Home | Resources | ROME System


ROME System

Photo of ML SystemThe ROME (Refinement and Optimization based on Machine lEarning) project is one of the major research efforts at the Intel® PCCSB. The project aims to develop a parallel computing software system for high-resolution cryo-EM structure determination and data analysis, which implements advanced machine learning approaches in modern computer sciences and runs natively in an HPC environment. The ROME project emphasizes the development and improvement of cutting-edge machine-learning algorithms that can tap into increasingly complicated cryo-EM data with lower SNRs, greater structural heterogeneity, and higher magnitude of big-data volume. The ROME system is expected to be optimized on both Intel® Xeon multi-core CPUs and Intel® Xeon Phi many-core coprocessors. The areas of investigation in this critical program include but are not limited to statistical pattern recognition, nonlinear dimensionality reduction and big-data processing.