Deep dive into technical specifications of our machine Within the last few years, we have seen the transformative impact of deep learning in many domains, particularly in speech recognition and computer vision, to the extent that the majority of expert practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. In this review, we provide an introductory overview into the theory of deep neural networks and their unique properties that distinguish them from traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including QSAR, virtual screening, protein structure prediction, quantum chemistry, materials design and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non-neural networks state-of-the-art models across disparate research topics, and deep neural network based models often exceeded the "glass ceiling" expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a valuable tool for computational chemistry. The combination of modern scientific computing with electronic structure theory can lead to an unprecedented amount of data amenable to intelligent data analysis for the identification of meaningful, novel, and predictive structure-property relationships. Such relationships enable highthroughput screening for relevant properties in an exponentially growing pool of virtual compounds that are synthetically accessible. Here, we present a machine learning (ML) model, trained on a database of ab initio calculation results for thousands of organic molecules that simultaneously predicts multiple electronic ground- and excited-state properties. The properties include atomization energy, polarizability, frontier orbital eigenvalues, ionization potential, electron affinity, and excitation energies. The ML model is based on a deep multi-task artificial neural network, exploiting underlying correlations between various molecular properties. The input is identical to ab initio methods, i.e. nuclear charges and Cartesian coordinates of all atoms. For small organic molecules the accuracy of such a “Quantum Machine” is similar, and sometimes superior, to modern quantum-chemical methods—at negligible computational cost. The OpenPOWER Foundation is an open technical membership organization that is enabling companies to rethink their approach to technology. Compute hardware is evolving at an amazing rate and the OpenPOWER foundation is helping to usher in a new era of hardware innovation and customization. These innovations include custom systems for large scale data centers, workload acceleration through GPU, FPGA or advanced I/O, platform optimization for SW appliances, or advanced hardware technology exploitation. CreativeC, an OpenPOWER member, and KnuEdge, a local San Diego innovation hub, will be providing hardware for us to demonstrate and test drive TensorFlow and LAMMPS Molecular Dynamics Simulator. The liquid-cooled Simul8 is the first OpenPOWER system designed for office us. It is equipped with 2 Xeon XXX, a 128-core Power8 processor, and 2 NVIDIA P100s. The interconnect is Mellanox's 100Gb/s EDR Infiniband. That equates to 10 Tflops of processing power.
