QPHAR: quantitative pharmacophore activity relationship: method and validation

QSAR methods are widely applied in the drug discovery process, both in the hit‐to‐lead and lead optimization phase, as well as in the drug-approval process. Most QSAR algorithms are limited to using molecules as input and disregard pharmacophores or pharmacophoric features entirely. However, due to the high level of abstraction, pharmacophore representations provide some advantageous properties for building quantitative SAR models. The abstract depiction of molecular interactions avoids a bias towards overrepresented functional groups in small datasets. Furthermore, a well‐crafted quantitative pharmacophore model can generalise to underrepresented or even missing molecular features in the training set by using pharmacophoric interaction patterns only. This paper presents a novel method to construct quantitative pharmacophore models and demonstrates its applicability and robustness on more than 250 diverse datasets. fivefold cross-validation on these datasets with default settings yielded an average RMSE of 0.62, with an average standard deviation of 0.18. Additional cross-validation studies on datasets with 15–20 training samples showed that robust quantitative pharmacophore models could be obtained. These low requirements for dataset sizes render quantitative pharmacophores a viable go-tomethod for medicinal chemists, especially in the lead-optimisation stage of drug discovery projects.

Deep Generative Design with 3D Pharmacophoric Constraints

Generative models have increasingly been proposed as a solution to the molecular design problem. However, it has proved challenging to control the design process or incorporate prior knowledge, limiting their practical use in drug discovery. In particular, generative methods have made limited use of three-dimensional (3D) structural information even though this is critical to binding. This work describes a method to incorporate such information and demonstrates the benefit of doing so. We combine an existing graph-based deep generative model, DeLinker, with a convolutional neural network to utilise physically-meaningful 3D representations of molecules and target pharmacophores. We apply our model, DEVELOP, to both linker and R-group design, demonstrating its suitability for both hit-to-lead and lead optimisation. The 3D pharmacophoric information results in improved generation and allows greater control of the design process. In multiple large-scale evaluations, we show that including 3D pharmacophoric constraints results in substantial improvements in the quality of generated molecules. On a challenging test set derived from PDBbind, our model improves the proportion of generated molecules with high 3D similarity to the original molecule by over 300%. In addition, DEVELOP recovers 10 × more of the original molecules compared to the base-line DeLinker method. Our approach is general-purpose, readily modifiable to alternate 3D representations, and can be incorporated into other generative frameworks. Code is available at https://github.com/oxpig/DEVELOP.

Lib-INVENT: Reaction Based Generative Scaffold Decoration for in silico Library Design

Due to the strong relationship between desired molecular activity to its structural core, screening of focused, core sharing chemical libraries is a key step in lead optimisation. Despite the plethora of current research focused on in silico methods for molecule generation, to our knowledge, no tool capable of designing such libraries has been proposed. In this work, we present a novel tool for de novo drug design called Lib-INVENT. This is capable of rapidly proposing chemical libraries of compounds sharing the same core while maximising a range of desirable properties. To further help the process of designing focused libraries, the user can list specific chemical reactions that can be used for the library creation. Lib-INVENT is therefore a flexible tool for generating virtual chemical libraries for lead optimisation in a broad range of scenarios. Additionally, the shared core ensures that the compounds in the library are similar, possessing desirable properties and can be also synthesized under the same or similar conditions.

Lib-INVENT: Reaction Based Generative Scaffold Decoration for in silico Library Design

Due to the strong relationship between desired molecular activity to its structural core, screening of focused, core sharing chemical libraries is a key step in lead optimisation. Despite the plethora of current research focused on in silico methods for molecule generation, to our knowledge, no tool capable of designing such libraries has been proposed. In this work, we present a novel tool for de novo drug design called Lib-INVENT. This is capable of rapidly proposing chemical libraries of compounds sharing the same core while maximising a range of desirable properties. To further help the process of designing focused libraries, the user can list specific chemical reactions that can be used for the library creation. Lib-INVENT is therefore a flexible tool for generating virtual chemical libraries for lead optimisation in a broad range of scenarios. Additionally, the shared core ensures that the compounds in the library are similar, possessing desirable properties and can be also synthesized under the same or similar conditions.

QPhAR – Quantitative Pharmacophore Activity Relationship: Method and Validation

QSAR methods are widely applied in the drug discovery process, both in the hit‑to‑lead and lead optimization phase, as well as in the drug-approval process. Most QSAR algorithms are limited to using molecules as input and disregard pharmacophores or pharmacophoric features entirely. However, due to the high level of abstraction, pharmacophore representations provide some advantageous properties for building quantitative SAR models. The abstract depiction of molecular interactions avoids a bias towards overrepresented functional groups in small datasets. Furthermore, a well‑crafted quantitative pharmacophore model can generalise to underrepresented or even missing molecular features in the training set by using pharmacophoric interaction patterns only. This paper presents a novel method to construct quantitative pharmacophore models and demonstrates its applicability and robustness on more than 250 diverse datasets. 5‑fold cross-validation on these datasets with default settings yielded an average RMSE of 0.62, with an average standard deviation of 0.18. Additional cross-validation studies on datasets with 15-20 training samples showed that robust quantitative pharmacophore models could be obtained. These low requirements for dataset sizes renders quantitative pharmacophores a viable go-to method for medicinal chemists, especially in the lead-optimisation stage of drug discovery projects.

The Use of In Silico Tools for the Toxicity Prediction of Potential Inhibitors of SARS-CoV-2

The current strategy for treating the Covid-19 coronavirus disease involves the repurposing of existing drugs or the use of convalescent plasma therapy, as no specific therapeutic intervention has yet received regulatory approval. However, severe adverse effects have been reported for some of these repurposed drugs. Recently, several in silico studies have identified compounds that are potential inhibitors of the main protease (3-chymotrypsin-like cysteine protease) and the nucleocapsid protein of SARS-CoV-2. An essential step of drug development is the careful evaluation of toxicity, which has a range of associated financial, temporal and ethical limitations. In this study, a number of in silico tools were used to predict the toxicity of 19 experimental compounds. A range of web-based servers and applications were used to predict hepatotoxicity, mutagenicity, acute oral toxicity, carcinogenicity, cardiotoxicity, and other potential adverse effects. The compounds were assessed based on the consensus of results, and were labelled as positive or negative for a particular toxicity endpoint. The compounds were then categorised into three classes, according to their predicted toxicity. Ten compounds (52.6%) were predicted to be non-mutagenic and non-hERG inhibitors, and exhibited zero or low level hepatotoxicity and carcinogenicity. Furthermore, from the consensus of results, all 19 compounds were predicted to be non-mutagenic and negative for acute oral toxicity. Overall, most of the compounds displayed encouraging toxicity profiles. These results can assist further lead optimisation studies and drug development efforts to combat Covid-19.

Fragments: where are we now?

Fragment-based drug discovery (FBDD) has become a mainstream technology for the identification of chemical hit matter in drug discovery programs. To date, the food and drug administration has approved four drugs, and over forty compounds are in clinical studies that can trace their origins to a fragment-based screen. The challenges associated with implementing an FBDD approach are many and diverse, ranging from the library design to developing methods for identifying weak affinity compounds. In this article, we give an overview of current progress in fragment library design, fragment to lead optimisation and on the advancement in techniques used for screening. Finally, we will comment on the future opportunities and challenges in this field.