Nowadays, sharing and use of human biomedical data is heavily restricted and regulated by multiple laws. Such data-sharing restrictions allow keeping privacy of the patients but at the same time it impedes the pace of biomedical research, slows down the development of treatments of various diseases and often costs human lives. COVID-19 pandemic is unfortunately a good illustration of how inaccessibility of clinical training data leads to casualties that can be otherwise avoided. Even the World Health Organization which is supposed to become a data hub for COVID-19 data, refuses to share most of the clinical data even in anonymous form due to the complexity of regulations. Such problems are also common for bioinformatics as training classifiers and regressors on patient *-omics data often involves dealing with medical records of the patients.
To address these problems, we propose to develop a package, HRC, which will be built on top of Federated Learning (FL) framework, to bridge the gap between healthcare provides and researchers.
This package will allow biomedical researchers to quickly modify and deploy FL for typical bioinformatic use-cases.