Structure-activity models of oral clearance, cytotoxicity, and LD50: A screen for promising anticancer compounds

Department of Experimental Therapeutics, University of Texas M, D, Anderson Cancer Center, 8000 El Rio, Houston, TX 77054, USA.
BMC Pharmacology (Impact Factor: 1.84). 02/2008; 8(1):12. DOI: 10.1186/1471-2210-8-12
Source: PubMed


Quantitative structure-activity relationship (QSAR) models have become popular tools to help identify promising lead compounds in anticancer drug development. Few QSAR studies have investigated multitask learning, however. Multitask learning is an approach that allows distinct but related data sets to be used in training. In this paper, a suite of three QSAR models is developed to identify compounds that are likely to (a) exhibit cytotoxic behavior against cancer cells, (b) exhibit high rat LD50 values (low systemic toxicity), and (c) exhibit low to modest human oral clearance (favorable pharmacokinetic characteristics). Models were constructed using Kernel Multitask Latent Analysis (KMLA), an approach that can effectively handle a large number of correlated data features, nonlinear relationships between features and responses, and multitask learning. Multitask learning is particularly useful when the number of available training records is small relative to the number of features, as was the case with the oral clearance data.
Multitask learning modestly but significantly improved the classification precision for the oral clearance model. For the cytotoxicity model, which was constructed using a large number of records, multitask learning did not affect precision but did reduce computation time. The models developed here were used to predict activities for 115,000 natural compounds. Hundreds of natural compounds, particularly in the anthraquinone and flavonoids groups, were predicted to be cytotoxic, have high LD50 values, and have low to moderate oral clearance.
Multitask learning can be useful in some QSAR models. A suite of QSAR models was constructed and used to screen a large drug library for compounds likely to be cytotoxic to multiple cancer cell lines in vitro, have low systemic toxicity in rats, and have favorable pharmacokinetic properties in humans.

1 Follower
6 Reads
  • Source
    • "Regression and classification models were built using KMLA (kernel multitask latent analysis), an approach developed by Xiang and Bennett [28] based on earlier work by Momma and Bennett [29] and used here with minor changes [19]. Briefly, KMLA is closely related to partial least squares (PLS) [30] and can be used for many of the same problems, although it has several distinct differences. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Safer and more effective mixtures of anticancer drugs are needed, and modeling can assist in this endeavor. This paper describes classification models that were constructed to predict which fixed-ratio mixtures created from a pool of 10 drugs would show a high degree of in-vitro synergism against H460 human lung cancer cells. One of the tested drugs was doxorubicin and the others were natural compounds including quercetin, curcumin, and EGCG. Explanatory variables were based on virtual docking profiles. Docking profiles for the 10 drugs were obtained for 1087 proteins using commercial docking software. The cytotoxicity of all 10 drugs and of 45 of the 1,013 possible mixtures was tested in the laboratory and synergism indices were generated using the MixLow method. Model accuracy was assessed using cross validation, as well as using predictions on a new set of 10 tested mixtures. Results were compared to models where explanatory variables were constructed using the pseudomolecule approach of Sheridan. On this data set, the pseudomolecule and docking data approach produce models of similar accuracy. Leave-one-out precision for the negative (highly synergistic) class and the positive (low- or non-synergistic) class was 0.73 and 0.80, respectively. Precision for a nonstandard leave-many-out cross validation procedure was 0.60 and 0.77 for the negative and positive classes, respectively. Useful classification models can be constructed to predict drug synergism, even in those situations where a limited subset of component drugs can be tested. Compared to the pseudomolecule approach, the virtual docking approach has the advantage of greater potential for biologic interpretation. This distinction may become important as virtual docking software becomes more accurate and docking results more closely resemble actual binding affinities. This is the first published report of a model designed to predict the degree of in-vitro synergism based on the pseudomolecule or docking data approach.
    BMC Pharmacology 02/2008; 8(1):13. DOI:10.1186/1471-2210-8-13 · 1.84 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Pinostrobin (5-hydroxy-7-methoxyflavanone) obtained in relatively large amounts from fingerroot (Boesenbergia pandurata) was converted to its C-6 and C-8 prenylated derivatives. The Mitsunobu reaction, europium(III)-catalyzed Claisen-Cope rearrangement, and Claisen reaction coupled with cross-metathesis were used as the key steps. Using a sealed-vessel microwave reactor, the Mitsunobu and Claisen/Cope reactions occurred smoothly with short reaction times and in satisfactory yields. The target compounds and five new intermediary substances showed cytotoxic activity toward SK-BR-3, MCF-7, PC-3, and Colo-320DM human tumor cell lines, and all of them had significantly lower IC(50) (microM) values than pinostrobin.
    Bioorganic & medicinal chemistry letters 02/2010; 20(7):2086-9. DOI:10.1016/j.bmcl.2010.02.068 · 2.42 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Flavonoids have shown anticarcinogenic activity in cancer cell lines, animal models, and some human studies. Quantitative structure-activity relationship (QSAR) models have become useful tools for identification of promising lead compounds in anticancer drug development. However, epidemiological and clinical studies are still scarce. Compounds with flavonoid scaffold have been the subject of many mechanistic studies in cells, but information on human chemopreventive properties is still missing. The knowledge of the mechanisms of action, anti-multidrug resistance, and QSAR studies on flavonoids and related compounds may help to enhance research on these compounds and their bioactivity. Therefore, once the issue is introduced, the mechanisms involved, and QSAR studies developed to predict the activity and toxicity of these chemicals to biological systems are discussed. QSAR studies on flavonoids as inhibitors of breast cancer resistance protein (BCRP/ABCG2), 17β-hydroxysteroid dehydrogenase (17β-HSD), PIM-1 kinase and cyclin-dependent kinases (CDKs) are analyzed. Combined treatment of flavonoids with TRAIL and current chemotherapy agents is also discussed as a promising cancer chemoprevention and/or therapy.
    Current Medicinal Chemistry 07/2012; 19(25):4324-47. DOI:10.2174/092986712802884277 · 3.85 Impact Factor
Show more

Similar Publications

Preview (2 Sources)

6 Reads
Available from