Digital affordances exist on the touchscreen, but the affordance of virtual buttons on smartphones is unknown. Therefore, this study investigated the on-screen affordances by examining whether the visual properties of virtual keyboard buttons could afford possible clicking actions and affect the entry performance. This study employed a three-way within-subject design: 2 (Symbol Position: standard mode vs. corrective mode) × 2 (Button Border: bordered button vs. borderless button) × 26 (Button Position: 26 positions). In the serial tapping task, 30 university students tapped virtual keyboard buttons with four button types. The results confirmed that the symbol-position and button-border variables influenced clicking actions. When employing offset-correcting symbols, the entry accuracy of virtual keyboard buttons increased without the speed-accuracy tradeoff. Additionally, button borders improved the perceived usability of virtual keyboard buttons despite failing to enhance the entry accuracy and speed. However, the button position moderated the effects of the symbol-position and button-border variables.

Deep Neural Networks (DNNs) have revolutionized artificial intelligence, achieving impressive results on diverse data types, including images, videos, and texts. However, DNNs still lag behind Gradient Boosting Decision Trees (GBDT) on tabular data, a format extensively utilized across various domains. This paper introduces DOFEN, which stands for Deep Oblivious Forest ENsemble. DOFEN is a novel DNN architecture inspired by oblivious decision trees and achieves on-off sparse selection of columns. DOFEN surpasses other DNNs on tabular data, achieving state-of-the-art performance on the well-recognized benchmark: Tabular Benchmark, which includes 73 total datasets spanning a wide array of domains. The code of DOFEN is available at: https://github.com/Sinopac-Digital-Technology-Division/DOFEN

Tabular data is arguably one of the most commonly used data structures in various practical domains, including finance, healthcare and e-commerce. The inherent heterogeneity allows tabular data to store rich information. However, based on a recently published tabular benchmark, we can see deep neural networks still fall behind tree-based models on tabular datasets. In this paper, we propose Trompt–which stands for Tabular Prompt–a novel architecture inspired by prompt learning of language models. The essence of prompt learning is to adjust a large pre-trained model through a set of prompts outside the model without directly modifying the model. Based on this idea, Trompt separates the learning strategy of tabular data into two parts. The first part, analogous to pre-trained models, focus on learning the intrinsic information of a table. The second part, analogous to prompts, focus on learning the variations among samples. Trompt is evaluated with the benchmark mentioned above. The experimental results demonstrate that Trompt outperforms state-of-the-art deep neural networks and is comparable to tree-based models.

BACKGROUND: Signal peptides play an important role in protein sorting, which is the mechanism whereby proteins are transported to their destination. Recognition of signal peptides is an important first step in determining the active locations and functions of proteins. Many computational methods have been proposed to facilitate signal peptide recognition. In recent years, the development of deep learning methods has seen significant advances in many research fields. However, most existing models for signal peptide recognition use one-hidden-layer neural networks or hidden Markov models, which are relatively simple in comparison with the deep neural networks that are used in other fields. RESULTS: This study proposes a convolutional neural network without fully connected layers, which is an important network improvement in computer vision. The proposed network is more complex in comparison with current signal peptide predictors. The experimental results show that the proposed network outperforms current signal peptide predictors on eukaryotic data. This study also demonstrates how model reduction and data augmentation helps the proposed network to predict bacterial data. CONCLUSIONS: The study makes three contributions to this subject: (a) an accurate signal peptide recognizer is developed, (b) the potential to leverage advanced networks from other fields is demonstrated and (c) important modifications are proposed while adopting complex networks on signal peptide recognition.

BACKGROUND: Zebrafish is a widely used model organism for studying heart development and cardiac-related pathogenesis. With the ability of surviving without a functional circulation at larval stages, strong genetic similarity between zebrafish and mammals, prolific reproduction and optically transparent embryos, zebrafish is powerful in modeling mammalian cardiac physiology and pathology as well as in large-scale high throughput screening. However, an economical and convenient tool for rapid evaluation of fish cardiac function is still in need. There have been several image analysis methods to assess cardiac functions in zebrafish embryos/larvae, but they are still improvable to reduce manual intervention in the entire process. This work developed a fully automatic method to calculate heart rate, an important parameter to analyze cardiac function, from videos. It contains several filters to identify the heart region, to reduce video noise and to calculate heart rates. RESULTS: The proposed method was evaluated with 32 zebrafish larval cardiac videos that were recording at three-day post-fertilization. The heart rate measured by the proposed method was comparable to that determined by manual counting. The experimental results show that the proposed method does not lose accuracy while largely reducing the labor cost and uncertainty of manual counting. CONCLUSIONS: With the proposed method, researchers do not have to manually select a region of interest before analyzing videos. Moreover, filters designed to reduce video noise can alleviate background fluctuations during the video recording stage (e.g. shifting), which makes recorders generate usable videos easily and therefore reduce manual efforts while recording.

BACKGROUND: Next-generation sequencing (NGS) technologies has brought an unprecedented amount of genomic data for analysis. Unlike array-based profiling technologies, NGS can reveal the expression profile across a transcript at the base level. Such a base-level read coverage provides further insights for alternative mRNA splicing, single-nucleotide polymorphism (SNP), novel transcript discovery, etc. However, to our best knowledge, none of existing NGS viewers can timely visualize genome-wide base-level read coverages in an interactive environment. RESULTS: This study proposes an efficient visualization pipeline and implements a lightweight read coverage viewer, Light-RCV, with the proposed pipeline. Light-RCV consists of four featured designs on the path from raw NGS data to the final visualized read coverage: i) read coverage construction algorithm, ii) multi-resolution profiles, iii) two-stage architecture and iv) storage format. With these designs, Light-RCV achieves a < 0.5s response time on any scale of genomic ranges, including whole chromosomes. Finally, a case study was performed to demonstrate the importance of visualizing base-level read coverage and the value of Light-RCV. CONCLUSIONS: Compared with multi-functional genome viewers such as Artemis, Savant, Tablet and Integrative Genomics Viewer (IGV), Light-RCV is designed only for visualization. Therefore, it does not provide advanced analyses. However, its backend technology provides an efficient kernel of base-level visualization that can be easily embedded to other viewers. This viewer is the first to provide timely visualization of genome-wide read coverage at the base level in an interactive environment. The software is available for free at http://lightrcv.ee.ncku.edu.tw.

MOTIVATION: Determination of the binding affinity of a protein-ligand complex is important to quantitatively specify whether a particular small molecule will bind to the target protein. Besides, collection of comprehensive datasets for protein-ligand complexes and their corresponding binding affinities is crucial in developing accurate scoring functions for the prediction of the binding affinities of previously unknown protein-ligand complexes. In the past decades, several databases of protein-ligand-binding affinities have been created via visual extraction from literature. However, such approaches are time-consuming and most of these databases are updated only a few times per year. Hence, there is an immediate demand for an automatic extraction method with high precision for binding affinity collection. RESULT: We have created a new database of protein-ligand-binding affinity data, AutoBind, based on automatic information retrieval. We first compiled a collection of 1586 articles where the binding affinities have been marked manually. Based on this annotated collection, we designed four sentence patterns that are used to scan full-text articles as well as a scoring function to rank the sentences that match our patterns. The proposed sentence patterns can effectively identify the binding affinities in full-text articles. Our assessment shows that AutoBind achieved 84.22% precision and 79.07% recall on the testing corpus. Currently, 13 616 protein-ligand complexes and the corresponding binding affinities have been deposited in AutoBind from 17 221 articles. AVAILABILITY: AutoBind is automatically updated on a monthly basis, and it is freely available at http://autobind.csie.ncku.edu.tw/ and http://autobind.mc.ntu.edu.tw/. All of the deposited binding affinities have been refined and approved manually before being released.

BACKGROUND: A common assumption about enzyme active sites is that their structures are highly conserved to specifically distinguish between closely similar compounds. However, with the discovery of distinct enzymes with similar reaction chemistries, more and more studies discussing the structural flexibility of the active site have been conducted. RESULTS: Most of the existing works on the flexibility of active sites focuses on a set of pre-selected active sites that were already known to be flexible. This study, on the other hand, proposes an analysis framework composed of a new data collecting strategy, a local structure alignment tool and several physicochemical measures derived from the alignments. The method proposed to identify flexible active sites is highly automated and robust so that more extensive studies will be feasible in the future. The experimental results show the proposed method is (a) consistent with previous works based on manually identified flexible active sites and (b) capable of identifying potentially new flexible active sites. CONCLUSIONS: This proposed analysis framework and the former analyses on flexibility have their own advantages and disadvantage, depending on the cause of the flexibility. In this regard, this study proposes an alternative that complements previous studies and helps to construct a more comprehensive view of the flexibility of enzyme active sites.

BACKGROUND: Many biological functions involve various protein-protein interactions (PPIs). Elucidating such interactions is crucial for understanding general principles of cellular systems. Previous studies have shown the potential of predicting PPIs based on only sequence information. Compared to approaches that require other auxiliary information, these sequence-based approaches can be applied to a broader range of applications. RESULTS: This study presents a novel sequence-based method based on the assumption that protein-protein interactions are more related to amino acids at the surface than those at the core. The present method considers surface information and maintains the advantage of relying on only sequence data by including an accessible surface area (ASA) predictor recently proposed by the authors. This study also reports the experiments conducted to evaluate a) the performance of PPI prediction achieved by including the predicted surface and b) the quality of the predicted surface in comparison with the surface obtained from structures. The experimental results show that surface information helps to predict interacting protein pairs. Furthermore, the prediction performance achieved by using the surface estimated with the ASA predictor is close to that using the surface obtained from protein structures. CONCLUSION: This work presents a sequence-based method that takes into account surface information for predicting PPIs. The proposed procedure of surface identification improves the prediction performance with an F-measure of 5.1%. The extracted surfaces are also valuable in other biomedical applications that require similar information.

BACKGROUND: MicroRNAs (miRNAs) are short non-coding RNA molecules, which play an important role in post-transcriptional regulation of gene expression. There have been many efforts to discover miRNA precursors (pre-miRNAs) over the years. Recently, ab initio approaches have attracted more attention because they do not depend on homology information and provide broader applications than comparative approaches. Kernel based classifiers such as support vector machine (SVM) are extensively adopted in these ab initio approaches due to the prediction performance they achieved. On the other hand, logic based classifiers such as decision tree, of which the constructed model is interpretable, have attracted less attention. RESULTS: This article reports the design of a predictor of pre-miRNAs with a novel kernel based classifier named the generalized Gaussian density estimator (G2DE) based classifier. The G2DE is a kernel based algorithm designed to provide interpretability by utilizing a few but representative kernels for constructing the classification model. The performance of the proposed predictor has been evaluated with 692 human pre-miRNAs and has been compared with two kernel based and two logic based classifiers. The experimental results show that the proposed predictor is capable of achieving prediction performance comparable to those delivered by the prevailing kernel based classification algorithms, while providing the user with an overall picture of the distribution of the data set. CONCLUSION: Software predictors that identify pre-miRNAs in genomic sequences have been exploited by biologists to facilitate molecular biology research in recent years. The G2DE employed in this study can deliver prediction accuracy comparable with the state-of-the-art kernel based machine learning algorithms. Furthermore, biologists can obtain valuable insights about the different characteristics of the sequences of pre-miRNAs with the models generated by the G2DE based predictor.

BACKGROUND: Elucidating protein-protein interactions (PPIs) is essential to constructing protein interaction networks and facilitating our understanding of the general principles of biological systems. Previous studies have revealed that interacting protein pairs can be predicted by their primary structure. Most of these approaches have achieved satisfactory performance on datasets comprising equal number of interacting and non-interacting protein pairs. However, this ratio is highly unbalanced in nature, and these techniques have not been comprehensively evaluated with respect to the effect of the large number of non-interacting pairs in realistic datasets. Moreover, since highly unbalanced distributions usually lead to large datasets, more efficient predictors are desired when handling such challenging tasks. RESULTS: This study presents a method for PPI prediction based only on sequence information, which contributes in three aspects. First, we propose a probability-based mechanism for transforming protein sequences into feature vectors. Second, the proposed predictor is designed with an efficient classification algorithm, where the efficiency is essential for handling highly unbalanced datasets. Third, the proposed PPI predictor is assessed with several unbalanced datasets with different positive-to-negative ratios (from 1:1 to 1:15). This analysis provides solid evidence that the degree of dataset imbalance is important to PPI predictors. CONCLUSIONS: Dealing with data imbalance is a key issue in PPI prediction since there are far fewer interacting protein pairs than non-interacting ones. This article provides a comprehensive study on this issue and develops a practical tool that achieves both good prediction performance and efficiency using only protein sequence information.

This article presents a comprehensive study on the main characteristics of a novel optimization algorithm specifically designed for simulation of protein-ligand interactions. Though design of optimization algorithms has been a research issue extensively studied by computer scientists for decades, the emerging applications in bioinformatics such as simulation of protein-ligand interactions and protein folding introduce additional challenges due to (1) the high dimensionality nature of the problem and (2) the highly rugged landscape of the energy function. As a result, optimization algorithms that are not carefully designed to tackle these two challenges may fail to deliver satisfactory performance. This study has been motivated by the observation that the RAME (Rank-based Adaptive Mutation Evolutionary) optimization algorithm specifically designed for simulation of protein-ligand docking has consistently outperformed the conventional optimization algorithms by a significant degree. Accordingly, it is of interest to conduct a comprehensive investigation on the characteristics of the proposed algorithm and to learn how it will perform in the more general cases.The experimental results reveal that the RAME algorithm proposed in this article is capable of delivering superior performance to several alternative versions of the genetic algorithm in handling highly-rugged functions in the high-dimensional vector space. This article also reports experiments conducted to analyze the causes of the observed performance difference. The experiences learned provide valuable clues for how the proposed algorithm can be effectively exploited to tackle other computational biology problems.

Data classification is an intensively studied machine learning problem and there are two major categories of data classification algorithms, namely the logic based and the kernel based. The logic based classifiers, such as the decision tree and the rule-based classifier, feature the advantage of presenting a good summary about the distinctive characteristics of different classes of data. On the other hand, the kernel based classifiers, such as the neural network and the support vector machine (SVM), typically can deliver higher prediction accuracy than the logic based classifiers. However, the user of a kernel based classifier normally cannot get an overall picture about the distribution of the data set. For some applications, the overall picture of the distribution of the data set can provide valuable insights about the distinctive characteristics of different classes of data and therefore is highly desirable. In this article, aiming to close the gap between the logic based classifiers and the kernel based classifiers, we propose a novel approach to carry out density estimation based on a mixture model composed of a limited number of generalized Gaussian components. One favorite feature of the classifier constructed with the proposed approach is that a user can easily obtain an overall picture of the distributions of the data set by examining the eigenvectors and eigenvalues of the covariance matrices associated with the generalized Gaussian components. Experimental results show that the classifier constructed with the proposed approach is capable of delivering superior prediction accuracy in comparison with the conventional logic based classifiers and the EM (Expectation Maximization) based classifier. On the other hand, though it cannot match the prediction accuracy delivered by the SVM, the proposed classifier enjoys one major advantage due to providing the user with an overall picture of the underlying distributions.

BACKGROUND: Prediction of protein solvent accessibility, also called accessible surface area (ASA) prediction, is an important step for tertiary structure prediction directly from one-dimensional sequences. Traditionally, predicting solvent accessibility is regarded as either a two- (exposed or buried) or three-state (exposed, intermediate or buried) classification problem. However, the states of solvent accessibility are not well-defined in real protein structures. Thus, a number of methods have been developed to directly predict the real value ASA based on evolutionary information such as position specific scoring matrix (PSSM). RESULTS: This study enhances the PSSM-based features for real value ASA prediction by considering the physicochemical properties and solvent propensities of amino acid types. We propose a systematic method for identifying residue groups with respect to protein solvent accessibility. The amino acid columns in the PSSM profile that belong to a certain residue group are merged to generate novel features. Finally, support vector regression (SVR) is adopted to construct a real value ASA predictor. Experimental results demonstrate that the features produced by the proposed selection process are informative for ASA prediction. CONCLUSION: Experimental results based on a widely used benchmark reveal that the proposed method performs best among several of existing packages for performing ASA prediction. Furthermore, the feature selection mechanism incorporated in this study can be applied to other regression problems using the PSSM. The program and data are available from the authors upon request.

BACKGROUND: MicroRNAs (miRNAs) are short non-coding RNA molecules participating in post-transcriptional regulation of gene expression. There have been many efforts to discover miRNA precursors (pre-miRNAs) over the years. Recently, ab initio approaches obtain more attention because that they can discover species-specific pre-miRNAs. Most ab initio approaches proposed novel features to characterize RNA molecules. However, there were fewer discussions on the associated classification mechanism in a miRNA predictor. RESULTS: This study focuses on the classification algorithm for miRNA prediction. We develop a novel ab initio method, miR-KDE, in which most of the features are collected from previous works. The classification mechanism in miR-KDE is the relaxed variable kernel density estimator (RVKDE) that we have recently proposed. When compared to the famous support vector machine (SVM), RVKDE exploits more local information of the training dataset. MiR-KDE is evaluated using a training set consisted of only human pre-miRNAs to predict a benchmark collected from 40 species. The experimental results show that miR-KDE delivers favorable performance in predicting human pre-miRNAs and has advantages for pre-miRNAs from the genera taxonomically distant to humans. CONCLUSION: We use a novel classifier of which the characteristic of exploiting local information is particularly suitable to predict species-specific pre-miRNAs. This study also provides a comprehensive analysis from the view of classification mechanism. The good performance of miR-KDE encourages more efforts on the classification methodology as well as the feature extraction in miRNA prediction.

In recent years, kernel density estimation has been exploited by computer scientists to model several important problems in machine learning, bioinformatics, and computer vision. However, in case the dimension of the data set is high, then the conventional kernel density estimators suffer poor convergence rates of the pointwise mean square error (MSE) and the integrated mean square error (IMSE). Therefore, design of a novel kernel density estimator that overcomes this problem has been a great challenge for many years. This paper proposes a relaxed model of the variable kernel density estimation and analyzes its performance in data classification applications. It is proved in this paper that, in terms of pointwise MSE, the convergence rate of the relaxed variable kernel density estimator can approach O(n/sup -1/) regardless of the dimension of the data set, where n is the number of sampling instances. Experiments with the data classification applications have shown that the improved convergence rate of the pointwise MSE leads to higher prediction accuracy. In fact, the experimental results have also shown that the data classifier constructed based on the relaxed variable kernel density estimator is capable of delivering the same level of prediction accuracy as the SVM with the Gaussian kernel.

Analysis of protein-ligand interactions is a fundamental issue in drug design. As the detailed and accurate analysis of protein-ligand interactions involves calculation of binding free energy based on thermodynamics and even quantum mechanics, which is highly expensive in terms of computing time, conformational and structural analysis of proteins and ligands has been widely employed as a screening process in computer-aided drug design. In this paper, an efficient mechanism for identifying possible protein-ligand interactions based on analysis of protein tertiary substructures is proposed. In one experiment reported in this paper, the proposed prediction mechanism has been exploited to obtain some clues about a hypothesis that the biochemists have been speculating. The main distinction in the design of the prediction mechanism is the filtering process incorporated to expedite the analysis. The filtering process extracts the residues located in a cave of the protein tertiary structure for analysis and operates with O(nlogn) time complexity, where n is the number of residues in the protein. In comparison, the /spl alpha/hull algorithm, which is a widely used algorithm in computer graphics for identifying those instances that are on the contour of a 3-dimensional object, features O(n/sup 2/) time complexity. Experimental results show that the filtering process presented in this paper is able to speed up the analysis by a factor ranging from 3.11 to 9.79 times.