Predicting Proteolysis in Complex Proteomes Using Deep LearningCitation formats

  • External authors:
  • Christopher I. Platt
  • Callum Stewart-McGuinness
  • Sarah A. Hibbert
  • Jerico Revote
  • Fuyi Li
  • Jiangning Song
  • Mike Bell

Standard

Predicting Proteolysis in Complex Proteomes Using Deep Learning. / Ozols, Matiss; Eckersley, Alexander; Platt, Christopher I.; Stewart-McGuinness, Callum; Hibbert, Sarah A.; Revote, Jerico; Li, Fuyi; Griffiths, Christopher E. M.; Watson, Rachel E. B.; Song, Jiangning; Bell, Mike; Sherratt, Michael J.

In: International Journal of Molecular Sciences, Vol. 22, No. 6, 3071, 17.03.2021, p. 1-20.

Research output: Contribution to journalArticlepeer-review

Harvard

Ozols, M, Eckersley, A, Platt, CI, Stewart-McGuinness, C, Hibbert, SA, Revote, J, Li, F, Griffiths, CEM, Watson, REB, Song, J, Bell, M & Sherratt, MJ 2021, 'Predicting Proteolysis in Complex Proteomes Using Deep Learning', International Journal of Molecular Sciences, vol. 22, no. 6, 3071, pp. 1-20. https://doi.org/10.3390/ijms22063071

APA

Ozols, M., Eckersley, A., Platt, C. I., Stewart-McGuinness, C., Hibbert, S. A., Revote, J., Li, F., Griffiths, C. E. M., Watson, R. E. B., Song, J., Bell, M., & Sherratt, M. J. (2021). Predicting Proteolysis in Complex Proteomes Using Deep Learning. International Journal of Molecular Sciences, 22(6), 1-20. [3071]. https://doi.org/10.3390/ijms22063071

Vancouver

Ozols M, Eckersley A, Platt CI, Stewart-McGuinness C, Hibbert SA, Revote J et al. Predicting Proteolysis in Complex Proteomes Using Deep Learning. International Journal of Molecular Sciences. 2021 Mar 17;22(6):1-20. 3071. https://doi.org/10.3390/ijms22063071

Author

Ozols, Matiss ; Eckersley, Alexander ; Platt, Christopher I. ; Stewart-McGuinness, Callum ; Hibbert, Sarah A. ; Revote, Jerico ; Li, Fuyi ; Griffiths, Christopher E. M. ; Watson, Rachel E. B. ; Song, Jiangning ; Bell, Mike ; Sherratt, Michael J. / Predicting Proteolysis in Complex Proteomes Using Deep Learning. In: International Journal of Molecular Sciences. 2021 ; Vol. 22, No. 6. pp. 1-20.

Bibtex

@article{52a84decf50d410caf81d050cfeec0c5,
title = "Predicting Proteolysis in Complex Proteomes Using Deep Learning",
abstract = "Both protease-and reactive oxygen species (ROS)-mediated proteolysis are thought to be key effectors of tissue remodeling. We have previously shown that comparison of amino acid composition can predict the differential susceptibilities of proteins to photo-oxidation. However, predicting protein susceptibility to endogenous proteases remains challenging. Here, we aim to develop bioin-formatics tools to (i) predict cleavage site locations (and hence putative protein susceptibilities) and (ii) compare the predicted vulnerabilities of skin proteins to protease-and ROS-mediated proteolysis. The first goal of this study was to experimentally evaluate the ability of existing protease cleavage site prediction models (PROSPER and DeepCleave) to identify experimentally determined MMP9 cleavage sites in two purified proteins and in a complex human dermal fibroblast-derived extracellular matrix (ECM) proteome. We subsequently developed deep bidirectional recurrent neural network (BRNN) models to predict cleavage sites for 14 tissue proteases. The predictions of the new models were tested against experimental datasets and combined with amino acid composition analysis (to predict ultraviolet radiation (UVR)/ROS susceptibility) in a new web app: the Manchester proteome susceptibility calculator (MPSC). The BRNN models performed better in predicting cleavage sites in native dermal ECM proteins than existing models (DeepCleave and PROSPER), and application of MPSC to the skin proteome suggests that: compared with the elastic fiber network, fibrillar collagens may be susceptible primarily to protease-mediated proteolysis. We also identify additional putative targets of oxidative damage (dermatopontin, fibulins and defensins) and protease action (laminins and nidogen). MPSC has the potential to identify potential targets of proteolysis in disparate tissues and disease states.",
keywords = "Aging, Biomark-ers, Deep-learning, Degradomics, Extracellular matrix, Machine learning, Protease, Skin",
author = "Matiss Ozols and Alexander Eckersley and Platt, {Christopher I.} and Callum Stewart-McGuinness and Hibbert, {Sarah A.} and Jerico Revote and Fuyi Li and Griffiths, {Christopher E. M.} and Watson, {Rachel E. B.} and Jiangning Song and Mike Bell and Sherratt, {Michael J.}",
note = "Funding Information: Funding: This research was funded by Walgreens Boots Alliance, Nottingham, UK. C.E.M.G. and R.E.B.W. are funded in part by the NIHR Manchester Biomedical Research Centre. Publisher Copyright: {\textcopyright} 2021 by the authors. Licensee MDPI, Basel, Switzerland. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.",
year = "2021",
month = mar,
day = "17",
doi = "10.3390/ijms22063071",
language = "English",
volume = "22",
pages = "1--20",
journal = "International Journal of Molecular Sciences",
issn = "1661-6596",
publisher = "MDPI",
number = "6",

}

RIS

TY - JOUR

T1 - Predicting Proteolysis in Complex Proteomes Using Deep Learning

AU - Ozols, Matiss

AU - Eckersley, Alexander

AU - Platt, Christopher I.

AU - Stewart-McGuinness, Callum

AU - Hibbert, Sarah A.

AU - Revote, Jerico

AU - Li, Fuyi

AU - Griffiths, Christopher E. M.

AU - Watson, Rachel E. B.

AU - Song, Jiangning

AU - Bell, Mike

AU - Sherratt, Michael J.

N1 - Funding Information: Funding: This research was funded by Walgreens Boots Alliance, Nottingham, UK. C.E.M.G. and R.E.B.W. are funded in part by the NIHR Manchester Biomedical Research Centre. Publisher Copyright: © 2021 by the authors. Licensee MDPI, Basel, Switzerland. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.

PY - 2021/3/17

Y1 - 2021/3/17

N2 - Both protease-and reactive oxygen species (ROS)-mediated proteolysis are thought to be key effectors of tissue remodeling. We have previously shown that comparison of amino acid composition can predict the differential susceptibilities of proteins to photo-oxidation. However, predicting protein susceptibility to endogenous proteases remains challenging. Here, we aim to develop bioin-formatics tools to (i) predict cleavage site locations (and hence putative protein susceptibilities) and (ii) compare the predicted vulnerabilities of skin proteins to protease-and ROS-mediated proteolysis. The first goal of this study was to experimentally evaluate the ability of existing protease cleavage site prediction models (PROSPER and DeepCleave) to identify experimentally determined MMP9 cleavage sites in two purified proteins and in a complex human dermal fibroblast-derived extracellular matrix (ECM) proteome. We subsequently developed deep bidirectional recurrent neural network (BRNN) models to predict cleavage sites for 14 tissue proteases. The predictions of the new models were tested against experimental datasets and combined with amino acid composition analysis (to predict ultraviolet radiation (UVR)/ROS susceptibility) in a new web app: the Manchester proteome susceptibility calculator (MPSC). The BRNN models performed better in predicting cleavage sites in native dermal ECM proteins than existing models (DeepCleave and PROSPER), and application of MPSC to the skin proteome suggests that: compared with the elastic fiber network, fibrillar collagens may be susceptible primarily to protease-mediated proteolysis. We also identify additional putative targets of oxidative damage (dermatopontin, fibulins and defensins) and protease action (laminins and nidogen). MPSC has the potential to identify potential targets of proteolysis in disparate tissues and disease states.

AB - Both protease-and reactive oxygen species (ROS)-mediated proteolysis are thought to be key effectors of tissue remodeling. We have previously shown that comparison of amino acid composition can predict the differential susceptibilities of proteins to photo-oxidation. However, predicting protein susceptibility to endogenous proteases remains challenging. Here, we aim to develop bioin-formatics tools to (i) predict cleavage site locations (and hence putative protein susceptibilities) and (ii) compare the predicted vulnerabilities of skin proteins to protease-and ROS-mediated proteolysis. The first goal of this study was to experimentally evaluate the ability of existing protease cleavage site prediction models (PROSPER and DeepCleave) to identify experimentally determined MMP9 cleavage sites in two purified proteins and in a complex human dermal fibroblast-derived extracellular matrix (ECM) proteome. We subsequently developed deep bidirectional recurrent neural network (BRNN) models to predict cleavage sites for 14 tissue proteases. The predictions of the new models were tested against experimental datasets and combined with amino acid composition analysis (to predict ultraviolet radiation (UVR)/ROS susceptibility) in a new web app: the Manchester proteome susceptibility calculator (MPSC). The BRNN models performed better in predicting cleavage sites in native dermal ECM proteins than existing models (DeepCleave and PROSPER), and application of MPSC to the skin proteome suggests that: compared with the elastic fiber network, fibrillar collagens may be susceptible primarily to protease-mediated proteolysis. We also identify additional putative targets of oxidative damage (dermatopontin, fibulins and defensins) and protease action (laminins and nidogen). MPSC has the potential to identify potential targets of proteolysis in disparate tissues and disease states.

KW - Aging

KW - Biomark-ers

KW - Deep-learning

KW - Degradomics

KW - Extracellular matrix

KW - Machine learning

KW - Protease

KW - Skin

U2 - 10.3390/ijms22063071

DO - 10.3390/ijms22063071

M3 - Article

C2 - 33803033

VL - 22

SP - 1

EP - 20

JO - International Journal of Molecular Sciences

JF - International Journal of Molecular Sciences

SN - 1661-6596

IS - 6

M1 - 3071

ER -