Globin-like蛋白质折叠类型识别

蛋白质折叠类型识别是蛋白质结构研究的重要内容.以SCOP中的Globin-like折叠为研究对象,选择其中序列同一性小于25%的17个代表性蛋白质为训练集,采用机器和人工结合的办法进行结构比对,产生序列排比,经过训练得到了适合Globin-like折叠的概形隐马尔科夫模型(profile HMM)用于该折叠类型的识别.以Astrall.65中的68057个结构域样本进行检验,识别敏感度为99.64%,特异性100%.在折叠类型水平上,与Pfam和SUPERFAMILY单纯使用序列比对构建的HMM相比,所用模型由多于100个归为一个,仍然保持了很高的识别效果.结果表明:对序列相似度很低但具有相同折叠类型的蛋白质,可以通过引入结构比对的方法建立统一的HMM模型,实现高准确率的折叠类型识别.     

蛋白质折叠识别方法综述

蛋白质折叠识别算法是蛋白质三维结构预测的重要方法之一,该方法在生物科学的许多方面得到卓有成效的应用。在过去的十年中,我们见证了一系列基于不同计算方式的蛋白质折叠识别方法。在这些计算方法中,机器学习和序列谱-序列谱比对是两种在蛋白质折叠中应用较为广泛和有效的方法。除了计算方法的进展外,不断增大的蛋白质结构数据库也是蛋白质折叠识别的预测精度不断提高的一个重要因素。在这篇文章中,我们将简要地回顾蛋白质折叠中的先进算法。另外,我们也将讨论一些可能可以应用于改进蛋白质折叠算法的策略。     

蛋白质折叠类型分类方法及分类数据库

蛋白质折叠规律研究是生命科学重大前沿课题,折叠分类是蛋白质折叠研究的基础。目前的蛋白质折叠类型分类基本上靠专家完成,不同的库分类并不相同,迫切需要一个建立在统一原理基础上的蛋白质折叠类型数据库。本文以ASTRAL-1.65数据库中序列同源性在25%以下、分辨率小于2.5的蛋白为基础,通过对蛋白质空间结构的观察及折叠类型特征的分析,提出以蛋白质折叠核心为中心、以蛋白质结构拓扑不变性为原则、以蛋白质折叠核心的规则结构片段组成、连接和空间排布为依据的蛋白质折叠类型分类方法,建立了低相似度蛋白质折叠分类数据库——LIFCA,包含259种蛋白质折叠类型。数据库的建立,将为进一步的蛋白质折叠建模及数据挖掘、蛋白质折叠识别、蛋白质折叠结构进化研究奠定基础。     

A structural pattern-based method for protein fold recognition

A method (SPREK) was developed to evaluate the register of a sequence on a structure based on the matching of structural patterns against a library derived from the protein structure databank. The scores obtained were normalized against random background distributions derived from sequence shuffling and permutation methods. 'Random' structures were also used to evaluate the effectiveness of the method. These were generated by a simple random-walk and a more sophisticated structure prediction method that produced protein-like folds. For comparison with other methods, the performance of the method was assessed using collections of models including decoys and models from the CASP-5 exercise. The performance of SPREK on the decoy models was equivalent to (and sometimes better than) those obtained with more complex approaches. An exception was the two smallest proteins, for which SPREK did not perform well due to a lack of patterns. Using the best parameter combination from trials on decoy models, the CASP models of intermediate difficulty were evaluated by SPREK and the quality of the top scoring model was evaluated by its CASP ranking. Of the 14 targets in this class, half lie in the top 10% (out of around 140 models for each target). The two worst rankings resulted from the selection by our method of a well-packed model that was based on the wrong fold. Of the other poor rankings, one was the smallest protein and the others were the four largest (all over 250 residues).     

Pcons: a neural-network-based consensus predictor that improves fold recognition

During recent years many protein fold recognition methods have been developed, based on different algorithms and using various kinds of information. To examine the performance of these methods several evaluation experiments have been conducted. These include blind tests in CASP/CAFASP, large scale benchmarks, and long-term, continuous assessment with newly solved protein structures. These studies confirm the expectation that for different targets different methods produce the best predictions, and the final prediction accuracy could be improved if the available methods were combined in a perfect manner. In this article a neural-network-based consensus predictor, Pcons, is presented that attempts this task. Pcons attempts to select the best model out of those produced by six prediction servers, each using different methods. Pcons translates the confidence scores reported by each server into uniformly scaled values corresponding to the expected accuracy of each model. The translated scores as well as the similarity between models produced by different servers is used in the final selection. According to the analysis based on two unrelated sets of newly solved proteins, Pcons outperforms any single server by generating approximately 8%-10% more correct predictions. Furthermore, the specificity of Pcons is significantly higher than for any individual server. From analyzing different input data to Pcons it can be shown that the improvement is mainly attributable to measurement of the similarity between the different models. Pcons is freely accessible for the academic community through the protein structure-prediction metaserver at http://bioinfo.pl/meta/.     

Enhanced protein fold recognition using secondary structure information from NMR.

NMR offers the possibility of accurate secondary structure for proteins that would be too large for structure determination. In the absence of an X-ray crystal structure, this information should be useful as an adjunct to protein fold recognition methods based on low resolution force fields. The value of this information has been tested by adding varying amounts of artificial secondary structure data and threading a sequence through a library of candidate folds. Using a literature test set, the threading method alone has only a one-third chance of producing a correct answer among the top ten guesses. With realistic secondary structure information, one can expect a 60-80% chance of finding a homologous structure. The method has then been applied to examples with published estimates of secondary structure. This implementation is completely independent of sequence homology, and sequences are optimally aligned to candidate structures with gaps and insertions allowed. Unlike work using predicted secondary structure, we test the effect of differing amounts of relatively reliable data.     

Scalable remote homology detection and fold recognition in massive protein networks

The global connectivities in very large protein similarity networks contain traces of evolution among the proteins for detecting protein remote evolutionary relations or structural similarities. To investigate how well a protein network captures the evolutionary information, a key limitation is the intensive computation of pairwise sequence similarities needed to construct very large protein networks. In this article, we introduce label propagation on low-rank kernel approximation (LP-LOKA) for searching massively large protein networks. LP-LOKA propagates initial protein similarities in a low-rank graph by Nyström approximation without computing all pairwise similarities. With scalable parallel implementations based on distributed-memory using message-passing interface and Apache-Hadoop/Spark on cloud, LP-LOKA can search protein networks with one million proteins or more. In the experiments on Swiss-Prot/ADDA/CASP data, LP-LOKA significantly improved protein ranking over the widely used HMM-HMM or profile-sequence alignment methods utilizing large protein networks. It was observed that the larger the protein similarity network, the better the performance, especially on relatively small protein superfamilies and folds. The results suggest that computing massively large protein network is necessary to meet the growing need of annotating proteins from newly sequenced species and LP-LOKA is both scalable and accurate for searching massively large protein networks.     

Improving fold recognition without folds

The most reliable way to align two proteins of unknown structure is through sequence-profile and profile-profile alignment methods. If the structure for one of the two is known, fold recognition methods outperform purely sequence-based alignments. Here, we introduced a novel method that aligns generalised sequence and predicted structure profiles. Using predicted 1D structure (secondary structure and solvent accessibility) significantly improved over sequence-only methods, both in terms of correctly recognising pairs of proteins with different sequences and similar structures and in terms of correctly aligning the pairs. The scores obtained by our generalised scoring matrix followed an extreme value distribution; this yielded accurate estimates of the statistical significance of our alignments. We found that mistakes in 1D structure predictions correlated between proteins from different sequence-structure families. The impact of this surprising result was that our method succeeded in significantly out-performing sequence-only methods even without explicitly using structural information from any of the two. Since AGAPE also outperformed established methods that rely on 3D information, we made it available through. If we solved the problem of CPU-time required to apply AGAPE on millions of proteins, our results could also impact everyday database searches.     

Helix-bundle membrane protein fold templates

In the fold recognition approach to structure prediction, a sequence is tested for compatibility with an already known fold. For membrane proteins, however, few folds have been determined experimentally. Here the feasibility of computing the vast majority of likely membrane protein folds is tested. The results indicate that conformation space can be effectively sampled for small numbers of helices. The vast majority of potential monomeric membrane protein structures can be represented by about 30-folds for three helices, but increases exponentially to about 1,500,000 folds for seven helices. The generated folds could serve as templates for fold recognition or as starting points for conformational searches that are well distributed throughout conformation space.     

Fold usage on genomes and protein fold evolution

We review fold usage on completed genomes to explore protein structure evolution. The patterns of presence or absence of folds on genomes gives us insights into the relationships between folds, the age of different folds and how we have arrived at the set of folds we see today. We examine the relationships between different measures which describe protein fold usage, such as the number of copies of a fold per genome, the number of families per fold, and the number of genomes a fold occurs on. We obtained these measures of fold usage by searching for the structural domains on 157 completed genome sequences from all three kingdoms of life. In our comparisons of these measures we found that bacteria have relatively more distinct folds on their genomes than archaea. Eukaryotes were found to have many more copies of a fold on their genomes. If we separate out the different fold classes, the alpha/beta class has relatively fewer distinct folds on large genomes, more copies of a fold on bacteria and more folds occurring in all three kingdoms simultaneously. These results possibly indicate that most alpha/beta folds originated earlier than other folds. The expected power law distribution is observed for copies of a fold per genome and we found a similar distribution for the number of families per fold. However, a more complicated distribution appears for fold occurrence across genomes, which strongly depends on fold class and kingdom. We also show that there is not a clear relationship between the three measures of fold usage. A fold which occurs on many genomes does not necessarily have many copies on each genome. Similarly, folds with many copies do not necessarily have many families or vice versa.