Engineering support vector machine kernels that recognize translation initiation sites
BioinformaticsPublished 1 September 2000Open access
Alexander Zien, Gunnar Rätsch, S. Mika, Bernhard Schölkopf, Thomas Lengauer, K. Müller
Citations425
SJR quartileQ1
SJR score2.45
SNIP1.47
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
With the described techniques the recognition performance can be improved by 26% over leading existing approaches, and there is evidence that existing related methods could profit from advanced TIS recognition.
Abstract
MOTIVATION: In order to extract protein sequences from nucleotide sequences, it is an important step to recognize points at which regions start that code for proteins. These points are called translation initiation sites (TIS). RESULTS: The task of finding TIS can be modeled as a classification problem. We demonstrate the applicability of support vector machines for this task, and show how to incorporate prior biological knowledge by engineering an appropriate kernel function. With the described techniques the recognition performance can be improved by 26% over leading existing approaches. We provide evidence that existing related methods (e.g. ESTScan) could profit from advanced TIS recognition.
Keywords
Biochemistry, Genetics and Molecular Biology
The Nature of Statistical Learning Theory
39,279 Citations1995Vladimir Vapnik
Machine LearningSupport-Vector Networks
33,035 Citations1995Corinna Cortes, Vladimir Vapnik
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Choice Reviews OnlineNeural networks for pattern recognition
18,687 Citations1994
This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
A training algorithm for optimal margin classifiers
11,594 Citations1992Bernhard E. Boser, Isabelle Guyon +1 more
A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented, applicable to a wide variety of the classification functions, including Perceptrons, polynomials, and Radial Basis Functions.
International Conference on Neural Information ProcessingAdvances in kernel methods: support vector learning
5,815 Citations1999Bernhard Schölkopf, Christopher J. C. Burges +1 more
Support vector machines for dynamic reconstruction of a chaotic system, Klaus-Robert Muller et al pairwise classification and support vector machines, Ulrich Kressel.
Journal of Molecular BiologyPrediction of complete gene structures in human genomic DNA
4,264 Citations1997Chris Burge, Samuel Karlin
A general probabilistic model of the gene structure of human genomic sequences which incorporates descriptions of the basic transcriptional, translational and splicing signals, as well as length distributions and compositional features of exons, introns and intergenic regions is introduced.
The Journal of Cell BiologyThe scanning model for translation: an update.
3,535 Citations1989M Kozak
The small (40S) subunit of eukaryotic ribosomes is believed to bind initially at the capped 5'-end of messenger RNA and then migrate, stopping at the first AUG codon in a favorable context for initiating translation.
Neural ComputationNew Support Vector Algorithms
2,816 Citations2000Bernhard Schölkopf, Alex Smola +2 more
A new class of support vector algorithms for regression and classification that eliminates one of the other free parameters of the algorithm: the accuracy parameter in the regression case, and the regularization constant C in the classification case.
Proceedings of the National Academy of SciencesKnowledge-based analysis of microarray gene expression data by using support vector machines
2,315 Citations2000Michael P. Brown, William Noble Grundy +6 more
A method of functionally classifying genes by using gene expression data from DNA microarray hybridization experiments, based on the theory of support vector machines (SVMs), to predict functional roles for uncharacterized yeast ORFs based on their expression data is introduced.
Lecture notes in computer scienceNeural Networks: Tricks of the Trade
2,146 Citations2012Montavon, Grégoire, Müller, Klaus-Robert +1 more
The second edition of the book augments the first edition with more tricks, which have resulted from 14 years of theory and experimentation by some of the world's most prominent neural network researchers.
Nature GeneticsIdentification of protein coding regions by database similarity search
1,688 Citations1993Warren Gish, David J. States
The computer program BLASTX performed conceptual translation of a nucleotide query sequence followed by a protein database search in one programmatic step and was characterized as appropriate for use in moderate and large scale sequencing projects at the earliest opportunity, when the data are most prone to containing errors.
Exploiting Generative Models in Discriminative Classifiers
1,285 Citations1998Tommi Jaakkola, David Haussler
A natural way of achieving this combination by deriving kernel functions for use in discriminative methods such as support vector machines from generative probability models is developed.
PubMedESTScan: a program for detecting, evaluating, and reconstructing potential coding regions in EST sequences.
1,108 Citations1999Christian Iseli, C. Victor Jongeneel +1 more
It is shown that ESTScan can detect and extract coding regions from low-quality sequences with high selectivity and sensitivity, and is able to accurately correct frameshift errors.
Mammalian GenomeInterpreting cDNA sequences: Some insights from studies on translation
778 Citations1996M Kozak
This review discusses some rules for assessing the completeness of a cDNA sequence and identifying the start site for translation and includes some advice for using in vitro translation systems for the expression of cDNAs.
GenomicsComparison of DNA Sequences with Protein Sequences
607 Citations1997William R. Pearson, Todd Wood +2 more
FASTX and FASTY are used to scan the Mycoplasma genitalium, Haemophilus influenzae, and Methanococcus jannaschii genomes for unidentified or misidentified protein-coding genes and are found to be quite accurate, except when an out-of-frame translation produces a low-complexity protein sequence.
Journal of Computational BiologyA Discriminative Framework for Detecting Remote Protein Homologies
494 Citations2000Tommi Jaakkola, Mark Diekhans +1 more
A new method for detecting remote protein homologies is introduced and shown to perform well in classifying protein domains by SCOP superfamily using a new kernel function derived from a generative statistical model for a protein family, in this case a hidden Markov model.
The EMBO JournalRecognition of AUG and alternative initiator codons is augmented by G in position +4 but is not generally affected by the nucleotides in positions +5 and +6
490 Citations1997Marilyn Kozak
The toeprinting assay was used with mRNAs that initiate translation at CUG instead of AUG, cugGAU was not recognized better than cugGGU, contradicting the hypothesis that initiation at non‐AUG codons might be favored by A instead of G in position +5.
PubMedUsing the Fisher kernel method to detect remote protein homologies.
414 Citations1999Tommi Jaakkola, Mark Diekhans +1 more
A new method, called the Fisher kernel method, for detecting remote protein homologies is introduced and shown to perform well in classifying protein domains by SCOP superfamily.
PubMedNeural network prediction of translation initiation sites in eukaryotes: perspectives for EST and genome analysis.
306 Citations1997Anders Gorm Pedersen, Henrik Nielsen
This paper employs artificial neural networks to predict which AUG triplet in an mRNA sequence is the start codon, and finds that their trained neural networks use a combination of local startcodon context and global sequence information.
Prior Knowledge in Support Vector Kernels
293 Citations1997Bernhard Schölkopf, Patrice Simard +2 more
It is shown that both invariances under group transformations and prior knowledge about locality in images can be incorporated by constructing appropriate kernel functions by exploring methods for incorporating prior knowledge in Support Vector learning machines.
BioinformaticsAssessing protein coding region integrity in cDNA sequencing projects.
168 Citations1998Asaf Salamov, Tetsuo Nishikawa +1 more
A linear discriminant approach that predicts this completeness of the protein coding region of a sequence by estimating the probability of each ATG being the initiation codon by exploiting the criterion that only a single prediction is allowed for each sequence.
Nucleic Acids ResearchPairWise and SearchWise: Finding the Optimal Alignment in a Simultaneous Comparison of a Protein Profile against All DNA Translation Frames
160 Citations1996Ewan Birney, Julie Thompson +1 more
A dynamic alignment algorithm is reported here which compares a protein profile (a residue scoring matrix for one or more aligned sequences) against the three translation frames of a DNA strand, allowing frameshifting.
Computer applications in the biosciencesA method for identifying splice sites and translational start sites in eukaryotic mRNA
128 Citations1997Steven L. Salzberg
PubMedThe ribosome scanning model for translation initiation: implications for gene prediction and full-length cDNA detection.
14 Citations1998Pankaj Agarwal, Vineet Bafna
This paper uses a set of experimentally verified translation initiation (TI) sites from eukaryotic sequences to train a range of methods, and then compares these methods, finding none of the methods is effective in predicting TI sites.