A neural network based predictor of residue contacts in proteins
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
We describe a method based on neural networks for predicting contact maps of proteins using as input chemicophysical and evolutionary information. Neural networks are trained on a data set comprising the contact maps of 200 non-homologous proteins of well resolved three-dimensional structures. The systems learn the association rules between the covalent structure of each protein and its correspondent contact map by means of a standard back propagation algorithm. Validation of the predictor on the training set and on 408 proteins of known structure which are not homologous to those contained in the training set indicate that this method scores higher than statistical approaches previously described and based on correlated mutations and sequence information.
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
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Kabsch, W., & Sander, C. (1983) · Biopolymers · doi:10.1002/bip.360221211 · Cited by 15,320 · cited 1×
“In this way a filter procedure is generated, which takes into account the secondary structure labels for the different residues from the DSSP files (Kabsch and Sander, 1983); moreover, for each residue predicted contacts are accepted provided that their number is less than the average number of…”
MethodThe protein data bank: A computer-based archival file for macromolecular structures
Bernstein, F. C., Koetzle, T. F., Williams, G. J. B., Meyer, E. F., Brice, M. D., Rodgers, J. R., Kennard, O., Shimanouchi, T., & Tasumi, M. (1977) · Journal of Molecular Biology · doi:10.1016/s0022-2836(77)80200-3 · Cited by 8,578 · cited 1×
“Neural networks were trained and tested on a database of proteins selected from the Protein Data Bank (PDB; Bernstein et al., 1977) using the PDB_select algorithm (Hobohmet al., 1992).”
MethodDatabase of homology‐derived protein structures and the structural meaning of sequence alignment
Sander, C., & Schneider, R. (1991) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.340090107 · Cited by 1,639 · cited 2×
“(A) An alignment of five (hypothetical) sequences they are represented in a HSSP file (Sander and Schneider, 1991).i and j stand for the positions of the two residues making or not making contact (A and D in the leading sequence or sequence 1).”
BackgroundMiyazawa, S., & Jernigan, R. L. (1985) · Macromolecules · doi:10.1021/ma00145a039 · Cited by 1,536 · cited 1×
“…in proteins of known 3D structure was first computed to derive mean force potentials with the aim of tackling the folding and the inverse folding problem (Miyazawa and Jernigan, 1985; Sippl, 1990; Mairov and Crippen, 1992, Grossmanet al., 1995; Huanget al., 1995; Mirny and Shaknovich, 1996).”
Hydrophobicity of Amino Acid Residues in Globular Proteins
Rose, G. D., Geselowitz, A. R., Lesser, G. J., Lee, R. H., & Zehfus, M. H. (1985) · Science · doi:10.1126/science.4023714 · Cited by 1,175
Calculation of conformational ensembles from potentials of mena force
Sippl, M. J. (1990) · Journal of Molecular Biology · doi:10.1016/s0022-2836(05)80269-4 · Cited by 1,070 · cited 1×
“…in proteins of known 3D structure was first computed to derive mean force potentials with the aim of tackling the folding and the inverse folding problem (Miyazawa and Jernigan, 1985; Sippl, 1990; Mairov and Crippen, 1992, Grossmanet al., 1995; Huanget al., 1995; Mirny and Shaknovich, 1996).”
Correlated mutations and residue contacts in proteins
Göbel, U., Sander, C., Schneider, R., & Valencia, A. (1994) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.340180402 · Cited by 863
Selection of representative protein data sets
Hobohm, U., Scharf, M., Schneider, R., & Sander, C. (1992) · Protein Science · doi:10.1002/pro.5560010313 · Cited by 819
Rost, B., Fariselli, P., & Casadio, R. (1996) · Protein Science · doi:10.1002/pro.5560050824 · Cited by 607
Self-citationContact potential that recognizes the correct folding of globular proteins
Maiorov, V. N., & Grippen, G. M. (1992) · Journal of Molecular Biology · doi:10.1016/0022-2836(92)90228-c · Cited by 342
Shindyalov, I. N., Kolchanov, N. A., & Sander, C. (1994) · "Protein Engineering, Design and Selection" · doi:10.1093/protein/7.3.349 · Cited by 297
Recovery of protein structure from contact maps
Vendruscolo, M., Kussell, E., & Domany, E. (1997) · Folding and Design · doi:10.1016/s1359-0278(97)00041-2 · Cited by 268
How to Derive a Protein Folding Potential? A New Approach to an Old Problem
Mirny, L. A., & Shakhnovich, E. I. (1996) · Journal of Molecular Biology · doi:10.1006/jmbi.1996.0704 · Cited by 267
A lattice model for protein structure prediction at low resolution.
Hinds, D. A., & Levitt, M. (1992) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.89.7.2536 · Cited by 217 · cited 1×
“This threshold value is chosen in order to guarantee that there is neither a third residue nor a water molecule between two amino acids in contact and it is equal to that previously used in other studies (Hinds and Levitt, 1992; Mirny and Domany, 1996).”
ResultOlmea, O., & Valencia, A. (1997) · Folding and Design · doi:10.1016/s1359-0278(97)00060-6 · Cited by 203 · cited 7×
“…the network, our results indicate that the neural network-based predictor achieves on average an improvement over a random predictor of a factor of 6, which is higher than that previously obtained by other methods developed to predict residue contacts (Thomaset al., 1996; Olmea and Valencia, 1997).”
BackgroundMethodResultInfluentialProtein distance constraints predicted by neural networks and probability density functions
Lund, O., Frimand, K., Gorodkin, J., Bohr, H., Bohr, J., Hansen, J., & Brunak, S. (1997) · Protein Engineering Design and Selection · doi:10.1093/protein/10.11.1241 · Cited by 155 · cited 1×
“Recently neural networks have been successfully applied to predict whether distances between pairs of amino acids are above or below a given variable threshold (Lund et al., 1997).”
Compensating changes in protein multiple sequence alignments
Taylor, W. R., & Hatrick, K. (1994) · "Protein Engineering, Design and Selection" · doi:10.1093/protein/7.3.341 · Cited by 150 · cited 1×
“Other methods more specifically address the problem of residue contact prediction using the information derived from occurrence of correlated mutations in similar proteins (Go¨bel et al., 1984; Shidyalov et al., 1994; Taylor and Hatrick, 1994).”
MethodRecognizing Native Folds by the Arrangement of Hydrophobic and Polar Residues
Huang, E. S., Subbiah, S., & Levitt, M. (1995) · Journal of Molecular Biology · doi:10.1006/jmbi.1995.0529 · Cited by 137
Bohr, H. G., Bohr, J., Brunak, S., COTTERILL, R. M. J., Fredholm, H., Lautrup, B. E., & Petersen, S. B. (1990) · FEBS Letters · doi:10.1016/0014-5793(90)80632-s · Cited by 130 · cited 1×
“Neural networks have been used in the pioneer work by Bohr et al. (1990) to predict distances between amino acids of homologous protein sequences and also to represent knowledge based potentials (Grossmanet al., 1995).”
MethodProgress of 1D protein structure prediction at last
Rost, B., & Sander, C. (1995) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.340230304 · Cited by 93 · cited 2×
“By this, the activation level of the output neuron can be regarded as a kind of reliability index (Rost and Sander, 1995).”
BackgroundThe prediction of protein contacts from multiple sequence alignments
Thomas, D. J., Casari, G., & Sander, C. (1996) · Protein Engineering Design and Selection · doi:10.1093/protein/9.11.941 · Cited by 80 · cited 1×
“The best performances described so far were obtained with a statistical and a joint method, respectively (Thomas et al., 1996; Olmea and Valencia, 1997).”
MethodProtein fold recognition and dynamics in the space of contact maps
Mirny, L. A., & Domany, E. (1996) · Proteins Structure Function and Bioinformatics · doi:10.1002/(sici)1097-0134(199612)26:4<391::aid-prot3>3.0.co;2-f · Cited by 78 · cited 1×
“This threshold value is chosen in order to guarantee that there is neither a third residue nor a water molecule between two amino acids in contact and it is equal to that previously used in other studies (Hinds and Levitt, 1992; Mirny and Domany, 1996).”
ResultPredicting secondary structures of membrane proteins with neural networks
Fariselli, P., Compiani, M., & Casadio, R. (1993) · European Biophysics Journal · doi:10.1007/bf00205811 · Cited by 34
Self-citationAn entropy criterion to detect minimally frustrated intermediates in native proteins
Compiani, M., Fariselli, P., Martelli, P. L., & Casadio, R. (1998) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.95.16.9290 · Cited by 22
Self-citationRelationships between protein sequence and structure patterns based on residue contacts
Selbig, J., & Argos, P. (1998) · Proteins Structure Function and Bioinformatics · doi:10.1002/(sici)1097-0134(19980501)31:2<172::aid-prot7>3.0.co;2-o · Cited by 22 · cited 1×
“Recently residue contact classification has been correlated to structural patterns (Selbig and Argos, 1998).”
Background
Cited by
Small-World Communication of Residues and Significance for Protein Dynamics
Atilgan, A. R., Akan, P., & Baysal, C. (2004) · Biophysical Journal · doi:10.1016/s0006-3495(04)74086-2 · Cited by 327
Improved residue contact prediction using support vector machines and a large feature set
Cheng, J., & Baldi, P. (2007) · BMC Bioinformatics · doi:10.1186/1471-2105-8-113 · Cited by 240
“These methods can be classified roughly into two non-exclusive categories: (1) statistical correlated mutations approaches [1622]; and (2) machine learning approaches [23-34].”
Olmea, O., Rost, B., & Valencia, A. (1999) · Journal of Molecular Biology · doi:10.1006/jmbi.1999.3208 · Cited by 168
“…be worth including correlation and conservation in other contact prediction approaches, such as statistical approaches (Galaktionov & Marshall, 1994; Galaktionov & Rodionov, 1981; Hubbard & Park, 1995; Thomas et al., 1996) or neural network training (Fariselli & Casadio, 1999; Lund et al., 1997).”
BackgroundDeep learning in biomedical data science
Baldi, P. (2018) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-080917-013343 · Cited by 119
rawMSA: End-to-end Deep Learning using raw Multiple Sequence Alignments
Mirabello, C., & Wallner, B. (2019) · PLOS ONE · doi:10.1371/journal.pone.0220182 · Cited by 105
Metadata
- Authors
- Fariselli, P., & Casadio, R.
- Venue
- Protein Engineering, Design and Selection
- Publisher
- Oxford University Press (OUP)
- Published
- 1999-01
- Volume
- 12
- Issue
- 1
- Pages
- 15-21
- ISSN
- 0269-2139 (ISSN-L)
- 1741-0134
- 1741-0126
- OpenAlex
- W2144152753
- Cited by
- 165
- References
- 26
- FWCI
- 2.50
- Type
- journal article
- Language
- en
- Open access
- bronze
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.