Feedback

Deep Transfer Learning Enables Robust Prediction of Antimicrobial Resistance for Novel Antibiotics

ORCID
0000-0002-0076-0857
Affiliation
Department of Data Science in Biomedicine, Faculty of Mathematics and Computer Science, Philipps-University of Marburg, 35032 Marburg, Germany
Ren, Yunxiao;
Affiliation
Institute of Medical Microbiology, Justus Liebig University Giessen, 35392 Giessen, Germany
Chakraborty, Trinad;
ORCID
0000-0002-0932-8542
Affiliation
Institute of Medical Microbiology, Justus Liebig University Giessen, 35392 Giessen, Germany
Doijad, Swapnil;
Affiliation
German Center for Infection Research, Partner Site Giessen-Marburg-Langen, 35392 Giessen, Germany
Falgenhauer, Linda;
Affiliation
Institute of Medical Microbiology, Justus Liebig University Giessen, 35392 Giessen, Germany
Falgenhauer, Jane;
Affiliation
German Center for Infection Research, Partner Site Giessen-Marburg-Langen, 35392 Giessen, Germany
Goesmann, Alexander;
Affiliation
German Center for Infection Research, Partner Site Giessen-Marburg-Langen, 35392 Giessen, Germany
Schwengers, Oliver;
ORCID
0000-0002-3108-8311
Affiliation
Department of Data Science in Biomedicine, Faculty of Mathematics and Computer Science, Philipps-University of Marburg, 35032 Marburg, Germany
Heider, Dominik

Antimicrobial resistance (AMR) has become one of the serious global health problems, threatening the effective treatment of a growing number of infections. Machine learning and deep learning show great potential in rapid and accurate AMR predictions. However, a large number of samples for the training of these models is essential. In particular, for novel antibiotics, limited training samples and data imbalance hinder the models’ generalization performance and overall accuracy. We propose a deep transfer learning model that can improve model performance for AMR prediction on small, imbalanced datasets. As our approach relies on transfer learning and secondary mutations, it is also applicable to novel antibiotics and emerging resistances in the future and enables quick diagnostics and personalized treatments.

Cite

Citation style:
Could not load citation form.

Access Statistic

Total:
Downloads:
Abtractviews:
Last 12 Month:
Downloads:
Abtractviews:

Rights

License Holder: © 2022 by the authors.

Use and reproduction: