Dataset Information

A new method to improve network topological similarity search: applied to fold recognition.

ABSTRACT: Similarity search is the foundation of bioinformatics. It plays a key role in establishing structural, functional and evolutionary relationships between biological sequences. Although the power of the similarity search has increased steadily in recent years, a high percentage of sequences remain uncharacterized in the protein universe. Thus, new similarity search strategies are needed to efficiently and reliably infer the structure and function of new sequences. The existing paradigm for studying protein sequence, structure, function and evolution has been established based on the assumption that the protein universe is discrete and hierarchical. Cumulative evidence suggests that the protein universe is continuous. As a result, conventional sequence homology search methods may be not able to detect novel structural, functional and evolutionary relationships between proteins from weak and noisy sequence signals. To overcome the limitations in existing similarity search methods, we propose a new algorithmic framework-Enrichment of Network Topological Similarity (ENTS)-to improve the performance of large scale similarity searches in bioinformatics.We apply ENTS to a challenging unsolved problem: protein fold recognition. Our rigorous benchmark studies demonstrate that ENTS considerably outperforms state-of-the-art methods. As the concept of ENTS can be applied to any similarity metric, it may provide a general framework for similarity search on any set of biological entities, given their representation as a network.Source code freely available upon request: lxie@iscb.org.

SUBMITTER: Lhota J

PROVIDER: S-EPMC4481851 | biostudies-literature | 2015 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A new method to improve network topological similarity search: applied to fold recognition.

Lhota John J Hauptman Ruth R Hart Thomas T Ng Clara C Xie Lei L

Bioinformatics (Oxford, England) 20150225 13

<h4>Motivation</h4>Similarity search is the foundation of bioinformatics. It plays a key role in establishing structural, functional and evolutionary relationships between biological sequences. Although the power of the similarity search has increased steadily in recent years, a high percentage of sequences remain uncharacterized in the protein universe. Thus, new similarity search strategies are needed to efficiently and reliably infer the structure and function of new sequences. The existing p ...[more]

PMID: 25717198

Similar Datasets

Project description:High throughput screening (HTS) is an important component of lead discovery, with virtual screening playing an increasingly important role. Both methods typically suffer from lack of sensitivity and specificity against their true biological targets. With ever-increasing screening libraries and virtual compound collections, it is now feasible to conduct follow-up experimental testing on only a small fraction of hits. In this context, advances in virtual screening that achieve enrichment of true actives among top-ranked compounds ("early recognition") and, hence, reduce the number of hits to test, are highly desirable. The standard ligand-based virtual screening method for large compound libraries uses a molecular similarity search method that ranks the likelihood of a compound to be active against a drug target by its highest Tanimoto similarity to known active compounds. This approach assumes that the distributions of Tanimoto similarity values to all active compounds are identical (i.e., same mean and standard deviation)-an assumption shown to be invalid (Baldi and Nasr, 2010). Here, we introduce two methods that improve early recognition of actives by exploiting similarity information of all molecules. The first method ranks a compound by its highest z-score instead of its highest Tanimoto similarity, and the second by an aggregated score calculated from its Tanimoto similarity values to all known actives and inactives (or a large number of structurally diverse molecules when information on inactives is unavailable). Our evaluations, which use datasets of over 20 HTS campaigns downloaded from PubChem, indicate that compared to the conventional approach, both methods achieve a ~10% higher Boltzmann-enhanced discrimination of receiver operating characteristic (BEDROC) score-a metric of early recognition. Given the increasing use of virtual screening in early lead discovery, these methods provide straightforward means to enhance early recognition.

Project description:Spectral similarity calculation is widely used in protein identification tools and mass spectra clustering algorithms while comparing theoretical or experimental spectra. The performance of the spectral similarity calculation plays an important role in these tools and algorithms especially in the analysis of large-scale datasets. Recently, deep learning methods have been proposed to improve the performance of clustering algorithms and protein identification by training the algorithms with existing data and the use of multiple spectra and identified peptide features. While the efficiency of these algorithms is still under study in comparison with traditional approaches, their application in proteomics data analysis is becoming more common. Here, we propose the use of deep learning to improve spectral similarity comparison. We assessed the performance of deep learning for spectral similarity, with GLEAMS and a newly trained embedder model (DLEAMSE), which uses high-quality spectra from PRIDE Cluster. Also, we developed a new bioinformatics tool (mslookup - https://github.com/bigbio/DLEAMSE/) that allows users to quickly search for spectra in previously identified mass spectra publish in public repositories and spectral libraries. Finally, we released a human database to enable bioinformaticians and biologists to search for identified spectra in their machines. SIGNIFICANCE STATEMENT: Spectral similarity calculation plays an important role in proteomics data analysis. With deep learning's ability to learn the implicit and effective features from large-scale training datasets, deep learning-based MS/MS spectra embedding models has emerged as a solution to improve mass spectral clustering similarity calculation algorithms. We compare multiple similarity scoring and deep learning methods in terms of accuracy (compute the similarity for a pair of the mass spectrum) and computing-time performance. The benchmark results showed no major differences in accuracy between DLEAMSE and normalized dot product for spectrum similarity calculations. The DLEAMSE GPU implementation is faster than NDP in preprocessing on the GPU server and the similarity calculation of DLEAMSE (Euclidean distance on 32-D vectors) takes about 1/3 of dot product calculations. The deep learning model (DLEAMSE) encoding and embedding steps needed to run once for each spectrum and the embedded 32-D points can be persisted in the repository for future comparison, which is faster for future comparisons and large-scale data. Based on these, we proposed a new tool mslookup that enables the researcher to find spectra previously identified in public data. The tool can be also used to generate in-house databases of previously identified spectra to share with other laboratories and consortiums.

Project description:Protein fold recognition is a critical step toward protein structure and function prediction, aiming at providing the most likely fold type of the query protein. In recent years, the development of deep learning (DL) technique has led to massive advances in this important field, and accordingly, the sensitivity of protein fold recognition has been dramatically improved. Most DL-based methods take an intermediate bottleneck layer as the feature representation of proteins with new fold types. However, this strategy is indirect, inefficient and conditional on the hypothesis that the bottleneck layer's representation is assumed as a good representation of proteins with new fold types. To address the above problem, in this work, we develop a new computational framework by combining triplet network and ensemble DL. We first train a DL-based model, termed FoldNet, which employs triplet loss to train the deep convolutional network. FoldNet directly optimizes the protein fold embedding itself, making the proteins with the same fold types be closer to each other than those with different fold types in the new protein embedding space. Subsequently, using the trained FoldNet, we implement a new residue-residue contact-assisted predictor, termed FoldTR, which improves protein fold recognition. Furthermore, we propose a new ensemble DL method, termed FSD_XGBoost, which combines protein fold embedding with the other two discriminative fold-specific features extracted by two DL-based methods SSAfold and DeepFR. The Top 1 sensitivity of FSD_XGBoost increases to 74.8% at the fold level, which is ~9% higher than that of the state-of-the-art method. Together, the results suggest that fold-specific features extracted by different DL methods complement with each other, and their combination can further improve fold recognition at the fold level. The implemented web server of FoldTR and benchmark datasets are publicly available at http://csbio.njust.edu.cn/bioinf/foldtr/.

Dataset Information

A new method to improve network topological similarity search: applied to fold recognition.

Publications

A new method to improve network topological similarity search: applied to fold recognition.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets