Using Chou’s pseudo amino acid composition based on approximate entropy and an ensemble of AdaBoost classifiers to predict protein subnuclear location

The knowledge of subnuclear localization in eukaryotic cells is essential for understanding the life function of nucleus. Developing prediction methods and tools for proteins subnuclear localization become important research fields in protein science for special characteristics in cell nuclear. In this study, a novel approach has been proposed to predict protein subnuclear localization. Sample of protein is represented by Pseudo Amino Acid (PseAA) composition based on approximate entropy (ApEn) concept, which reflects the complexity of time series. A novel ensemble classifier is designed incorporating three AdaBoost classifiers. The base classifier algorithms in three AdaBoost are decision stumps, fuzzy K nearest neighbors classifier, and radial basis-support vector machines, respectively. Different PseAA compositions are used as input data of different AdaBoost classifier in ensemble. Genetic algorithm is used to optimize the dimension and weight factor of PseAA composition. Two datasets often used in published works are used to validate the performance of the proposed approach. The obtained results of Jackknife cross-validation test are higher and more balance than them of other methods on same datasets. The promising results indicate that the proposed approach is effective and practical. It might become a useful tool in protein subnuclear localization. The software in Matlab and supplementary materials are available freely by contacting the corresponding author.     

Using the concept of Chou’s pseudo amino acid composition to predict protein subcellular localization: an approach by incorporating evolutionary information and von Neumann entropies

The rapidly increasing number of sequence entering into the genome databank has called for the need for developing automated methods to analyze them. Information on the subcellular localization of new found protein sequences is important for helping to reveal their functions in time and conducting the study of system biology at the cellular level. Based on the concept of Chou’s pseudo-amino acid composition, a series of useful information and techniques, such as residue conservation scores, von Neumann entropies, multi-scale energy, and weighted auto-correlation function were utilized to generate the pseudo-amino acid components for representing the protein samples. Based on such an infrastructure, a hybridization predictor was developed for identifying uncharacterized proteins among the following 12 subcellular localizations: chloroplast, cytoplasm, cytoskeleton, endoplasmic reticulum, extracell, Golgi apparatus, lysosome, mitochondria, nucleus, peroxisome, plasma membrane, and vacuole. Compared with the results reported by the previous investigators, higher success rates were obtained, suggesting that the current approach is quite promising, and may become a useful high-throughput tool in the relevant areas.     

Genetic programming for creating Chou’s pseudo amino acid based features for submitochondria localization

Given a protein that is localized in the mitochondria it is very important to know the submitochondria localization of that protein to understand its function. In this work, we propose a submitochondria localizer whose feature extraction method is based on the Chou's pseudo-amino acid composition. The pseudo-amino acid based features are obtained by combining pseudo-amino acid compositions with hundreds of amino-acid indices and amino-acid substitution matrices, then from this huge set of features a small set of 15 "artificial" features is created. The feature creation is performed by genetic programming combining one or more "original" features by means of some mathematical operators. Finally, the set of combined features are used to train a radial basis function support vector machine. This method is named GP-Loc. Moreover, we also propose a very few parameterized method, named ALL-Loc, where all the "original" features are used to train a linear support vector machine. The overall prediction accuracy obtained by GP-Loc is 89% when the jackknife cross-validation is used, this result outperforms the performance obtained in the literature (85.2%) using the same dataset. While the overall prediction accuracy obtained by ALL-Loc is 83.9%.     

Predicting protein submitochondria locations by combining different descriptors into the general form of Chou’s pseudo amino acid composition

Knowledge of the submitochondria location of protein is integral to understanding its function and a necessity in the proteomics era. In this work, a new submitochondria data set is constructed, and an approach for predicting protein submitochondria locations is proposed by combining the amino acid composition, dipeptide composition, reduced physicochemical properties, gene ontology, evolutionary information, and pseudo-average chemical shift. The overall prediction accuracy is 93.57% for the submitochondria location and 97.79% for the three membrane protein types in the mitochondria inner membrane using the algorithm of the increment of diversity combined with the support vector machine. The performance of the pseudo-average chemical shift is excellent. For contrast, the method is also used to predict submitochondria locations in the data set constructed by Du and Li; an accuracy of 94.95% is obtained by our method, which is better than that of other existing methods.     

Predicting DNA-binding proteins: approached from Chou’s pseudo amino acid composition and other specific sequence features

Summary. DNA-binding proteins play a pivotal role in gene regulation. It is vitally important to develop an automated and efficient method for timely identification of novel DNA-binding proteins. In this study, we proposed a method based on alone the primary sequences of proteins to predict the DNA-binding proteins. DNA-binding proteins were encoded by autocross-covariance transform, pseudo-amino acid composition, dipeptide composition, respectively and also the different combinations of the three encoded methods; further, these feature matrices were applied to support vector machine classifiers to predict the DNA-binding proteins. All modules were trained and validated by the jackknife cross-validation test. Through comparing the performance of these substituted modules, the best result was obtained from pseudo-amino acid composition with the overall accuracy of 96.6% and the sensitivity of 90.7%. The results suggest that it can efficiently predict the novel DNA-binding proteins only using the primary sequences. Authors’ address: Menglong Li, College of Chemistry, Sichuan University, Chengdu, Sichuan 610064, P.R. China     

Constructing a personalized prognostic risk model for colorectal cancer using machine learning and multi-omics approach based on epithelial–mesenchymal transition-related genes

The progression and the metastatic potential of colorectal cancer (CRC) are intricately linked to the epithelial–mesenchymal transition (EMT) process. The present study harnesses the power of machine learning combined with multi-omics data to develop a risk stratification model anchored on EMT-associated genes. The aim is to facilitate personalized prognostic assessments in CRC. We utilized publicly accessible gene expression datasets to pinpoint EMT-associated genes, employing a CoxBoost algorithm to sift through these genes for prognostic significance. The resultant model, predicated on gene expression levels, underwent rigorous independent validation across various datasets. Our model demonstrated a robust capacity to segregate CRC patients into distinct high- and low-risk categories, each correlating with markedly different survival probabilities. Notably, the risk score emerged as an independent prognostic indicator for CRC. High-risk patients were characterized by an immunosuppressive tumor milieu and a heightened responsiveness to certain chemotherapeutic agents, underlining the model's potential in steering tailored oncological therapies. Moreover, our research unearthed a putative repressive interaction between the long non-coding RNA PVT1 and the EMT-associated genes TIMP1 and MMP1, offering new insights into the molecular intricacies of CRC. In essence, our research introduces a sophisticated risk model, leveraging machine learning and multi-omics insights, which accurately prognosticates outcomes for CRC patients, paving the way for more individualized and effective oncological treatment paradigms.     

Accounting for non-independence of extinction probabilities in the derivation of conservation priorities based on Weitzman’s diversity concept

In the original formulation of Weitzman’s diversity concept, extinction probabilities of different operational taxonomic units (OTUs) are implicitly defined to be independent. In this study, it is shown, that dependencies like concurrence or synergistic relations between OTUs can be accounted for by assuming that joint extinction probabilities differ from the product of the extinction probabilities of the interacting OTUs. A fully analytical treatment is provided for the case of two interacting OTUs, and all cases are illustrated with an example data set. For the case of concurring OTUs, the following general results are derived: (a) concurrence between OTUs always reduces the amount of diversity expected to be conserved in the future; (b) concurrence has a more adverse effect on the more endangered OTUs involved; (c) concurrence can change conservation priorities between OTUs; and (d) with high levels of concurrence, investments in the conservation of some of the concurring OTUs can have a negative effect on the overall diversity conserved. In addition to conservation activities targeted towards some of the OTUs, reduction of the causes of concurrence may be a valid and cost-efficient alternative. For the case of synergistic dependencies between OTUs it was found, that such dependencies always increase the conservation potential of the involved OTUs but may lead to a change of priority ranking in extreme cases. Finally possible extensions and generalisations of the suggested approach are discussed and it is argued, that by adopting these extensions Weitzman’s diversity concept becomes an even more powerful and flexible tool to derive conservation priorities both in an ecological and in a farm animal context.     

The influence of fermentation conditions and recycling on the phospholipid and fatty acid composition of the brewer’s yeast plasma membranes

Phospholipid (PL) and fatty acid (FA) compositions of the plasma membrane (PM), as well as the FA composition of the PM phosphatidylcholine (PtdCho) and phosphatidylethanolamine (PtdEtn) in the pure culture (zero generation) and the first three recycled generations of the bottom-fermenting brewer’s yeast, have been determined. The PL composition differed markedly among the generations; in the zero generation, phosphatidylinositol (PtdIns) was the main PL, accounting for 27% of total PLs, followed by phosphatidic acid and PtdCho. In all recycled generations, the main PL was PtdCho with a marked increase in the first generation compared with the zero (32% and 20%, respectively), followed by PtdIns in the first and second generations. In the FA composition of the PM, 22 FAs were identified, ranging from C₁₀ to C₂₆. The compositions of the PM FAs, as well as those of PtdCho and PtdEtn, were characterised by a high preponderance of C₁₆ acids. Saturated FAs prevailed in the zero generation, whilst unsaturated prevailed in the first and second generation. Although the profiles of FAs in PtdCho and PtdEtn were similar, some marked differences were observed, pointing out to their specific functions in the regulation of membrane properties.     

The effect of using a case study on the academic achievement of students in learning about the topic of ‘Vitamins’

This study investigates the impact of the Case-Based Learning (CBL) method for the topic of ‘B6, B9 and B12 Vitamins’ on students’ academic achievement in a biochemistry course for an associate degree level in health. To this end, a case study with the title ‘The Reasons for Depression: Do We Know What They Are?’ was developed and implemented. The study had a one-group pre-test and post-test research design. The ‘Vitamins’ Achievement Test’ (VAT) and a Structured Interview Form were used as data collection tools. First-year students of Medical Laboratory Techniques at the Ahmet Erdogan Vocational School of Health Services at Bulent Ecevit University (N = 34) who were aged between18 and 20 made up the study group. The VAT and the Structured Interview Form were analysed using content analysis and the paired-samples t-test was used for the VAT. The results indicated that the frequency of students’ responses in the ‘clear understanding’ category improved in the VAT post-test and it was concluded that there was a significant positive difference in the post-test scores of students. The results of the structured interview indicated that most of the students had positive opinions about the method, material and case study.     

The effect of a digital learning environment on children’s conceptions about the protection of endemic plants

This study presents the results of a pilot learning intervention for improving children’s ideas about plant protection. The research was executed in two phases. The first phase aimed at exploring children’s ideas about plant protection. These ideas were taken into account for the design and development of a digital learning environment. The second phase concerned the development, implementation and evaluation of the learning environment. In the first phase, 262 participants (10–12 years old) were asked to write a short text about ‘Environmental protection’. During the second phase, twenty-six participants (10–12 years old) were asked to write a text on ‘How we can protect the endemic plants’, before and after the implementation of the learning activities. Responses were content analysed and their meaning was classified according to the coding scheme of Blanchet-Cohen, Ragan, and Amsden (Children, Youth and Environments 2003; 13: 1–7). The results of the first phase showed that participants mentioned individual lifestyle actions of environmental protection and, therefore, the learning environment should emphasise the importance of other types of environmental protection (eg political actions, legislation, social actions). The proposed learning activities enriched participants’ awareness about the importance of social and legal actions for plant protection.     

The risk prediction of Alzheimer’s disease based on the deep learning model of brain 18F-FDG positron emission tomography

In order to predict the risks of Alzheimer’s Disease (AD) based on the deep learning model of brain 18F-FDG positron emission tomography (PET), a total of 350 mild cognitive impairment (MCI) participants from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database were selected as the research objects; in addition, the Convolutional Architecture for Fast Feature Embedding (CAFFE) was selected as the framework of the deep learning platform; the FDG PET image features of each participant were extracted by a deep convolution network model to construct the prediction and classification models; therefore, the MCI stage features were classified and the transformation was predicted. The results showed that in terms of the MCI transformation prediction, the sensitivity and specificity of conv3 classification were respectively 91.02% and 77.63%; in terms of the Late Mild Cognitive Impairment (LMCI) and Early Mild Cognitive Impairment (EMCI) classification, the accuracy of conv5 classification was 72.19%, and the sensitivity and specificity of conv5 were all 73% approximately. Thus, it was seen that the model constructed in the research could be used to solve the problems of MCI transformation prediction, which also had certain effects on the classifications of EMCI and LMCI. The risk prediction of AD based on the deep learning model of brain 18F-FDG PET discussed in the research matched the expected results. It provided a relatively accurate reference model for the prediction of AD. Despite the deficiencies of the research process, the research results have provided certain references and guidance for the future exploration of accurate AD prediction model; therefore, the research is of great significance.     

Spatial heterogeneity of the species composition of a clavarioid fungi’s compex in the Eurasian Arctic

Using the example of a model group of macromycete (clavarioid fungi), a large-scale investigation into the mycological complex of the Eurasian Arctic is conducted. The species composition of clavarioid fungi’s complex is revealed in all longitudinal sectors and latitudinal subzones, and a comparative analysis is carried out. It has been determined that, among groups of aphyllophoroid fungi, the clavarioid life form is the most adapted to the extremally psychrophilic conditions of the Arctic. It is shown that the near-oceanic sectors are the richest, whereas the continental sectors are much poorer. The distribution of the species composition of fungi conforms to the similar distribution of flowering plants, especially hemicryptophytes. The average annual quantity of atmospheric precipitation is the leading climatic factor. The differences make it possible to subdivide the Eurasian Arctic into four mycogeographical regions: Atlantic (European), Siberian, Chukotian (Beringian), and High Arctic.     

Adaptive control of an operator’s performance based on biological feedback using the parameters of spatial synchronization of brain cortex areas

The efficiency of an operator’s performance under the determined (D-activity) and stochastic (S-activity) conditions depends on the readiness and synchronization of the frontoparietal and parietooccipital brain cortex areas. The algorithm for the generation of the feedback signal and program of adaptive control based on parameters of these cortical areas’ spatial synchronization were developed. To develop the adaptive control based on this algorithm, two series of experiments on volunteers were performed. The results of the study showed a connection between the initial readiness estimated by Luscher’s test and the efficiency of S- and D-activities modeled by computer games. The objective signs of initial readiness for S- and D-activity were found using parameters of spatial synchronization of the studied cortical areas’ activity in different spectral bands. The possibility of developing adaptive control skills based on the algorithm of the feedback signal generation and maintenance of these skills for one month was also demonstrated. Adaptive control sessions were found to improve characteristics of S- and D-activity, modeled by computer games.     

Genetic mapping of the wheat dimeric α-amylase inhibitor multi-gene family using allele-specific primers based on intergenomic SNPs

Single nucleotide polymorphisms (SNPs) identified in EST sequences can be used to map expressed genes. Though SNPs are useful markers for genetic mapping, SNP mapping of genes in common wheat is challenging because the genetic complement of wheat consists of three closely related genomes (designated A, B, and D), and most genes are present in triplicate sets. Mapping multi-gene family members is further complicated by the fact that it is difficult to distinguish SNP differences between the various paralogs from those between the different genomes. We have developed a PCR-based method for assigning wheat EST sequences to their proper genetic loci by first identifying and mapping SNPs that distinguish the three genomes. To develop this method, we focused on EST sequences encoding the dimeric α-amylase inhibitors (WDAI), The WDAI coding regions of hexaploid wheat were aligned. The sequences were classified into three groups based on nucleotide variations. Twenty-two SNPs were identified that distinguish the three groups. Group-specific primers based on these SNPs were designed to permit selective amplification of each group. The chromosomal location of each group was then determined using Group 3 ditelosomic lines of Chinese Spring. Groups 1 and 2 were assigned to chromosome locations 3DS and 3BS, respectively, whereas no sequence could be assigned to 3AS. A remarkable feature of this method is the ability to discriminate the location of homoeologous multigenes in the three genomes of wheat. This strategy can be useful for assigning unknown wheat EST sequences to specific chromosomes.     

Studies on the UV spectrum of poly(γ-glutamic acid) based on development of a simple quantitative method

A simple and valid ultraviolet (UV) spectrophotometric method for the determination of poly(γ-glutamic acid) is developed. The method is based on the UV absorption spectrum of γ-PGA in aqueous solution, which exhibits a maximum absorption wavelength at 216 nm. The results obtained were comparable to those obtained with the reported high-performance liquid chromatography (HPLC) method according to ICH guidelines. Under the proposed procedure, the calibration graph is linear over the range of 20-200 μg/ml with regression correlation coefficient of 0.9997. Precision (%R.S.D.<1.50) and recovery (%R.>99.29%) are good. The limit of detection (LOD) and limit of quantitation (LOQ) are 0.39 and 1.19 μg/ml, respectively. These results agree well with those of HPLC method. Its spectrum properties studies showed that the spectrum of γ-PGA remarkably changed with an increase in temperature due to γ-PGA was digested into glutamate monomer. In spite of this, the determining procedure could carried out in a wide temperature range (25-50°C). In addition, the method is not influenced by the molecular weight, but the measurement system need to control in pH 3.0-10.0 and ionic strength not more than 0.5M. The proposed method is applied successfully for high-throughput quantification of poly(γ-glutamic acid) in biological samples. The advantages of the UV method are simplicity of operation, rapidity, sensitive, low-cost and high-throughput.