The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Machine learning detection of tumor genes from epigenetic data

A deep learning method is proposed for detecting tumor genes based on their unique combined epigenetic signatures. Large volumes of epigenetic data will be processed by the Tomoiaga group at Manhattan College and Columbia. This data will be utilized to train and validate deep network models capable of accurately detecting epigenetic patterns, which can then be leveraged for the classification of genes as tumor, tumor suppressor, or non-tumor. A key advantage of this approach is its applicability across various tissue and tumor types, allowing for the identification of new tumor genes, even in rare cancers.

Optimizing cell reprogramming to pluripotency. Image of method overview.

 

Selected publications

Pielies Avellí M., Cancer Driver Gene Detection using Deep Convolutional Neural Networks on H3K4me3 Enrichment Profiles, LUP Student Papers, 2022

Project participants

Associate professor Alin Tomoiaga, MSc, PhD. Photo.
Associate professor Alin Tomoiaga, MSc, PhD

Marc Pielies Avelli, MSc.

Ming-Heng Hsiung, MSc-student. Photo.
Ming-Heng Hsiung, MSc-student.
Senior Lecturer Victor Olariu, MSc, PhD. Photo
Senior Lecturer Victor Olariu, MSc, PhD