Protein secondary structure prediction using logic-based machine learning

S. Muggleton; R. D. King; M. J E Sternberg

doi:10.1093/protein/6.5.549

Protein secondary structure prediction using logic-based machine learning

S. Muggleton, R. D. King, M. J E Sternberg

Research output: Contribution to journal › Article › peer-review

Abstract

Protein Engineering, 5, 647-657. An error was found (Leberman, 1993) in the selection of non-homologous proteins used to train the machine learning program Golem. The proteins 155C (cytochrome C550) and 2C2C (cytochrome C2 oxidized) have 43.5% sequence homology. Removal of the result for 2C2C (the most accurately predicted of the two proteins) produces a Q3 accuracy of 78% (no change) and a Matthew's correlation of 0.53 (a reduction of 0.04). Removal of 2C2C makes no difference to results for the independent test set of non-homologous proteins.Reference.Leberman, R. (1993) Protein Engng, 6, 547. © 1993 Oxford University Press.

Original language	English
Pages (from-to)	549
Number of pages	1
Journal	Protein Engineering, Design and Selection
Volume	6
Issue number	5
DOIs	https://doi.org/10.1093/protein/6.5.549
Publication status	Published - Jul 1993

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1093/protein/6.5.549

Cite this

@article{f454361450ab458e9e2b334977e0397f,

title = "Protein secondary structure prediction using logic-based machine learning",

abstract = "Protein Engineering, 5, 647-657. An error was found (Leberman, 1993) in the selection of non-homologous proteins used to train the machine learning program Golem. The proteins 155C (cytochrome C550) and 2C2C (cytochrome C2 oxidized) have 43.5% sequence homology. Removal of the result for 2C2C (the most accurately predicted of the two proteins) produces a Q3 accuracy of 78% (no change) and a Matthew's correlation of 0.53 (a reduction of 0.04). Removal of 2C2C makes no difference to results for the independent test set of non-homologous proteins.Reference.Leberman, R. (1993) Protein Engng, 6, 547. {\textcopyright} 1993 Oxford University Press.",

author = "S. Muggleton and King, {R. D.} and Sternberg, {M. J E}",

year = "1993",

month = jul,

doi = "10.1093/protein/6.5.549",

language = "English",

volume = "6",

pages = "549",

journal = "Protein Engineering, Design and Selection",

issn = "1741-0126",

publisher = "Oxford University Press",

number = "5",

}

TY - JOUR

T1 - Protein secondary structure prediction using logic-based machine learning

AU - Muggleton, S.

AU - King, R. D.

AU - Sternberg, M. J E

PY - 1993/7

Y1 - 1993/7

N2 - Protein Engineering, 5, 647-657. An error was found (Leberman, 1993) in the selection of non-homologous proteins used to train the machine learning program Golem. The proteins 155C (cytochrome C550) and 2C2C (cytochrome C2 oxidized) have 43.5% sequence homology. Removal of the result for 2C2C (the most accurately predicted of the two proteins) produces a Q3 accuracy of 78% (no change) and a Matthew's correlation of 0.53 (a reduction of 0.04). Removal of 2C2C makes no difference to results for the independent test set of non-homologous proteins.Reference.Leberman, R. (1993) Protein Engng, 6, 547. © 1993 Oxford University Press.

AB - Protein Engineering, 5, 647-657. An error was found (Leberman, 1993) in the selection of non-homologous proteins used to train the machine learning program Golem. The proteins 155C (cytochrome C550) and 2C2C (cytochrome C2 oxidized) have 43.5% sequence homology. Removal of the result for 2C2C (the most accurately predicted of the two proteins) produces a Q3 accuracy of 78% (no change) and a Matthew's correlation of 0.53 (a reduction of 0.04). Removal of 2C2C makes no difference to results for the independent test set of non-homologous proteins.Reference.Leberman, R. (1993) Protein Engng, 6, 547. © 1993 Oxford University Press.

U2 - 10.1093/protein/6.5.549

DO - 10.1093/protein/6.5.549

M3 - Article

SN - 1741-0126

VL - 6

SP - 549

JO - Protein Engineering, Design and Selection

JF - Protein Engineering, Design and Selection

IS - 5

ER -

Protein secondary structure prediction using logic-based machine learning

Abstract

UN SDGs

Access to Document

Fingerprint

Cite this