Descriptor collision and confusion: Toward the design of descriptors to mask chemical structures

QSAR Modeling of SARS-CoV Mpro Inhibitors Identifies Sufugolix, Cenicriviroc, Proglumetacin, and other Drugs as Candidates for Repurposing against SARS-CoV-2

The main protease (M^pro) of the SARS-CoV-2 has been proposed as one of the major drug targets for COVID-19. We have identified the experimental data on the inhibitory activity of compounds tested against the closely related (96 % sequence identity, 100 % active site conservation) M^pro of SARS-CoV. We developed QSAR models of these inhibitors and employed these models for virtual screening of all drugs in the DrugBank database. Similarity searching and molecular docking were explored in parallel, but docking failed to correctly discriminate between experimentally active and inactive compounds, so it was not relied upon for prospective virtual screening. Forty-two compounds were identified by our models as consensus computational hits. Subsequent to our computational studies, NCATS reported the results of experimental screening of their drug collection in SARS-CoV-2 cytopathic effect assay (https://opendata.ncats.nih.gov/covid19/). Coincidentally, NCATS tested 11 of our 42 hits, and three of them, cenicriviroc (AC₅₀ of 8.9 μM), proglumetacin (tested twice independently, with AC₅₀ of 8.9 μM and 12.5 μM), and sufugolix (AC₅₀ 12.6 μM), were shown to be active. These observations support the value of our modeling approaches and models for guiding the experimental investigations of putative anti-COVID-19 drug candidates. All data and models used in this study are publicly available via Supplementary Materials, GitHub (https://github.com/alvesvm/sars-cov-mpro), and Chembench web portal (https://chembench.mml.unc.edu/).

Building attention and edge message passing neural networks for bioactivity and physical-chemical property prediction

Neural Message Passing for graphs is a promising and relatively recent approach for applying Machine Learning to networked data. As molecules can be described intrinsically as a molecular graph, it makes sense to apply these techniques to improve molecular property prediction in the field of cheminformatics. We introduce Attention and Edge Memory schemes to the existing message passing neural network framework, and benchmark our approaches against eight different physical–chemical and bioactivity datasets from the literature. We remove the need to introduce a priori knowledge of the task and chemical descriptor calculation by using only fundamental graph-derived properties. Our results consistently perform on-par with other state-of-the-art machine learning approaches, and set a new standard on sparse multi-task virtual screening targets. We also investigate model performance as a function of dataset preprocessing, and make some suggestions regarding hyperparameter selection.

Bigger data, collaborative tools and the future of predictive drug discovery

Over the past decade we have seen a growth in the provision of chemistry data and cheminformatics tools as either free websites or software as a service commercial offerings. These have transformed how we find molecule-related data and use such tools in our research. There have also been efforts to improve collaboration between researchers either openly or through secure transactions using commercial tools. A major challenge in the future will be how such databases and software approaches handle larger amounts of data as it accumulates from high throughput screening and enables the user to draw insights, enable predictions and move projects forward. We now discuss how information from some drug discovery datasets can be made more accessible and how privacy of data should not overwhelm the desire to share it at an appropriate time with collaborators. We also discuss additional software tools that could be made available and provide our thoughts on the future of predictive drug discovery in this age of big data. We use some examples from our own research on neglected diseases, collaborations, mobile apps and algorithm development to illustrate these ideas.

Sharing chemical relationships does not reveal structures

In this study, we propose a new, secure method of sharing useful chemical information from small-molecule libraries, without revealing the structures of the libraries' molecules. Our method shares the relationship between molecules rather than structural descriptors. This is an important advance because, over the past few years, several groups have developed and published new methods of analyzing small-molecule screening data. These methods include advanced hit-picking protocols, promiscuous active filters, economic optimization algorithms, and screening visualizations, which can identify patterns in the data that might otherwise be overlooked. Application of these methods to private data requires finding strategies for sharing useful chemical data without revealing chemical structures. This problem has been examined in the context of ADME prediction models, with results from information theory suggesting it is impossible to share useful chemical information without revealing structures. In contrast, we present a new strategy for encoding the relationships between molecules instead of their structures, based on anonymized scaffold networks and trees, that safely shares enough chemical information to be useful in analyzing chemical data, while also sufficiently blinding structures from discovery. We present the details of this encoding, an analysis of the usefulness of the information it conveys, and the security of the structures it encodes. This approach makes it possible to share data across institutions, and may securely enable collaborative analysis that can yield insight into both specific projects and screening technology as a whole.

Inroads to predict in vivo toxicology-an introduction to the eTOX Project

There is a widespread awareness that the wealth of preclinical toxicity data that the pharmaceutical industry has generated in recent decades is not exploited as efficiently as it could be. Enhanced data availability for compound comparison (“read-across”), or for data mining to build predictive tools, should lead to a more efficient drug development process and contribute to the reduction of animal use (3Rs principle). In order to achieve these goals, a consortium approach, grouping numbers of relevant partners, is required. The eTOX (“electronic toxicity”) consortium represents such a project and is a public-private partnership within the framework of the European Innovative Medicines Initiative (IMI). The project aims at the development of in silico prediction systems for organ and in vivo toxicity. The backbone of the project will be a database consisting of preclinical toxicity data for drug compounds or candidates extracted from previously unpublished, legacy reports from thirteen European and European operation-based pharmaceutical companies. The database will be enhanced by incorporation of publically available, high quality toxicology data. Seven academic institutes and five small-to-medium size enterprises (SMEs) contribute with their expertise in data gathering, database curation, data mining, chemoinformatics and predictive systems development. The outcome of the project will be a predictive system contributing to early potential hazard identification and risk assessment during the drug development process. The concept and strategy of the eTOX project is described here, together with current achievements and future deliverables.

IGERS: inferring Gibbs energy changes of biochemical reactions from reaction similarities

Mathematical analysis and modeling of biochemical reaction networks requires knowledge of the permitted directionality of reactions and membrane transport processes. This information can be gathered from the standard Gibbs energy changes (DeltaG(0)) of reactions and the concentration ranges of their reactants. Currently, experimental DeltaG(0) values are not available for the vast majority of cellular biochemical processes. We propose what we believe to be a novel computational method to infer the unknown DeltaG(0) value of a reaction from the known DeltaG(0) value of the chemically most similar reaction. The chemical similarity of two arbitrary reactions is measured by the relative number (T) of co-occurring changes in the chemical attributes of their reactants. Testing our method across a validated reference set of 173 biochemical reactions with experimentally determined DeltaG(0) values, we found that a minimum reaction similarity of T = 0.6 is required to infer DeltaG(0) values with an error of <10 kJ/mol. Applying this criterion, our method allows us to assign DeltaG(0) values to 458 additional reactions of the BioPath database. We believe our approach permits us to minimize the number of DeltaG(0) measurements required for a full coverage of a given reaction network with reliable DeltaG(0) values.