Self-organizing Map Analysis Research Articles

Boreal Summer Intraseasonal Phases Identified by Nonlinear Multivariate Empirical Orthogonal Function–Based Self-Organizing Map (ESOM) Analysis

Abstract This study develops an empirical orthogonal function (EOF)-based self-organizing map (SOM) (ESOM) analysis to identify the nonlinear characteristics of the boreal summer intraseasonal oscillation (BSISO), which involves interactions between the summer mean circulation and the convectively coupled equatorial waves, which make BSISO evolution more complex than the Madden–Julian oscillation. The method utilizes the first five principal components of the outgoing longwave radiation (OLR) and the zonal wind at 850 hPa (U850) and has the advantages of filtering out uncertainties from noise and being free from mathematical restrictions, such as orthogonality and linearity. The ESOM analysis enables the detection of BSISO over the Asian summer monsoon region with eight phases. The four most distinguishable phases represent 1) a pair of stationary patterns with a dipole between the eastern Indian Ocean and the Philippine Sea (phases 1 and 5) and 2) a pair of propagating patterns with a northwest–southeast-tilted rain belt structure (phases 3 and 7). Phases 1 and 5 show an alternating seesaw oscillation throughout the summer with a 30–60-day period, whereas phases 3 and 7 peak in mid-June and early June denoting the monsoon rainy season and premonsoon period of Asian summer monsoon. ESOM captures that phases 1 and 5 happen more frequently and last longer than phases 3 and 7, whereas multivariate EOF analysis fails to describe this nonlinear occurrence. Phases 3 and phase 7 display distinct asymmetries in convective activity over the eastern Indian Ocean related to the relatively slow-growing and fast-decaying convective activity. The relationship with large-scale SST forcing is also discussed.

Inter-joint coordination of posture on a seesaw device

Even though specific adjustments of the multi-joint control of posture have been observed when posture is challenged, multi-joint coordination on a seesaw device has never been accurately assessed. The current study was conducted in order to investigate the multi-joint coordination when subjects were standing on either a seesaw device or on a stable surface, with the eyes open or closed. Eighteen healthy active subjects were recruited. A principal component analysis and a Self-Organizing Maps analysis were performed on the joint angles in order to detect and characterize dominant coordination patterns. Intermuscular EMG coherence was analysed in order to assess the neurophysiological mechanisms associated with these coordination patterns. The results illustrated a multi-joint organization of posture on both stable ground and on the seesaw, with a higher variability among the individual postural responses observed when standing on the seesaw. These findings challenge the classical assumption of ankle mechanisms as dominating control on seesaw devices and confirm that inter-joint coordination in postural control is strongly modulated by stance conditions. When standing on the seesaw without vision, a decrease in intermuscular coherence was observed without any impact on the joint coordination patterns, likely due to an increase dependence on proprioceptive information.

ANALYSIS OF THE SELF-ORGANIZING MAP-BASED INVESTMENT STRATEGY

The following paper presents the application of Self-Organizing Maps (SOM) to construct and apply investment strategy on the stock market. Characteristics of this type of neural network and their influence on the investment strategy performance are verified. Considered parameters include the SOM size, here connected to the size of the training set (number of examples). The average number of patterns per neuron was selected as the appropriate measure. Other aspects of the SOM analysis included conscience mechanism, which allows more neurons to be stimulated during the learning process, method of weights updating, determining the number of stimulated neurons. Additionally, the impact of the correlation between features was verified to eliminate redundant ones. Performance of each designed network was verified against the simple investment strategy, generating “buy”, ”sell” and “hold” signals based on the average Rate of Return (RoR). Results show that SOMs with the conscience mechanism outperform their simpler configurations. Elimination of correlated data also improves performance of the SOM-based investment strategy.

Estimation and optimization operation in dealing with inflow and infiltration of a hybrid sewerage system in limited infrastructure facility data

Inflow and infiltration (I/I) are serious problems in hybrid sewerage systems. Limited sewerage information impedes the estimation accuracy of I/I for each catchment. A new method dealing with I/I of a large-scale hybrid sewerage system with limited infrastructure facility data is proposed in this study. The catchment of representative pump stations was adopted to demonstrate the homological catchments that have similar wastewater fluctuation characteristics. Homological catchments were clustered using the self-organizing map (SOM) analysis based on long-term daily flow records of 50 pumping stations. An assessment index was applied to describe the I/I and overflow risk in the catchment based on the hourly wastewater quality and quantity data of representative pump stations. The potential operational strategy of homological catchments was determined by the assessment index of representative pump stations. The simulation results of the potential operational strategy indicated that the optimized operation strategy could reduce surcharge events and significantly improve the quality of wastewater treatment plant effluent. Open image in new window

Phytophthora megakarya and P. palmivora, closely related causal agents of cacao black pod rot, underwent increases in genome sizes and gene numbers by different mechanisms.

Phytophthora megakarya (Pmeg) and Phytophthora palmivora (Ppal) are closely related species causing cacao black pod rot. Although Ppal is a cosmopolitan pathogen, cacao is the only known host of economic importance for Pmeg. Pmeg is more virulent on cacao than Ppal. We sequenced and compared the Pmeg and Ppal genomes and identified virulence-related putative gene models (PGeneM) that may be responsible for their differences in host specificities and virulence. Pmeg and Ppal have estimated genome sizes of 126.88 and 151.23 Mb and PGeneM numbers of 42,036 and 44,327, respectively. The evolutionary histories of Pmeg and Ppal appear quite different. Postspeciation, Ppal underwent whole-genome duplication whereas Pmeg has undergone selective increases in PGeneM numbers, likely through accelerated transposable element-driven duplications. Many PGeneMs in both species failed to match transcripts and may represent pseudogenes or cryptic genetic reservoirs. Pmeg appears to have amplified specific gene families, some of which are virulence-related. Analysis of mycelium, zoospore, and in planta transcriptome expression profiles using neural network self-organizing map analysis generated 24 multivariate and nonlinear self-organizing map classes. Many members of the RxLR, necrosis-inducing phytophthora protein, and pectinase genes families were specifically induced in planta. Pmeg displays a diverse virulence-related gene complement similar in size to and potentially of greater diversity than Ppal but it remains likely that the specific functions of the genes determine each species’ unique characteristics as pathogens.

Phytophthora megakarya and P. palmivora, Causal Agents of Black Pod Rot, Induce Similar Plant Defense Responses Late during Infection of Susceptible Cacao Pods.

Phytophthora megakarya (Pmeg) and Phytophthora palmivora (Ppal) cause black pod rot of Theobroma cacao L. (cacao). Of these two clade 4 species, Pmeg is more virulent and is displacing Ppal in many cacao production areas in Africa. Symptoms and species specific sporangia production were compared when the two species were co-inoculated onto pod pieces in staggered 24 h time intervals. Pmeg sporangia were predominantly recovered from pod pieces with unwounded surfaces even when inoculated 24 h after Ppal. On wounded surfaces, sporangia of Ppal were predominantly recovered if the two species were simultaneously applied or Ppal was applied first but not if Pmeg was applied first. Pmeg demonstrated an advantage over Ppal when infecting un-wounded surfaces while Ppal had the advantage when infecting wounded surfaces. RNA-Seq was carried out on RNA isolated from control and Pmeg and Ppal infected pod pieces 3 days post inoculation to assess their abilities to alter/suppress cacao defense. Expression of 4,482 and 5,264 cacao genes was altered after Pmeg and Ppal infection, respectively, with most genes responding to both species. Neural network self-organizing map analyses separated the cacao RNA-Seq gene expression profiles into 24 classes, 6 of which were largely induced in response to infection. Using KEGG analysis, subsets of genes composing interrelated pathways leading to phenylpropanoid biosynthesis, ethylene and jasmonic acid biosynthesis and action, plant defense signal transduction, and endocytosis showed induction in response to infection. A large subset of genes encoding putative Pr-proteins also showed differential expression in response to infection. A subset of 36 cacao genes was used to validate the RNA-Seq expression data and compare infection induced gene expression patterns in leaves and wounded and unwounded pod husks. Expression patterns between RNA-Seq and RT-qPCR were generally reproducible. The level and timing of altered gene expression was influenced by the tissues studied and by wounding. Although, in these susceptible interactions gene expression patterns were similar, some genes did show differential expression in a Phytophthora species dependent manner. The biggest difference was the more intense changes in expression in Ppal inoculated wounded pod pieces further demonstrating its rapid progression when penetrating through wounds.

Assessment of social vulnerability to natural hazards in South Korea: case study for typhoon hazard

Most often, disaster vulnerabilities are discussed from the perspective of developing countries. This paper extends the argument using an example from a developed country, by focusing on the South Korea during the period from 2009 to 2013. South Korea has suffered from a range of natural hazards throughout its history, and experienced one to three typhoons per year on the average, with most events occurring in August and September. Since 1945, around 17 major typhoons have directly affected South Korea. This study used Self Organizing Map (SOM) and Social Vulnerability Index (SoVI) for data analysis in terms of the number of social vulnerability variables and samples. The dataset used for social vulnerability analysis consisted of 12 variables, which were adopted and adapted from the research literature related to Hurricane Katrina. However, some of the variables employed in this study might be more or less redundant, necessitating the removal of redundant variables from the accurate SOM analysis. Overall, during the period from 2009 to 2013, the variables of ELDRY (elderly population), POPDNSTY (population density), and DISBLD (disabled population) are the dominant variables which frequently appear as the two top variables that lead to an increase in social vulnerability. According to the findings related to the social vulnerability index, nearly half of all regions have positive values, which are categorized as highly vulnerable. As there are growing concerns on the adequacy of using the concept of vulnerability to address loss and damage, an additional approach was attempted by using typhoon hazard examples, e.g. Typhoons Dianmu and Kompasu of 2010, Typhoon Muifa of 2011, and Typhoon Sanba of 2012. Additional factors such as shortest distance from the typhoon track and maximum wind speed were considered together to obtain the weighted correlation between them. Based on the process of this study, SOM has an essential benefit in evaluating SoVI.

Abstract 198: Endovascular Biopsy: in vivo Brain Aneurysm Endothelial Cell Sampling and Gene Expression Analysis

Introduction: Cerebral aneurysms affect 1-6% of the population and their rupture carries significant mortality and morbidity. The paucity of data related to histopathological features of aneurysms stems largely from the risks associated with aneurysm tissue collection. We set out to establish a feasible technique to isolate viable endothelial cells (EC) and to characterize the differences in genetic expression (GE) between iliac arterial cells vs. aneurysm cells and non-ruptured vs. ruptured aneurysm cells. Methods: 10 patients (5 non-ruptured and 5 ruptured) undergoing aneurysm treatment were enrolled under IRB approval. ECs from aneurysms and iliac arteries were sampled using an appropriately sized coil and a 0.035 “J” wire respectively. Coils and wires were processed via FACS and single cell qPCR to quantify expression of 48 genes implicated in EC function and aneurysm pathogenesis. Mixed models were performed using each GE level as the outcome with multiple predictors. Unsupervised cluster analysis including: hierarchical heat-map clustering, K-medoids, principle components, cART, and self-organizing maps (SOM) were used to find cell clusters based on coordinately expressed GE. Results: 437 FACS-sorted cells were collected and 319 demonstrated CD31, CD34 and CD105 triple-positive expression. Of these, 94 were aneurysmal cells. The average number of extracted aneurysm cells per patient was 9.4 (1-24, median 6.5) with a trend for higher cell yields from ruptured aneurysms (p = 0.116). Mixed model analyses revealed a history of smoking showed the strongest associations with GE (median p-value 0.104 with 11/48 analyses p < 0.05); 5 genes significantly predicted rupture status (median p-value 0.363 with 5/48 analyses p < 0.05); and one gene significantly differentiated cell type (median p-value 0.557, with 1/48 analyses p < 0.05). SOM analysis revealed clustered GE profiles suggestive of distinct functional EC sub-populations. Conclusion: Cerebral endovascular sampling is a safe and reliable means for targeted cell collection for genetic analysis. Smoking was strongly associated with GE levels. Our analysis provides evidence that GE levels may be associated with cell type and rupture status.

A Self-Organizing-Map-Based Evaluation of the Antarctic Mesoscale Prediction System Using Observations from a 30-m Instrumented Tower on the Ross Ice Shelf, Antarctica

Abstract Accurate representation of the stability of the surface layer in numerical weather prediction models is important because of the impact it has on forecasts of surface energy, moisture, and momentum fluxes. It also impacts boundary layer processes such as the generation of turbulence, the creation of near-surface flows, and fog formation. This paper uses observations from a 30-m automatic weather station on the Ross Ice Shelf, Antarctica, to evaluate the near-surface layer in the Antarctic Mesoscale Prediction System (AMPS), a numerical weather prediction system used for forecasting in Antarctica. The method of self-organizing maps (SOM) is used to identify characteristic potential temperature anomaly profiles observed at the 30-m tower. The SOM-identified profiles are then used to evaluate the performance of AMPS as a function of atmospheric stability. The results indicate AMPS underpredicts the frequency of near-neutral profiles and instead overpredicts the frequency of weakly unstable and weak to moderately stable profiles. AMPS does not forecast the strongest statically stable patterns observed by Tall Tower, but in the median, the AMPS forecasts are more statically stable across all wind speeds, indicating a possible mechanical mixing error or a negative radiation bias. The SOM analysis identifies a negative radiation bias under near-neutral to weakly stable conditions, causing an overrepresentation of the static stability in AMPS. AMPS has a positive wind speed bias in moderate to strongly stable conditions, which generates too much mechanical mixing and an underrepresentation of the static stability. Model errors increase with increasing atmospheric stability.

P1.05-021 circRNAs: Potential Novel Biomarkers for the Early Detection of Lung Cancer

Lung cancer is the leading cancer killer globally. Cancers such as colon, breast, and prostate all have relatively reliable early detection tests. In contrast, lung cancer does not. If caught early, lung cancer has a much better prognosis. Non-invasive or minimally invasive tools to improve early detection of lung cancer represents a critical unmet need. Analysis of the human transcriptome indicates that a mere 2% of the genome corresponds to protein coding transcripts, yet ∼ 75% of the genome is transcribed. It is now well established that these non-coding RNAs (ncRNAs) play important regulatory functions within the cell and their expression are often altered in cancer. Circular RNAs (circRNAs) are a species of ncRNAs. They are abundant, conserved and demonstrate cell-type specific expression patterns. Moreover, they are extremely stable with half-life’s greater than 48 hours, are resistant to degradation by RNA exonucleases, and have been shown to play important roles in cancer. Taken together these suggest that circRNAs could potentially be important biomarkers in early lung cancer diagnosis. Total RNAs isolated from a panel of matched normal/tumor NSCLC adenocarcinoma (Stage IA/IB) samples (n=6) were probed for circRNAs using the Arraystar circRNA microarray. Survival was assessed on linear mRNAs with associated circRNAs using KM-Plot. Interim analysis of the data has identified n=206 circRNAs with a 2-fold difference in expression between their matched normal vs. tumor counterparts. Principal Component Analysis (PCA) demonstrated a clear separation of the samples (Tumor vs. Normal). Self-Organizing Maps (SOMs) analysis generated distinctive SOMS clusters of circRNAs, while associated linear pathway enrichment for microRNA and transcriptional binding motifs identified several additional potential networks. Moreover, an analysis of linear mRNAs associated with 10 circRNAs with altered expression in adenocarcinomas found that these mRNAs were linked to overall survival, and that the majority were adenocarcinoma specific. Altered levels of a number of circRNAs were associated with lung adenocarcinoma. A separate cohort of squamous cell carcinomas is currently being assessed for circRNAs. At present we are validating the expression of these circRNAs in a larger cohort of specimens, and assessing whether or not these are detectable in plasma/serum from the same individuals. Overall, circRNAs may represent novel potential biomarkers for the detection of NSCLC, and may provide additional critical basic knowledge regarding the development and biology of NSCLC.

Stress test of a biological early warning system with zebrafish (Danio rerio).

The aim of this work was to develop a novel methodology to stress test the diagnostic capability of a video tracking system with zebrafish (Danio rerio), against two pre-established disturbances. Eight different treatments were tested varying the presence or absence of a toxicant (NaOCl) and two disturbances: the passing of a shadow (mimicking a predator) and entrapment of the fish. The concentration tested corresponded to a sublethal (1 % 24 h-LC50) and short term exposure (2 h). A total of 56 organisms were tested resulting in 112 diagnoses (before and after the contamination). A statistical model of diagnosis was developed using Self-organizing Map (SOM) and Correspondence Analysis (CA). Sensitivity, specificity, accuracy, false positive and false negative values were calculated to evaluate the diagnostic performance. The disturbances did not negatively affect the capability of the model. In the presence of at least one of these variables, the diagnostic performance was similar or even superior to the baseline results without disturbances. Furthermore, the system produced a large number of correct diagnoses, at an ecologically relevant concentration of exposure, in a non-invasive way.

Spatiotemporal characteristics of the sea level anomaly in the Kuroshio Extension using a self-organizing map

AbstractSatellite altimeter SSH data in the Kuroshio Extension (KE) region gathered during the period January 1993 to December 2014 are analyzed using self-organizing map (SOM) analysis. Four spatial patterns (SOM1, SOM2, SOM3, and SOM4) are extracted, and the corresponding time series are used to characterize the variation of the sea level anomaly. Except in some individual months, SOM1 and SOM2 with single-branch jet structures appear alternately during the periods 1993–1998 and 2002–2011. However, during 1999–2001 and 2012–2014, SOM3 and SOM4 with double-branch jet structures are dominant. The sea level anomalies exhibit interannual variations, while the KE stream demonstrates decadal variation. For SOM1, the change in the KE path is less evident, although the KE jet is strong and narrow. For SOM2, the KE jet is weakened and widened and its jet axis moves towards the southwest. Compared with the SOM3, for SOM4 the trough and ridge in the upstream KE region are deeper in the northeast–southwest directio...

Development of an Electronic Nose to Identify and Classify Odours from Spirits Beverages

This paper presents the development of an electronic nose (e-nose) prototype for classifying odours from alcoholic beverages, as well as butanol and methanol vapours. The e-nose mainly comprises an array of commercial gas sensors based on metal oxide semiconductor (MOS) technology. Instrumental measurements were based on obtaining the voltage response from the sensor array for each odorant sample. Then, these signals were pre-processed by Principal Component Analysis (PCA) and processed to achieve qualitative results. Three classification tools were used: a Multi-Layer Perceptron (MLP), a Self-Organizing Map (SOM) and Clustering Analysis (CA). The analysis by MLP showed a suitable prediction capability of 92.5 %, while, SOM and CA, being unsupervised techniques, were applied to establish certain odour patterns among the odorants samples. The results of this study support the potential of e-noses as reliable electronic instruments for qualitative analyses of odorants from different alcoholic beverages.

Evaluating the relationships between watershed physiography, land use patterns, and phosphorus loading in the bay of Quinte basin, Ontario, Canada

Abstract The Bay of Quinte, a Z-shaped embayment at the northeastern end of Lake Ontario, represents a characteristic case of an area of concern (AOC) where scientific uncertainty underlies management efforts to address eutrophication problems. The present study attempts to examine the relationships between total phosphorus (TP) (i.e., concentrations from point and non-point sources, net export, and yield) and watershed attributes, including land use cover and physiographic characteristics. Dynamic linear modeling is applied to assess temporal trends in the flow rates in five major tributaries of the area. Urbanized catchments near the Bay of Quinte show more dynamic flow patterns with significant within- and among-year variability and stronger response to local precipitation patterns. The “flashy” behavior of urban land is characterized by relatively high net TP export and TP yield. Self-organizing map analysis, classified the watershed into six distinct spatial clusters, representing two agricultural, one forested, one urban, one pasture-dominated, and one transitional area. Our study shows that agricultural and urban sites profoundly shape riverine TP dynamics. We also provide evidence that tributaries draining agricultural areas exhibit considerable variability, depending on management practices and soil properties. Excessive fertilizer or manure application in croplands, management practices (e.g., crop types and tillage methods) and soil hydrological characteristics (e.g., hydraulic conductivity and permeability) generally determine soil phosphorus level and consequent losses through erosion and runoff from agricultural sites. In a similar manner, pasture-based grazing systems appear to play an important role in modulating the fate and transport of phosphorus in the Bay of Quinte watershed.

Characterization of DOM adsorption of CNTs by using excitation–emission matrix fluorescence spectroscopy and multiway analysis

ABSTRACTCarbon nanotubes (CNTs) were utilized to adsorb DOM in micro-polluted water. The characteristics of DOM adsorption on CNTs were investigated based on UV254, TOC, and fluorescence spectrum measurements. Based on PARAFAC (parallel factor) analysis, four fluorescent components were extracted, including one protein-like component (C4) and three humic acid-like components (C1, C2, and C3). The adsorption isotherms, kinetics, and thermodynamics of DOM adsorption on CNTs were further investigated. A Freundlich isotherm model fit the adsorption data well with high values of correlation. As a type of macro-porous and meso-porous adsorbent, CNTs preferably adsorb humic acid-like substances rather than protein-like substances. The increasing temperature will speed up the adsorption process. The self-organizing map (SOM) analysis further explains the fluorescent properties of water samples. The results provide a new insight into the adsorption behaviour of DOM fluorescent components on CNTs.

Assessment of heavy metal contamination in the surface sediments: A reexamination into the offshore environment in China

The contents of Cu, Pb, Zn, Cd, Cr, Hg and As in the surface sediments of over 668 sites were monitored in a comprehensive program for assessing the degree of heavy-metal pollution and adverse biological effects of the offshore sediments in China. The contamination factor and geoaccumulation index indicated that As and Pb might be two of the most influential pollution loading in these metals. Cluster analysis separated 19 areas in China's near seas into 7 groups with different pollution characteristic, where the sediments along Zhejiang coast were the most highly-contaminated. Based on biological adverse effects index and sediment quality guideline for As, nearly half of sites in China's near seas induced slight adverse biological effects. With correlation analysis, self-organizing map and factor analysis, different sources as well as various adsorption mechanisms/anthropogenic factors were suggested to be important roles in altering the concentration of heavy metals in the sediments.

A Validation of the Antarctic Mesoscale Prediction System Using Self-Organizing Maps and High-Density Observations from SNOWWEB

This study compares high-resolution output (1.1-km horizontal grid length) from twice-daily forecasts produced by the Antarctic Mesoscale Prediction System (AMPS) with a dense observational network east of Ross Island. Covering 10 000 km2, 15 SNOWWEB stations significantly increased the number of observation stations in the area to 19 during the 2014–15 austral summer. Collocated “virtual stations” created from AMPS output are combined with observations, producing a single dataset of zonal and meridional wind components used to train a self-organizing map (SOM). The resulting SOM is used to individually classify the observational and AMPS datasets, producing a time series of classifications for each dataset directly comparable to the other. Analysis of class composites shows two dominant weather patterns: low but directionally variable winds and high but directionally constant winds linked to the Ross Ice Shelf airstream (RAS). During RAS events the AMPS and SNOWWEB data displayed good temporal class alignment with good surface wind correlation. SOM analysis shows that AMPS did not accurately forecast surface-level wind speed or direction during light wind conditions where synoptic forcing was weak; however, it was able to forecast the low wind period occurrence accurately. Coggins’s regimes provide synoptic-scale context and show a reduced synoptic pressure gradient during these classes, increasing reliance on the ability of Polar WRF to resolve mesoscale dynamics. Available initialization data have insufficient resolution for the region’s complex topography, which likely impacts performance. The SOM analysis methods used are shown to be effective for model validation and are widely applicable.

Investigating the effect of landfill leachates on the characteristics of dissolved organic matter in groundwater using excitation-emission matrix fluorescence spectra coupled with fluorescence regional integration and self-organizing map.

For the purpose of investigating the effect of landfill leachate on the characteristics of organic matter in groundwater, groundwater samples were collected near and in a landfill site, and dissolved organic matter (DOM) was extracted from the groundwater samples and characterized by excitation-emission matrix (EEM) fluorescence spectra combined with fluorescence regional integration (FRI) and self-organizing map (SOM). The results showed that the groundwater DOM comprised humic-, fulvic-, and protein-like substances. The concentration of humic-like matter showed no obvious variation for all groundwater except the sample collected in the landfill site. Fulvic-like substance content decreased when the groundwater was polluted by landfill leachates. There were two kinds of protein-like matter in the groundwater. One kind was bound to humic-like substances, and its content did not change along with groundwater pollution. However, the other kind was present as "free" molecules or else bound in proteins, and its concentration increased significantly when the groundwater was polluted by landfill leachates. The FRI and SOM methods both can characterize the composition and evolution of DOM in the groundwater. However, the SOM analysis can identify whether protein-like moieties was bound to humic-like matter.

Homogeneous region determination using linear and nonlinear techniques

Similarity between catchments in a region can be determined depending on catchment properties. This helps to understand the response behavior of the similar catchments more appropriately. Catchment classification plays a major role in the process of hydrological prediction in the case of ungauged catchments. The following categorization was carried out for 32 catchments of India. Principal Component Analysis (PCA) along with K-means clustering, was applied as linear classification; and Self-Organizing Map (SOM) and Kernel Principal Component Analysis (KPCA) were implemented as nonlinear classification methods on catchment attributes and daily streamflow time series. The classification established on streamflow signatures was taken as the reference classification. Results obtained from PCA, SOM, and KPCA were compared with results of the reference classification. The absence of discordant catchments from the clusters of SOM, based on catchment attributes, suggests homogeneity among SOM-derived clusters. Similarity index scores are 0.48 and 0.47, 0.46 and 0.42 ​for first, second, third and fourth clusters of SOM respectively with that of the reference classification technique. Nonlinear techniques with high similarity index values outperformed standard techniques. This study demonstrated the ability of classification based on catchment attributes to classify ungauged catchments.

Rapid activity prediction of HIV-1 integrase inhibitors: harnessing docking energetic components for empirical scoring by chemometric and artificial neural network approaches.

Improving performance of scoring functions for drug docking simulations is a challenging task in the modern discovery pipeline. Among various ways to enhance the efficiency of scoring function, tuning of energetic component approach is an attractive option that provides better predictions. Herein we present the first development of rapid and simple tuning models for predicting and scoring inhibitory activity of investigated ligands docked into catalytic core domain structures of HIV-1 integrase (IN) enzyme. We developed the models using all energetic terms obtained from flexible ligand-rigid receptor dockings by AutoDock4, followed by a data analysis using either partial least squares (PLS) or self-organizing maps (SOMs). The models were established using 66 and 64 ligands of mercaptobenzenesulfonamides for the PLS-based and the SOMs-based inhibitory activity predictions, respectively. The models were then evaluated for their predictability quality using closely related test compounds, as well as five different unrelated inhibitor test sets. Weighting constants for each energy term were also optimized, thus customizing the scoring function for this specific target protein. Root-mean-square error (RMSE) values between the predicted and the experimental inhibitory activities were determined to be <1 (i.e. within a magnitude of a single log scale of actual IC50 values). Hence, we propose that, as a pre-functional assay screening step, AutoDock4 docking in combination with these subsequent rapid weighted energy tuning methods via PLS and SOMs analyses is a viable approach to predict the potential inhibitory activity and to discriminate among small drug-like molecules to target a specific protein of interest.