Multi-omics integration using a fully differentiable set autoencoder for consensus molecular subtyping of colorectal cancer
ColoRectal cancer (CRC) was the third most frequently diagnosed cancer in Switzerland in 2018. Despite decades of research, 5-year survival for CRC patients is only 60%, and there exist few molecular biomarkers and treatment options. The Consensus Molecular Subtypes (CMS) published in 2015 provided the first comprehensive molecular classification of CRC with clinical implications (prognosis and treatment response prediction).
The aim of this project is to extend a Fully Differentiable Set Autoencoder, published in KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, to learn a combined representation of the various omics data (genomics, proteomics, and transcriptomics) available for CRC. The quality and robustness of this representation will be tested through the downstream task of predicting the CMS class of the patient.
The objectives are two-fold:
- Set Matching module:
a. Formulate an objective function that ensures bijective mapping between 2 sets, i.e, unique label assignment in a multi-class classification problem.
- Set Autoencoder:
a. Integrate >2 omics associated with CRC to learn a robust representation.
b. Use this representation in a downstream task, namely, predicting the CMS class.
A generative version of the model can be discussed. The student has the creative freedom to explore other research ideas to improve the Fully Differentiable Set Autoencoder model.
- The student must currently be enrolled in a Master’s program in computer science, bioinformatics, or similar programs that encourage technical and mathematical skills.
- Proficiency in Python and PyTorch.
- Experience with deep learning.
- Familiarity with GitHub and continuous integration pipelines.
- Proficiency in English – written and oral.
- Good interpersonal skills and must take initiative.
- Passion for research, a curious mind and creative ideas.
IBM is committed to diversity at the workplace. With us you will find an open, multicultural environment. Excellent flexible working arrangements enable all genders to strike the desired balance between their professional development and their personal lives.
How to apply
Please submit your application and CV through the link below.