Antiproliferative Activity Predictor: A New Reliable In Silico Tool for Drug Response Prediction against NCI60 Panel

Abstract

In vitro antiproliferative assays still represent one of the most important tools in the anticancer drug discovery field, especially to gain insights into the mechanisms of action of anticancer small molecules. The NCI-DTP (National Cancer Institute Developmental Therapeutics Program) undoubtedly represents the most famous project aimed at rapidly testing thousands of compounds against multiple tumor cell lines (NCI60). The large amount of biological data stored in the National Cancer Institute (NCI) database and many other databases has led researchers in the fields of computational biology and medicinal chemistry to develop tools to predict the anticancer properties of new agents in advance. In this work, based on the available antiproliferative data collected by the NCI and the manipulation of molecular descriptors, we propose the new in silico Antiproliferative Activity Predictor (AAP) tool to calculate the GI₅₀ values of input structures against the NCI60 panel. This ligand-based protocol, validated by both internal and external sets of structures, has proven to be highly reliable and robust. The obtained GI₅₀ values of a test set of 99 structures present an error of less than ±1 unit. The AAP is more powerful for GI₅₀ calculation in the range of 4-6, showing that the results strictly correlate with the experimental data. The encouraging results were further supported by the examination of an in-house database of curcumin analogues that have already been studied as antiproliferative agents. The AAP tool identified several potentially active compounds, and a subsequent evaluation of a set of molecules selected by the NCI for the one-dose/five-dose antiproliferative assays confirmed the great potential of our protocol for the development of new anticancer small molecules. The integration of the AAP tool in the free web service DRUDIT provides an interesting device for the discovery and/or optimization of anticancer drugs to the medicinal chemistry community. The training set will be updated with new NCI-tested compounds to cover more chemical spaces, activities, and cell lines. Currently, the same protocol is being developed for predicting the TGI (total growth inhibition) and LC₅₀ (median lethal concentration) parameters to estimate toxicity profiles of small molecules.

Keywords: DRUDIT; GI50; NCI60; antiproliferative activity predictor; ligand-based tools; molecular descriptors.

Figure 1

Flowchart of the antiproliferative predictor protocol: GI_50i is the GI₅₀ value for cell line, S is the fingerprint score, GI_50i(FP) is the GI₅₀ value predicted by the FP module, and GI_50i(CL) is the GI₅₀ value assigned by the CL module.

Figure 2

NCI selection data used in the AAP tool: compounds screened in five-dose assay and published until 2014 were used as training set; the 5‰ of these structures was used for the internal validation of the protocol (panels A,C,D); those structures screened in five-dose assay and published until 2016 were used as test set to evaluate the predictive performance of the entire protocol (panels B,E).

Figure 3

Template building process.

Figure 4

Graphical representation of GI₅₀ prediction by the CL module for a cell line. D1, D2…Dn: molecular descriptors values for the input structure.

Figure 5

|DTV(GI₅₀)| vs. frequencies of the data for the external test validation.

Figure 6

Curcumin and curcumin-like biologically active compounds.

Figure 7

In-house structure database of curcumin-like compounds investigated by the AAP tool.

Scheme 1

Synthesis of cinnamils 1a–o.

Scheme 2

Synthesis of 1,2,4-oxadiazole derivatives 2a–e.

Scheme 3

Synthesis of 1,3,4-oxadiazole derivatives 3a–e.

Figure 8

Chemical structures of the five curcumin-like compounds selected by NCI for the one-dose antiproliferative assay.

Figure 9

(a) Comparison between AAP-predicted GI₅₀ values and the corresponding experimental GI₅₀ values measured by NCI for the two selected compounds, 1a and 3e (inside each bar, the corresponding GI₅₀ value is indicated). (b) Mean error graphs for the two selected compounds, 1a and 3e.

Figure 9

(a) Comparison between AAP-predicted GI₅₀ values and the corresponding experimental GI₅₀ values measured by NCI for the two selected compounds, 1a and 3e (inside each bar, the corresponding GI₅₀ value is indicated). (b) Mean error graphs for the two selected compounds, 1a and 3e.

Figure 10

Performance of AAP vs. pdCSM-cancer tools: blue and red vertical lines indicate the |DTV(GI₅₀)| for the AAP and pdCSM tools, respectively.