Sayed is an AI in healthcare enthusiast, passionate about saving and improving people’s lives with AI. He graduated from University of Malaya, Malaysia with a bachelor’s degree in computer science, where he specialized in AI. As his final year project, he developed a deep learning model for autism spectrum disorder (ASD) screening in children. He loves teaching and has taught various courses on machine learning and programming at DeepNets.
At Mohamed Bin Zayed University of Artificial Intelligence, Sayed was co-supervised by Dr. Karthik Nandakumar and Dr. Mohammad Yaqub, and worked on developing self-supervised learning mdels on multi-omics data. He has two published papers - Pacific Symposium on Biocomputing (PSB) 2023 and the International Conference on Bioinformatics and Computational Biology (ICBCB) 2022.
In one of his works named Self-omics, he developed a novel and efficient pre-training paradigm that consists of various SSL components, including but not limited to contrastive alignment, data recovery from corrupted samples, and using one type of omics data to recover other omic types. This pre-training paradigm improved performance on downstream tasks with limited labelled data. He showed that the approach outperforms the state-of-the-art method in cancer type classification on the TCGA pan-cancer dataset in semi-supervised setting. The architecture of the proposed method is shown below and the code is available at https://github.com/hashimsayed0/self-omics.
