Not every AI-loving company operates in logistics, marketing or healthcare. Artificial intelligence isn't picky about which industries it revolutionizes, and many niches have already embraced automation. Given the global value of AI, it's no surprise the tech is spreading. Statista estimates that worldwide AI revenue will hit $90 billion by 2025. With so much wealth to go around, no industry is safe from disruption.

Molecule property prediction is a fundamental problem for computer-aided drug discovery and materials science. Quantum-chemical simulations such as density functional theory (DFT) have been widely used for calculating the molecule properties, however, because of the heavy computational cost, it is difficult to search a huge number of potential chemical compounds. Machine learning methods for molecular modeling are attractive alternatives, however, the development of expressive, accurate, and scalable graph neural networks for learning molecular representations is still challenging. In this work, we propose a simple and powerful graph neural networks for molecular property prediction. We model a molecular as a directed complete graph in which each atom has a spatial position, and introduce a recursive neural network with simple gating function. We also feed input embeddings for every layers as skip connections to accelerate the training. Experimental results show that our model achieves the state-of-the-art performance on the standard benchmark dataset for molecular property prediction.

Automation and digitalization are increasingly used in almost every major industry to improve efficiency. Thanks to rapid advances in artificial intelligence and robotics, and innovations like X-ray diffraction and electric vehicles, the mining sector is also catching up with the technological revolution. According to a White Paper by the World Economic Forum and Accenture, digitalization could bring about over USD $425 billion of value for the mining industry, customers, society and environment by 2025. It could also lead to a reduction of 610 million t of CO2 emissions, as well as a significant improvement in safety, saving lives and preventing injuries. With the vision to create a sustainable and smart mining system, a team of experts have developed a 5G radio network under the EU-funded SIMS project.

Newswise -- According to a release issued earlier this month by the Los Alamos National Laboratory (LANL), researchers have developed a machine learning approach called transfer learning that lets them model novel materials by learning from data collected about millions of other compounds. The new approach can be applied to new molecules in milliseconds, enabling research into a far greater number of compounds over much longer timescales. The new technique, called ANI-1ccx potential, promises to advance the capabilities of researchers in many fields and improve the accuracy of machine learning-based potentials in future studies of metal alloys and detonation physics. "Our quantum mechanical calculations to create ANI-1ccx potential were conducted over two years with time split on the Comet supercomputer at the San Diego Supercomputer Center and the Badger supercomputer at LANL," said Olexandr Isayev, paper author and a pharmacy professor at the University of North Carolina at Chapel Hill. "We chose these two supercomputers to train our neural networks as there are few machines that can run these – due to the high memory and core requirements."

The chemical and allied industries face such challenges as ready access to reliable energy supplies, waste reduction, water conservation, and energy efficiency. Organic electrosynthesis--an electricity-driven, energy-efficient process that can easily integrate with renewable energy sources--could help solve them. A team at the NYU Tandon School of Engineering reported that in its search to develop an innovative, environmentally friendly process to make adiponitrile (ADN) - the main precursor to nylon 6, 6--it found a way to greatly improve the efficiency of organic electrosynthesis. The researchers credited their success in part to what they believe is the first use of artificial intelligence to optimize an electrochemical process. Miguel Modestino, a professor of chemical and biomolecular engineering, and doctoral student Daniela Blanco tweaked how electrical current is delivered to catalytic electrodes and then applied artificial intelligence (AI) to further optimize the reaction.

BASF and Technische Universität Berlin (TU Berlin) have signed an agreement to cooperate closely in the area of machine learning. The aim of the Berlin-based Joint Lab for Machine Learning (BASLEARN) is to develop workable new mathematical models and algorithms for fundamental questions relating to chemistry, for example from process or quantum chemistry. Both partners are jointly committed to this aim in the coming years. As an essential part of the cooperation, BASF will support the research work of Dr. Klaus Robert Müller, professor of machine learning and spokesperson for the Berlin Center for Machine Learning at TU Berlin, with a total of over €2.5 million over the coming five years. Machine learning is a key pillar of artificial intelligence. The objective is to analyze large volumes of data to recognize patterns and relationships which can be used to develop prediction models that optimize themselves based on their results.

However, the execution of complex chemical syntheses in itself requires expert knowledge, usually acquired over many years of study and hands-on laboratory practice. The development of technologies with potential to streamline and automate chemical synthesis is a half-century-old endeavour yet to be fulfilled. Renewed interest in artificial intelligence (AI), driven by improved computing power, data availability and algorithms, is overturning the limited success previously obtained. In this Review, we discuss the recent impact of AI on different tasks of synthetic chemistry and dissect selected examples from the literature. By examining the underlying concepts, we aim to demystify AI for bench chemists in order that they may embrace it as a tool rather than fear it as a competitor, spur future research by pinpointing the gaps in knowledge and delineate how chemical AI will run in the era of digital chemistry.

The demands on machine learning methods to cater for ultra high dimensional datasets, datasets with millions of features, have been increasing in domains like life sciences and the Internet of Things (IoT). While Random Forests are suitable for "wide" datasets, current implementations such as Google's PLANET lack the ability to scale to such dimensions. Recent improvements by Yggdrasil begin to address these limitations but do not extend to Random Forest. This paper introduces CursedForest, a novel Random Forest implementation on top of Apache Spark and part of the VariantSpark platform, which parallelises processing of all nodes over the entire forest. CursedForest is 9 and up to 89 times faster than Google's PLANET and Yggdrasil, respectively, and is the first method capable of scaling to millions of features.

Recently, hybrid metaheuristics have become a trend in operations research. A successful example combines the Greedy Randomized Adaptive Search Procedures (GRASP) and data mining techniques, where frequent patterns found in high-quality solutions can lead to an efficient exploration of the search space, along with a significant reduction of computational time. In this work, a GRASP-based state-of-the-art heuristic for the Minimum Latency Problem (MLP) is improved by means of data mining techniques for two MLP variants. Computational experiments showed that the approaches with data mining were able to match or improve the solution quality for a large number of instances, together with a substantial reduction of running time. In addition, 88 new cost values of solutions are introduced into the literature. To support our results, tests of statistical significance, impact of using mined patterns, equal time comparisons and time-to-target plots are provided.

High-performance copper alloys are fundamental to the lead frames of integrated circuits (ICs). For example, the traditional copper alloys, including Cu–Fe–P, Cu–Ni–Si and Cu–Cr–Zr alloys, are hardly be used in the next generation of very-large-scale integration (VLSI) ICs, which requires a ultimate tensile strength (UTS) over 800 MPa and an electrical conductivity (EC) over 50.0% To improve the mechanical and electrical properties of copper alloys, one or more alloying elements, such as Ti, Co, P, Mg, Cr, Zr, Be, and Fe, can be introduced. Many efforts have been devoted to this field and showed that the alloying elements should have little effect on the EC and possesses a large solid solubility change from high temperature to room temperature.6,7,8,9,10 However, there is a lack of a model that quantitatively describes the relationship between alloy composition and performance.