Electrochemical energy storage is central to modern society -- from consumer electronics to electrified transportation and the power grid. It is no longer just a convenience but a critical enabler of the transition to a resilient, low-carbon economy.
The large pluralistic battery research and development community serving these needs has evolved into diverse specialties spanning materials discovery, battery chemistry, design innovation, scale-up, manufacturing and deployment. Despite the maturity and the impact of battery science and technology, the data and software practices among these disparate groups are far behind the state-of-the-art in other fields (e.g. drug discovery), which have enjoyed significant increases in the rate of innovation. Incremental performance gains and lost research productivity, which are the consequences, retard innovation and societal progress. Examples span every field of battery research , from the slow and iterative nature of materials discovery, to the repeated and time-consuming performance testing of cells and the mitigation of degradation and failures. The fundamental issue is that modern data science methods require large amounts of data and the battery community lacks the requisite scalable, standardized data hubs required for immediate use of these approaches. Lack of uniform data practices is a central barrier to the scale problem. In this perspective we identify the data- and software-sharing gaps and propose the unifying principles and tools needed to build a robust community of data hubs, which provide flexible sharing formats to address diverse needs. The Battery Data Genome is offered as a data-centric initiative that will enable the transformative acceleration of battery science and technology, and will ultimately serve as a catalyst to revolutionize our approach to innovation.
We examine a pair of graph generative models for the therapeutic design of novel drug candidates targeting SARS-CoV-2 viral proteins. Due to a sense of urgency, we chose well-validated models with unique strengths: an autoencoder that generates molec
ules with similar structures to a dataset of drugs with anti-SARS activity and a reinforcement learning algorithm that generates highly novel molecules. During generation, we explore optimization toward several design targets to balance druglikeness, synthetic accessability, and anti-SARS activity based on icfifty. This generative frameworkfootnote{https://github.com/exalearn/covid-drug-design} will accelerate drug discovery in future pandemics through the high-throughput generation of targeted therapeutic candidates.
Design of new drug compounds with target properties is a key area of research in generative modeling. We present a small drug molecule design pipeline based on graph-generative models and a comparison study of two state-of-the-art graph generative mo
dels for designing COVID-19 targeted drug candidates: 1) a variational autoencoder-based approach (VAE) that uses prior knowledge of molecules that have been shown to be effective for earlier coronavirus treatments and 2) a deep Q-learning method (DQN) that generates optimized molecules without any proximity constraints. We evaluate the novelty of the automated molecule generation approaches by validating the candidate molecules with drug-protein binding affinity models. The VAE method produced two novel molecules with similar structures to the antiretroviral protease inhibitor Indinavir that show potential binding affinity for the SARS-CoV-2 protein target 3-chymotrypsin-like protease (3CL-protease).
Researchers worldwide are seeking to repurpose existing drugs or discover new drugs to counter the disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). A promising source of candidates for such studies is molecules that hav
e been reported in the scientific literature to be drug-like in the context of coronavirus research. We report here on a project that leverages both human and artificial intelligence to detect references to drug-like molecules in free text. We engage non-expert humans to create a corpus of labeled text, use this labeled corpus to train a named entity recognition model, and employ the trained model to extract 10912 drug-like molecules from the COVID-19 Open Research Dataset Challenge (CORD-19) corpus of 198875 papers. Performance analyses show that our automated extraction model can achieve performance on par with that of non-expert humans.
Intermolecular and long-range interactions are central to phenomena as diverse as gene regulation, topological states of quantum materials, electrolyte transport in batteries, and the universal solvation properties of water. We present a set of chall
enge problems for preserving intermolecular interactions and structural motifs in machine-learning approaches to chemical problems, through the use of a recently published dataset of 4.95 million water clusters held together by hydrogen bonding interactions and resulting in longer range structural patterns. The dataset provides spatial coordinates as well as two types of graph representations, to accommodate a variety of machine-learning practices.
Materials discovery is crucial for making scientific advances in many domains. Collections of data from experiments and first-principle computations have spurred interest in applying machine learning methods to create predictive models capable of map
ping from composition and crystal structures to materials properties. Generally, these are regression problems with the input being a 1D vector composed of numerical attributes representing the material composition and/or crystal structure. While neural networks consisting of fully connected layers have been applied to such problems, their performance often suffers from the vanishing gradient problem when network depth is increased. In this paper, we study and propose design principles for building deep regression networks composed of fully connected layers with numerical vectors as input. We introduce a novel deep regression network with individual residual learning, IRNet, that places shortcut connections after each layer so that each layer learns the residual mapping between its output and input. We use the problem of learning properties of inorganic materials from numerical attributes derived from material composition and/or crystal structure to compare IRNets performance against that of other machine learning techniques. Using multiple datasets from the Open Quantum Materials Database (OQMD) and Materials Project for training and evaluation, we show that IRNet provides significantly better prediction performance than the state-of-the-art machine learning approaches currently used by domain scientists. We also show that IRNets use of individual residual learning leads to better convergence during the training phase than when shortcut connections are between multi-layer stacks while maintaining the same number of parameters.
Recent studies illustrate how machine learning (ML) can be used to bypass a core challenge of molecular modeling: the tradeoff between accuracy and computational cost. Here, we assess multiple ML approaches for predicting the atomization energy of or
ganic molecules. Our resulting models learn the difference between low-fidelity, B3LYP, and high-accuracy, G4MP2, atomization energies, and predict the G4MP2 atomization energy to 0.005 eV (mean absolute error) for molecules with less than 9 heavy atoms and 0.012 eV for a small set of molecules with between 10 and 14 heavy atoms. Our two best models, which have different accuracy/speed tradeoffs, enable the efficient prediction of G4MP2-level energies for large molecules and are available through a simple web interface.
We report the computational investigation of a series of ternary X$_4$Y$_2$Z and X$_5$Y$_2$Z$_2$ compounds with X={Mg, Ca, Sr, Ba}, Y={P, As, Sb, Bi}, and Z={S, Se, Te}. The compositions for these materials were predicted through a search guided by m
achine learning, while the structures were resolved using the minima hopping crystal structure prediction method. Based on $textit{ab initio}$ calculations, we predict that many of these compounds are thermodynamically stable. In particular, 21 of the X$_4$Y$_2$Z compounds crystallize in a tetragonal structure with $textit{I-42d}$ symmetry, and exhibit band gaps in the range of 0.3 and 1.8 eV, well suited for various energy applications. We show that several candidate compounds (in particular X$_4$Y$_2$Te and X$_4$Sb$_2$Se) exhibit good photo absorption in the visible range, while others (e.g., Ba$_4$Sb$_2$Se) show excellent thermoelectric performance due to a high power factor and extremely low lattice thermal conductivities.
The atomic structure of the supercooled liquid has often been discussed as a key source of glass formation in metals. The presence of icosahedrally-coordinated clusters and their tendency to form networks have been identified as one possible structur
al trait leading to glass forming ability in the Cu-Zr binary system. In this work, we show that this theory is insufficient to explain glass formation at all compositions in that binary system. Instead, we propose that the formation of ideally-packed clusters at the expense of atomic arrangements with excess or deficient free volume can explain glass-forming by a similar mechanism. We show that this behavior is reflected in the structural relaxation of a metallic glass during constant pressure cooling and the time evolution of structure at a constant volume. We then demonstrate that this theory is sufficient to explain slowed diffusivity in compositions across the range of Cu-Zr metallic glasses.
