Detail publikace

SoluProt: prediction of soluble protein expression in Escherichia coli

HON, J. MARUŠIAK, M. MARTÍNEK, T. BEDNÁŘ, D. DAMBORSKÝ, J. KUNKA, A. ZENDULKA, J.

Originální název

SoluProt: prediction of soluble protein expression in Escherichia coli

Anglický název

SoluProt: prediction of soluble protein expression in Escherichia coli

Jazyk

en

Originální abstrakt

Motivation: Poor protein solubility hinders the production of many therapeutic and industrially useful proteins. Experimental efforts to increase solubility are plagued by low success rates and often reduce biological activity. Computational prediction of protein expressibility and solubility in Escherichia coli using only sequence information could reduce the cost of experimental studies by enabling prioritisation of highly soluble proteins. Results: A new tool for sequence-based prediction of soluble protein expression in Escherichia coli, SoluProt, was created using the gradient boosting machine technique with the TargetTrack database as a training set. When evaluated against a balanced independent test set derived from the NESG database, SoluProts accuracy of 58.4% and AUC of 0.60 exceeded those of a suite of alternative solubility prediction tools. There is also evidence that it could significantly increase the success rate of experimental protein studies. SoluProt is freely available as a standalone program and a user-friendly webserver at https://loschmidt.chemi.muni.cz/soluprot/.

Anglický abstrakt

Motivation: Poor protein solubility hinders the production of many therapeutic and industrially useful proteins. Experimental efforts to increase solubility are plagued by low success rates and often reduce biological activity. Computational prediction of protein expressibility and solubility in Escherichia coli using only sequence information could reduce the cost of experimental studies by enabling prioritisation of highly soluble proteins. Results: A new tool for sequence-based prediction of soluble protein expression in Escherichia coli, SoluProt, was created using the gradient boosting machine technique with the TargetTrack database as a training set. When evaluated against a balanced independent test set derived from the NESG database, SoluProts accuracy of 58.4% and AUC of 0.60 exceeded those of a suite of alternative solubility prediction tools. There is also evidence that it could significantly increase the success rate of experimental protein studies. SoluProt is freely available as a standalone program and a user-friendly webserver at https://loschmidt.chemi.muni.cz/soluprot/.

Dokumenty

BibTex


@article{BUT168540,
  author="Jiří {Hon} and Martin {Marušiak} and Tomáš {Martínek} and David {Bednář} and Jiří {Damborský} and Jaroslav {Zendulka}",
  title="SoluProt: prediction of soluble protein expression in Escherichia coli",
  annote="Motivation: Poor protein solubility hinders the production of many therapeutic
and industrially useful proteins. Experimental efforts to increase solubility are
plagued by low success rates and often reduce biological activity. Computational
prediction of protein expressibility and solubility in Escherichia coli using
only sequence information could reduce the cost of experimental studies by
enabling prioritisation of highly soluble proteins.
Results: A new tool for sequence-based prediction of soluble protein expression
in Escherichia coli, SoluProt, was created using the gradient boosting machine
technique with the TargetTrack database as a training set. When evaluated against
a balanced independent test set derived from the NESG database, SoluProts
accuracy of 58.4% and AUC of 0.60 exceeded those of a suite of alternative
solubility prediction tools. There is also evidence that it could significantly
increase the success rate of experimental protein studies. SoluProt is freely
available as a standalone program and a user-friendly webserver at
https://loschmidt.chemi.muni.cz/soluprot/.",
  address="NEUVEDEN",
  chapter="168540",
  doi="10.1093/bioinformatics/btaa1102",
  edition="NEUVEDEN",
  howpublished="print",
  institution="NEUVEDEN",
  volume="NEUVEDEN",
  year="2020",
  month="december",
  pages="0--0",
  publisher="NEUVEDEN",
  type="journal article - other"
}