A multiple linear regression method was applied to predict real values of solvent accessibility from the sequence and evolutionary information. This method allowed us to obtain coefficients of regression and correlation between the occurrence of an amino-acid residue at a specific target and its sequence neighbor positions on the one hand, and the solvent accessibility of that residue on the other. Our linear regression model based on sequence information and evolutionary models was found to predict residue accessibility with 18.9% and 16.2% mean absolute error respectively, which is better than or comparable to the best available methods. A correlation matrix for several neighbor positions to examine the role of evolutionary information at these positions has been developed and analyzed. As expected, the effective frequency of hydrophobic residues at target positions shows a strong negative correlation with solvent accessibility, whereas the reverse is true for charged and polar residues. The correlation of solvent accessibility with effective frequencies at neighboring positions falls abruptly with distance from target residues. Longer protein chains have been found to be more accurately predicted than their smaller counterparts.

No abstract

We developed dictionaries of two-, three-, and five-residue patterns in proteins and computed the average solvent accessibility of the central residues in their native proteins. These dictionaries serve as a look-up table for making subsequent predictions of solvent accessibility of amino acid residues. We find that predictions made in this way are very close to those made using more sophisticated methods of solvent accessibility prediction. We also analyzed the effect of immediate neighbors on the solvent accessibility of residues. This helps us in understanding how the same residue type may have different accessible surface areas in different proteins and in different positions of the same protein. We observe that certain residues have a tendency to increase or decrease the solvent accessibility of their neighboring residues in C- or N-terminal positions. Interestingly, the C-terminal and N-terminal neighbor residues are found to have asymmetric roles in modifying solvent accessibility of residues. As expected, similar neighbors enhance the hydrophobic or hydrophilic character of residues. Detailed look-up tables are provided on the web at www.netasa.org/look-up/.

A number of methods for predicting levels of solvent accessibility or accessible surface area (ASA) of amino acid residues in proteins have been developed. These methods either predict regularly spaced states of relative solvent accessibility or an analogue real value indicating relative solvent accessibility. While discrete states of exposure can be easily obtained by post prediction assignment of thresholds to the predicted or computed real values of ASA, the reverse, that is, obtaining a real value from quantized states of predicted ASA, is not straightforward as a two-state prediction in such cases would give a large real valued errors. However, prediction of ASA into larger number of ASA states and then finding a corresponding scheme for real value prediction may be helpful in integrating the two approaches of ASA prediction. We report a novel method of obtaining numerical real values of solvent accessibility, using accumulation cutoff set and support vector machine. This so-called SVM-Cabins method first predicts discrete states of ASA of amino acid residues from their evolutionary profile and then maps the predicted states onto a real valued linear space by simple algebraic methods. Resulting performance of such a rigorous approach using 13-state ASA prediction is at least comparable with the best methods of ASA prediction reported so far. The mean absolute error in this method reaches the best performance of 15.1% on the tested data set of 502 proteins with a coefficient of correlation equal to 0.66. Since, the method starts with the prediction of discrete states of ASA and leads to real value predictions, performance of prediction in binary states and real values are simultaneously optimized.

To reduce effectively the reading anxiety of learners while reading English articles, a C4.5 decision tree, a widely used data mining technique, was used to develop a personalized reading anxiety prediction model (PRAPM) based on individual learners' reading annotation behavior in a collaborative digital reading annotation system (CDRAS). In addition to forecasting immediately the reading anxiety levels of learners, the proposed PRAPM can be used to identify the key factors that cause reading anxiety based on the fired prediction rules determined by the developed decision tree. By understanding these key factors that cause reading anxiety, instructors can apply reading strategies to reduce reading anxiety, thus promoting English-language reading performance. To assess whether the proposed PRAPM can assist instructors in reducing the reading anxiety of learners, this study applies the quasi-experimental method to compare the learning performance of three learning groups, which are, respectively, supported by a CDRAS with individual annotations, collaborative annotations, and collaborative annotations with online instructor's support to reduce reading anxiety by the proposed PRAPM. The instructional experiment was conducted on Grade 7 students at Taipei Municipal Wan-Fang high school. Experimental results indicate that the average correct prediction rate of the proposed PRAPM in identifying the reading anxiety levels of learners was as high as 70%. Moreover, analytical results show that the collaborative annotation with online instructor's support for reducing reading anxiety by the proposed PRAPM indeed helps learners reduce reading anxiety, particularly for the male learners, showing that gender difference exists. Furthermore, based on online instructor's support for reducing reading anxiety by the proposed PRAPM, the correlation analysis also shows that the online instructor's interaction with the male learners is significantly correlated with the reading anxiety reduction. Furthermore, English-language learning performance of the three learners groups, which were given a CDRAS with different learning mechanisms, was significantly promoted.Interactive Learning Environments, 2014 http://dx.

No abstract

No abstract

Purpose Developing attention-aware systems and interfaces based on eye tracking technology could revolutionize mainstream human–computer interaction to make the interaction between human beings and computers more intuitive, effective and immersive than can be achieved traditionally using a computer mouse. This paper aims to propose an eye-controlled interactive reading system (ECIRS) that uses human eyes instead of the traditional mouse to control digital text to support screen-based digital reading. Design/methodology/approach This study uses a quasi-experimental design to examine the effects of an experimental group and a control group of learners who, respectively, used the ECIRS and a mouse-controlled interactive reading system (MCIRS) to conduct their reading of two types of English-language text online – pure text and Q&A-type articles on reading comprehension, cognitive load, technology acceptance, and reading behavioural characteristics. Additionally, the effects of learners with field-independent (FI) and field-dependence (FD) cognitive styles who, respectively, used the ECIRS and MCIRS to conduct their reading of two types of English-language text online – pure text and Q&A-type articles on reading comprehension are also examined. Findings Analytical results reveal that the reading comprehension of learners in the experimental group significantly exceeded those in the control group for the Q&A article, but the difference was insignificant for the pure text article. Moreover, the ECIRS improved the reading comprehension of field-independent learners more than it did that of field-dependent learners. Moreover, neither the cognitive loads of the two groups nor their acceptance of the technology differed significantly, whereas the reading time of the experimental group significantly exceeded that of the control group. Interestingly, for all articles, the control group of learners read mostly from top to bottom without repetition, whereas most of the learners in the experimental group read most paragraphs more than once. Clearly, the proposed ECIRS supports deeper digital reading than does the MCIRS. Originality/value This study proposes an emerging ECIRS that can automatically provide supplementary information to a reader and control a reading text based on a reader’s eye movement to replace the widely used mouse-controlled reading system on a computer screen to effectively support digital reading for English language learning. The implications of this study are that the highly interactive reading patterns of digital text with ECIRS support increase motivation and willingness to learn while giving learners a more intuitive and natural reading experience as well as reading an article online with ECIRS support guides learners’ attention in deeper digital reading than does the MCIRS because of simultaneously integrating perceptual and cognitive processes of selection, awareness and control based on human eye movement.