing the hypotheses whether zones privileged by potent binders are clearly separated from the ones preferred by decoys on the maps. Hybrid maps were better in both challenges and outperformed the classical energy and individual contact satisfaction scores in discriminating ligands by potency. Moreover, the intuitive visualization and analysis of docking CS may, as already mentioned, have several applications&ndash, from highlighting of key contacts to monitoring docking calculation convergence.

Here, we report the data visualization, analysis and modeling for a large set of 4830 S(N)2 reactions the rate constant of which (logk) was measured at different experimental conditions (solvent, temperature). The reactions were encoded by one single molecular graph - Condensed Graph of Reactions, which allowed us to use conventional chemoinformatics techniques developed for individual molecules. Thus, Matched Reaction Pairs approach was suggested and used for the analyses of substituents effects on the substrates and nucleophiles reactivity. The data were visualized with the help of the Generative Topographic Mapping approach. Consensus Support Vector Regression (SVR) model for the rate constant was prepared. Unbiased estimation of the model's performance was made in cross-validation on reactions measured on unique structural transformations. The model's performance in cross-validation (RMSE=0.61 logk units) and on the external test set (RMSE=0.80) is close to the noise in data. Performances of the local models obtained for selected subsets of reactions proceeding in particular solvents or with particular type of nucleophiles were similar to that of the model built on the entire set. Finally, four different definitions of model's applicability domains for reactions were examined.

Recent outbreaks of dangerous viral infections, such as Ebola virus disease, Zika fever, etc., are forcing the search for new antiviral compounds. Preferably, such compounds should possess broad-spectrum antiviral activity, as the development of drugs for the treatment of dozens of viral infections lacking specific treatment would require significant resources. Antiviral activity data present in public resources are very sparse and further investigation of structure-activity relationships is necessary. One of the strategies could be the investigation of chemical space around known active compounds and assessment of activity against closely related viruses in order to fill in the antiviral activity matrix. Here we present an investigation of antiviral activity using universal maps built with generative topographic mapping (GTM) algorithm. The GTM-based maps were used to find commercially available compounds in close proximity to already known compounds with anti-flaviviral and anti-enteroviral activities. Selected compounds were then assessed in cell-based assays against tick-borne encephalitis virus (TBEV) and a panel of enteroviruses. This approach allowed us to identify 23 new compounds showing anti-TBEV activity with EC50 values in micromolar and submicromolar range.

Background Principal component analysis (PCA) is a standard method to correct for population stratification in ancestry-specific genome-wide association studies (GWASs) and is used to cluster individuals by ancestry. Using the 1000 genomes project data, we examine how non-linear dimensionality reduction methods such as t-distributed stochastic neighbor embedding (t-SNE) or generative topographic mapping (GTM) can be used to provide improved ancestry maps by accounting for a higher percentage of explained variance in ancestry, and how they can help to estimate the number of principal components necessary to account for population stratification. GTM generates posterior probabilities of class membership which can be used to assess the probability of an individual to belong to a given population - as opposed to t-SNE, GTM can be used for both clustering and classification. Results PCA only partially identifies population clusters and does not separate most populations within a given continent, such as Japanese and Han Chinese in East Asia, or Mende and Yoruba in Africa. t-SNE and GTM, taking into account more data variance, can identify more fine-grained population clusters. GTM can be used to build probabilistic classification models, and is as efficient as support vector machine (SVM) for classifying 1000 Genomes Project populations. Conclusion The main interest of probabilistic GTM maps is to attain two objectives with only one map: provide a better visualization that separates populations efficiently, and infer genetic ancestry for individuals or populations. This paper is a first application of GTM for ancestry classification models. Our code (https://github.com/hagax8/ancestry_viz) and interactive visualizations (https://lovingscience.com/ancestries) are available online. Electronic supplementary material The online version of this article (10.1186/s12859-019-2680-1) contains supplementary material, which is available to authorized users.

The previously reported procedure to generate "universal" Generative Topographic Maps (GTMs) of the drug-like chemical space is in practice a multi-task learning process, in which both operational GTM parameters (example: map grid size) and hyperparameters (key example: the molecular descriptor space to be used) are being chosen by an evolutionary process in order to fit/select "universal" GTM manifolds. After selection (a one-time task aimed at optimizing the compromise in terms of neighborhood behavior compliance, over a large pool of various biological targets), for any further use the manifolds are ready to provide "fit-free" predictive models. Using any structure-activity set-irrespectively whether the associated target served at map fitting stage or not-the generation or "coloring" a property landscape enables predicting the property for any external molecule, with zero additional fitable parameters involved. While previous works have signaled the excellent behavior of such models in aggressive three-fold cross-validation assessments of their predictive power, the present work wished to explore their behavior in Virtual Screening (VS), here simulated on hand of external DUD ligand and decoy series that are fully disjoint from the ChEMBL-extracted landscape coloring sets. Beyond the rather robust results of the universal GTM manifolds in this challenge, it could be shown that the descriptor spaces selected by the evolutionary multi-task learner were intrinsically able to serve as an excellent support for many other VS procedures, starting from parameter-free similarity searching, to local (target-specific) GTM models, to parameter-rich, nonlinear Random Forest and Neural Network approaches.

The need for predictive capabilities greater than 95% with very limited false alarms are demanding requirements for reliable disruption prediction systems in tokamaks such as JET or, in the near future, ITER. The prediction of an upcoming disruption must be provided sufficiently in advance in order to apply effective disruption avoidance or mitigation actions to prevent the machine from being damaged. In this paper, following the typical machine learning workflow, a generative topographic mapping (GTM) of the operational space of JET has been built using a set of disrupted and regularly terminated discharges. In order to build the predictive model, a suitable set of dimensionless, machine-independent, physics-based features have been synthesized, which make use of 1D plasma profile information, rather than simple zero-D time series. The use of such predicting features, together with the power of the GTM in fitting the model to the data, obtains, in an unsupervised way, a 2D map of the multi-dimensional parameter space of JET, where it is possible to identify a boundary separating the region free from disruption from the disruption region. In addition to helping in operational boundaries studies, the GTM map can also be used for disruption prediction exploiting the potential of the developed GTM toolbox to monitor the discharge dynamics. Following the trajectory of a discharge on the map throughout the different regions, an alarm is triggered depending on the disruption risk of these regions. The proposed approach to predict disruptions has been evaluated on a training and an independent test set and achieves very good performance with only one tardive detection and a limited number of false detections. The warning times are suitable for avoidance purposes and, more important, the detections are consistent with physical causes and mechanisms that destabilize the plasma leading to disruptions.

This work describes a procedure to build generative topographic maps (GTM) as 2D representation of the conformational space (CS) of dipeptides. GTMs with excellent propensities to support highly predictive landscapes of various conformational properties were reported for three dipeptides (AA, KE and KR). CS monitoring via GTMproceeds through the projection of conformer ensembles on the map, producing cumulated responsibility (CR) vectors characteristic of the CS areas covered by the ensemble. Overlap of the CS areas visited by two distinct simulations can be expressed by the Tanimoto coefficient Tc of the associated CRs. This idea was used to monitor the reproducibility of the stochastic evolutionary conformer generation process implemented in S4MPLE. It could be shown that conformers produced by

In this work has been implemented the manifold grand tour with a GTM structureas a way to improve the intuitiveness of the visualization of the GTM manifold. It is done travelling across each point of the GTM structure and optimizing the discrimination of the classes.

This paper aims to present a novel concept roadmap-the patent roadmap-and suggest an advanced patent roadmapping process, based on the Generative Topographic Mapping (GTM) and Bass diffusion model. The process for patent roadmapping is composed of two modules: Developing the GTM-based patent map and determining the appearance time of the emerging patent through Bass model. The result of this research is meaningful knowledge from analyzing a vast store of patent data with quantitative methods and automated tools. It can serve as an effective patent planning tool, and proposes a strategic Research and Business Development (R&BD) for both firms and governments.

In this paper, we study fundamental properties of the Self-Organizing Map (SOM) and the Generative Topographic Mapping (GTM), ramifications of the initialization of the algorithms and properties of the algorithms in the presence of missing data. We show that the commonly used principal component analysis (PCA) initialization of the GTM does not guarantee good learning results with high-dimensional data. Initializing the GTM with the SOM is shown to yield improvements in self-organization with three high-dimensional data sets: commonly used MNIST and ISOLET data sets and epigenomic ENCODE data set. We also propose a revision of handling missing data to the batch SOM algorithm called the Imputation SOM and show that the new algorithm is more robust in the presence of missing data. We benchmark the performance of the topographic mappings in the missing value imputation task and conclude that there are better methods for this particular task. Finally, we announce a revised version of the SOM Toolbox for Matlab with added GTM functionality.

The analysis of structure–activity relationships (SARs) becomes rather challenging when large and heterogeneous compound data sets are studied. In such cases, many different compounds and their activities need to be compared, which quickly goes beyond the capacity of subjective assessments. For a comprehensive large-scale exploration of SARs, computational analysis and visualization methods are required. Herein, we introduce a two-layered SAR visualization scheme specifically designed for increasingly large compound data sets. The approach combines a new compound pair-based variant of generative topographic mapping (GTM), a machine learning approach for nonlinear mapping, with chemical space networks (CSNs). The GTM component provides a global view of the activity landscapes of large compound data sets, in which informative local SAR environments are identified, augmented by a numerical SAR scoring scheme. Prioritized local SAR regions are then projected into CSNs that resolve these regions at the level of individual compounds and their relationships. Analysis of CSNs makes it possible to distinguish between regions having different SAR characteristics and select compound subsets that are rich in SAR information.

Identification of "privileged structural motifs" associated with specific target families is of particular importance for designing novel bioactive compounds. Here, we demonstrate that they can be extracted from a data distribution represented on a two-dimensional map obtained by Generative Topographic Mapping (GTM). In GTM, structurally related molecules are grouped together on the map. Zones of the map preferentially populated by target-specific compounds were delineated, which helped to capture common substructures on the basis of which these compounds were grouped together by GTM. Such privileged structural motifs were identified across three major target superfamilies including proteases, kinases, and G protein coupled receptors. Traditionally, the search for privileged structural motifs focused on scaffolds, whereas motifs were detected here without prior knowledge of compound classification in GTMs. This alternative way of navigating medicinal chemistry space further extends the classical, scaffold-centric approach. Importantly, detected motifs might also comprise fuzzy sets of similar scaffolds, pharmacophore-like patterns, or, by contrast, well-defined scaffolds with specific substituent patterns.

Many drug discovery projects rely on commercial compounds to discover active leads. However, current commercial libraries, with mostly synthetic compounds, access a small fraction of the possible chemical diversity. Natural products, in contrast, possess a vast structural diversity and have proven to be an outstanding source of new drugs. Several chemoinformatic analyses of natural products have demonstrated their diversity and structural complexity. However, to our knowledge, the scaffold content and structural diversity of fungal secondary metabolites have never been studied. Herein, the scaffold diversity of 223 fungal metabolites was measured and compared to the diversity of approved drugs and commercial libraries for HTS containing natural, synthetic, and semi-synthetic compounds. In addition, the global diversity of the fungal isolates was assessed and compared to other reference data sets using Consensus Diversity Plots, a chemoinformatic tool recently developed. It was concluded that fungal secondary metabolites are cyclic systems with few ramifications and more diverse than the commercial libraries with natural products and semi-synthetic compounds. The fungal metabolites data set was one of the most structurally diverse, containing a large proportion of different and unique scaffolds not found in the other compound data sets including ChEMBL. Therefore, fungal metabolites offer a rich source of molecules suited for identifying diverse candidates for drug discovery.

© 2017, Springer International Publishing AG. Generative topographic mapping (GTM) approach is used to visualize the chemical space of organic molecules (L) with respect to binding a wide range of 41 different metal cations (M) and also to b uild predictive models for stability constants (logK) of 1:1 (M:L) complexes using “density maps,” “activity landscapes,” and “selectivity landscapes” techniques. A two-dimensional map describing the entire set of 2962 metal binders reveals the selectivity and promiscuity zones with respect to individual metals or groups of metals with similar chemical properties (lanthanides, transition metals, etc). The GTM-based global (for entire set) and local (for selected subsets) models demonstrate a good predictive performance in the cross-validation procedure. It is also shown that the data likelihood could be used as a definition of the applicability domain of GTM-based models. Thus, the GTM approach represents an efficient tool for the predictive cartography of metal binders, which can both visualize their chemical space and predict the affinity profile of metals for new ligands.

We describe SILIRID (Simple Ligand–Receptor Interaction Descriptor), a novel fixed size descriptor characterizing protein–ligand interactions. SILIRID can be obtained from the binary interaction fingerprints (IFPs) by summing up the bits corresponding to identical amino acids. This results in a vector of 168 integer numbers corresponding to the product of the number of entries (20 amino acids and one cofactor) and 8 interaction types per amino acid (hydrophobic, aromatic face to face, aromatic edge to face, H-bond donated by the protein, H-bond donated by the ligand, ionic bond with protein cation and protein anion, and interaction with metal ion). Efficiency of SILIRID to distinguish different protein binding sites has been examined in similarity search in sc-PDB database, a druggable portion of the Protein Data Bank, using various protein–ligand complexes as queries. The performance of retrieval of structurally and evolutionary related classes of proteins was comparable to that of state-of-the-art approaches (ROC AUC≈0.91). SILIRID can efficiently be used to visualize chemogenomic space covered by sc-PDB using Generative Topographic Mapping (GTM): sc-PDB SILIRID data form clusters corresponding to different protein types.

The visualization and characterization of protein pockets is the starting point for many structure-based drug design projects. The size and shape of protein pockets dictate 3D geometry of ligands that can strongly inhibit the following biological events. Thus, a minimal requirement for inhibition is that a molecule sterically binds the active site with some allowance for induced fit. Methods for direct display of active sites in a protein have become prevalent in recent years. In this study, a new mapping method, generative topographic mapping, is investigated to describe the 3D surface of protein pocket. The β2 receptor protein is used as a benchmark. By mapping the molecular surface points and assigning the associated molecular electrostatic potential (MEP) values, the original 3D structure of the active site is well reproduced by the 2D latent map in generative topographic mapping. The distributions of MEP values of two 2D latent maps derived from the inhibitor and the β2 receptor protein are well complemented. Using three-way partial least squares modeling, a predictive model linking the inhibitory activity and their MEP values can be constructed, which was not feasible in the previous spherical self-organizing map studies. The resulting regression coefficient matrix of the three-way partial least squares model has many insights for understanding the structural requirements for β2 inhibitory activity. Copyright © 2014 John Wiley & Sons, Ltd.

Generative Topographic Mapping (GTM) is a nonlinear latent variable model introduced as a data visualization technique by Bishop et al. In this paper, we focus on variational Bayesian inference in GTM. Variational Bayesian GTM, first proposed by Olier et al., uses a single regularization term and regularization parameter to avoid overfitting and therefore cannot be used to control the degree of regularization locally. To overcome this problem, we propose variational Bayesian inference with Automatic Relevance Determination (ARD) hierarchical prior for use with GTM. The proposed model uses multiple regularization parameters and therefore can be used to control the degree of regularization in local areas of data space individually. Several experiments show that GTM that we propose provides better visualization than conventional GTM approaches.

As the intense competition for the international standardization of technology has increased, many companies are concentrating their capabilities on securing essential patents that claim one or more inventions required to practice a given industry standard; however, despite the importance of developing essential patents, the approaches to exploring promising essential patent: have some limitations in terms of methodology and data. As a remedy, this article proposes a method that derives an essential patent through Generative Topographic Mapping (GTM)-based standard and patent maps. The suggested approach involves a systematic process that identifies vacuums on a standard map in a specific technology field and enables analysts to find candidate for promising essential patents instead of relying on the experts. By applying the proposed methodology, this research discovered the vacuums in an industrial standard document about fuel cell technology as well as the candidates of essential patents in thi...

The generative topographic mapping (GTM) approach has been used both to build predictive models linking chemical structure of molecules and their ability to bind some membrane transport proteins (transporters) and to visualize a chemical space of transporters’ binders on two-dimensional maps. For this purpose, experimental data on 2958 molecules active against up to 11 transporters have been used. It has been shown that GTM-based classification (active/inactive) models display reasonable predictive performance, comparable with that of such popular machine-learning methods as Random Forest, SVM, or k-NN. Moreover, GTM offers its own models applicability domain definition which may significantly improve the models performance. GTM maps themselves represent an interesting tool of the chemical space analysis of the transporters’ ligands. Thus, with the help of class landscapes, they identify distinct zones populated by active or inactive molecules with respect to a given transporter. As demonstrated in this paper, the superposition of class landscapes describing different activities delineates the areas mostly populated by the compounds of desired pharmacological profile.

Curation, standardization and data fusion of the antiviral information present in the ChEMBL public database led to the definition of a robust data set, providing an association of antiviral compounds to seven broadly defined antiviral activity classes. Generative topographic mapping (GTM) subjected to evolutionary tuning was then used to produce maps of the antiviral chemical space, providing an optimal separation of compound families associated with the different antiviral classes. The ability to pinpoint the specific spots occupied (responsibility patterns) on a map by various classes of antiviral compounds opened the way for a GTM-supported search for privileged structural motifs, typical for each antiviral class. The privileged locations of antiviral classes were analyzed in order to highlight underlying privileged common structural motifs. Unlike in classical medicinal chemistry, where privileged structures are, almost always, predefined scaffolds, privileged structural motif detection based on GTM responsibility patterns has the decisive advantage of being able to automatically capture the nature ("resolution detail"-scaffold, detailed substructure, pharmacophore pattern, etc.) of the relevant structural motifs. Responsibility patterns were found to represent underlying structural motifs of various natures-from very fuzzy (groups of various "interchangeable" similar scaffolds), to the classical scenario in medicinal chemistry (underlying motif actually being the scaffold), to very precisely defined motifs (specifically substituted scaffolds).

© 2016, Springer Science+Business Media New York.The generative topographic mapping (GTM) approach has been used both to build predictive models linking chemical structure of molecules and their ability to bind some membrane transport proteins (transporters) and to visualize a chemical space of transporters’ binders on two-dimensional maps. For this purpose, experimental data on 2958 molecules active against up to 11 transporters have been used. It has been shown that GTM-based classification (active/inactive) models display reasonable predictive performance, comparable with that of such popular machine-learning methods as Random Forest, SVM, or k-NN. Moreover, GTM offers its own models applicability domain definition which may significantly improve the models performance. GTM maps themselves represent an interesting tool of the chemical space analysis of the transporters’ ligands. Thus, with the help of class landscapes, they identify distinct zones populated by active or inactive molecules with respect to a given transporter. As demonstrated in this paper, the superposition of class landscapes describing different activities delineates the areas mostly populated by the compounds of desired pharmacological profile.

A Self Organizing Map (SOM) projects high-dimensional feature vectors onto a low-dimensional space. If an appropriate feature vector is chosen, this ability may be used for measuring and adjusting different levels of diversity in the selection of models for building ensembles. In this paper, we present the results of using a SOM for selecting suitable models in ensembles used for long-term time series prediction. The temporal behavior of the predictors is represented by feature vectors built with a sequence of the errors achieved in each prediction step. Each neuron in the map represents a cluster of models with similar accuracy; the adjustment of diversity between models is achieved by measuring the distance between neurons on the map. Our experiments showed that this strategy generated ensembles with an appropriate level of diversity among their components, obtaining a better performance than just using a unique model.

Generative Topographic Mapping (GTM) is an important technique for dimension reduction which has been successfully applied to many fields. However the usual Expectation-Maximization (EM) approach to GTM can easily get stuck in local minima and so we introduce a Deterministic Annealing (DA) approach to GTM which is more robust and less sensitive to initial conditions so we do not need to use many initial values to find good solutions. DA has been very successful in clustering, hidden Markov Models and Multidimensional Scaling but typically uses a fixed cooling schemes to control the temperature of the system. We propose a new cooling scheme which can adaptively adjust the choice of temperature in the middle of process to find better solutions. Our experimental measurements suggest that deterministic annealing improves the quality of GTM solutions.

General finite mixture models are powerful tools for the density-based grouping of multivariate i.i.d. data, but they lack data visualization capabilities, which reduces their practical applicability to real-world problems. Generative topographic mapping (GTM) was originally formulated as a constrained mixture of distributions in order to provide simultaneous visualization and clustering of multivariate data. In its inception, the adaptive parameters were determined by maximum likelihood (ML), using the expectation-maximization (EM) algorithm. The original GTM is, therefore, prone to data overfitting unless a regularization mechanism is included. In this paper, we define an alternative variational formulation of GTM that provides a full Bayesian treatment to a Gaussian process (GP)-based variation of the model. The generalization capabilities of the proposed Variational Bayesian GTM are assessed in some detail and compared with those of alternative GTM regularization approaches in terms of test log-likelihood, using several artificial and real datasets.

© 2015 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim. In this paper we demonstrate that Generative Topographic Mapping (GTM), a machine learning method traditionally used for data visualisation, can be efficiently applied to QSAR modelling using probability distribution functions (PDF) computed in the latent 2-dimensional space. Several different scenarios of the activity assessment were considered: (i) the "activity landscape" approach based on direct use of PDF, (ii) QSAR models involving GTM-generated on descriptors derived from PDF, and, (iii) the k-Nearest Neighbours approach in 2D latent space. Benchmarking calculations were performed on five different datasets: stability constants of metal cations Ca2+, Gd3+ and Lu3+ complexes with organic ligands in water, aqueous solubility and activity of thrombin inhibitors. It has been shown that the performance of GTM-based regression models is similar to that obtained with some popular machine-learning methods (random forest, k-NN, M5P regression tree and PLS) and ISIDA fragment descriptors. By comparing GTM activity landscapes built both on predicted and experimental activities, we may visually assess the model's performance and identify the areas in the chemical space corresponding to reliable predictions. The applicability domain used in this work is based on data likelihood. Its application has significantly improved the model performances for 4 out of 5 datasets.

In large-scale tokamaks disruptions have the potential to create serious damage to the facility. Hence disruptions must be avoided, but, when a disruption is unavoidable, minimizing its severity is mandatory. A reliable detection of a disruptive event is required to trigger proper mitigation actions. To this purpose machine learning methods have been widely studied to design disruption prediction systems at ASDEX Upgrade. The training phase of the proposed approaches is based on the availability of disrupted and non-disrupted discharges. In literature disruptive configurations were assumed appearing into the last 45 ms of each disruption. Even if the achieved results in terms of correct predictions were good, it has to be highlighted that the choice of such a fixed temporal window might have limited the prediction performance. In fact, it generates confusing information in cases of disruptions with disruptive phase different from 45 ms. The assessment of a specific disruptive phase for each disruptive discharge represents a relevant issue in understanding the disruptive events. In this paper, the Mahalanobis distance is applied to define a specific disruptive phase for each disruption, and a logistic regressor has been trained as disruption predictor. The results show that enhancements on the achieved performance on disruption prediction are possible by defining a specific disruptive phase for each disruption.

Heterogeneous and incomplete datasets are common in many real-world visualisation applications. The probabilistic nature of the Generative Topographic Mapping (GTM), which was originally developed for complete continuous data, can be extended to model heterogeneous (i.e. containing both continuous and discrete values) and missing data. This paper describes and assesses the resulting model on both synthetic and real-world heterogeneous data with missing values.

In this thesis we focus on prototype-based learning techniques, namely three unsuper- vised techniques: generative topographic mapping (GTM), neural gas (NG) and affinity propagation (AP), and two supervised techniques: generalized learning vector quantiza- tion (GLVQ) and robust soft learning vector quantization (RSLVQ). We extend their abilities with respect to the following central aspects: • Applicability on dissimilarity data: Due to the increased complexity of data, in many cases data are only available in form of (dis)similarities which describe the relations between objects. Classical methods can not directly deal with this kind of data. For unsupervised methods this problem has been studied, here we transfer the same idea to the two supervised prototype-based techniques such that they can directly deal with dissimilarities without an explicit embedding into a vector space. • Quadratic complexity issue: For dealing with dissimilarity data, due to the need of the full dissimilarity matrix, the complexity becomes quadratic which is infeasible for large data sets. In this thesis we investigate two linear approximation techniques: Nyström approximation and patch processing, and integrate them into unsupervised and supervised prototype-based techniques. • Reliability of prototype-based classifiers: In practical applications, a relia- bility measure is beneficial for evaluating the classification quality expected by the end users. Here we adopt concepts from conformal prediction (CP), which provides point-wise confidence measure of the prediction, and we combine those with supervised prototype-based techniques. • Model complexity: By means of the confidence values provided by CP, the model complexity can be automatically adjusted by adding new prototypes to cover low confidence data space. • Extendability to semi-supervised problems: Besides its ability to evaluate a classifier, conformal prediction can also be considered as a classifier. This opens a way that supervised techniques can be easily extended for semi-supervised settings by means of a self-training approach.

Uncertainty is inherent in medical decision making and poses a challenge for intelligent technologies. This paper focuses on magnetic resonance spectra (MRS) for discrimination of brain tumour types and grades. Modelling of this type of high-dimensional data is commonly affected by uncertainty caused by the presence of outliers. Multivariate data clustering and visualization of MRS data is proposed using the GTM framework with basis functions comprising Student t-distributions in order to minimize the negative impact on the model from outliers. The effectiveness of this model on the MRS data is demonstrated empirically.

We introduce GTM-SD (Generative Topographic Mapping for Structured Data), which is the first compositional generative model for topographic mapping of tree-structured data. GTM-SD exploits a scalable bottom-up hidden-tree Markov model that was introduced in Part I of this paper to achieve a recursive topographic mapping of hierarchical information. The proposed model allows efficient exploitation of contextual information from shared substructures by a recursive upward propagation on the tree structure which distributes substructure information across the topographic map. Compared to its noncompositional generative counterpart, GTM-SD is shown to allow the topographic mapping of the full sample tree, which includes a projection onto the lattice of all the distinct subtrees rooted in each of its nodes. Experimental results show that the continuous projection space generated by the smooth topographic mapping of GTM-SD yields a finer grained discrimination of the sample structures with respect to the state-of-the-art recursive neural network approach.

G-Protein-Coupled Receptors (GPCRs) are cell membrane proteins with a key role in biological processes. GPCRs of class C, in particular, are of great interest in pharmacology. The lack of knowledge about their 3-D structures means they must be investigated through their primary amino acid sequences. Sequence visualization can help to explore the existing receptor sub-groupings at different partition levels. In this paper, we focus on Metabotropic Glutamate Receptors (mGluR), a subtype of class C GPCRs. Different versions of a probabilistic manifold learning model are employed to comparatively sub-group and visualize them through different transformations of their sequences.