Motif extraction and protein classification

Kunik, Vered; Solan, Zach; Edelman, Shimon; Ruppin, Eytan; Horn, D.

doi:10.1109/csb.2005.39

Cited by 22 publications

(20 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Motif-based Classification. Motifs have been used for sequence classification in biological domain [6,15,8]. This is usually done in two steps: i) first motifs are extracted, then ii) each time series is represented as an attribute vector using motifs so that a classifier like SVM [15], Naive Bayes [8], Decision Tree [6], etc.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Motif-Based Classification of Time Series with Bayesian Networks and SVMs

Búza

Schmidt-Thieme²

2009

Advances in Data Analysis, Data Handling and Business Intelligence

View full text Add to dashboard Cite

Summary. Classification of time series is an important task with many challenging applications like brain wave (EEG) analysis, signature verification or speech recognition. In this paper we show how characteristic local patterns (motifs) can improve the classification accuracy. We introduce a new motif class, generalized semi-continuous motifs. To allow flexibility and noise robustness, these motifs may include gaps of various lengths, generic and more specific wildcards. We propose an efficient algorithm for mining generalized sequential motifs. In experiments on real medical data, we show how generalized semi-continuous motifs improve the accuracy of SVMs and Bayesian Networks for time series classificiation.

show abstract

Section: Related Workmentioning

confidence: 99%

“…can be applied. Some possible ways of construction of attributes are: i) there is a binary attribute for each motif, which indicates if the motif is contained in the time series or not [16,6,15] (see Fig. 2), ii) aggregating attributes may indicate the total count and/or average length of motifs occurring in a time series [8].…”

Section: Related Workmentioning

confidence: 99%

Motif-Based Classification of Time Series with Bayesian Networks and SVMs

Búza

Schmidt-Thieme²

2009

Advances in Data Analysis, Data Handling and Business Intelligence

View full text Add to dashboard Cite

show abstract

“…Cheminformatics and bioinformatics share common goals: In cheminformatics, one searches for similar compounds, while in bioinformatics one seeks homologous sequences; in cheminformatics one predicts activities and properties of small molecules, whereas in bioinformatics one predicts functions and properties of macromolecules; in cheminformatics one computes binding affinities between chemicals and proteins, and in bioinformatics one predicts the possibility of two biomolecules to interact. Bioinformatics techniques use Enzyme Commission (EC) numbers to predict the metabolites a given sequence can catalyze [26][27][28] , and structure-and sequence-based methods to locate homologous ligand binding sites 29 . Cheminformatics techniques such as virtual screening seek to identify novel compounds for a given target 19,30 , can classify metabolic 31 and organic 32 reactions, and predict the EC number given a metabolic reaction 33 .…”

Section: Cheminformatics Meets Bioinformaticsmentioning

confidence: 99%

Systems chemical biology

Oprea¹,

et al. 2007

View full text Add to dashboard Cite

The increasing availability of data related to genes, proteins and their modulation by small molecules, paralleled by the emergence of simulation tools in systems biology, has provided a vast amount of biological information. However, there is a critical need to develop cheminformatics tools that can integrate chemical knowledge with these biological databases, with the goal of creating systems chemical biology.Hailed as a departure from the "reductionist approach", where investigators dedicate their efforts to the study of a single gene or protein, systems biology is generally regarded as the "comprehensive approach". Large networks describing the regulation of entire genomes, metabolic or signal transduction pathways are analyzed in their totality at different levels of biological organization 1 . Systems biology, which blends theory, computational modeling, and high-throughput experimentation 2 , has already led to advances in the understanding of cell signaling 3 , developmental biology 4 , cell physiology 5 , and metabolic networks 6 . However, despite these advances in biological insight, what is currently lacking from these approaches is any holistic understanding of how small molecules affect biological systems. The introduction of cheminformatics tools that can be seamlessly integrated with currently available bio-and cheminformatic databases and biological network simulations and software will be required to move toward a systematic understanding of the way small molecules impact biological systems -a field which we call "systems chemical biology."Although some systems biology approaches have been applied to targets in lead 7 and drug discovery 8,9 within the pharmaceutical industry, this type of general integration of chemistry and systems biology has not yet been seen in academics. However, a tremendous opportunity now exists because academic biomolecular screening efforts, particularly the Molecular Libraries Screening Centers Network (MLSCN) being funded by the NIH Roadmap via the Molecular Libraries Initiative (MLI) 10 have created a wealth of systematic data describing the biological effects of small molecules. The new data that is being generated is particularly valuable because it extends information beyond the relatively limited number of biological and screening data available from industry to the entire array of macromolecules and macromolecular networks that are being experimentally evaluated in academic laboratories. Via the MLI, the effects of hundreds of thousands of small molecules on biological systems of varied complexity, ranging from screens with purified targets to simultaneous multi-target (multiplex) screens, phenotypic screens, and even whole organism assays, are being investigated. Central to the MLI is public access, and bioassay data from MLSCN screens are being deposited in PubChem, a freely accessible database. This unprecedented effort has created an opportunity to integrate chemical

show abstract

“…One possibility is to use motif information from protein databases (Ben-hur and Brutlag, 2003;Wang et al, 2003) in which motifs are assumed to be already available for the family of proteins to be classified. Most of the methods of subsequence-based approach attempt to extract motifs explicitly for the given families (Hannenhalli and Russell, 2000;Wang et al, 2001;Liu and Califano, 2001;Kunik et al, 2005;Blekas et al, 2005). Although motifs are powerful discriminators even in low similarity (remote homology) situations, motif finding is a very difficult task, especially for protein sequences since there are 20 different amino acids and many plausible mutations.…”

Section: Introductionmentioning

confidence: 99%

Subsequence-based feature map for protein function classification

Saraç

Gürsoy-Yüzügüllü

Cetin-Atalay

et al. 2008

Computational Biology and Chemistry

View full text Add to dashboard Cite

Automated classification of proteins is indispensable for further in vivo investigation of excessive number of unknown sequences generated by large scale molecular biology techniques. This study describes a discriminative system based on feature space mapping, called subsequence profile map (SPMap) for functional classification of protein sequences. SPMap takes into account the information coming from the subsequences of a protein. A group of protein sequences that belong to the same level of classification is decomposed into fixed-length subsequences and they are clustered to obtain a representative feature space mapping. Mapping is defined as the distribution of the subsequences of a protein sequence over these clusters. The resulting feature space representation is used to train discriminative classifiers for functional families. The aim of this approach is to incorporate information coming from important subregions that are conserved over a family of proteins while avoiding the difficult task of explicit motif identification. The performance of the method was assessed through tests on various protein classification tasks. Our results showed that SPMap is capable of high accuracy classification in most of these tasks. Furthermore SPMap is fast and scalable enough to handle large datasets.

show abstract

Motif extraction and protein classification

Cited by 22 publications

References 10 publications

Motif-Based Classification of Time Series with Bayesian Networks and SVMs

Motif-Based Classification of Time Series with Bayesian Networks and SVMs

Systems chemical biology

Subsequence-based feature map for protein function classification

Contact Info

Product

Resources

About