Prediction of ketoacyl synthase family using reduced amino acid alphabets

Chen, Wei; Feng, Pengmian; Lin, Hao

doi:10.1007/s10295-011-1047-z

Cited by 31 publications

(9 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The three statistical validation methods are k -fold cross validation, the jackknife test [ 28 ], and an independent test. Among these methods, the jackknife test is considered to best determine whether the method yields a unique result for a given benchmark dataset [ 43 – 54 ]. The jackknife test isolates each protein one by one and trains the predictor by the remaining proteins in the learning dataset.…”

Section: Methodsmentioning

confidence: 99%

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

2017

View full text Add to dashboard Cite

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).Electronic supplementary materialThe online version of this article (10.1186/s12864-017-4128-1) contains supplementary material, which is available to authorized users.

show abstract

Section: Methodsmentioning

confidence: 99%

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

2017

View full text Add to dashboard Cite

show abstract

“…Thirdly, a sequence that was annotated based on homology or prediction. Then, redundant sequences were removed by using the CD-HIT [ 21 ] program with a sequence identity threshold of 40%, which has been widely used to filter out redundant samples in genomics and proteomics [ 22 , 23 , 24 , 25 , 26 ].…”

Section: Methodsmentioning

confidence: 99%

IonchanPred 2.0: A Tool to Predict Ion Channels and Their Types

Zhao

Yang

et al. 2017

IJMS

Self Cite

View full text Add to dashboard Cite

Ion channels (IC) are ion-permeable protein pores located in the lipid membranes of all cells. Different ion channels have unique functions in different biological processes. Due to the rapid development of high-throughput mass spectrometry, proteomic data are rapidly accumulating and provide us an opportunity to systematically investigate and predict ion channels and their types. In this paper, we constructed a support vector machine (SVM)-based model to quickly predict ion channels and their types. By considering the residue sequence information and their physicochemical properties, a novel feature-extracted method which combined dipeptide composition with the physicochemical correlation between two residues was employed. A feature selection strategy was used to improve the performance of the model. Comparison results of in jackknife cross-validation demonstrated that our method was superior to other methods for predicting ion channels and their types. Based on the model, we built a web server called IonchanPred which can be freely accessed from .

show abstract

“…In statistical prediction, several test methods such as n -fold cross-validation test, jackknife cross-validation test, independent data test can be used to estimate the predictive performance of proposed method 34 . Jackknife cross-validation test is usually more suitable for small sample problem and always yields a unique results for a given benchmark dataset 28 35 36 , however, it is time-consuming. Thus, we used five-fold cross-validation in this study to evaluate the performance of our model.…”

Section: Methodsmentioning

confidence: 99%

Identification of apolipoprotein using feature selection technique

Tang

Ping

Zhang

et al. 2016

Sci Rep

Self Cite

View full text Add to dashboard Cite

Apolipoprotein is a kind of protein which can transport the lipids through the lymphatic and circulatory systems. The abnormal expression level of apolipoprotein always causes angiocardiopathy. Thus, correct recognition of apolipoprotein from proteomic data is very crucial to the comprehension of cardiovascular system and drug design. This study is to develop a computational model to predict apolipoproteins. In the model, the apolipoproteins and non-apolipoproteins were collected to form benchmark dataset. On the basis of the dataset, we extracted the g-gap dipeptide composition information from residue sequences to formulate protein samples. To exclude redundant information or noise, the analysis of various (ANOVA)-based feature selection technique was proposed to find out the best feature subset. The support vector machine (SVM) was selected as discrimination algorithm. Results show that 96.2% of sensitivity and 99.3% of specificity were achieved in five-fold cross-validation. These findings open new perspectives to improve apolipoproteins prediction by considering the specific dipeptides. We expect that these findings will help to improve drug development in anti-angiocardiopathy disease.

show abstract

Prediction of ketoacyl synthase family using reduced amino acid alphabets

Cited by 31 publications

References 46 publications

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

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

IonchanPred 2.0: A Tool to Predict Ion Channels and Their Types

Identification of apolipoprotein using feature selection technique

Contact Info

Product

Resources

About