Moran's Autocorrelation Research Articles

The spatiotemporal epidemiological study on human brucellosis in shenyang, China from 2013 to 2022

BackgroundEpidemiological characteristics of human brucellosis (HB) have changed over the last decade. In this study, we depicted the spatiotemporal features of HB in Shenyang, China, from 2013 to 2022 and the objective was to visualise spatiotemporal patterns and identify high-risk regions with the purpose to provide evidence for HB prevention and control. MethodsWe performed an observational epidemiological study using HB data obtained from the National Notifiable Disease Reporting System (NNDRS). Joinpoint regression analysis was employed to determine the changing trends in the annual incidence. A vector boundary map of Shenyang was used to visualise spatial distribution. Spatial autocorrelation was identified using both global and local Moran's autocorrelation coefficients, while hotspot areas were determined using the Getis-Ord statistic. ResultsA combined sum of 4103 HB cases were analysed, and the average level of annual incidence of HB was 5.52 per 100,000. The incidence of HB showed obvious seasonality, with a notable peak observed from April to July (summer peak). The annual incidence in Shenyang has been on the rise since 2013, with an annual percentage change (APC) of 6.39% (95%CI 1.29%, 12.39%). Xinmin County exhibited the most elevated average annual incidence rate, with Faku County ranking second. The average annual incidence in rural areas exhibited a significantly greater disparity compared to suburban areas (P < 0.001), whereas the incidence rate in suburban areas demonstrated a significantly higher contrast when compared to urban areas (P < 0.001). A clustered distribution of the annual incidence of HB was observed for all years from 2013 to 2022. Abnormally high values were found in suburban areas, and no abnormally high values were found after 2017. The low-low clustering areas were found in urban as well as suburban areas from 2013 to 2022. Hotspots (P < 0.05) were located in rural areas, while cold spots (P < 0.05) were found in both urban and suburban areas. Since 2020, there have been no hotspots in Shenyang. ConclusionsRural areas are high-risk areas for HB and may be key to controlling HB epidemics. Although the annual incidence of HB in rural areas has increased, owing to the stability of spatial relationships and the disappearance of hotspots, there is little possibility of outbreaks; however, stricter monitoring should be applied in rural areas to prevent the emergence of new transmission routes.

SPATIAL DIFFERENTIATION OF THE EMISSIVITY OF AGRICULTURE IN EUROPE

This paper presents the results of a study aimed at determining the spatial variation in the carbon intensity of the agricultural sector in Europe. The analyses used the volume of greenhouse gas emissions from the agricultural sector (in 2020), expressed in carbon dioxide equivalent, calculated according to the IPCC methodology for 31 European countries. To reduce variance and the impact of country size on emissions, three emissivity factors were calculated, depending on: agricultural area, value of goods produced by agriculture and population. To verify the relationship between emissivity and location, the Moran autocorrelation coefficient was used, calculated on a modified weighting matrix that, in addition to the criterion of a common border, takes into account the similarity of objects in terms of the values of diagnostic variables (similarity determined using cluster analysis) – in this case indicators describing the emissivity of the agricultural sector. The study showed that there was no reason to reject the hypothesis of a random distribution of objects in space with respect to the values of the indicators included in the study. It can therefore be concluded that there are some similarities in the emissivity from the different European economies, as evidenced by the cluster analysis results, while there is no spatial correlation.

In-silico studies of 2-aminothiazole derivatives as anticancer agents by QSAR, molecular docking, MD simulation and MM-GBSA approaches

Targeting Hec1/Nek2 is considered as crucial target for cancer treatment due to its significant role in cell proliferation. In pursuit of this, a series of twenty-five 2-aminothiazoles derivatives, along with their Hec1/Nek2 inhibitory activities were subjected to QSAR studies utilizing QSARINS software. The significant three descriptor QSAR model was generated, showing noteworthy statistical parameters: a correlation coefficient of cross validation leave one out (Q2 LOO) = 0.7965, coefficient of determination (R2) = 0.8436, (R2ext) = 0.6308, cross validation leave many out (Q2LMO) = 0.7656, Concordance Correlation Coefficient (CCCCV = 0.8875), CCCtr = 0.9151, and CCCext = 0.0.7241. The descriptors integral to generated QSAR model include Moreau-Broto autocorrelation, which represents the spatial autocorrelation of a property along the molecular graph’s topological structure (ATSC1i), Moran autocorrelation at lag 8, which is weighted by charges (MATS8c) and RPSA representing the total molecular surface area. It was noted that these descriptors significantly influence Hec1/Nek2 inhibitory activity of 2-aminothiazoles derivatives. New lead molecules were designed and predicted for their Hec1/Nek2 inhibitory activity based on the developed three descriptor model. Further, the ADMET and Molecular docking studies were carried out for these designed molecules. The three molecules were selected based on their docking score and further subjected for MD simulation studies. Post-MD MM-GBSA analysis were also performed to predicted the free binding energies of molecules. The study helped us to understand the key interactions between 2-aminothiazoles derivatives and Hec1/Nek2 protein that may be necessary to develop new lead molecules against cancer. Communicated by Ramaswamy H. Sarma

Fall-Related Hospitalizations in Elderly People: Temporal Trend and Spatial Distribution in Brazil

This study aims to identify the temporal variation and the spatial dependence structure of the hospitalization rate for falls in the elderly residing in Brazil in the period between 2010 and 2021. This ecological study employs secondary data from the Brazilian Ministry of Health about the fall-related hospitalization of people aged 60 years old and over. A time-series analysis was carried out, employing the joinpoint model. For the spatial analysis, the Moran autocorrelation technique was employed. In Brazil, between 2010 and 2021, there were 1,270,341 hospitalizations for falls recorded among the elderly in the Brazilian Hospitalization System. There was a continuous upward trend between 2010 and 2019 for all age groups, female and male, and all Brazilian regions. The trend stabilized between 2019 to 2021. The North and Northeast regions had faster upward trends among all Brazilian regions, and there was also a faster upward trend among women compared to men. A high-high pattern in hospitalization incidence was noticed from 2011 to 2019 in the states of São Paulo, Minhas Gerais, Paraná, and Mato Grosso do Sul. The results of this study provide subsidies for Brazilian health authorities to implement more efficient public policies to improve the quality of life of elderly people.

Survival study on deep learning techniques for IoT enabled smart healthcare system.

The paper is to study a review of the employment of deep learning (DL) techniques inside the healthcare sector, together with the highlight of the strength and shortcomings of existing methods together with several research ultimatums. Our study lays the foundation for healthcare professionals and government with present-day inclinations in DL-based data analytics for smart healthcare. A deep learning-based technique is designed to extract sensor displacement effects and predict abnormalities for activity recognition via Artificial Intelligence (AI). The presented technique minimizes the vanishing gradient issue of Recurrent Neural Networks (RNN), thereby reducing the time for detecting abnormalities with consideration of temporal and spatial factors. Proposed Moran Autocorrelation and Regression-based Elman Recurrent Neural Network (MAR-ERNN) introduced. Experimental results show the feasibility of the proposed method. The results show that the proposed method improves accuracy by 95% and reduces execution time by 18%. MAR-ERNN performs well in the activity recognition of health status. Collectively, this IoT-enabled smart healthcare system is utilized by enhancing accuracy, and minimizing time and overhead reduction.

Spatio-temporal analysis of the COVID-19 pandemic in Iran

Globally, the COVID-19 pandemic is a top-level public health concern. This paper is an attempt to identify and COVID-19 pandemic in Iran using spatial analysis approaches. This study was based on secondary data of confirmed cases, deaths, recoveries, number of hospitals, hospital beds and population from March 2, 2019 to the end of November 2021 in 31 provinces of Iran from hospitals and the website of the National Institute of Health. In this paper, three geographical models in ArcGIS10.3 were utilized to analyze and evaluate COVID-19, including Geographic Weight Regression (GWR), Getis-OrdGi* (G-i-star) statistics (hot and cold spot), and Moran autocorrelation spatial analysis. Moran statistics, based on the GWR model, demonstrated that deaths and recoveries followed a clustering pattern for the confirmed cases index during the study period. The Moran Z-score for all three indicators confirmed cases, deaths, and recoveries, which was greater than 2.5 (95% confidence level). The Getis-OrdGi* (G-I-Star) (hot and cold spot) data revealed a wide range of levels for six variables (confirmed cases, deaths, recoveries, population, hospital beds, and hospital) across Iran's provinces. The overall number of deaths exceeded the population and the number of hospitals in the central and southern regions, including the provinces of Qom, Alborz, Tehran, Markazi, Isfahan, Razavi Khorasan, East Azerbaijan, Fars, and Yazd, which had the largest number and The Z-score for the deaths Index is greater than 14.314. The results of this research can pave the way for future studies.

Sigma70Pred: A highly accurate method for predicting sigma70 promoter in Escherichia coli K-12 strains.

Sigma70 factor plays a crucial role in prokaryotes and regulates the transcription of most of the housekeeping genes. One of the major challenges is to predict the sigma70 promoter or sigma70 factor binding site with high precision. In this study, we trained and evaluate our models on a dataset consists of 741 sigma70 promoters and 1,400 non-promoters. We have generated a wide range of features around 8,000, which includes Dinucleotide Auto-Correlation, Dinucleotide Cross-Correlation, Dinucleotide Auto Cross-Correlation, Moran Auto-Correlation, Normalized Moreau-Broto Auto-Correlation, Parallel Correlation Pseudo Tri-Nucleotide Composition, etc. Our SVM based model achieved maximum accuracy 97.38% with AUROC 0.99 on training dataset, using 200 most relevant features. In order to check the robustness of the model, we have tested our model on the independent dataset made by using RegulonDB10.8, which included 1,134 sigma70 and 638 non-promoters, and able to achieve accuracy of 90.41% with AUROC of 0.95. Our model successfully predicted constitutive promoters with accuracy of 81.46% on an independent dataset. We have developed a method, Sigma70Pred, which is available as webserver and standalone packages at https://webs.iiitd.edu.in/raghava/sigma70pred/. The services are freely accessible.

Machine learning-based approach for prediction of ion channels and their subclasses.

Ion channels are ion-permeable protein pores that are found in all cell lipid membranes. Distinct ion channels play multiple roles in biological processes. Proteomic data is fast accumulating as a result of the fast growth of mass spectrometry and giving us the chance to comprehensively explore ion channel classes along with their subclasses. This paper proposes an eXtreme Gradient Boosting(XGBoost)-based method to estimate the ion channel classes and their subclasses. Here, 12feature vectors are applied to better characterize protein sequences like amino acid composition, pseudo-amino acid composition, normalized moreau-broto autocorrelation, amphiphilic pseudo-amino acid composition, dipeptide composition, Geary autocorrelation, tripeptide composition, sequence-order-coupling number, composition/transition/distribution, conjoint triad, moran autocorrelation, quasi-sequence-order descriptors. Here, a total of 9920 features are extracted from the protein sequence. The principal component analysis is applied to determine the optimal number of features to optimize the performance. In 10-fold cross-validation the proposed XGBoost based approach with optimal 50 features achieved accuracy of 100%, 98.70%, 98.77%, 97.26%, 87.40%, 97.39%, 98.03%, 96.42%, and F1-Score of 100%, 99%, 99%, 97%, 87%, 97%, 98%, 97%, for prediction of ion channel and nonion channel, voltage-gated and ligand-gated ion channels, subclasses of voltage-gated ion channels (VGICs), subclasses of ligand-gated ion channels (LGICs), subclasses of voltage-gated calcium channels (VGCCs), subclasses of voltage-gated potassium channels (VGKCs), subclasses of voltage-gated sodium channels (VGSCs), and subclasses of voltage-gated chloride channels, respectively. Here the proposed approach also compares with the other approaches such as support vector machine, k-nearest neighbor, Gaussian Naïve Bayes,and random forest and also compares with existing methods such as support vector machine(SVM) with maximum relevance maximum distancewith an accuracy of 86.6%, 83.7%, and 85.1%, for ion channels, non-ion channels and overall respectively and SVM with radial basis functionkernel-based method with an accuracy of 100%, 97% and 99.9% for ion channels, nonion channels, and overall accuracy, respectively.

MHC2AffyPred: A machine-learning approach to estimate affinity of MHC class II peptides based on structural interaction fingerprints.

Understanding how MHC class II (MHC-II) binding peptides with differing lengths exhibit specific interaction at the core and extended sites within the large MHC-II pocket is a very important aspect of immunological research for designing peptides. Certain efforts were made to generate peptide conformations amenable for MHC-II binding and calculate the binding energy of such complex formation but not directed toward developing a relationship between the peptide conformation in MHC-II structures and the binding affinity (BA) (IC50 ). We present here a machine-learning approach to calculate the BA of the peptides within the MHC-II pocket for HLA-DRA1, HLA-DRB1, HLA-DP, and HLA-DQ allotypes. Instead of generating ensembles of peptide conformations conventionally, the biased mode of conformations was created by considering the peptides in the crystal structures of pMHC-II complexes as the templates, followed by site-directed peptide docking. The structural interaction fingerprints generated from such docked pMHC-II structures along with the Moran autocorrelation descriptors were trained using a random forest regressor specific to each MHC-II peptide lengths (9-19). The entire workflow is automated using Linux shell and Perl scripts to promote the utilization of MHC2AffyPred program to any characterized MHC-II allotypes and is made for free access at https://github.com/SiddhiJani/MHC2AffyPred. The MHC2AffyPred attained better performance (correlation coefficient [CC] of .612-.898) than MHCII3D (.03-.594) and NetMHCIIpan-3.2 (.289-.692) programs in the HLA-DRA1, HLA-DRB1 types. Similarly, the MHC2AffyPred program achieved CC between .91 and .98 for HLA-DP and HLA-DQ peptides (13-mer to 17-mer). Further, a case study on MHC-II binding 15-mer peptides of severe acute respiratory syndrome coronavirus-2 showed very close competency in computing the IC50 values compared to the sequence-based NetMHCIIpan v3.2 and v4.0 programs with a correlation of .998 and .570, respectively.

Magnitude of visceral leishmaniasis and HIV coinfection and association with social determinants of health in the Northeast region of Brazil: a retrospective, spatiotemporal model (2010-2018).

The Northeast region of Brazil (NRB) includes the states with the highest prevalence of visceral leishmaniasis (VL), as well as those with significant increases in HIV cases. This study aims to analyze the spatiotemporal patterns of VL-HIV coinfection and its association with the social determinants of health (SDH) in the NRB. Time trend analysis and Bayesian spatial statistical inferences, Moran's autocorrelation, and retrospective space-time scanning were performed. Spatial regression modelling was used to build an explanatory model for the occurrence of VL-HIV coinfection within NRB. A total of 1550 cases of VL-HIV coinfection were confirmed. We observed a higher prevalence among males (1232; 83%), individuals aged from 20 to 59years (850; 54.8%), non-white skin color (1,422; 91.7%), and with low education (550; 35.48%). NRB showed an increasing and significant trend in the detection rate of coinfection (APC, 5.3; 95% CI, 1.4 to 9.4). The states of Maranhão and Piauí comprised the high-risk cluster. The SDH that most correlated with the occurrence of coinfection were poor housing, low income, and low education. VL-HIV is dispersed in the NRB but chiefly affects states with greater social vulnerability. Taken together, these findings reinforce the necessity to implement surveillance strategies that will contribute to the reduction of cases in these populations.

Quantitative prediction model for affinity of drug\u2013target interactions based on molecular vibrations and overall system of ligand-receptor

BackgroundThe study of drug–target interactions (DTIs) affinity plays an important role in safety assessment and pharmacology. Currently, quantitative structure–activity relationship (QSAR) and molecular docking (MD) are most common methods in research of DTIs affinity. However, they often built for a specific target or several targets, and most QSAR and MD methods were based either on structure of drug molecules or on structure of receptors with low accuracy and small scope of application. How to construct quantitative prediction models with high accuracy and wide applicability remains a challenge. To this end, this paper screened molecular descriptors based on molecular vibrations and took molecule-target as a whole system to construct prediction models with high accuracy-wide applicability based on dissociation constant (Kd) and concentration for 50% of maximal effect (EC50), and to provide reference for quantifying affinity of DTIs.ResultsAfter comprehensive comparison, the results showed that RF models are optimal models to analyze and predict DTIs affinity with coefficients of determination (R2) are all greater than 0.94. Compared to the quantitative models reported in literatures, the RF models developed in this paper have higher accuracy and wide applicability. In addition, E-state molecular descriptors associated with molecular vibrations and normalized Moreau-Broto autocorrelation (G3), Moran autocorrelation (G4), transition-distribution (G7) protein descriptors are of higher importance in the quantification of DTIs.ConclusionThrough screening molecular descriptors based on molecular vibrations and taking molecule-target as whole system, we obtained optimal models based on RF with more accurate-widely applicable, which indicated that selection of molecular descriptors associated with molecular vibrations and the use of molecular-target as whole system are reliable methods for improving performance of models. It can provide reference for quantifying affinity of DTIs.

A cross-sectional study of Leishmania spp. in draft horses from the Distrito Federal, Brazil: Seroprevalence, spatial distribution, and associated factors

Equine leishmaniasis is a neglected tropical disease caused by the protozoan of the Leishmania genus, and it has been reported in several countries around the world, especially Brazil. Therefore, the present investigation aims to conduct a cross-sectional study to determine the prevalence, spatial distribution, and associated factors with seropositivity for Leishmania spp. in draft horses from the Distrito Federal, Brazil. The serological survey was conducted on 411 animals, employing the Indirect Immunofluorescence Test (IFA) and Enzyme-Linked Immunosorbent Assay (ELISA). The Kappa (κ) and gross agreement indexes evaluated the Leishmania spp. seropositivity by IFA and ELISA test. The statistical analysis was performed using the Chi-square test and logistic regression. The spatial analysis showed the areas with the highest number of seropositive and the Moran autocorrelation analyses between the spatial distribution and the epidemiological model's explanatory variables. A 27.01 % co-positivity was observed with a κ index of 52.64 %. The final model considered the variables: access to water bodies (p-value = 0.008, Odds Ratio (OR) = 2.26, Confidence Interval (CI) = 1.24–4.13), the absence of the use of ectoparasiticide (p-value = 0.008, OR = 1.93 CI = 1.18–3.15) and traveling animal (p-value = 0.059, OR = 1.54, CI = 0.98–2.41). The Kernel map showed hot areas with a high concentration of nine positive animals per area and some lighter areas ranging from five to seven positive animals per area where control measures should be performed. The Moran autocorrelation analysis was significant for the variables: traveling animal (Moran's I = 0.540 and pseudo-p-value = 0.001) and the absence of use ectoparasiticide (Moran's I = 0.259 and pseudo-p-value = 0.005). The current study exposes a high seroprevalence of Leishmania spp. in horses in the Distrito Federal, Brazil. Moreover, it proposes that traveling animal, the access to water bodies and the absence of the use of ectoparasiticide are significantly associated with seropositivity for Leishmania spp. in draft horses, which may contribute to the implementation of prophylactic and controls measures where leishmaniasis is already stalled.

Spatial and temporal analysis of the human immunodeficiency virus in an area of social vulnerability in Northeast Brazil.

Human Immunodeficiency Virus (HIV) infection still represents an important public health problem, because it involves clinical, epidemiological, social, economic and political issues. We analyzed the temporal and spatial pattern of the HIV incidence in an area of social inequality in northeast Brazil and its association with socioeconomic indicators. An ecological study was carried out with a focus on all HIV cases reported in Alagoas State, Northeast Brazil from 2007 to 2016 using its 102 municipalities as the units of our analysis. Data from the Brazilian information systems were used. Georeferenced data were analyzed using TerraView 4.2.2 software, QGis 2.18.2 and GeoDa 1.14.0. Time trend analyses were performed by the Joinpoint Regression software and the spatial analyses included the empirical Bayesian model and Moran autocorrelation. Spatial regression was used to determine the influence of space on HIV incidence rate and socioeconomic inequalities. There was an increasing trend of HIV rates, especially in the municipalities of the interior. Significant spatial correlations were observed with the formation of clusters with emphasis on the coast of the state and in tourist regions. Spatial regression explained 46% of the dependent variable. The HIV incidence rate was positively influenced by rate of primary health care units (P=0.00), and negatively by Gini index (P=0.00) and proportion of heads of household without or low education (P=0.02). We conclude that the relationship found between indicators of better socioeconomic conditions and HIV infection suggests unequal access to the diagnosis of infection. Prevention and control strategies can be established according to each epidemiological reality.

QSAR rationales for the dipeptidyl peptidase-4 (DPP-4) inhibitors: The imidazolopyrimidine amides

The DPP4 inhibition activity of imidazolopyrimidine amides has been quantitatively analyzed in terms of chemometric descriptors. The statistically validated QSAR models provided rationales to explain the inhibition activity of these congeners. The descriptors identified through CP-MLR analysis have highlighted the role of mean electrotopological state (Ms), number of double bonds in molecular structure (nDB), 2D Petitijean shape index (PJI2), Moran autocorrelation of lag-2/weighted by atomic polarizabilities (MATS2p), Moran autocorrelation of lag-6 and lowest eigenvalue n.5 of Burden matrix /weighted by atomic Sanderson electronegativities (MATS6e and BELe5), lowest eigenvalue n.3 and highest eigenvalue n.1 of Burden matrix/weighted by atomic van der Waals volumes (BELv3 and BEHv1). In addition to these 2nd order mean Galvez topological charge index (JGI2), number of ring tertiary C(sp3) (nCrHR) and R--CR--X type structural fragments (C-028) have also shown prevalence to model the inhibitory activity. From statistically validated models, positive contribution of descriptors Ms, PJI2, JGI2, MATS2p, BELe5, BELv3 and BEHv1 suggested that higher values of these are conducive in improving the DPP4 inhibition activity. On the other hand, negative contribution of descriptors nDB, C-028, nCrHR and MATS6e advocated that absence of number of double bonds (nDB), R--CR--X type structural fragment (C-028), number of ring tertiary C(sp3) (nCrHR) and lower value of descriptor MATS6e would be advantageous. PLS analysis has confirmed the dominance of the CP‐MLR identified descriptors and applicability domain analysis revealed the acceptable predictability of suggested models. All the compounds are within the applicability domain of the proposed models and were evaluated correctly.

Replicated point processes with application to population dynamics models

In this paper we study spatially clustered distribution of individuals using point process theory. In particular we discuss the spatially explicit neutral model of population dynamics of Shimatani (2010) which extends previous works on Malécot theory of isolation by distance. We reformulate Shimatani model of replicated Neyman–Scott process to allow for a general dispersal kernel function and we show that the random migration hypothesis can be substituted by the long dispersal distance property of the kernel. Moreover, the extended framework presented here is fit to handle spatially explicit statistical estimators of genetic variability like Moran autocorrelation index or Sørensen similarity index. We discuss the pivotal role of the choice of dispersal kernel for the above estimators in a toy model of dynamic population genetics theory.

Spatio-temporal distribution analysis of zoonotic cutaneous leishmaniasis in Qom Province, Iran.

Geographic information system (GIS) nowadays is one of the most helpful epidemiological tools for identifying the high risk areas of cutaneous leishmaniasis (CL). This study was conducted to determine the spatio-temporal distribution of CL in Qom province during 2009-2017. In a cross-sectional study, for the survey of spatial dispersion of CL in the study region, the incidence rate of disease was calculated in all of 23 villages during 2009-2017. Then, spatial analysis of the infection was performed using two methods: spatial autocorrelation (Moran's I)in order to determine the special distribution pattern of disease and Kriging method to reveal high risk areas for disease. The incidence of CL in Qom province has been decreasing as of 2009-2015 and increasing in 2015-2017. The highest incidence was stated in 2009 (36.5 per 100,000) and the least was reported in 2015 (13.3 per 100,000). The Moran autocorrelation index revealed that the study area has a cluster pattern. The temporal distribution of disease incidence showed that northeast, southwest and northwest parts of Qom province involved highest incidence of CL in 90% significant level. Leishmaniasis incidence is a function of spatial and geographical trends, thus spatial variations of the infection incidence illustrate that the incidence rate does not increase or decrease from one region to another intensively. The results of this study indicate that marking high risk areas using spatial analysis can be helpful as a main tool in CL control and prevention.

Predicting apoptosis protein subcellular localization by integrating auto-cross correlation and PSSM into Chou’s PseAAC

The prediction of subcellular localization of an apoptosis protein is still a challenging task, and existing methods mainly based on protein primary sequences. In this study, we propose a novel model called MACC–PSSM by integrating Moran autocorrelation and cross correlation with PSSM. Then a 3600-dimensional feature vector is constructed to predict apoptosis protein subcellular localization. Finally, 210 features are selected using principal component analysis (PCA) on the ZW225 dataset, and support vector machine is adopted as classifier. To evaluate the performance of the proposed method, jackknife cross-validation tests are performed on two widely used benchmark datasets: ZW225 and CL317. Our model achieves competitive performance on prediction accuracies, especially for the overall prediction accuracies for datasets ZW225 and CL317, which reach 84.9% and 90.5%, respectively. Comparison of our results with other methods demonstrates that MACC–PSSM model can be used as a potential candidate for the accurate prediction of apoptosis protein subcellular localization.

CP-MLR Directed QSAR Rationales for the 1-aryl Sulfonyl Tryptamines as 5-HT6 Receptor Ligands

A QSAR study has been carried out to rationalize the 5-HT6 receptor binding affinities of the 1-aryl sulfonyl tryptamine derivatives using Dragon descriptors. A higher value of molecular symmetry and topology accounting Randic shape index descriptor PW4 (path/walk 4) would be favorable to improve the binding affinity. Presence of more number of bromine atoms (descriptor nBR) and presence of such structural fragment in which a hydrogen atom attached to sp3 hybridized carbon with no hetero atom rather than one hetero atom attached to next carbon atom (descriptors H-046 and H-052) will be supportive to the activity. The prevalence of atomic properties to explain the binding affinity is evident from the associations of polarizability to the path length 7 of Moran autocorrelation (MATS7p), masses to eigenvalues n.2 and 7 of Burden m atrix (BELm2 and BEHm7), Sanderson electronegativity to highest eigenvalue n.2 Burden matrix (BEHe2) and van der Waals volume to path length 8 of Geary autocorrelation (GATS8v) and charge content in terms of topological and mean topological charge indices (GGI3 and JGI2). The dominance of the information content of the descriptors, emerged in CP-MLR models, has also confirmed by the PLS analysis. The derived QSAR models and descriptors shared in these models revealed that the substituents of tryptamine moiety have sufficient scope for further modification.

PseKNC-General: a cross-platform package for generating various modes of pseudo nucleotide compositions.

The avalanche of genomic sequences generated in the post-genomic age requires efficient computational methods for rapidly and accurately identifying biological features from sequence information. Towards this goal, we developed a freely available and open-source package, called PseKNC-General (the general form of pseudo k-tuple nucleotide composition), that allows for fast and accurate computation of all the widely used nucleotide structural and physicochemical properties of both DNA and RNA sequences. PseKNC-General can generate several modes of pseudo nucleotide compositions, including conventional k-tuple nucleotide compositions, Moreau-Broto autocorrelation coefficient, Moran autocorrelation coefficient, Geary autocorrelation coefficient, Type I PseKNC and Type II PseKNC. In every mode, >100 physicochemical properties are available for choosing. Moreover, it is flexible enough to allow the users to calculate PseKNC with user-defined properties. The package can be run on Linux, Mac and Windows systems and also provides a graphical user interface. The package is freely available at: http://lin.uestc.edu.cn/server/pseknc.

Prediction of protein-protein interactions based on protein-protein correlation using least squares regression.

In order to transform protein sequences into the feature vectors, several works have been done, such as computing auto covariance (AC), conjoint triad (CT), local descriptor (LD), moran autocorrelation (MA), normalized moreaubroto autocorrelation (NMB) and so on. In this paper, we shall adopt these transformation methods to encode the proteins, respectively, where AC, CT, LD, MA and NMB are all represented by '+' in a unified manner. A new method, i.e. the combination of least squares regression with '+' (abbreviated as LSR(+)), will be introduced for encoding a protein-protein correlation-based feature representation and an interacting protein pair. Thus there are totally five different combinations for LSR(+), i.e. LSRAC, LSRCT, LSRLD, LSRMA and LSRNMB. As a result, we combined a support vector machine (SVM) approach with LSR(+) to predict protein-protein interactions (PPI) and PPI networks. The proposed method has been applied on four datasets, i.e. Saaccharomyces cerevisiae, Escherichia coli, Homo sapiens and Caenorhabditis elegans. The experimental results demonstrate that all LSR(+) methods outperform many existing representative algorithms. Therefore, LSR(+) is a powerful tool to characterize the protein-protein correlations and to infer PPI, whilst keeping high performance on prediction of PPI networks.