Search

High-throughput screening (HTS), as one of the key techniques in drug discovery, is frequently used to identify promising drug candidates in a largely automated and cost-effective way. One of the necessary conditions for successful HTS campaigns is a large and diverse compound library, enabling hundreds of thousands of activity measurements per project. Such collections of data hold great promise for computational and experimental drug discovery efforts, especially when leveraged in combination with modern deep learning techniques, and potentially leading to improved drug activity predictions and cheaper and more effective experimental design. However, existing collections of machine learning ready public datasets do not exploit the multiple data modalities present in real-world HTS projects. Thus, the largest fraction of experimental measurements, corresponding to hundreds of thousands of 'noisy' activity values from primary screening, are effectively ignored in the majority of machine learning models of HTS data. To address these limitations, we introduce MF-PCBA (Multi Fidelity PubChem BioAssay), a curated collection of 60 datasets that includes two data modalities for each dataset, corresponding to primary and confirmatory screening, an aspect that we call multi-fidelity. Multi-fidelity data accurately reflects real-world HTS conventions, and presents a new, challenging task for machine learning: the integration of low and high-fidelity measurements through molecular representation learning, taking into account the orders-of-magnitude difference in size between the primary and confirmatory screens. Here, we detail the steps taken to assemble MF-PCBA, in terms of data acquisition from PubChem and the filtering steps required to curate the raw data. We also provide an evaluation of a recent, deep-learning based method for multi-fidelity integration across the introduced datasets, demonstrating the benefit of leveraging all HTS modalities, and a discussion in terms of the roughness of the molecular activity landscape. In total, MF-PCBA contains over 16.6 million unique molecule-protein interactions. The datasets can be easily assembled by using the source code available at https://github.com/davidbuterez/mf-pcba.

High throughput screening (HTS) is one of the leading techniques for hit identification in drug discovery and is often done in two phases, primary and confirmatory. The resulting data is multi-fidelity, with noisy primary screening data available on a large number of compounds and higher quality confirmatory data on a low-to-moderate number of compounds. Existing computational pipelines do not integrate primary and confirmatory screening data of individual HTS campaigns, resulting in millions of potentially useful screening data points being unused in models of confirmatory bioactivity prediction. Furthermore, there is currently a lack of publicly available multi-fidelity bioactivity benchmarks to support modelling real-world high-throughput screening data. To address these challenges, we first compiled a public collection of 23 multi-fidelity HTS datasets from PubChem for benchmarking, including more than 6.1 million data points. Additionally, we assembled a private collection of 19 AstraZeneca HTS datasets, spanning more than 22.8 million data points. We then designed and evaluated machine learning models to assess the improvements offered by the integration of multi-fidelity data, including classical machine learning and novel deep learning approaches, the latter based on graph neural networks. Jointly modelling primary and confirmatory data led to a decrease of 12% in mean absolute error (MAE) and an increase of 152% in R-squared on the public datasets, and a reduction of 17% in MAE coupled with an uplift of 46% in R-squared on the AstraZeneca datasets (averaged across all evaluated methods). Furthermore, supplementing with molecular embeddings produced by previously trained deep learning models led to improved metrics for compounds that were not part of the primary screen, with up to double the baseline performance. We conclude that joint modelling of multi-fidelity HTS data improves predictive performance and that deep learning enables the use of unique and highly desirable strategies such as leveraging signals from multi-million scale datasets and transfer learning.

In this work, we present Link-INVENT as an extension to the existing de novo molecular design platform REINVENT. We provide illustrative examples on how Link-INVENT can be applied on fragment linking, scaffold hopping, and PROTACs design case studies where the desirable molecules should satisfy a combination of different criteria. With the help of Reinforcement Learning, the agent used by Link-INVENT learns to generate favourable linkers connecting molecular subunits that satisfy diverse objectives, facilitating practical application of the model for real-world drug discovery projects. We also introduce a range of linker-specific objectives in the scoring function of REINVENT. The code is freely available at https://github.com/MolecularAI/Reinvent.

Strategies for machine-learning (ML)-accelerated discovery that are general across material composition spaces are essential, but demonstrations of ML have been primarily limited to narrow composition variations. By addressing the scarcity of data in promising regions of chemical space for challenging targets such as open-shell transition-metal complexes, general representations and transferable ML models that leverage known relationships in existing data will accelerate discovery. Over a large set (∼1000) of isovalent transition-metal complexes, we quantify evident relationships for different properties (i.e., spin-splitting and ligand dissociation) between rows of the Periodic Table (i.e., 3d/4d metals and 2p/3p ligands). We demonstrate an extension to the graph-based revised autocorrelation (RAC) representation (i.e., eRAC) that incorporates the group number alongside the nuclear charge heuristic that otherwise overestimates dissimilarity of isovalent complexes. To address the common challenge of discovery in a new space where data are limited, we introduce a transfer learning approach in which we seed models trained on a large amount of data from one row of the Periodic Table with a small number of data points from the additional row. We demonstrate the synergistic value of the eRACs alongside this transfer learning strategy to consistently improve model performance. Analysis of these models highlights how the approach succeeds by reordering the distances between complexes to be more consistent with the Periodic Table, a property we expect to be broadly useful for other material domains.

Despite being attractive targets for functional materials, the discovery of transition metal complexes with high-throughput computational screening is challenged by the amount of feasible coordination numbers, spin states, or oxidation states and the potentially large sizes of ligands. To overcome these limitations, we take inspiration from organic chemistry where full enumeration of neutral, closed-shell molecules under the constraint of size has enriched discovery efforts. We design monodentate and bidentate ligands from scratch for the construction of mononuclear, octahedral transition metal complexes with up to 13 heavy atoms (i.e., metal, C, N, O, P, or S). From >11 000 theoretical ligands, we develop a heuristic score for ranking a chemically feasible 2500 ligand subset, only 71 of which were previously included in common organic molecule databases. We characterize the top 20% of scored ligands with density functional theory (DFT) in an octahedral homoleptic ligand database (OHLDB). The OHLDB contains i) the geometry optimized structures of 1250 homoleptic octahedral complexes obtained from the enumerated pool of ligands and an open-shell transition metal (M(II)/M(III), M = Cr, Mn, Fe, or Co) and ii) the resulting high-spin/low-spin adiabatic electronic energy differences (ΔEH–L) obtained with hybrid DFT. Over the OHLDB, we observe structure–property (i.e., ΔEH–L) relationships different from those expected on the basis of ligand field arguments or from our prior data sets. Finally, we demonstrate how incorporating OHLDB data into artificial neural network (ANN) training improves ANN out-of-sample performance on much larger transition metal complexes.

Reinforcement learning (RL) is a powerful paradigm that has gained popularity across multiple domains. However, applying RL may come at a cost of multiple interactions between the agent and the environment. This cost can be especially pronounced when the single feedback from the environment is slow or computationally expensive, causing extensive periods of nonproductivity. Curriculum learning (CL) provides a suitable alternative by arranging a sequence of tasks of increasing complexity with the aim of reducing the overall cost of learning. Here, we demonstrate the application of CL for drug discovery. We implement CL in the de novo design platform, REINVENT, and apply it on illustrative de novo molecular design problems of different complexity. The results show both accelerated learning and a positive impact on the quality of the output when compared to standard policy based RL. To our knowledge, this is the first application of CL for the purposes of de novo molecular design. The code is freely available at https://github.com/MolecularAI/Reinvent.

Reinforcement learning (RL) is a powerful paradigm that has gained popularity across multiple domains. However, applying RL may come at a cost of multiple interactions between the agent and the environment. This cost can be especially pronounced when the single feedback from the environment is slow or computationally expensive, causing extensive periods of nonproductivity. Curriculum learning (CL) provides a suitable alternative by arranging a sequence of tasks of increasing complexity with the aim of reducing the overall cost of learning. Here, we demonstrate the application of CL for drug discovery. We implement CL in the de novo design platform, REINVENT, and apply it on illustrative de novo molecular design problems of different complexity. The results show both accelerated learning and a positive impact on the quality of the output when compared to standard policy based RL. To our knowledge, this is the first application of CL for the purposes of de novo molecular design. The code is freely available at https://github.com/MolecularAI/Reinvent.

Recently, we have released the de novo design platform REINVENT in version 2.0. This improved and extended iteration supports far more features and scoring function components, which allows bespoke and tailor-made protocols to maximize impact in small molecule drug discovery projects. A major obstacle of generative models is producing active compounds, in which predictive (QSAR) models have been applied to enrich target activity. However, QSAR models are inherently limited by their applicability domains. To overcome these limitations, we introduce a structure-based scoring component for REINVENT. DockStream is a flexible, stand-alone molecular docking wrapper that provides access to a collection of ligand embedders and docking backends. Using the benchmarking and analysis workflow provided in DockStream, execution and subsequent analysis of a variety of docking configurations can be automated. Docking algorithms vary greatly in performance depending on the target and the benchmarking and analysis workflow provides a streamlined solution to identifying productive docking configurations. We show that an informative docking configuration can inform the REINVENT agent to optimize towards improving docking scores using public data. With docking activated, REINVENT is able to retain key interactions in the binding site, discard molecules which do not fit the binding cavity, harness unused (sub-)pockets, and improve overall performance in the scaffold-hopping scenario. The code is freely available at https://github.com/MolecularAI/DockStream.

Metal-oxo moieties are important catalytic intermediates in the selective partial oxidation of hydrocarbons and in water splitting. Stable metal-oxo species have reactive properties that vary depending on the spin state of the metal, complicating the development of structure-property relationships. To overcome these challenges, we train machine-learning (ML) models capable of predicting metal-oxo formation energies across a range of first-row metals, oxidation states, and spin states. Using connectivity-only features tailored for inorganic chemistry as inputs to kernel ridge regression or artificial neural network (ANN) ML models, we achieve good mean absolute errors (4-5 kcal/mol) on set-aside test data across a range of ligand orientations. Analysis of feature importance for oxo formation energy prediction reveals the dominance of nonlocal, electronic ligand properties in contrast to other transition metal complex properties (e.g., spin-state or ionization potential). We enumerate the theoretical catalyst space with an ANN, revealing expected trends in oxo formation energetics, such as destabilization of the metal-oxo species with increasing d-filling, as well as exceptions, such as weak correlations with indicators of oxidative stability of the metal in the resting state or unexpected spin-state dependence in reactivity. We carry out uncertainty-aware evolutionary optimization using the ANN to explore a > 37 000 candidate catalyst space. New metal and oxidation state combinations are uncovered and validated with density functional theory (DFT), including counterintuitive oxo formation energies for oxidatively stable complexes. This approach doubles the density of confirmed DFT leads in originally sparsely populated regions of property space, highlighting the potential of ML-model-driven discovery to uncover catalyst design rules and exceptions. Keywords: metal-oxo species; machine learning; density functional theory; spin-state-dependent reactivity; transition metal catalysis

High-throughput computational screening for chemical discovery mandates the automated and unsupervised simulation of thousands of new molecules and materials. In challenging materials spaces, such as open shell transition metal chemistry, characterization requires time-consuming first-principles simulation that often necessitates human intervention. These calculations can frequently lead to a null result, e.g., the calculation does not converge or the molecule does not stay intact during a geometry optimization. To overcome this challenge toward realizing fully automated chemical discovery in transition metal chemistry, we have developed the first machine learning models that predict the likelihood of successful simulation outcomes. We train support vector machine and artificial neural network classifiers to predict simulation outcomes (i.e., geometry optimization result and degree of deviation) for a chosen electronic structure method based on chemical composition. For these static models, we achieve an area under the curve of at least 0.95, minimizing computational time spent on non- productive simulations and therefore enabling efficient chemical space exploration. We introduce a metric of model uncertainty based on the distribution of points in the latent space to systematically improve model prediction confidence. In a complementary approach, we train a convolutional neural network classification model on simulation output electronic and geometric structure time series data. This dynamic model generalizes more readily than the static classifier by becoming more predictive as input simulation length increases. Finally, we describe approaches for using these models to enable autonomous job control in transition metal complex discovery.

The variability of chemical bonding in open-shell transition-metal complexes not only motivates their study as functional materials and catalysts but also challenges conventional computational modeling tools. Here, tailoring ligand chemistry can alter preferred spin or oxidation states as well as electronic structure properties and reactivity, creating vast regions of chemical space to explore when designing new materials atom by atom. Although first-principles density functional theory (DFT) remains the workhorse of computational chemistry in mechanism deduction and property prediction, it is of limited use here. DFT is both far too computationally costly for widespread exploration of transition-metal chemical space and also prone to inaccuracies that limit its predictive performance for localized d electrons in transition-metal complexes. These challenges starkly contrast with the well-trodden regions of small-organic-molecule chemical space, where the analytical forms of molecular mechanics force fields and semiempirical theories have for decades accelerated the discovery of new molecules, accurate DFT functional performance has been demonstrated, and gold-standard methods from correlated wavefunction theory can predict experimental results to chemical accuracy.The combined promise of transition-metal chemical space exploration and lack of established tools has mandated a distinct approach. In this Account, we outline the path we charted in exploration of transition-metal chemical space starting from the first machine learning (ML) models (i.e., artificial neural network and kernel ridge regression) and representations for the prediction of open-shell transition-metal complex properties. The distinct importance of the immediate coordination environment of the metal center as well as the lack of low-level methods to accurately predict structural properties in this coordination environment first motivated and then benefited from these ML models and representations. Once developed, the recipe for prediction of geometric, spin state, and redox potential properties was straightforwardly extended to a diverse range of other properties, including in catalysis, computational "feasibility", and the gas separation properties of periodic metal-organic frameworks. Interpretation of selected features most important for model prediction revealed new ways to encapsulate design rules and confirmed that models were robustly mapping essential structure-property relationships. Encountering the special challenge of ensuring that good model performance could generalize to new discovery targets motivated investigation of how to best carry out model uncertainty quantification. Distance-based approaches, whether in model latent space or in carefully engineered feature space, provided intuitive measures of the domain of applicability. With all of these pieces together, ML can be harnessed as an engine to tackle the large-scale exploration of transition-metal chemical space needed to satisfy multiple objectives using efficient global optimization methods. In practical terms, bringing these artificial intelligence tools to bear on the problems of transition-metal chemical space exploration has resulted in ML-model assessments of large, multimillion compound spaces in minutes and validated new design leads in weeks instead of decades.

Millions of distinct metal-organic frameworks (MOFs) can be made by combining metal nodes and organic linkers. At present, over 90,000 MOFs have been synthesized and over 500,000 predicted. This raises the question whether a new experimental or predicted structure adds new information. For MOF chemists, the chemical design space is a combination of pore geometry, metal nodes, organic linkers, and functional groups, but at present we do not have a formalism to quantify optimal coverage of chemical design space. In this work, we develop a machine learning method to quantify similarities of MOFs to analyse their chemical diversity. This diversity analysis identifies biases in the databases, and we show that such bias can lead to incorrect conclusions. The developed formalism in this study provides a simple and practical guideline to see whether new structures will have the potential for new insights, or constitute a relatively small variation of existing structures., At present there are databases with over 500,000 predicted or synthesized MOF structures, yet a method to establish whether a new material adds new information does not exist. Here the authors propose a machine-learning based approach to quantify the structural and chemical diversity in common MOF databases.

Determination of ground-state spins of open-shell transition metal complexes is critical to understanding catalytic and materials properties but also challenging with approximate electronic structure methods. As an alternative approach, we demonstrate how structure alone can be used to guide assignment of ground-state spin from experimentally determined crystal structures of transition metal complexes. We first identify the limits of distance-based heuristics from distributions of metal–ligand bond lengths of over 2,000 unique mononuclear Fe(II)/Fe(III) transition metal complexes. To overcome these limits, we employ artificial neural networks (ANNs) to predict spin-state-dependent metal–ligand bond lengths and classify experimental ground state spins based on agreement of experimental structures with the ANN predictions. Although the ANN is trained on hybrid density functional theory data, we exploit the method-insensitivity of geometric properties to enable assignment of ground states for the majority (ca. 80-90%) of structures. We demonstrate the utility of the ANN by data-mining the literature for spin-crossover (SCO) complexes, which have experimentally-observed temperature-dependent geometric structure changes, by correctly assigning almost all (> 95%) spin states in the 46 Fe(II) SCO complex set. This approach represents a promising complement to more conventional energy-based spin-state assignment from electronic structure theory at the low cost of a machine learning model.

Machine learning (ML) has emerged as a powerful complement to simulation for materials discovery by reducing time for evaluation of energies and properties at accuracy competitive with first-principles methods. We use genetic algorithm (GA) optimization to discover unconventional spin-crossover complexes in combination with efficient scoring from an artificial neural network (ANN) that predicts spin-state splitting of inorganic complexes. We explore a compound space of over 5600 candidate materials derived from eight metal/oxidation state combinations and a 32-ligand pool. We introduce a strategy for error-aware ML-driven discovery by limiting how far the GA travels away from the nearest ANN training points while maximizing property (i.e., spin-splitting) fitness, leading to discovery of 80% of the leads from full chemical space enumeration. Over a 51-complex subset, average unsigned errors (4.5 kcal/mol) are close to the ANN's baseline 3 kcal/mol error. By obtaining leads from the trained ANN within seconds rather than days from a DFT-driven GA, this strategy demonstrates the power of ML for accelerating inorganic material discovery.

Virtual high throughput screening, typically driven by first-principles, density functional theory calculations, has emerged as a powerful tool for the discovery of new materials. Although the computational materials science community has benefited from open source tools for the rapid structure generation, calculation, and analysis of crystalline inorganic materials, software and strategies to address the unique challenges of inorganic complex discovery have not been as widely available. We present a unified view of our recent developments in the open source molSimplify code for inorganic discovery. Building on our previous efforts in the automated generation of highly accurate inorganic molecular structures, first-principles simulation, and property analysis to accelerate high-throughput screening, we have recently incorporated a neural network that both improves structure generation and predicts electronic properties prior to first-principles calculation. We also provide an overview of how multimillion ...

Despite being attractive targets for functional materials, the discovery of transition metal complexes with high-throughput computational screening is challenged by the amount of feasible coordination numbers, spin states, or oxidation states and the potentially large sizes of ligands. To overcome these limitations, we take inspiration from organic chemistry where full enumeration of neutral, closed shell molecules under the constraint of size has enriched discovery efforts. We design monodentate and bidentate ligands from scratch for the construction of mononuclear, octahedral transition metal complexes with up to 13 heavy atoms (i.e., metal, C, N, O, P, or S). From > 11,000 theoretical ligands, we develop a heuristic score for ranking a chemically feasible 2,500 ligand subset, only 71 of which were previously included in common organic molecule databases. We characterize the top 20% of scored ligands with density functional theory (DFT) in an octahedral homoleptic ligand database (OHLDB). The OHLDB contains i) the geometry optimized structures of 1,250 homoleptic octahedral complexes obtained from the enumerated pool of ligands and an open-shell transition metal (M(II)/M(III), M = Cr, Mn, Fe, or Co), and ii) the resulting high-spin/low-spin adiabatic electronic energies (ΔEH-L) obtained with hybrid DFT. Over the OHLDB, we observe structure–property (i.e., ΔEH-L) relationships different from those expected on the basis of ligand field arguments or from our prior data sets. Finally, we demonstrate how incorporating OHLDB data into artificial neural network (ANN) training improves ANN out-of-sample performance on much larger transition metal complexes.

A predictive approach for driving down machine learning model errors is introduced and demonstrated across discovery for inorganic and organic chemistry., Machine learning (ML) models, such as artificial neural networks, have emerged as a complement to high-throughput screening, enabling characterization of new compounds in seconds instead of hours. The promise of ML models to enable large-scale chemical space exploration can only be realized if it is straightforward to identify when molecules and materials are outside the model's domain of applicability. Established uncertainty metrics for neural network models are either costly to obtain (e.g., ensemble models) or rely on feature engineering (e.g., feature space distances), and each has limitations in estimating prediction errors for chemical space exploration. We introduce the distance to available data in the latent space of a neural network ML model as a low-cost, quantitative uncertainty metric that works for both inorganic and organic chemistry. The calibrated performance of this approach exceeds widely used uncertainty metrics and is readily applied to models of increasing complexity at no additional cost. Tightening latent distance cutoffs systematically drives down predicted model errors below training errors, thus enabling predictive error control in chemical discovery or identification of useful data points for active learning.

Machine learning (ML) models, such as artificial neural networks, have emerged as a complement to high-throughput screening, enabling characterization of new compounds in seconds instead of hours. The promise of ML models to enable large-scale, chemical space exploration can only be realized if it is straightforward to identify when molecules and materials are outside the model’s domain of applicability. Established uncertainty metrics for neural network models are either costly to obtain (e.g., ensemble models) or rely on feature engineering (e.g., feature space distances), and each has limitations in estimating prediction errors for chemical space exploration. We introduce the distance to available data in the latent space of a neural network ML model as a low-cost, quantitative uncertainty metric that works for both inorganic and organic chemistry. The calibrated performance of this approach exceeds widely used uncertainty metrics and is readily applied to models of increasing complexity at no additional cost. Tightening latent distance cutoffs systematically drives down predicted model errors below training errors, thus enabling predictive error control in chemical discovery or identification of useful data points for active learning.

Recent transformative advances in computing power and algorithms have made computational chemistry central to the discovery and design of new molecules and materials. First-principles simulations are increasingly accurate and applicable to large systems with the speed needed for high-throughput computational screening. Despite these strides, the combinatorial challenges associated with the vastness of chemical space mean that more than just fast and accurate computational tools are needed for accelerated chemical discovery. In transition-metal chemistry and catalysis, unique challenges arise. The variable spin, oxidation state, and coordination environments favored by elements with well-localized d or f electrons provide great opportunity for tailoring properties in catalytic or functional (e.g., magnetic) materials but also add layers of uncertainty to any design strategy. We outline five key mandates for realizing computationally driven accelerated discovery in inorganic chemistry: (i) fully automated simulation of new compounds, (ii) knowledge of prediction sensitivity or accuracy, (iii) faster-than-fast property prediction methods, (iv) maps for rapid chemical space traversal, and (v) a means to reveal design rules on the kilocompound scale. Through case studies in open-shell transition-metal chemistry, we describe how advances in methodology and software in each of these areas bring about new chemical insights. We conclude with our outlook on the next steps in this process toward realizing fully autonomous discovery in inorganic chemistry using computational chemistry.

Machine learning the electronic structure of open shell transition metal complexes presents unique challenges, including robust and automated data set generation. Here, we introduce tools that simplify data acquisition from density functional theory (DFT) and validation of trained machine learning models using the molSimplify automatic design (mAD) workflow. We demonstrate this workflow by training and comparing the performance of LASSO, kernel ridge regression (KRR), and artificial neural network (ANN) models using heuristic, topological revised autocorrelation (RAC) descriptors we have recently introduced for machine learning inorganic chemistry. On a series of open shell transition metal complexes, we evaluate set aside test errors of these models for predicting the HOMO level and HOMO-LUMO gap. The best performing models are ANNs, which show 0.15 and 0.25 eV test set mean absolute errors on the HOMO level and HOMO-LUMO gap, respectively. Poor performing KRR models using the full 153-feature RAC set are improved to nearly the same performance as the ANNs when trained on down-selected subsets of 20-30 features. Analysis of the essential descriptors for HOMO and HOMO-LUMO gap prediction as well as comparison to subsets previously obtained for other properties reveals the paramount importance of non-local, steric properties in determining frontier molecular orbital energetics. We demonstrate our model performance on diverse complexes and in the discovery of molecules with target HOMO-LUMO gaps from a large 15,000 molecule design space in minutes rather than days that full DFT evaluation would require.

Machine learning the electronic structure of open shell transition metal complexes presents unique challenges, including robust and automated data set generation. Here, we introduce tools that simplify data acquisition from density functional theory (DFT) and validation of trained machine learning models using the molSimplify automatic design (mAD) workflow. We demonstrate this workflow by training and comparing the performance of LASSO, kernel ridge regression (KRR), and artificial neural network (ANN) models using heuristic, topological revised autocorrelation (RAC) descriptors we have recently introduced for machine learning inorganic chemistry. On a series of open shell transition metal complexes, we evaluate set aside test errors of these models for predicting the HOMO level and HOMO-LUMO gap. The best performing models are ANNs, which show 0.15 and 0.25 eV test set mean absolute errors on the HOMO level and HOMO-LUMO gap, respectively. Poor performing KRR models using the full 153-feature RAC set are improved to nearly the same performance as the ANNs when trained on down-selected subsets of 20-30 features. Analysis of the essential descriptors for HOMO and HOMO-LUMO gap prediction as well as comparison to subsets previously obtained for other properties reveals the paramount importance of non-local, steric properties in determining frontier molecular orbital energetics. We demonstrate our model performance on diverse complexes and in the discovery of molecules with target HOMO-LUMO gaps from a large 15,000 molecule design space in minutes rather than days that full DFT evaluation would require.

Flashing flow is an important phenomenon in many industrial contexts; however simulation of these flows remains difficult. CFD simulations are able to describe the distribution and evolution of 3D structures in the flow but are dependent on good closure relations for interphase transfer. Nucleation during flashing flow is often neglected in CFD simulation where a minimum starting vapour fraction and a constant bubble number density are given. Models that include nucleation have used wall nucleation terms from 1D system code models, averaged over the domain. In this work, three models for wall nucleation are tested and compared with experimental data from a converging–diverging nozzle. Nucleation is applied at the walls of the domain, and various models are investigated. Good agreement with the critical flow rate and axial profiles are found, but agreement with the radial void fraction data is not satisfactory. Methods of addressing this are explored, and it is found that including a small bulk heterogeneous nucleation term gives the best agreement with the radial profiles, with negligible impact on the axial average properties.

Machine learning (ML) of quantum mechanical properties shows promise for accelerating chemical discovery. For transition metal chemistry where accurate calculations are computationally costly and available training data sets are small, the molecular representation becomes a critical ingredient in ML model predictive accuracy. We introduce a series of revised autocorrelation functions (RACs) that encode relationships between the heuristic atomic properties (e.g., size, connectivity, and electronegativity) on a molecular graph. We alter the starting point, scope, and nature of the quantities evaluated in standard ACs to make these RACs amenable to inorganic chemistry. On an organic molecule set, we first demonstrate superior standard AC performance to other presently-available topological descriptors for ML model training, with mean unsigned errors (MUEs) for atomization energies on set-aside test molecules as low as 6 kcal/mol. For inorganic chemistry, our RACs yield 1 kcal/mol ML MUEs on set-aside test molecules in spin-state splitting in comparison to 15-20x higher errors from feature sets that encode whole-molecule structural information. Systematic feature selection methods including univariate filtering, recursive feature elimination, and direct optimization (e.g., random forest and LASSO) are compared. Random-forest- or LASSO-selected subsets 4-5x smaller than RAC-155 produce sub- to 1-kcal/mol spin-splitting MUEs, with good transferability to metal-ligand bond length prediction (0.004-5 {\AA} MUE) and redox potential on a smaller data set (0.2-0.3 eV MUE). Evaluation of feature selection results across property sets reveals the relative importance of local, electronic descriptors (e.g., electronegativity, atomic number) in spin-splitting and distal, steric effects in redox potential and bond lengths., Comment: 43 double spaced pages, 11 figures, 4 tables

High-throughput computational screening has emerged as a critical component of materials discovery. Direct density functional theory (DFT) simulation of inorganic materials and molecular transition metal complexes is often used to describe subtle trends in inorganic bonding and spin-state ordering, but these calculations are computationally costly and properties are sensitive to the exchange-correlation functional employed. To begin to overcome these challenges, we trained artificial neural networks (ANNs) to predict quantum-mechanically-derived properties, including spin-state ordering, sensitivity to Hartree-Fock exchange, and spin- state specific bond lengths in transition metal complexes. Our ANN is trained on a small set of inorganic-chemistry-appropriate empirical inputs that are both maximally transferable and do not require precise three-dimensional structural information for prediction. Using these descriptors, our ANN predicts spin-state splittings of single-site transition metal complexes (i.e., Cr-Ni) at arbitrary amounts of Hartree-Fock exchange to within 3 kcal/mol accuracy of DFT calculations. Our exchange-sensitivity ANN enables improved predictions on a diverse test set of experimentally-characterized transition metal complexes by extrapolation from semi-local DFT to hybrid DFT. The ANN also outperforms other machine learning models (i.e., support vector regression and kernel ridge regression), demonstrating particularly improved performance in transferability, as measured by prediction errors on the diverse test set. We establish the value of new uncertainty quantification tools to estimate ANN prediction uncertainty in computational chemistry, and we provide additional heuristics for identification of when a compound of interest is likely to be poorly predicted by the ANN., 26 pages of text, 13 figures, 4 tables

The most significant health problem in the world is breast cancer and early detection is the key to pr edict it. Mammography is the most reliable method to diagnose breast cancer at the earliest. The classification of the two most findings in the digital mammograms, micro calcifications and mass are valuable for early detection. Since, the appearance of the masses are similar to the surrounding parenchyma, the classifi cation is not an easy task. In this study, an efficient ap proach to classify masses in the Mammography Image Analysis Society (MIAS) database mammogram images is presented. The key features used for the classification is the energies of shearlet decompos ed image. These features are fed into SVM classifie r to classify mass/non mass images and also benign/malignant. The results demonstrate that the proposed shearlet energy features outperforms the wavelet en ergy features in terms of accuracy.

By utilizing distributed computing, we can store the information on remote servers and permit information access to open inquiry clients through the cloud server’s. The document set ought to ordinarily encoded before transferred to cloud server. These data is called outsourced data. It has certain limit to search on encrypted data. We are providing security for search data through cloud server. Encryption of data in the form of keywords. The search users can easily access the data from cloud servers by using empower of fine grained multi-keyword search. In this paper, we address the two issues with respect to multi-watchword seek. First issue as we consider the extensibility of document set and multiuser environment. By using these type of search users can easily access the data in the file format. These files consist of some indexes to search. The complete data can be stored in the form of file. And the total file will be stored in an order and encrypted by the information proprietor (data owner) and send to the cloud. Second issues as we think about creating as a scalable searchable encryption to get effective results on pragmatic databases.

Cloud computing is a rapidly growing computation paradigm. Cloud Computing combines all the Information Technology (IT) capabilities. As it has turned into the standard for cloud suppliers to have numerous server farms the world over, noteworthy requests exist for between server farm's information moves in extensive volumes, e.g., relocation of huge information. A test emerges on the best way to plan the mass information exchanges at various criticalness levels, keeping in mind the end goal to completely use the accessible between server farm's data transfer capacity. The model mass information exchange framework in light of the open stream outline work. The Bulk Data Transfer (BDT) framework lives over the vehicle layer in the system layer and stack, with no unique necessity on the lower transport layer and organizing layer conventions, where the standard TCP/IP stack is embraced. It applies the time extension chart method which is later embraced by Postcard, whose calculation overhead keeps the planning from happening as every now and again as our own. Our propose a dependable and productive basic mass information move administration in a between server farm's system, including ideal directing for particular lumps after some time, which can be incidentally put away at transitional server farm's and sent at precisely figured times. Our proposed objectives are optimizing the data transfer by using effective snappy compression/ decompression techniques in client's side. Snappy has high compression ratio and input/output performance. Compression will be done via block size, tag, offset, length, index, encoding. It reduces the time because, it is a lossless algorithm. Hence we propose an improvement in data movement by using the techniques snappy and BDT.