Drug resistance classification for Mycobacterium tuberculosis using multi-output model with stacked auto-encoders
This work explores deep-learning model to classify drug resistance for Mycobacterium tuberculosis. We applied an end-to-end model on DNA mutations of the pathogen and lab-based phenotyping results. The model first stacks 3 auto-encoders, and then applies multiple classifiers to classify resistance f...
| Main Authors: | , |
|---|---|
| Format: | Conference item |
| Published: |
Institute of Electrical and Electronics Engineers
2017
|
| _version_ | 1826260179430146048 |
|---|---|
| author | Yang, Y Clifton, D |
| author_facet | Yang, Y Clifton, D |
| author_sort | Yang, Y |
| collection | OXFORD |
| description | This work explores deep-learning model to classify drug resistance for Mycobacterium tuberculosis. We applied an end-to-end model on DNA mutations of the pathogen and lab-based phenotyping results. The model first stacks 3 auto-encoders, and then applies multiple classifiers to classify resistance for four first-line drugs. The results is promising and show the potential of the model for drug resistance analysis. |
| first_indexed | 2024-03-06T19:01:32Z |
| format | Conference item |
| id | oxford-uuid:13b2e972-d194-4a31-9831-76696291bf27 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T19:01:32Z |
| publishDate | 2017 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | oxford-uuid:13b2e972-d194-4a31-9831-76696291bf272022-03-26T10:15:21ZDrug resistance classification for Mycobacterium tuberculosis using multi-output model with stacked auto-encodersConference itemhttp://purl.org/coar/resource_type/c_5794uuid:13b2e972-d194-4a31-9831-76696291bf27Symplectic Elements at OxfordInstitute of Electrical and Electronics Engineers2017Yang, YClifton, DThis work explores deep-learning model to classify drug resistance for Mycobacterium tuberculosis. We applied an end-to-end model on DNA mutations of the pathogen and lab-based phenotyping results. The model first stacks 3 auto-encoders, and then applies multiple classifiers to classify resistance for four first-line drugs. The results is promising and show the potential of the model for drug resistance analysis. |
| spellingShingle | Yang, Y Clifton, D Drug resistance classification for Mycobacterium tuberculosis using multi-output model with stacked auto-encoders |
| title | Drug resistance classification for Mycobacterium tuberculosis using multi-output model with stacked auto-encoders |
| title_full | Drug resistance classification for Mycobacterium tuberculosis using multi-output model with stacked auto-encoders |
| title_fullStr | Drug resistance classification for Mycobacterium tuberculosis using multi-output model with stacked auto-encoders |
| title_full_unstemmed | Drug resistance classification for Mycobacterium tuberculosis using multi-output model with stacked auto-encoders |
| title_short | Drug resistance classification for Mycobacterium tuberculosis using multi-output model with stacked auto-encoders |
| title_sort | drug resistance classification for mycobacterium tuberculosis using multi output model with stacked auto encoders |
| work_keys_str_mv | AT yangy drugresistanceclassificationformycobacteriumtuberculosisusingmultioutputmodelwithstackedautoencoders AT cliftond drugresistanceclassificationformycobacteriumtuberculosisusingmultioutputmodelwithstackedautoencoders |