Quantifying the Benefits of Imputation over QSAR Methods in Toxicology Data Modeling.

Imputation machine learning (ML) surpasses traditional approaches in modeling toxicity data. The method was tested on an open-source data set comprising approximately 2500 ingredients with limited in vitro and in vivo data obtained from the OECD QSAR Toolbox. By leveraging the relationships between different toxicological end points, imputation extracts more valuable information from each data point compared to well-established single end point methods, such as ML-based Quantitative Structure Activity Relationship (QSAR) approaches, providing a final improvement of up to around 0.2 in the coefficient of determination. A significant aspect of this methodology is its resilience to the inclusion of extraneous chemical or experimental data. While additional data typically introduces a considerable level of noise and can hinder performance of single end point QSAR modeling, imputation models remain unaffected. This implies a reduction in the need for laborious manual preprocessing tasks such as feature selection, thereby making data preparation for ML analysis more efficient. This successful test, conducted on open-source data, validates the efficacy of imputation approaches in toxicity data analysis. This work opens the way for applying similar methods to other types of sparse toxicological data matrices, and so we discuss the development of regulatory authority guidelines to accept imputation models, a key aspect for the wider adoption of these methods.

Prediction of In Vivo Pharmacokinetic Parameters and Time-Exposure Curves in Rats Using Machine Learning from the Chemical Structure.

Animal pharmacokinetic (PK) data as well as human and animal in vitro systems are utilized in drug discovery to define the rate and route of drug elimination. Accurate prediction and mechanistic understanding of drug clearance and disposition in animals provide a degree of confidence for extrapolation to humans. In addition, prediction of in vivo properties can be used to improve design during drug discovery, help select compounds with better properties, and reduce the number of in vivo experiments. In this study, we generated machine learning models able to predict rat in vivo PK parameters and concentration-time PK profiles based on the molecular chemical structure and either measured or predicted in vitro parameters. The models were trained on internal in vivo rat PK data for over 3000 diverse compounds from multiple projects and therapeutic areas, and the predicted endpoints include clearance and oral bioavailability. We compared the performance of various traditional machine learning algorithms and deep learning approaches, including graph convolutional neural networks. The best models for PK parameters achieved R2 = 0.63 [root mean squared error (RMSE) = 0.26] for clearance and R2 = 0.55 (RMSE = 0.46) for bioavailability. The models provide a fast and cost-efficient way to guide the design of molecules with optimal PK profiles, to enable the prediction of virtual compounds at the point of design, and to drive prioritization of compounds for in vivo assays.

An Open Drug Discovery Competition: Experimental Validation of Predictive Models in a Series of Novel Antimalarials.

The Open Source Malaria (OSM) consortium is developing compounds that kill the human malaria parasite, Plasmodium falciparum, by targeting PfATP4, an essential ion pump on the parasite surface. The structure of PfATP4 has not been determined. Here, we describe a public competition created to develop a predictive model for the identification of PfATP4 inhibitors, thereby reducing project costs associated with the synthesis of inactive compounds. Competition participants could see all entries as they were submitted. In the final round, featuring private sector entrants specializing in machine learning methods, the best-performing models were used to predict novel inhibitors, of which several were synthesized and evaluated against the parasite. Half possessed biological activity, with one featuring a motif that the human chemists familiar with this series would have dismissed as "ill-advised". Since all data and participant interactions remain in the public domain, this research project "lives" and may be improved by others.

Imputation of sensory properties using deep learning.

Predicting the sensory properties of compounds is challenging due to the subjective nature of the experimental measurements. This testing relies on a panel of human participants and is therefore also expensive and time-consuming. We describe the application of a state-of-the-art deep learning method, Alchemite™, to the imputation of sparse physicochemical and sensory data and compare the results with conventional quantitative structure-activity relationship methods and a multi-target graph convolutional neural network. The imputation model achieved a substantially higher accuracy of prediction, with improvements in R2 between 0.26 and 0.45 over the next best method for each sensory property. We also demonstrate that robust uncertainty estimates generated by the imputation model enable the most accurate predictions to be identified and that imputation also more accurately predicts activity cliffs, where small changes in compound structure result in large changes in sensory properties. In combination, these results demonstrate that the use of imputation, based on data from less expensive, early experiments, enables better selection of compounds for more costly studies, saving experimental time and resources.

OPTIMADE, an API for exchanging materials data.

The Open Databases Integration for Materials Design (OPTIMADE) consortium has designed a universal application programming interface (API) to make materials databases accessible and interoperable. We outline the first stable release of the specification, v1.0, which is already supported by many leading databases and several software packages. We illustrate the advantages of the OPTIMADE API through worked examples on each of the public materials databases that support the full API specification.

Machine learning to predict mesenchymal stem cell efficacy for cartilage repair.

Inconsistent therapeutic efficacy of mesenchymal stem cells (MSCs) in regenerative medicine has been documented in many clinical trials. Precise prediction on the therapeutic outcome of a MSC therapy based on the patient's conditions would provide valuable references for clinicians to decide the treatment strategies. In this article, we performed a meta-analysis on MSC therapies for cartilage repair using machine learning. A small database was generated from published in vivo and clinical studies. The unique features of our neural network model in handling missing data and calculating prediction uncertainty enabled precise prediction of post-treatment cartilage repair scores with coefficient of determination of 0.637 ± 0.005. From this model, we identified defect area percentage, defect depth percentage, implantation cell number, body weight, tissue source, and the type of cartilage damage as critical properties that significant impact cartilage repair. A dosage of 17 - 25 million MSCs was found to achieve optimal cartilage repair. Further, critical thresholds at 6% and 64% of cartilage damage in area, and 22% and 56% in depth were predicted to significantly compromise on the efficacy of MSC therapy. This study, for the first time, demonstrated machine learning of patient-specific cartilage repair post MSC therapy. This approach can be applied to identify and investigate more critical properties involved in MSC-induced cartilage repair, and adapted for other clinical indications.

Enhancing NEMD with automatic shear rate sampling to model viscosity and correction of systematic errors in modeling density: Application to linear and light branched alkanes.

We perform molecular dynamics simulations to model density as a function of temperature for 74 alkanes with 5-10 carbon atoms and non-equilibrium molecular dynamics simulations in the NVT ensemble to model the kinematic viscosity of 10 linear alkanes as a function of molecular weight, pressure, and temperature. To model density, we perform simulations in the NPT ensemble before applying correction factors to exploit the systematic error in the SciPCFF force field and compare the results to experimental values, obtaining an average absolute deviation of 3.4 gl at 25 °C and of 7.2 gl at 100 °C. We develop a sampling algorithm that automatically selects good shear rates at which to perform viscosity simulations in the NVT ensemble and use the Carreau model with weighted least squares regression to extrapolate Newtonian viscosity. Viscosity simulations are performed at experimental densities and show an excellent agreement with experimental viscosities, with an average percent deviation of -1% and an average absolute percent deviation of 5%. Future plans to study and apply the sampling algorithm are outlined.

Practical Applications of Deep Learning To Impute Heterogeneous Drug Discovery Data.

Contemporary deep learning approaches still struggle to bring a useful improvement in the field of drug discovery because of the challenges of sparse, noisy, and heterogeneous data that are typically encountered in this context. We use a state-of-the-art deep learning method, Alchemite, to impute data from drug discovery projects, including multitarget biochemical activities, phenotypic activities in cell-based assays, and a variety of absorption, distribution, metabolism, and excretion (ADME) endpoints. The resulting model gives excellent predictions for activity and ADME endpoints, offering an average increase in R2 of 0.22 versus quantitative structure-activity relationship methods. The model accuracy is robust to combining data across uncorrelated endpoints and projects with different chemical spaces, enabling a single model to be trained for all compounds and endpoints. We demonstrate improvements in accuracy on the latest chemistry and data when updating models with new data as an ongoing medicinal chemistry project progresses.

Absence of diagonal force constants in cubic Coulomb crystals.

The quasi-harmonic model proposes that a crystal can be modelled as atoms connected by springs. We demonstrate how this viewpoint can be misleading: a simple application of Gauss's law shows that the ion-ion potential for a cubic Coulomb system can have no diagonal harmonic contribution and so cannot necessarily be modelled by springs. We investigate the repercussions of this observation by examining three illustrative regimes: the bare ionic, density tight-binding and density nearly-free electron models. For the bare ionic model, we demonstrate the zero elements in the force constants matrix and explain this phenomenon as a natural consequence of Poisson's law. In the density tight-binding model, we confirm that the inclusion of localized electrons stabilizes all major crystal structures at harmonic order and we construct a phase diagram of preferred structures with respect to core and valence electron radii. In the density nearly-free electron model, we verify that the inclusion of delocalized electrons, in the form of a background jellium, is enough to counterbalance the diagonal force constants matrix from the ion-ion potential in all cases and we show that a first-order perturbation to the jellium does not have a destabilizing effect. We discuss our results in connection to Wigner crystals in condensed matter, Yukawa crystals in plasma physics, as well as the elemental solids.

Tail-regression estimator for heavy-tailed distributions of known tail indices and its application to continuum quantum Monte Carlo data.

Standard statistical analysis is unable to provide reliable confidence intervals on expectation values of probability distributions that do not satisfy the conditions of the central limit theorem. We present a regression-based estimator of an arbitrary moment of a probability distribution with power-law heavy tails that exploits knowledge of the exponents of its asymptotic decay to bypass this issue entirely. Our method is applied to synthetic data and to energy and atomic force data from variational and diffusion quantum Monte Carlo calculations, whose distributions have known asymptotic forms [J. R. Trail, Phys. Rev. E 77, 016703 (2008)PLEEE81539-375510.1103/PhysRevE.77.016703; A. Badinski et al., J. Phys.: Condens. Matter 22, 074202 (2010)JCOMEL0953-898410.1088/0953-8984/22/7/074202]. We obtain convergent, accurate confidence intervals on the variance of the local energy of an electron gas and on the Hellmann-Feynman force on an atom in the all-electron carbon dimer. In each of these cases the uncertainty on our estimator is 45% and 60 times smaller, respectively, than the nominal (ill-defined) standard error.