A physicochemical descriptor-based scoring scheme for effective and rapid filtering of kinase-like chemical space

Incorporating Synthetic Accessibility in Drug Design: Predicting Reaction Yields of Suzuki Cross-Couplings by Leveraging AbbVie's 15-Year Parallel Library Data Set

Despite the increased use of computational tools to supplement medicinal chemists' expertise and intuition in drug design, predicting synthetic yields in medicinal chemistry endeavors remains an unsolved challenge. Existing design workflows could profoundly benefit from reaction yield prediction, as precious material waste could be reduced, and a greater number of relevant compounds could be delivered to advance the design, make, test, analyze (DMTA) cycle. In this work, we detail the evaluation of AbbVie's medicinal chemistry library data set to build machine learning models for the prediction of Suzuki coupling reaction yields. The combination of density functional theory (DFT)-derived features and Morgan fingerprints was identified to perform better than one-hot encoded baseline modeling, furnishing encouraging results. Overall, we observe modest generalization to unseen reactant structures within the 15-year retrospective library data set. Additionally, we compare predictions made by the model to those made by expert medicinal chemists, finding that the model can often predict both reaction success and reaction yields with greater accuracy. Finally, we demonstrate the application of this approach to suggest structurally and electronically similar building blocks to replace those predicted or observed to be unsuccessful prior to or after synthesis, respectively. The yield prediction model was used to select similar monomers predicted to have higher yields, resulting in greater synthesis efficiency of relevant drug-like molecules.

Maximizing the integration of virtual and experimental screening in hit discovery

INTRODUCTION

Experimental and virtual screening contributes to the discovery of more than 50% of clinical candidates. Considering the similar concept and goals, early-phase drug discovery would benefit from the effective integration of these approaches.

AREAS COVERED

After reviewing the recent trends in both experimental and virtual screening, the authors discuss different integration strategies from parallel, focused, sequential, and iterative screening. Strategic considerations are demonstrated in a number of real-life case studies.

EXPERT OPINION

Experimental and virtual screening are complementary approaches that should be integrated in lead discovery settings. Virtual screening can access extremely large synthetically feasible chemical space that can be effectively searched on GPU clusters or cloud architectures. Experimental screening provides reliable datasets by quantitative HTS applications, and DNA-encoded libraries (DEL) have enlarged the chemical space covered by these technologies. These developments, together with the use of artificial intelligence methods, represent new options for their efficient integration. The case studies discussed here demonstrate the benefits of complementary strategies, such as focused and iterative screening.

Drug-likeness scoring based on unsupervised learning

Drug-likeness prediction is important for the virtual screening of drug candidates. It is challenging because the drug-likeness is presumably associated with the whole set of necessary properties to pass through clinical trials, and thus no definite data for regression is available. Recently, binary classification models based on graph neural networks have been proposed but with strong dependency of their performances on the choice of the negative set for training. Here we propose a novel unsupervised learning model that requires only known drugs for training. We adopted a language model based on a recurrent neural network for unsupervised learning. It showed relatively consistent performance across different datasets, unlike such classification models. In addition, the unsupervised learning model provides drug-likeness scores that well separate distributions with increasing mean values in the order of datasets composed of molecules at a later step in a drug development process, whereas the classification model predicted a polarized distribution with two extreme values for all datasets presumably due to the overconfident prediction for unseen data. Thus, this new concept offers a pragmatic tool for drug-likeness scoring and further can be applied to other biochemical applications.

Automated and enabling technologies for medicinal chemistry

Having always been driven by the need to get new treatments to patients as quickly as possible, drug discovery is a constantly evolving process. This chapter will review how medicinal chemistry was established, how it has changed over the years due to the emergence of new enabling technologies, and how early advances in synthesis, purification and analysis, have provided the foundations upon which the current automated and enabling technologies are built. Looking beyond the established technologies, this chapter will also consider technologies that are now emerging, and their impact on the future of drug discovery and the role of medicinal chemists.

HerbiPAD: a free web platform to comprehensively analyze constitutive property and herbicide-likeness to estimate chemical bioavailability

BACKGROUND

Herbicides, as efficient weed control measures, play a crucial role in ensuring food security. The emergence of herbicide-resistant weeds has negatively affected food security and promoted the demand for new and improved herbicides. The balance between bioavailability and the potency of a compound is one of the most pressing challenges in the development of novel ideal herbicides. Herbicide-likeness analysis is crucial for the evaluation of this balance and thus may help to address this issue. Many herbicide-likeness analysis methods have been developed to screen potential novel lead compounds. However, there remains a lack of user-friendly and integrated tools to comprehensively evaluate herbicide-likeness.

RESULTS

Herbicide-likeness of compounds was assessed through integrated analysis incorporating the physicochemical properties of commercial herbicides, a qualitative rule, and three quantitative scoring functions developed for evaluating herbicide-likeness. HerbiPAD (http://agroda.gzu.edu.cn:9999/ccb/database/HerbiPAD/) is a free web platform integrated with the collected database and scoring model. This platform contains 542 approved herbicides and > 29 000 physicochemical descriptors. The accuracy of HerbiPAD in distinguishing known herbicides from nonherbicides was 84.2%. In the case study, HerbiPAD evaluated 60 new compounds from seven different herbicide targets, and the accuracy of predicting better bioavailability was 83.3%.

CONCLUSIONS

HerbiPAD was designed to quickly and efficiently evaluate herbicide-likeness by integrating qualitative and quantitative analyses. The simple and effective interpretation of the analysis interface may help noncomputational experts understand herbicide-likeness. © 2020 Society of Chemical Industry.

A drug-likeness toolbox facilitates ADMET study in drug discovery

Undesirable pharmacokinetic (PK) properties or unacceptable toxicity are the main causes of the failure of drug candidates at the clinical trial stage. Since the concept of drug-likeness was first proposed, it has become an important consideration in the selection of compounds with desirable bioavailability during the early phases of drug discovery. Over the past decade, online resources have effectively facilitated drug-likeness studies in an economical and time-efficient manner. Here, we provide a comprehensive summary and comparison of current accessible online resources, in terms of their key features, application fields, and performance for in silico drug-likeness studies. We hope that the assembled toolbox will provide useful guidance to facilitate future in silico drug-likeness research.

A physicochemical descriptor based method for effective and rapid screening of dual inhibitors against BACE-1 and GSK-3β as targets for Alzheimer's disease

Due to multifactorial nature of Alzheimer's disease one target-one ligand hypothesis often looks insufficient. BACE-1 and GSK-3β are well established therapeutic drug targets and interaction between BACE-1 and GSK-3β pathways has also been established. Thus, designing of dual inhibitor for these two targets seems rational and may provide effective therapeutic strategies against AD. Recent studies revealed that only two scaffolds i.e. triazinone and curcumin act as a dual inhibitor against BACE-1 and GSK-3β. Thus, this discovery set the path to screen new chemical entities from a vast chemical space (∼10⁶⁰ compounds) that inhibit both the targets. However, small part of the large chemical space will only show biological activity for specific targets. Virtual screening of large libraries is impractical and computational expensive especially in case of dual inhibitor design. In the case of dual or multi target inhibitor designing, we screened the database for each target that further increases time and resources. In this study we have done physicochemical descriptor based profiling to know the biological relevant chemical space for BACE-1 and GSK-3β inhibitors and proposed the suitable range of important physicochemical properties, occurrence of functional groups. We generated scaffolds tree of known inhibitors of BACE-1 and GSK-3β suggesting the common structure/fragment that can be used to design dual inhibitors. This approach can filter the potential dual inhibitor candidates of BACE-1 and GSK-3β from non inhibitors.

Cheminformatic characterization of natural products from Panama

In this work, we discuss the characterization and diversity analysis of 354 natural products (NPs) from Panama, systematically analyzed for the first time. The in-house database was compared to NPs from Brazil, compounds from Traditional Chinese Medicine, natural and semisynthetic collections used in high-throughput screening, and compounds from ChEMBL. An analysis of the "global diversity" was conducted using molecular properties of pharmaceutical interest, three molecular fingerprints of different design, molecular scaffolds, and molecular complexity. The global diversity was visualized using consensus diversity plots that revealed that the secondary metabolites in the Panamanian flora have a large scaffold diversity as compared to other composite databases and also have several unique scaffolds. The large scaffold diversity is in agreement with the broad range of biological activities that this collection of NPs from Panama has shown. This study also provided further quantitative evidence of the large structural complexity of NPs. The results obtained in this study support that NPs from Panama are promising candidates to identify selective molecules and are suitable sources of compounds for virtual screening campaigns.

Property-based characterization of kinase-like ligand space for library design and virtual screening

A property-based desirability scoring scheme has been developed for kinase-focused library design and ligand-based pre-screening of large compound sets.

Identification of novel compounds for human bitter taste receptors

The finely tuned bitter taste sensing in humans is orchestrated by a group of 25 bitter taste receptors (TAS2Rs), which belong to the G-protein-coupled receptor superfamily. TAS2Rs are expressed in the specialized taste bud cells of the gustatory system and perceive a plethora of bitter substances with versatile structures. To date, more than one hundred bitter ligands have been matched with their cognate receptors, but the understanding of the molecular mechanisms of TAS2Rs remains limited. Additionally, the extraoral expression of TAS2R genes was found in the gastrointestinal tract and respiratory system, which suggests other important physiological functions for TAS2Rs. To gain insight into the physiological functions of TAS2Rs, we established a heterologous expression system and characterized the response of 24 TAS2Rs against a library of potential bitter compounds. Among these bitter compounds of interest, 18 bitter compounds activated 16 TAS2Rs, representing 42 tastant-receptor pairs. We then calculated 14 descriptor properties for the 18 positive compounds. By comparison with 102 previously annotated bitter compounds in the database, we discovered common descriptor properties that may contribute to the discovery of additional bitter ligands and further expand the known molecular receptive ranges of human TAS2Rs.

DrugMint: a webserver for predicting and designing of drug-like molecules

BACKGROUND

Identification of drug-like molecules is one of the major challenges in the field of drug discovery. Existing approach like Lipinski rule of 5 (Ro5), Operea have their own limitations. Thus, there is a need to develop computational method that can predict drug-likeness of a molecule with precision. In addition, there is a need to develop algorithm for screening chemical library for their drug-like properties.

RESULTS

In this study, we have used 1347 approved and 3206 experimental drugs for developing a knowledge-based computational model for predicting drug-likeness of a molecule. We have used freely available PaDEL software for computing molecular fingerprints/descriptors of the molecules for developing prediction models. Weka software has been used for feature selection in order to identify the best fingerprints. We have developed various classification models using different types of fingerprints like Estate, PubChem, Extended, FingerPrinter, MACCS keys, GraphsOnlyFP, SubstructureFP, Substructure FPCount, Klekota-RothFP, Klekota-Roth FPCount. It was observed that the models developed using MACCS keys based fingerprints, discriminated approved and experimental drugs with higher precision. Our model based on one hundred fifty nine MACCS keys predicted drug-likeness of the molecules with 89.96% accuracy along with 0.77 MCC. Our analysis indicated that MACCS keys (ISIS keys) 112, 122, 144, and 150 were highly prevalent in the approved drugs. The screening of ZINC (drug-like) and ChEMBL databases showed that around 78.33% and 72.43% of the compounds present in these databases had drug-like potential.

CONCLUSION

It was apparent from above study that the binary fingerprints could be used to discriminate approved and experimental drugs with high accuracy. In order to facilitate researchers working in the field of drug discovery, we have developed a webserver for predicting, designing, and screening novel drug-like molecules (http://crdd.osdd.net/oscadd/drugmint/).