Determination of eukaryotic protein coding regions using neural networks and information theory
The DOI matches its Crossref record; 10 of the 11 references it cites were found in a registry or an index.
Abstract
Our previous work applied neural network techniques to the problem of discriminating open reading frame (ORF) sequences taken from introns versus exons. The method counted the codon frequencies in an ORF of a specified length, and then used this codon frequency representation of DNA fragments to train a neural net (essentially a Perceptron with a sigmoidal, or "soft step function", output) to perform this discrimination. After training, the network was then applied to a disjoint "predict" set of data to assess accuracy. The resulting accuracy in our previous work was 98.4%, exceeding accuracies reported in the literature at that time for other algorithms. Here, we report even higher accuracies stemming from calculations of mutual information (a correlation measure) of spatially separated codons in exons, and in introns. Significant mutual information exists in exons, but not in introns, between adjacent codons. This suggests that dicodon frequencies of adjacent codons are important for intron/exon discrimination. We report that accuracies obtained using a neural net trained on the frequency of dicodons is significantly higher at smaller fragment lengths than even our original results using codon frequencies, which were already higher than simple statistical methods that also used codon frequencies. We also report accuracies obtained from including codon and dicodon statistics in all six reading frames, i.e. the three frames on the original and complement strand. Inclusion of six-frame statistics increases the accuracy still further. We also compare these neural net results to a Bayesian statistical prediction method that assumes independent codon frequencies in each position. The performance of the Bayesian scheme is poorer than any of the neural based schemes, however many methods reported in the literature either explicitly, or implicitly, use this method. Specifically, Bayesian prediction schemes based on codon frequencies achieve 90.9% accuracy on 90 codon ORFs, while our best neural net scheme reaches 99.4% accuracy on 60 codon ORFs. "Accuracy" is defined as the average of the exon and intron sensitivities. Achievement of sufficiently high accuracies on short fragment lengths can be useful in providing a computational means of finding coding regions in unannotated DNA sequences such as those arising from the mega-base sequencing efforts of the Human Genome Project. We caution that the high accuracies reported here do not represent a complete solution to the problem of identifying exons in "raw" base sequences. The accuracies are considerably lower from exons of small length, although still higher than accuracies reported in the literature for other methods. Short exon lengths are not uncommon.(ABSTRACT TRUNCATED AT 400 WORDS)
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Mutual information has been applied for reverse engineering biological networks since the 1990s. In early applications [63–67], genetic interactions were hypothesized from high values of pairwise mutual information between genes.”
From Reverse engineering and identification in systems biology: strategies, perspectives and challenges (2014) · cites this paper as [63]
Citations
Cites
Recognition of protein coding regions in DNA sequences
Fickett, J. W. (1982) · Nucleic Acids Research · doi:10.1093/nar/10.17.5303 · Cited by 904
Computer methods to locate signals in nucleic acid sequences
Staden, R. (1984) · Nucleic Acids Research · doi:10.1093/nar/12.1part2.505 · Cited by 664
Codon preference and its use in identifying protein coding regions in long DNA sequences
Staden, R., & McLachian, A. D. (1982) · Nucleic Acids Research · doi:10.1093/nar/10.1.141 · Cited by 462
Gribskov, M., Devereux, J., & Burgess, R. R. (1984) · Nucleic Acids Research · doi:10.1093/nar/12.1part2.539 · Cited by 376
Staden, R. (1984) · Nucleic Acids Research · doi:10.1093/nar/12.1part2.551 · Cited by 248
Application of Neural Networks and Other Machine Learning Algorithms to DNA Sequence Analysis
Lapedes, A. S., Barnes, C., Burks, C., Farber, R., & Sirotkin, K. M. (2018) · Routledge eBooks · doi:10.4324/9780429501463-15 · Cited by 77
Self-citationStatistical method for predicting protein coding regions in nucleic acid sequences
Fichant, G. A., & Gautier, C. (1987) · Computer applications in the biosciences · doi:10.1093/bioinformatics/3.4.287 · Cited by 59
Computers in Molecular Biology: Current Applications and Emerging Trends
DeLisi, C. (1988) · Science · doi:10.1126/science.3281255 · Cited by 48
A method to locate protein coding sequences in DNA of prokaryotic systems
Kolaskar, A. S., & Reddy, B. V. B. (1985) · Nucleic Acids Research · doi:10.1093/nar/13.1.185 · Cited by 43
Delineation of Coding Areas in DNA Sequences Through Assignment of Codon Probabilities
Hinds, P. W., & Blake, R. D. (1985) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.1985.10508442 · Cited by 16
Research works printed but not linked: 2
- Press, 1988
- Rummelhart, 1986, vol. 1
Cited by
Prediction of probable genes by Fourier analysis of genomic sequences
Tiwari, S., Ramachandran, S., Bhattacharya, A., Bhattacharya, S., & Ramaswamy, R. (1997) · Bioinformatics · doi:10.1093/bioinformatics/13.3.263 · Cited by 433
“…1982) or oligonucleotide frequencies (Shulman etal., 1981, Fickett, 1982; Borodovsky et al., 1986, 1994), or train neural nets (Lapedes et al., 1990; Uberbacher and Mural, 1991; Farber et al., 1992; Xu et al., 1994; Snyder and Stormo, 1995) to recognize the distinctive features of the two sets.”
BackgroundSolovyev, V. V., Salamov, A. A., & Lawrence, C. B. (1994) · Nucleic Acids Research · doi:10.1093/nar/22.24.5156 · Cited by 353
Positional Dependence, Cliques, and Predictive Motifs in the bHLH Protein Domain
Atchley, W. R., Terhalle, W., & Dress, A. (1999) · Journal of Molecular Evolution · doi:10.1007/pl00006494 · Cited by 345
“If events are independent, then the mutual information is 0; if events are dependent, mutual information is positive ( Farber et al. 1992; Herzel and Gross 1995; Clarke, 1995; Roman-Roldan et al. 1996).”
BackgroundA hidden Markov model that finds genes inE.coliDNA
Krogh, A., Mian, I. S., & Haussler, D. (1994) · Nucleic Acids Research · doi:10.1093/nar/22.22.4768 · Cited by 315
Computational methods for the identification of genes in vertebrate genomic sequences
Claverie, J. (1997) · Human Molecular Genetics · doi:10.1093/hmg/6.10.1735 · Cited by 264
“The contrast in the usage of six nucleotide words (hexamers) (17,21) was found to be the best single property to predict whether a window of vertebrate genomic sequence was coding or non-coding (16, 22 ).”
Background
Metadata
- Authors
- Farber, R., Lapedes, A., & Sirotkin, K.
- Affiliations
- Los Alamos National Laboratory (US)
- National Institutes of Health (US)
- ORCID
- Sirotkin, Karl
- Venue
- Journal of Molecular Biology
- Publisher
- Elsevier BV
- Published
- 1992-07
- Volume
- 226
- Issue
- 2
- Pages
- 471-479
- ISSN
- 0022-2836 (ISSN-L)
- OpenAlex
- W1982115165
- Cited by
- 113
- References
- 11
- Citations by year
- 2025: 1 · 2024: 1 · 2023: 2 · 2021: 1 · 2019: 1 · 2018: 1 · 2017: 1 · 2015: 2 · 2014: 6 · 2013: 6 · 2012: 1
- FWCI
- 3.15
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.elsevier.com/tdm/userlicense/1.0/ (tdm)
- Locations
- Journal of Molecular Biology (publishedVersion)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Funders
- National Institutes of Health (1r01gm040789-01)
- National Institute of General Medical Sciences (GM 40789-03)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Fractal and DNA sequence analysis
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Keywords
- open reading frames, codon frequency, mutual information, neural network classification, Bayesian forecasting, exon prediction, codon usage bias
- MeSH terms
- Base Sequence, Codon, Exons, Genes, Introns, Molecular Sequence Data, Open Reading Frames, Neural Networks, Computer
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Determination of eukaryotic protein coding regions using neural networks and information theory. https://app.cochat.ai/papers/10.1016/0022-2836(92)90961-i
- The paper
- Farber, R., Lapedes, A., & Sirotkin, K. (1992). Determination of eukaryotic protein coding regions using neural networks and information theory. Journal of Molecular Biology. https://doi.org/10.1016/0022-2836(92)90961-i
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.