Survival and drug response prediction for BRCA patients
Vidhi Malik »
Yogesh Kalakoti »
Durai Sundar »
DAILAB, Indian Institute of Technology, Delhi
This workflow evaluates the utility of an integrative multi-omics framework employing the recent advances in statistics and machine learning to estimate clinical outcomes in Breast cancer (BRCA) patients. A neural net workflow capable of quantifying survival and drug response along with identifying critical biomarkers was stringenltly optimized for roubusteness. The presented results demonstrates the effectiveness of our models in terms of sensitivity, specificity, accuracy among others. Moreover, conventional linear prediction models for data integration are limited due to steep dimensionality and heterogeneity associated with omics datasets. To mitigate theis drawback, we established a viable multi omics integration stratergy that can also be used in numerous scenarios other than just survival and drug response prediction.
Key highlights:
- Integration framework for multi omics data
- Workflow for predicting survival in BRCA patients
- Workflow for predicting drug responses for 100 drugs 😄
Our workflows can provide immense utility in improving personalized theraputic options and assisting clinicians in making rational decisions.
This section should list any major frameworks that you built your project using. Leave any add-ons/plugins for the acknowledgements section. Here are a few examples.
Use this space to show useful examples of how a project can be used. Additional screenshots, code examples and demos work well in this space. You may also link to more resources.
For more examples, please refer to the Documentation
See the open issues for a list of proposed features (and known issues). -->
Distributed under the MIT License. See LICENSE for more information.