Prospective performance evaluation of selected common virtual screening tools. Case study: Cyclooxygenase (COX) 1 and 2

Abstract

Computational methods can be applied in drug development for the identification of novel lead candidates, but also for the prediction of pharmacokinetic properties and potential adverse effects, thereby aiding to prioritize and identify the most promising compounds. In principle, several techniques are available for this purpose, however, which one is the most suitable for a specific research objective still requires further investigation. Within this study, the performance of several programs, representing common virtual screening methods, was compared in a prospective manner. First, we selected top-ranked virtual screening hits from the three methods pharmacophore modeling, shape-based modeling, and docking. For comparison, these hits were then additionally predicted by external pharmacophore- and 2D similarity-based bioactivity profiling tools. Subsequently, the biological activities of the selected hits were assessed in vitro, which allowed for evaluating and comparing the prospective performance of the applied tools. Although all methods performed well, considerable differences were observed concerning hit rates, true positive and true negative hits, and hitlist composition. Our results suggest that a rational selection of the applied method represents a powerful strategy to maximize the success of a research project, tightly linked to its aims. We employed cyclooxygenase as application example, however, the focus of this study lied on highlighting the differences in the virtual screening tool performances and not in the identification of novel COX-inhibitors.

Synthesis and biological evaluation of fluorinated 1,5-diarylpyrrole-3-alkoxyethyl ether derivatives as selective COX-2 inhibitors endowed with anti-inflammatory activity

“…In particular, very recently novel chemical entities have been identified by different approaches such as: i) rational design providing novel scaffolds based on 4-phenylpyrimidine-2(1H)-thiones [8] and, indole based peptidomimetics [9], or ii) computational procedures providing novel and structurally unrelated COX-2 inhibitors [10].…”

In Silico Predictions of Drug – Drug Interactions Caused by CYP1A2, 2C9 and 3A4 Inhibition – a Comparative Study of Virtual Screening Performance

“…However, a systematic and prospective investigation of the applicability of these tools for the different stages and tasks in drug development has not been accomplished so far. We already analyzed the suitability of different pharmacophore‐, shape‐, and 2D similarity‐based methods, and docking for cyclooxygenases (COX) 1 and 2 40. We applied COX as representative of classical enzymes that catalyze the production of specific endogenous molecules according to the physiological requirements.…”

“…In contrast to that target class, we investigated CYP enzymes interacting with a large variety of exogenous molecules in this study. In the COX‐study, we observed large differences in the performance of these programs,40 suggesting the need of a critical selection of the screening method for performing in silico activity predictions. Compared to classical enzymes, xenobiotic metabolizing proteins have to fulfill a completely different biological function, and therefore also differ in their structural features.…”

Neccessasity of Bio-imaging Hybrid Approaches Accelerating Drug Discovery Process (Mini-Review)

“…To elaborate the virtual screening process for drug discovery, authors of [25,24] evaluated common virtual screening tool, which is used to identify novel bioactive molecules for cyclooxygenases-1 and -2 as representatives of classical enzymes [25] and to identify novel peroxisome proliferator-activated receptor (PPARγ) ligands [24]. PPARγ belongs to nuclear receptor class, and is a valuable drug target.…”