Predicting CD4 T-cell epitopes based on antigen cleavage, MHCII presentation, and TCR recognition. Schneidman-Duhovny, D., Khuri, N., Dong, G. Q., Winter, M. B, Shifrut, E., Friedman, N., Craik, C. S, Pratt, K. P, Paz, P., Aswad, F., & Sali, A. PLoS One, 13(11):e0206654, Public Library of Science (PLoS), November, 2018. abstract bibtex Accurate predictions of T-cell epitopes would be useful for designing vaccines, immunotherapies for cancer and autoimmune diseases, and improved protein therapies. The humoral immune response involves uptake of antigens by antigen presenting cells (APCs), APC processing and presentation of peptides on MHC class II (pMHCII), and T-cell receptor (TCR) recognition of pMHCII complexes. Most in silico methods predict only peptide-MHCII binding, resulting in significant over-prediction of CD4 T-cell epitopes. We present a method, ITCell, for prediction of T-cell epitopes within an input protein antigen sequence for given MHCII and TCR sequences. The method integrates information about three stages of the immune response pathway: antigen cleavage, MHCII presentation, and TCR recognition. First, antigen cleavage sites are predicted based on the cleavage profiles of cathepsins S, B, and H. Second, for each 12-mer peptide in the antigen sequence we predict whether it will bind to a given MHCII, based on the scores of modeled peptide-MHCII complexes. Third, we predict whether or not any of the top scoring peptide-MHCII complexes can bind to a given TCR, based on the scores of modeled ternary peptide-MHCII-TCR complexes and the distribution of predicted cleavage sites. Our benchmarks consist of epitope predictions generated by this algorithm, checked against 20 peptide-MHCII-TCR crystal structures, as well as epitope predictions for four peptide-MHCII-TCR complexes with known epitopes and TCR sequences but without crystal structures. ITCell successfully identified the correct epitopes as one of the 20 top scoring peptides for 22 of 24 benchmark cases. To validate the method using a clinically relevant application, we utilized five factor VIII-specific TCR sequences from hemophilia A subjects who developed an immune response to factor VIII replacement therapy. The known HLA-DR1-restricted factor VIII epitope was among the six top-scoring factor VIII peptides predicted by ITCall to bind HLA-DR1 and all five TCRs. Our integrative approach is more accurate than current single-stage epitope prediction algorithms applied to the same benchmarks. It is freely available as a web server (http://salilab.org/itcell).
@ARTICLE{Schneidman-Duhovny2018-fc,
title = "Predicting {CD4} T-cell epitopes based on antigen cleavage,
{MHCII} presentation, and {TCR} recognition",
author = "Schneidman-Duhovny, Dina and Khuri, Natalia and Dong, Guang
Qiang and Winter, Michael B and Shifrut, Eric and Friedman, Nir
and Craik, Charles S and Pratt, Kathleen P and Paz, Pedro and
Aswad, Fred and Sali, Andrej",
abstract = "Accurate predictions of T-cell epitopes would be useful for
designing vaccines, immunotherapies for cancer and autoimmune
diseases, and improved protein therapies. The humoral immune
response involves uptake of antigens by antigen presenting cells
(APCs), APC processing and presentation of peptides on MHC class
II (pMHCII), and T-cell receptor (TCR) recognition of pMHCII
complexes. Most in silico methods predict only peptide-MHCII
binding, resulting in significant over-prediction of CD4 T-cell
epitopes. We present a method, ITCell, for prediction of T-cell
epitopes within an input protein antigen sequence for given
MHCII and TCR sequences. The method integrates information about
three stages of the immune response pathway: antigen cleavage,
MHCII presentation, and TCR recognition. First, antigen cleavage
sites are predicted based on the cleavage profiles of cathepsins
S, B, and H. Second, for each 12-mer peptide in the antigen
sequence we predict whether it will bind to a given MHCII, based
on the scores of modeled peptide-MHCII complexes. Third, we
predict whether or not any of the top scoring peptide-MHCII
complexes can bind to a given TCR, based on the scores of
modeled ternary peptide-MHCII-TCR complexes and the distribution
of predicted cleavage sites. Our benchmarks consist of epitope
predictions generated by this algorithm, checked against 20
peptide-MHCII-TCR crystal structures, as well as epitope
predictions for four peptide-MHCII-TCR complexes with known
epitopes and TCR sequences but without crystal structures.
ITCell successfully identified the correct epitopes as one of
the 20 top scoring peptides for 22 of 24 benchmark cases. To
validate the method using a clinically relevant application, we
utilized five factor VIII-specific TCR sequences from hemophilia
A subjects who developed an immune response to factor VIII
replacement therapy. The known HLA-DR1-restricted factor VIII
epitope was among the six top-scoring factor VIII peptides
predicted by ITCall to bind HLA-DR1 and all five TCRs. Our
integrative approach is more accurate than current single-stage
epitope prediction algorithms applied to the same benchmarks. It
is freely available as a web server (http://salilab.org/itcell).",
journal = "PLoS One",
publisher = "Public Library of Science (PLoS)",
volume = 13,
number = 11,
pages = "e0206654",
month = nov,
year = 2018,
copyright = "http://creativecommons.org/licenses/by/4.0/",
language = "en"
}
Downloads: 0
{"_id":"hXvGcthH4W72BAk9K","bibbaseid":"schneidmanduhovny-khuri-dong-winter-shifrut-friedman-craik-pratt-etal-predictingcd4tcellepitopesbasedonantigencleavagemhciipresentationandtcrrecognition-2018","authorIDs":["5cc6a620aa96b4da010000d7","RxpzMWmPrvwrFLPRs","XTqeFBq8hj6RekJoE","XybFBYqD7cfyv4Gag","YAgo5nTspXhkCSz6J"],"author_short":["Schneidman-Duhovny, D.","Khuri, N.","Dong, G. Q.","Winter, M. B","Shifrut, E.","Friedman, N.","Craik, C. S","Pratt, K. P","Paz, P.","Aswad, F.","Sali, A."],"bibdata":{"bibtype":"article","type":"article","title":"Predicting CD4 T-cell epitopes based on antigen cleavage, MHCII presentation, and TCR recognition","author":[{"propositions":[],"lastnames":["Schneidman-Duhovny"],"firstnames":["Dina"],"suffixes":[]},{"propositions":[],"lastnames":["Khuri"],"firstnames":["Natalia"],"suffixes":[]},{"propositions":[],"lastnames":["Dong"],"firstnames":["Guang","Qiang"],"suffixes":[]},{"propositions":[],"lastnames":["Winter"],"firstnames":["Michael","B"],"suffixes":[]},{"propositions":[],"lastnames":["Shifrut"],"firstnames":["Eric"],"suffixes":[]},{"propositions":[],"lastnames":["Friedman"],"firstnames":["Nir"],"suffixes":[]},{"propositions":[],"lastnames":["Craik"],"firstnames":["Charles","S"],"suffixes":[]},{"propositions":[],"lastnames":["Pratt"],"firstnames":["Kathleen","P"],"suffixes":[]},{"propositions":[],"lastnames":["Paz"],"firstnames":["Pedro"],"suffixes":[]},{"propositions":[],"lastnames":["Aswad"],"firstnames":["Fred"],"suffixes":[]},{"propositions":[],"lastnames":["Sali"],"firstnames":["Andrej"],"suffixes":[]}],"abstract":"Accurate predictions of T-cell epitopes would be useful for designing vaccines, immunotherapies for cancer and autoimmune diseases, and improved protein therapies. The humoral immune response involves uptake of antigens by antigen presenting cells (APCs), APC processing and presentation of peptides on MHC class II (pMHCII), and T-cell receptor (TCR) recognition of pMHCII complexes. Most in silico methods predict only peptide-MHCII binding, resulting in significant over-prediction of CD4 T-cell epitopes. We present a method, ITCell, for prediction of T-cell epitopes within an input protein antigen sequence for given MHCII and TCR sequences. The method integrates information about three stages of the immune response pathway: antigen cleavage, MHCII presentation, and TCR recognition. First, antigen cleavage sites are predicted based on the cleavage profiles of cathepsins S, B, and H. Second, for each 12-mer peptide in the antigen sequence we predict whether it will bind to a given MHCII, based on the scores of modeled peptide-MHCII complexes. Third, we predict whether or not any of the top scoring peptide-MHCII complexes can bind to a given TCR, based on the scores of modeled ternary peptide-MHCII-TCR complexes and the distribution of predicted cleavage sites. Our benchmarks consist of epitope predictions generated by this algorithm, checked against 20 peptide-MHCII-TCR crystal structures, as well as epitope predictions for four peptide-MHCII-TCR complexes with known epitopes and TCR sequences but without crystal structures. ITCell successfully identified the correct epitopes as one of the 20 top scoring peptides for 22 of 24 benchmark cases. To validate the method using a clinically relevant application, we utilized five factor VIII-specific TCR sequences from hemophilia A subjects who developed an immune response to factor VIII replacement therapy. The known HLA-DR1-restricted factor VIII epitope was among the six top-scoring factor VIII peptides predicted by ITCall to bind HLA-DR1 and all five TCRs. Our integrative approach is more accurate than current single-stage epitope prediction algorithms applied to the same benchmarks. It is freely available as a web server (http://salilab.org/itcell).","journal":"PLoS One","publisher":"Public Library of Science (PLoS)","volume":"13","number":"11","pages":"e0206654","month":"November","year":"2018","copyright":"http://creativecommons.org/licenses/by/4.0/","language":"en","bibtex":"@ARTICLE{Schneidman-Duhovny2018-fc,\n title = \"Predicting {CD4} T-cell epitopes based on antigen cleavage,\n {MHCII} presentation, and {TCR} recognition\",\n author = \"Schneidman-Duhovny, Dina and Khuri, Natalia and Dong, Guang\n Qiang and Winter, Michael B and Shifrut, Eric and Friedman, Nir\n and Craik, Charles S and Pratt, Kathleen P and Paz, Pedro and\n Aswad, Fred and Sali, Andrej\",\n abstract = \"Accurate predictions of T-cell epitopes would be useful for\n designing vaccines, immunotherapies for cancer and autoimmune\n diseases, and improved protein therapies. The humoral immune\n response involves uptake of antigens by antigen presenting cells\n (APCs), APC processing and presentation of peptides on MHC class\n II (pMHCII), and T-cell receptor (TCR) recognition of pMHCII\n complexes. Most in silico methods predict only peptide-MHCII\n binding, resulting in significant over-prediction of CD4 T-cell\n epitopes. We present a method, ITCell, for prediction of T-cell\n epitopes within an input protein antigen sequence for given\n MHCII and TCR sequences. The method integrates information about\n three stages of the immune response pathway: antigen cleavage,\n MHCII presentation, and TCR recognition. First, antigen cleavage\n sites are predicted based on the cleavage profiles of cathepsins\n S, B, and H. Second, for each 12-mer peptide in the antigen\n sequence we predict whether it will bind to a given MHCII, based\n on the scores of modeled peptide-MHCII complexes. Third, we\n predict whether or not any of the top scoring peptide-MHCII\n complexes can bind to a given TCR, based on the scores of\n modeled ternary peptide-MHCII-TCR complexes and the distribution\n of predicted cleavage sites. Our benchmarks consist of epitope\n predictions generated by this algorithm, checked against 20\n peptide-MHCII-TCR crystal structures, as well as epitope\n predictions for four peptide-MHCII-TCR complexes with known\n epitopes and TCR sequences but without crystal structures.\n ITCell successfully identified the correct epitopes as one of\n the 20 top scoring peptides for 22 of 24 benchmark cases. To\n validate the method using a clinically relevant application, we\n utilized five factor VIII-specific TCR sequences from hemophilia\n A subjects who developed an immune response to factor VIII\n replacement therapy. The known HLA-DR1-restricted factor VIII\n epitope was among the six top-scoring factor VIII peptides\n predicted by ITCall to bind HLA-DR1 and all five TCRs. Our\n integrative approach is more accurate than current single-stage\n epitope prediction algorithms applied to the same benchmarks. It\n is freely available as a web server (http://salilab.org/itcell).\",\n journal = \"PLoS One\",\n publisher = \"Public Library of Science (PLoS)\",\n volume = 13,\n number = 11,\n pages = \"e0206654\",\n month = nov,\n year = 2018,\n copyright = \"http://creativecommons.org/licenses/by/4.0/\",\n language = \"en\"\n}\n\n","author_short":["Schneidman-Duhovny, D.","Khuri, N.","Dong, G. Q.","Winter, M. B","Shifrut, E.","Friedman, N.","Craik, C. S","Pratt, K. P","Paz, P.","Aswad, F.","Sali, A."],"key":"Schneidman-Duhovny2018-fc","id":"Schneidman-Duhovny2018-fc","bibbaseid":"schneidmanduhovny-khuri-dong-winter-shifrut-friedman-craik-pratt-etal-predictingcd4tcellepitopesbasedonantigencleavagemhciipresentationandtcrrecognition-2018","role":"author","urls":{},"metadata":{"authorlinks":{"shifrut, e":"https://1964311524-atari-embeds.googleusercontent.com/embeds/16cb204cf3a9d4d223a0a3fd8b0eec5d/inner-frame-minified.html"}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/network/files/xos2PRkrJXRcypZwA","creationDate":"2019-04-29T07:28:37.058Z","downloads":0,"keywords":[],"search_terms":["predicting","cd4","cell","epitopes","based","antigen","cleavage","mhcii","presentation","tcr","recognition","schneidman-duhovny","khuri","dong","winter","shifrut","friedman","craik","pratt","paz","aswad","sali"],"title":"Predicting CD4 T-cell epitopes based on antigen cleavage, MHCII presentation, and TCR recognition","year":2018,"dataSources":["HKMAdWbuCdpcjTfsQ","AHkfRF5sD5CBc7YbG","WGzqbPDoqXMkKdgJ7","wmRjNkA5ZsjNtvjhZ"]}