Accurate prediction of protein fold type by integration of template-based assignment and ab-initio m

来源 :第七届全国生物信息学与系统生物学学术大会 | 被引量 : 0次 | 上传用户:gag123
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
  Prediction of fold type is a critical step in protein structure prediction[1].we developed two algorithms,HH-fold and SVM-fold for protein fold type prediction.HH-fold is a template-based fold assignment algorithm using the HMM-HMM alignrment program HHsearch[2].SVM-fold is a support vector machine-based ab-initio modeling algorithm,in which a comprehensive set of features are extracted from three complementary sequence profiles.These two algorithms are then combined,resulting to the ensemble approach TA-fold.TA-fold was evaluated and compared with five recently developed methods on four benchmark datasets.
其他文献
Acute myocardial infarction (AMI) is a kind of common disease of cardiovascular disease.During the course of AMI morbidity,it will lead to potential complication from the disease,like atrial fibrillat
Various types of mutation and editing (M/E) events in miRNAs can change the stabilities of pre-miRNAs and/or complementarities between miRNAs and their targets.Small RNA (sRNA) high-throughput sequenc
Protein-protein interacts through specific interface residues to execute biological functions.Correctly understanding the mechanisms of interface recognition and predicting the interface residues are
会议
The CRISPR-Cas (clustered regularly interspaced short palindromic repeats-CRISPR-associated proteins) adaptive immune systems are discovered in many bacteria and most archaea.These defence systems are
Enzymatic catalysis mechanism,which is the central to understand the biogenesis and diversity of natural products,would shed bright light on the rational drug design and protein engineering.The biosyn
Modular protein interaction domains form the building blocks of cell signaling pathways.Many of them,known as peptide recognition domains,mediate protein-protein interactions by recognizing short,line
Predicting the biological functions of proteins is one of the key challenges in the post genomic era.Computational models have demonstrated the utility of applying machine learning methods to predict
As the number of sequenced genomes rapidly grows,there are a large number of proteins with unknown function in new genomes.Active learning methods can assist biologists for selecting the most valuable
A new carboxylic esterase RhEst1 which catalyzes the hydrolysis of (S)-(+)-2,2-dimethylcyclopropanecarboxylate (S-DmCpCe),the key chiral building block of cilastatin,was identified and subsequently cr
With the coming of the post-genomic age,protein sequences have increased rapidly.It has been a topic issue about using intelligent calculation method to predict the protein subcellular localization.In