On Position-Specific Scoring Matrix for Protein Function Prediction
The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Abstract
While genome sequencing projects have generated tremendous amounts of protein sequence data for a vast number of genomes, substantial portions of most genomes are still unannotated. Despite the success of experimental methods for identifying protein functions, they are often lab intensive and time consuming. Thus, it is only practical to use in silico methods for the genome-wide functional annotations. In this paper, we propose new features extracted from protein sequence only and machine learning-based methods for computational function prediction. These features are derived from a position-specific scoring matrix, which has shown great potential in other bininformatics problems. We evaluate these features using four different classifiers and yeast protein data. Our experimental results show that features derived from the position-specific scoring matrix are appropriate for automatic function annotation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“In this study, four commonly used classifiers are employed for evaluating PSSM-based protein function prediction: Naı̈ve Bayesian (NB) [37], support vector machines (SVMs) [38], decision trees (DTs) [39], and random forest (RF) [40].”
MethodGapped BLAST and PSI-BLAST: a new generation of protein database search programs
Altschul, S. (1997) · Nucleic Acids Research · doi:10.1093/nar/25.17.3389 · Cited by 73,302 · cited 8×
“Position-specific iterated BLAST (PSI-BLAST) [1], [35] is the most commonly used application, which compares PSSM profiles for detecting remotely related homologous proteins or DNA.”
MethodInfluentialLIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918
Classification and Regression Trees.
Gordon, A. D., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1984) · Biometrics · doi:10.2307/2530946 · Cited by 23,522
An overview of statistical learning theory
Vapnik, V. N. (1999) · IEEE Transactions on Neural Networks · doi:10.1109/72.788640 · Cited by 6,266 · cited 1×
“In this study, four commonly used classifiers are employed for evaluating PSSM-based protein function prediction: Naı̈ve Bayesian (NB) [37], support vector machines (SVMs) [38], decision trees (DTs) [39], and random forest (RF) [40].”
MethodJones, D. T. (1999) · Journal of Molecular Biology · doi:10.1006/jmbi.1999.3091 · Cited by 5,449 · cited 1×
“The PSSM has been successfully applied to protein secondary structure prediction [31], protein binding site prediction [32], protein function prediction (not machine learning-based) [33], and prediction of disordered regions [34].”
MethodProtein Structure Comparison by Alignment of Distance Matrices
Holm, L., & Sander, C. (1993) · Journal of Molecular Biology · doi:10.1006/jmbi.1993.1489 · Cited by 3,984 · cited 1×
“structure patterns [17], [18], [19], [20].”
(2024) · Physics Subject Headings (PhySH) · doi:10.29172/7c2a6982-6d72-4cd8-bba6-2fccb06a7011 · Cited by 3,857
On the Optimality of the Simple Bayesian Classifier under Zero-One Loss
Domingos, P., & Pazzani, M. (1997) · Machine Learning · doi:10.1023/a:1007413511361 · Cited by 3,101
Detecting Protein Function and Protein-Protein Interactions from Genome Sequences
Marcotte, E. M., Pellegrini, M., Ng, H.-L., Rice, D. W., Yeates, T. O., & Eisenberg, D. (1999) · Science · doi:10.1126/science.285.5428.751 · Cited by 1,670 · cited 1×
“For example, gene fusion, also known as Rosetta Stone, is based on the observation that if certain protein families in a given species consist of fused domains, each corresponding to single and full-length proteins in other species, then one can conclude that the two component proteins may be functionally related [12]…”
BackgroundAssigning protein functions by comparative genome analysis: Protein phylogenetic profiles
Pellegrini, M., Marcotte, E. M., Thompson, M. J., Eisenberg, D., & Yeates, T. O. (1999) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.96.8.4285 · Cited by 1,585
BIND--The Biomolecular Interaction Network Database
Bader, G. D. (2001) · Nucleic Acids Research · doi:10.1093/nar/29.1.242 · Cited by 1,560
Profile analysis: detection of distantly related proteins.
Gribskov, M., McLachlan, A. D., & Eisenberg, D. (1987) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.84.13.4355 · Cited by 1,325 · cited 5×
“It was generated from a group of sequences previously aligned by structural or sequence similarity [30].”
BackgroundMethodInfluentialBIND: the Biomolecular Interaction Network Database
Bader, G. D. (2003) · Nucleic Acids Research · doi:10.1093/nar/gkg056 · Cited by 1,114 · cited 1×
“database [42].”
Hulo, N. (2006) · Nucleic Acids Research · doi:10.1093/nar/gkj063 · Cited by 971 · cited 1×
“Sequence pattern-based approach is another type of sequence-based methods [6], [7], [8].”
MethodProtein function in the post-genomic era
Eisenberg, D., Marcotte, E. M., Xenarios, I., & Yeates, T. O. (2000) · Nature · doi:10.1038/35015694 · Cited by 749 · cited 1×
“In the late 1990s, a class of sequence-based methods for protein annotation emerged on the basis of genomic context [9], [10], 11].”
MethodGlobal protein function prediction from protein-protein interaction networks
Vazquez, A., Flammini, A., Maritan, A., & Vespignani, A. (2003) · Nature Biotechnology · doi:10.1038/nbt825 · Cited by 693
Todd, A. E., Orengo, C. A., & Thornton, J. M. (2001) · Journal of Molecular Biology · doi:10.1006/jmbi.2001.4513 · Cited by 683 · cited 1×
“structure patterns [17], [18], [19], [20].”
A combined algorithm for genome-wide prediction of protein function
Marcotte, E. M., Pellegrini, M., Thompson, M. J., Yeates, T. O., & Eisenberg, D. (1999) · Nature · doi:10.1038/47048 · Cited by 682 · cited 1×
“Methods integrating various data from different sources, such as gene expression, gene fusion, and correlated mutations, are also investigated for function prediction [24], [25], [26].”
BackgroundIterated profile searches with PSI-BLAST—a tool for discovery in protein databases
Altschul, S. F., & Koonin, E. V. (1998) · Trends in Biochemical Sciences · doi:10.1016/s0968-0004(98)01298-5 · Cited by 680 · cited 2×
“In our study, we used PSI-BLAST [1], [35] to create PSSMs for each protein sequence.”
MethodCai, C. Z. (2003) · Nucleic Acids Research · doi:10.1093/nar/gkg600 · Cited by 576 · cited 1×
“Recently, feature-based machine learning approaches using protein sequences have shown great promise for protein function annotation, especially for proteins with weakly homologous proteins and orphan proteins (proteins that do not have detectable sequence similarity in other genomes) [27], [28], [29].”
BackgroundPRINTS and its automatic supplement, prePRINTS
Attwood, T. K. (2003) · Nucleic Acids Research · doi:10.1093/nar/gkg030 · Cited by 388 · cited 1×
“Sequence pattern-based approach is another type of sequence-based methods [6], [7], [8].”
MethodPrediction of protein–protein interactions using random decision forest framework
Chen, X.-W., & Liu, M. (2005) · Bioinformatics · doi:10.1093/bioinformatics/bti721 · Cited by 382
Self-citationCYGD: the Comprehensive Yeast Genome Database
Guldener, U. (2004) · Nucleic Acids Research · doi:10.1093/nar/gki053 · Cited by 338
Whole-genome annotation by using evidence integration in functional-linkage networks
Karaoz, U., Murali, T. M., Letovsky, S., Zheng, Y., Ding, C., Cantor, C. R., & Kasif, S. (2004) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0307326101 · Cited by 315 · cited 1×
“Methods integrating various data from different sources, such as gene expression, gene fusion, and correlated mutations, are also investigated for function prediction [24], [25], [26].”
BackgroundCoevolution of gene expression among interacting proteins
Fraser, H. B., Hirsh, A. E., Wall, D. P., & Eisen, M. B. (2004) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0402591101 · Cited by 248 · cited 1×
“Another class of protein function prediction methods takes the advantage of the ever-increasing accumulation of high-throughput data such as gene expressions can be a better predictor than the coevolution of sequences [21] and protein-protein interaction data [2], [22], [23].”
BackgroundPrediction of human protein function according to Gene Ontology categories
Jensen, L. J., Gupta, R., Stærfeldt, H.-H., & Brunak, S. (2003) · Bioinformatics · doi:10.1093/bioinformatics/btg036 · Cited by 246 · cited 1×
“Recently, feature-based machine learning approaches using protein sequences have shown great promise for protein function annotation, especially for proteins with weakly homologous proteins and orphan proteins (proteins that do not have detectable sequence similarity in other genomes) [27], [ 28 ], [29].”
BackgroundDiscovery of uncharacterized cellular systems by genome-wide analysis of functional linkages
Date, S. V., & Marcotte, E. M. (2003) · Nature Biotechnology · doi:10.1038/nbt861 · Cited by 227 · cited 1×
“In the late 1990s, a class of sequence-based methods for protein annotation emerged on the basis of genomic context [9], [10], 11].”
MethodPrediction of disordered regions in proteins from position specific score matrices
Jones, D. T., & Ward, J. J. (2003) · Proteins: Structure, Function, and Genetics · doi:10.1002/prot.10528 · Cited by 212 · cited 1×
“The PSSM has been successfully applied to protein secondary structure prediction [31], protein binding site prediction [32], protein function prediction (not machine learning-based) [33], and prediction of disordered regions [34].”
MethodProtein Molecular Function Prediction by Bayesian Phylogenomics
Engelhardt, B. E., Jordan, M. I., Muratore, K. E., & Brenner, S. E. (2005) · PLoS Computational Biology · doi:10.1371/journal.pcbi.0010045 · Cited by 196 · cited 2×
“It is thus critical to make families and assign function to a protein based on its closest the most out of the sequence data by characterizing what ortholog, not necessarily the most similar sequence. proteins do within a biological context, i.e., understanding Representative implementation includes RIO [3], SIFTER th…”
MethodRIO: Analyzing proteomes by automated phylogenomics using resampled inference of orthologs
Zmasek, C. M., & Eddy, S. R. (2002) · BMC Bioinformatics · doi:10.1186/1471-2105-3-14 · Cited by 190 · cited 3×
“[3] C.M. Zmasek and S.R. Eddy, RIO: Analyzing Proteomes by Automated Phylogenomics Using Resampled Inference of Orthologs, BMC Bioinformatics, vol. 3, article no. 14, May 2002.”
MethodAutomated prediction of protein function and detection of functional sites from structure
Pazos, F., & Sternberg, M. J. E. (2004) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0404569101 · Cited by 174 · cited 1×
“structure patterns [17], [18], [19], [20].”
Yanai, I., Derti, A., & DeLisi, C. (2001) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.141236298 · Cited by 166 · cited 1×
“For example, gene fusion, also known as Rosetta Stone, is based on the observation that if certain protein families in a given species consist of fused domains, each corresponding to single and full-length proteins in other species, then one can conclude that the two component proteins may be functionally related [12]…”
BackgroundSequence-based prediction of protein interaction sites with an integrative method
Chen, X., & Jeong, J. C. (2009) · Bioinformatics · doi:10.1093/bioinformatics/btp039 · Cited by 153 · cited 1×
“The PSSM has been successfully applied to protein secondary structure prediction [31], protein binding site prediction [32], protein function prediction (not machine learning-based) [33], and prediction of disordered regions [34].”
MethodSelf-citationStrong, M., Mallick, P., Pellegrini, M. A., Thompson, M. J., & Eisenberg, D. S. (2003) · Genome biology · doi:10.1186/gb-2003-4-9-r59 · Cited by 108 · cited 1×
“Other methods include gene neighborhood-based methods, which are based on the fact that bacterial genomes are organized into regions that tend to code for functionally related proteins called operons [15].”
MethodConFunc—functional annotation in the twilight zone
Wass, M. N., & Sternberg, M. J. E. (2008) · Bioinformatics · doi:10.1093/bioinformatics/btn037 · Cited by 106 · cited 1×
“The PSSM has been successfully applied to protein secondary structure prediction [31], protein binding site prediction [32], protein function prediction (not machine learning-based) [33], and prediction of disordered regions [34].”
Method[37] Understanding protein structure: Using scop for fold interpretation
Brenner, S. E., Chothia, C., Hubbard, T., & Murzin, A. G. (1996) · Methods in enzymology on CD-ROM/Methods in enzymology · doi:10.1016/s0076-6879(96)66039-x · Cited by 100 · cited 1×
“Since protein structures are better preserved than their sequences, structure-based methods detect the function of proteins with structure similarities but little or no sequence similarities [16].”
BackgroundIn Silico Characterization of Proteins: UniProt, InterPro and Integr8
Mulder, N., Kersey, P. J., Pruess, M., & Apweiler, R. (2007) · Molecular Biotechnology · doi:10.1007/s12033-007-9003-x · Cited by 83 · cited 1×
“Sequence pattern-based approach is another type of sequence-based methods [6], [7], [8].”
MethodPredicting functional linkages from gene fusions with confidence.
Marcotte, C. V., & Marcotte, E. M. (2002) · PubMed · Cited by 66
FFPred: an integrated feature-based function prediction server for vertebrate proteomes
Lobley, A., Nugent, T., Orengo, C. A., & Jones, D. T. (2008) · Nucleic Acids Research · doi:10.1093/nar/gkn193 · Cited by 64 · cited 1×
“Recently, feature-based machine learning approaches using protein sequences have shown great promise for protein function annotation, especially for proteins with weakly homologous proteins and orphan proteins (proteins that do not have detectable sequence similarity in other genomes) [27], [28], [29].”
BackgroundLiu, M., Chen, X., & Jothi, R. (2009) · Bioinformatics · doi:10.1093/bioinformatics/btp480 · Cited by 26 · cited 1×
“Another class of protein function prediction methods takes the advantage of the ever-increasing accumulation of high-throughput data such as gene expressions can be a better predictor than the coevolution of sequences [21] and protein-protein interaction data [2], [22], [23].”
Self-citationProtein Function Assignment through Mining Cross-Species Protein-Protein Interactions
Chen, X., Liu, M., & Ward, R. (2008) · PLoS ONE · doi:10.1371/journal.pone.0001562 · Cited by 26 · cited 3×
“Research has shown that cross-species information provides valuable information for protein function prediction and can improve the performance of a predictive system significantly [2].”
BackgroundSelf-citation
Cited by
Drug–target affinity prediction using graph neural network and contact maps
Jiang, M., Li, Z., Zhang, S., Wang, S., Wang, X., Yuan, Q., & Wei, Z. (2020) · RSC Advances · doi:10.1039/d0ra02297g · Cited by 372
DeepSS2GO: protein function prediction from secondary structure
Song, F. V., Su, J., Huang, S., Zhang, N., Li, K., Ni, M., & Liao, M. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae196 · Cited by 26
Metadata
- Authors
- Jeong, J. C., Lin, X., & Chen, X.-W.
- Venue
- IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Published
- 2011-03
- Volume
- 8
- Issue
- 2
- Pages
- 308-315
- ISSN
- 1545-5963 (ISSN-L)
- 1557-9964
- 2374-0043
- OpenAlex
- W2147580225
- Cited by
- 198
- References
- 42
- FWCI
- 2.24
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.