Substituted 1,4-naphthoquinones for potential anticancer therapeutics: In vitro cytotoxic effects and QSAR-guided design of new analogs

Abstract

1,4-Naphthoquinone is a promising pharmacophore in drug discovery due to its unique redox reactive nature and wide-ranging bioactivities. Herein, a series of 1,4-naphthoquinones (1-14) were investigated for their anticancer activities against 4 cancer cell lines (i.e., HepG2, HuCCA-1, A549, and MOLT-3). Compound 11 was found to be the most potent and selective anticancer agent against all tested cell lines (IC₅₀ = 0.15 - 1.55 μM, selectivity index = 4.14 - 43.57). QSAR modelling was performed to elucidate key structural features influencing activities against four cancer cell lines. Four QSAR models were successfully constructed using multiple linear regression (MLR) algorithm providing good predictive performance (R: training set = 0.8928-0.9664; testing set = 0.7824-0.9157; RMSE: training set = 0.1755-0.2600; testing set = 0.2726-0.3748). QSAR models suggested that the potent anticancer activities of these naphthoquinones were mainly influenced by polarizability (MATS3p and BELp8), van der Waals volume (GATS5v, GATS6v, and Mor16v), mass (G1m), electronegativity (E1e), and dipole moment (Dipole and EEig15d) as well as ring complexity (RCI) and shape of the compound (SHP2). The models were further applied for guiding the design and predicting activities of an additional set of 248 structurally modified compounds in which the ones with promising predicted activities were highlighted for potential further development. Additionally, pharmacokinetic profiles and possible binding modes towards potential biological targets of the compounds were virtually assessed. Structure-activity relationship analysis was also conducted to highlight key structural features beneficial for further successful design of the related naphthoquinones.

Keywords: ADMET; Anticancer; Computer-aided drug design; Naphthoquinone; QSAR.

Graphical abstract

Fig. 1

Chemical structures of naphthoquinone derivatives (1-14).

Fig. 2

Overview workflow of the study. 1: A set of 14 original NQ derivatives were experimentally investigated for their cytotoxic effects. 2: Chemical structures of original compounds along with experimental IC₅₀ values were used for preparing dataset for QSAR modelling. 2.1: QSAR modelling was performed using multiple linear regression (MLR) algorithm to obtain 4 QSAR models. 2.2: The constructed models were used for guiding design and predicting activities of an additional set of 248 structurally modified compounds. 2.3: A set of promising newly designed compounds with good predicted activities and original compounds were investigated for their ADMET properties and potential biological targets. Structure-activity relationships were analyzed to highlight key structural features required for potent activities.

Fig. 3

Modification strategies for rational design of additional 248 compounds.

Fig. 4

Plots of experimental activities versus predicted activities from 4 QSAR models. A: HuCCA-1 model (N = 14), B: A549 model (N = 13), C: HepG2 model (N = 13), D: MOLT-3 model (N = 12). Plots of training set are presented as blue circles and blue solid regression lines whereas those of testing set (leave-one-out cross-validation) are shown as green circles and green regression lines. The points are labeled with compound’s number in red. Experimental and predicted pIC₅₀ values are grouped for each compound with dotted circles.

Fig. 5

Summary of top-ranking newly designed compounds with promising predicted activities.

Fig. 6

Summary of key structural features influencing potent predicted activities of newly designed compounds.

Fig. 7

Summary of potential biological targets of selected NQ compounds (10, 11, 14, 10g3, 11c7, 11c10, and 14i3). Values indicated probability (lowest = 0, and highest = 1). Red, blue, and yellow dotted lines indicated the relationships with probability value ranges of greater than 0.900, between 0.100 and 0.200, and between 0.030 and 0.099, respectively. List of abbreviations: Histone acetyltransferase p300 (EP300), Dual specificity phosphatase Cdc25B (CDC25B), Indoleamine 2,3-dioxygenase (IDO1), Carbonic anhydrase II (CA2), Serine/threonine-protein kinase PIM1(PIM1), Dual specificity mitogen-activated protein kinase kinase 1 (MAP2K1), Caspase-3 (CASP3), Intercellular adhesion molecule-1 (ICAM1), Vascular cell adhesion protein 1 (VCAM1), Toll-like receptor (TLR7/TLR9), Inhibitor of nuclear factor kappa B kinase beta subunit (IKBKB).

Fig. 8

Possible binding modes and 2D protein-ligand interaction diagrams of the selected naphthoquinones against three predicted targets. A: EP300 (PDB ID: 5KJ2), docked compounds 10 and 11 are illustrated in yellow and cyan, respectively. B: CDC25B (PDB ID: 4WH9), docked compounds 10, 11, 14, 11c7, and 11c10 are shown in yellow, cyan, pink, light blue, and dark blue, respectively. C: CA2 (PDB ID: 5NY6), docked compounds 14, 10g3, and 14i3 are displayed in pink, grey, and purple, respectively.