Search

The CompTox Chemistry Dashboard (ToxCast) contains one of the largest public databases on Zebrafish (Danio rerio) developmental toxicity. The data consists of 19 toxicological endpoints on unique 1018 compounds measured in relatively low concentration ranges. The endpoints are related to developmental effects occurring in dechorionated zebrafish embryos for 120 hours post fertilization and monitored via gross malformations and mortality. We report the predictive capability of 209 quantitative structure–activity relationship (QSAR) models developed by machine learning methods using penalization techniques and diverse model quality metrics to cope with the imbalanced endpoints. All these QSAR models were generated to test how the imbalanced classification (toxic or non-toxic) endpoints could be predicted regardless which of three algorithms is used: logistic regression, multi-layer perceptron, or random forests. Additionally, QSAR toxicity models are developed starting from sets of classical molecular descriptors, structural fingerprints and their combinations. Only 8 out of 209 models passed the 0.20 Matthew’s correlation coefficient value defined a priori as a threshold for acceptable model quality on the test sets. The best models were obtained for endpoints mortality (MORT), ActivityScore and JAW (deformation). The low predictability of the QSAR model developed from the zebrafish embryotoxicity data in the database is mainly due to a higher sensitivity of 19 measurements of endpoints carried out on dechorionated embryos at low concentrations.

Atomic environment fingerprints are widely used in computational materials science, from machine learning potentials to the quantification of similarities between atomic configurations. Many approaches to the construction of such fingerprints, also called structural descriptors, have been proposed. In this work, we compare the performance of fingerprints based on the Overlap Matrix(OM), the Smooth Overlap of Atomic Positions (SOAP), Behler-Parrinello atom-centered symmetry functions (ACSF), modified Behler-Parrinello symmetry functions (MBSF) used in the ANI-1ccx potential and the Faber-Christensen-Huang-Lilienfeld (FCHL) fingerprint under various aspects. We study their ability to resolve differences in local environments and in particular examine whether there are certain atomic movements that leave the fingerprints exactly or nearly invariant. For this purpose, we introduce a sensitivity matrix whose eigenvalues quantify the effect of atomic displacement modes on the fingerprint. Further, we check whether these displacements correlate with the variation of localized physical quantities such as forces. Finally, we extend our examination to the correlation between molecular fingerprints obtained from the atomic fingerprints and global quantities of entire molecules., Comment: 18 pages, 11 figures

Structure-property relationships at the atomic scale are usually understood in terms of recurrent structural motifs formed by atoms and molecules, and how they transform and interact with each other. We introduce with this thesis a novel analysis approach, capable of determining such patterns automatically. This analysis provides a unique fingerprint for metastable motifs, that is based exclusively on structural information. The rational behind the method and its functioning will be presented, followed by a discussion regarding its application to a wide range of problems in materials science and biology. We will begin by showing how it is possible to use our methodology to define adaptively the hydrogen bond in some different systems, including water, ammonia and peptides. We will then demonstrate how such definition can be used to probe the topological defects in the 3-dimensional hydrogen bond network of liquid water and will propose a method to study the non-trivial correlations among them. Furthermore, we will apply our framework to the identification of coordination environments in nanoclusters, and to the recognition of secondary-structure patterns in oligopeptides and proteins. We will prove that it is not only possible to obtain an algorithmic definition, which is unbiased and adaptive, of local motifs of matter, but also to identify and classify structures in their entirety. We will also demonstrate that a clear interpretation of the stability of the system can be obtained through the automatic analysis of atomistic simulation results, and will discuss possible applications, such as the definition of collective variables for enhanced-sampling simulation techniques or the identification of recurrent patterns in complex systems that escape an interpretation in terms of conventional structural motifs, such as intrinsically disordered proteins.