Machine learning model identifies antibody targets
2022
University of Illinois at Urbana-Champaign, Urbana, USA
Using the information derived from 88 research publications and 13 patents, the researchers assembled a dataset of ∼8,000 human antibodies to the SARS-CoV-2 spike protein from >200 donors. They demonstrated that the common (public) responses to different domains of the spike protein were quite different. Furthermore, they used these sequences to train a deep-learning model to accurately distinguish between the human antibodies to SARS-CoV-2 spike protein and those to influenza hemagglutinin protein. Overall, this study provides an informative resource for antibody research and enhances our molecular understanding of public antibody responses.
A large-scale systematic survey reveals recurring molecular features of public antibody responses to SARS-CoV-2
Nicholas C. Wu
Added on: 09-08-2022
[1] https://www.cell.com/immunity/fulltext/S1074-7613(22)00142-X?_returnURL=https%3A%2F%2Flinkinghub.elsevier.com%2Fretrieve%2Fpii%2FS107476132200142X%3Fshowall%3Dtrue[2] https://www.drugtargetreview.com/news/102832/a-machine-learning-model-that-could-identify-antibody-targets/?utm_source=Email+marketing&utm_medium=email&utm_campaign=DTR+-+Industry+Insight+-+Thermo+Fisher+-+Lab+Automation+-+03.06.22&utm_term=New+machine+learning+technique+to+develop+new+drugs&utm_content=https%3a%2f%2femails.drugtargetreview.com%2frussellpublishinglz%2f&gator_td=7fjQZ2dXMWRo0TTxTaLpc66pHkJKGkKovqljZfpFAQtYmgCox7oSCPkwyS0dW%2fn%2fKqMgmIelmMI9oCi6z2C2BO9eSFqg0i8omoxtQQX%2bwNDC4uIwGaBMLvT9CYYIm1MRfEm2ten9tDa%2fU6sq9joEKKOZdVqewEGCiAbt%2fxUmmqoEndZXCK7lY7bS%2f6qzaJUeAwV2LyXy3%2fJOIiojxP%2bRFiK%2f0wRrZIkFysWMnBBriDik%2f7e2HZjFioejerenphzs0WlymulB0FHkBXBOFRlPKQ%3d%3d
