Feature Representation Algorithm Research Articles

SkipCPP-Pred: an improved and promising sequence-based predictor for predicting cell-penetrating peptides

BackgroundCell-penetrating peptides (CPPs) are short peptides (5–30 amino acids) that can enter almost any cell without significant damage. On account of their high delivery efficiency, CPPs are promising candidates for gene therapy and cancer treatment. Accordingly, techniques that correctly predict CPPs are anticipated to accelerate CPP applications in future therapeutics. Recently, computational methods have been reportedly successful in predicting CPPs. Unfortunately, the predictive performance of existing methods is not satisfactory and reliable so as to accurately identify CPPs.ResultsIn this study, we propose a novel computational predictor called SkipCPP-Pred to further improve the predictive performance. The novelty of the proposed predictor is that we present a sequence-based feature representation algorithm called adaptive k-skip-n-gram that sufficiently captures the intrinsic correlation information of residues. By fusing the proposed adaptive skip features with a random forest (RF) classifier, we successfully construct the prediction model of SkipCPP-Pred. The various jackknife results demonstrate that the proposed SkipCPP-Pred is 3.6% higher than state-of-the-art CPP predictors in terms of accuracy. Moreover, we construct a high-quality benchmark dataset by reducing the data redundancy and enhancing the similarity between the positive and negative classes. Using this dataset to build prediction models, we can successfully avoid the performance bias lying in existing methods and yield a promising predictive model.ConclusionsThe proposed SkipCPP-Pred is a simple and fast sequence-based predictor featured with the adaptive k-skip-n-gram model for the improved prediction of CPPs. Currently, SkipCPP-Pred is publicly available from an online webserver (http://server.malab.cn/SkipCPP-Pred/Index.html).

Identifying N6-methyladenosine sites using multi-interval nucleotide pair position specificity and support vector machine

N6-methyladenosine (m6A) refers to methylation of the adenosine nucleotide acid at the nitrogen-6 position. It plays an important role in a series of biological processes, such as splicing events, mRNA exporting, nascent mRNA synthesis, nuclear translocation and translation process. Numerous experiments have been done to successfully characterize m6A sites within sequences since high-resolution mapping of m6A sites was established. However, as the explosive growth of genomic sequences, using experimental methods to identify m6A sites are time-consuming and expensive. Thus, it is highly desirable to develop fast and accurate computational identification methods. In this study, we propose a sequence-based predictor called RAM-NPPS for identifying m6A sites within RNA sequences, in which we present a novel feature representation algorithm based on multi-interval nucleotide pair position specificity, and use support vector machine classifier to construct the prediction model. Comparison results show that our proposed method outperforms the state-of-the-art predictors on three benchmark datasets across the three species, indicating the effectiveness and robustness of our method. Moreover, an online webserver implementing the proposed predictor has been established at http://server.malab.cn/RAM-NPPS/. It is anticipated to be a useful prediction tool to assist biologists to reveal the mechanisms of m6A site functions.

Low Dimensional Representation of Fisher Vectors for Microscopy Image Classification.

Microscopy image classification is important in various biomedical applications, such as cancer subtype identification, and protein localization for high content screening. To achieve automated and effective microscopy image classification, the representative and discriminative capability of image feature descriptors is essential. To this end, in this paper, we propose a new feature representation algorithm to facilitate automated microscopy image classification. In particular, we incorporate Fisher vector (FV) encoding with multiple types of local features that are handcrafted or learned, and we design a separation-guided dimension reduction method to reduce the descriptor dimension while increasing its discriminative capability. Our method is evaluated on four publicly available microscopy image data sets of different imaging types and applications, including the UCSB breast cancer data set, MICCAI 2015 CBTC challenge data set, and IICBU malignant lymphoma, and RNAi data sets. Our experimental results demonstrate the advantage of the proposed low-dimensional FV representation, showing consistent performance improvement over the existing state of the art and the commonly used dimension reduction techniques.

PhosPred-RF: A Novel Sequence-Based Predictor for Phosphorylation Sites Using Sequential Information Only.

Many recent efforts have been made for the development of machine learning-based methods for fast and accurate phosphorylation site prediction. Currently, a majority of well-performing methods are based on hybrid information to build prediction models, such as evolutionary information, disorder information, and so on. Unfortunately, this type of methods suffers two major limitations: one is that it would not be much of help for protein phosphorylation site prediction in case of no obvious homology detected; the other is that computing such the complicated information is time-consuming, which probably limits the usage of predictors in practical applications. In this paper, we present a simple, fast, and powerful feature representation algorithm, which sufficiently explores the sequential information from multiple perspectives only based on primary sequences, and successfully captures the differences between true phosphorylation sites and hboxnon-phosphorylation sites. Using the proposed features, we propose a random forest-based predictor named PhosPred-RF in the prediction of protein phosphorylation sites from proteins. We evaluate and compare the proposed predictor with the state-of-the-art predictors on some benchmark data sets. The experimental results show that PhosPred-RF outperforms other existing predictors, demonstrating its potential to be a useful tool for protein phosphorylation site prediction. Currently, the proposed PhosPred-RF is freely accessible to the public through the user-friendly webserver http://server.malab.cn/PhosPred-RF.

Exploring local discriminative information from evolutionary profiles for cytokine–receptor interaction prediction

Cytokine–receptor interaction is one of the most important types of protein–protein interactions that are widely involved in cellular regulatory processes. Knowledge of cytokine–receptor interactions facilitates to deeply understand several physiological functions. In post-genomic era of sequence explosion, there is an increasing demand for developing machine learning based computational methods for the fast and accurate cytokine–receptor interaction prediction. However, the major problem lying on existing machine learning based methods is that the overall prediction accuracy is relatively low. To improve the accuracy, a crucial step is to establish a well-defined feature representation algorithm. Motivated on this perspective, we propose a novel feature representation method by integrating local information embedded in evolutionary profiles with the Pse-PSSM and AAC-PSSM-AC feature models. We further develop an improved prediction method, namely CRI-Pred, based on the proposed feature set using the Random Forest classifier. Experimental results evaluated with the jackknife test show that the CRI-Pred predictor outperforms the state-of-the-art methods, 5.1% higher in terms of the overall accuracy. This indicates the effectiveness and superiority of CRI-Pred. A webserver that implements CRI-Pred is now freely available at http://server.malab.cn/CRIPred/Index.html to the public to use in practical applications.

Novel classification method for remote sensing images based on information entropy discretization algorithm and vector space model

Various kinds of remote sensing image classification algorithms have been developed to adapt to the rapid growth of remote sensing data. Conventional methods typically have restrictions in either classification accuracy or computational efficiency. Aiming to overcome the difficulties, a new solution for remote sensing image classification is presented in this study. A discretization algorithm based on information entropy is applied to extract features from the data set and a vector space model (VSM) method is employed as the feature representation algorithm. Because of the simple structure of the feature space, the training rate is accelerated. The performance of the proposed method is compared with two other algorithms: back propagation neural networks (BPNN) method and ant colony optimization (ACO) method. Experimental results confirm that the proposed method is superior to the other algorithms in terms of classification accuracy and computational efficiency.

Transfer Feature Representation via Multiple Kernel Learning

Learning an appropriate feature representation across source and target domains is one of the most effective solutions to domain adaptation problems. Conventional cross-domain feature learning methods rely on the Reproducing Kernel Hilbert Space (RKHS) induced by a single kernel. Recently, Multiple Kernel Learning (MKL), which bases classifiers on combinations of kernels, has shown improved performance in the tasks without distribution difference between domains. In this paper, we generalize the framework of MKL for cross-domain feature learning and propose a novel Transfer Feature Representation (TFR) algorithm. TFR learns a convex combination of multiple kernels and a linear transformation in a single optimization which integrates the minimization of distribution difference with the preservation of discriminating power across domains. As a result, standard machine learning models trained in the source domain can be reused for the target domain data. After rewritten into a differentiable formulation, TFR can be optimized by a reduced gradient method and reaches the convergence. Experiments in two real-world applications verify the effectiveness of our proposed method.

The Study on Educational Resources Based on the Recommended Services

In the network teaching system, with the increasing teaching resources, student resources are increasingly difficult to find interesting, so join teaching resource referral service in online teaching system allows students freed from the vast network of information resources, greatly saving time and effort spent on students in search of information. Under these conditions and needs, educational resources referral service technology has been progressively developed. This article is recommended for Educational Resources Services referral service model, resource feature representation and recommendation algorithm based on machine learning and other key technologies were discussed and studied.

Evaluation of shape similarity measurement methods for spine X-ray images

Efficient content-based image retrieval (CBIR) of biomedical images is a challenging problem. Feature representation algorithms used in indexing medical images on the pathology of interest have to address conflicting goals of reducing feature dimensionality while retaining important and often subtle biomedical features. At the Lister Hill National Center for Biomedical Communications, an intramural R&D division of the U.S. National Library of Medicine, we are developing CBIR prototype for digitized images of a collection of 17,000 cervical and lumbar spine X-rays taken as a part of the second National Health and Nutrition Examination Survey (NHANES II). The vertebra shape effectively describes various pathologies identified by medical experts as being consistently and reliably found in the image collection. A suitable shape algorithm must represent shapes in low dimension, be invariant to rotation, translation, and scale transforms, and retain relevant pathology. Additionally, supported similarity algorithms must be useful in retrieving images that are relevant to the queries posed by the intended target community, viz. medical researchers, physicians, etc. This paper describes an evaluation of two popular shape similarity methods from the literature on a set of 250 vertebra boundary shapes. The polygon approximation method achieved a performance score of 55.94% and bettered the Fourier descriptor algorithm which had a performance score of 46.96%.