Limits...
Potential Compounds for Oral Cancer Treatment: Resveratrol, Nimbolide, Lovastatin, Bortezomib, Vorinostat, Berberine, Pterostilbene, Deguelin, Andrographolide, and Colchicine.

Bundela S, Sharma A, Bisen PS - PLoS ONE (2015)

Bottom Line: The molecular targets of the predicted anti-cancer compounds were mined from reliable sources like experimental bioassays studies associated with the compound, and from protein-compound interaction databases.The majority of the compounds in this list are natural products, which are well-tolerated and have minimal side-effects compared to the synthetic counterparts.Some of the potential therapeutic compounds identified in the current study are resveratrol, nimbolide, lovastatin, bortezomib, vorinostat, berberine, pterostilbene, deguelin, andrographolide, and colchicine.

View Article: PubMed Central - PubMed

Affiliation: Defence Research Development Establishment, Defence Research Development Organization, Ministry of Defence, Govt. of India, Gwalior, Madhya Pradesh, India.

ABSTRACT
Oral cancer is one of the main causes of cancer-related deaths in South-Asian countries. There are very limited treatment options available for oral cancer. Research endeavors focused on discovery and development of novel therapies for oral cancer, is necessary to control the ever rising oral cancer related mortalities. We mined the large pool of compounds from the publicly available compound databases, to identify potential therapeutic compounds for oral cancer. Over 84 million compounds were screened for the possible anti-cancer activity by custom build SVM classifier. The molecular targets of the predicted anti-cancer compounds were mined from reliable sources like experimental bioassays studies associated with the compound, and from protein-compound interaction databases. Therapeutic compounds from DrugBank, and a list of natural anti-cancer compounds derived from literature mining of published studies, were used for building partial least squares regression model. The regression model thus built, was used for the estimation of oral cancer specific weights based on the molecular targets. These weights were used to compute scores for screening the predicted anti-cancer compounds for their potential to treat oral cancer. The list of potential compounds was annotated with corresponding physicochemical properties, cancer specific bioactivity evidences, and literature evidences. In all, 288 compounds with the potential to treat oral cancer were identified in the current study. The majority of the compounds in this list are natural products, which are well-tolerated and have minimal side-effects compared to the synthetic counterparts. Some of the potential therapeutic compounds identified in the current study are resveratrol, nimbolide, lovastatin, bortezomib, vorinostat, berberine, pterostilbene, deguelin, andrographolide, and colchicine.

No MeSH data available.


Related in: MedlinePlus

Coarse Grid Search for C and γ for parameter estimation.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4633227&req=5

pone.0141719.g003: Coarse Grid Search for C and γ for parameter estimation.

Mentions: In the current study, we performed an exhaustive grid—search on C and γ using 5-fold cross-validation. After feature extraction and data transformation of the benchmark dataset (see section Feature Extraction), we first did a coarse grid search for finding best C and γ using 5-fold cross-validation. We first started with coarse grid search with an exponentially growing sequence of C and γ (C = 2−5, 2−4, 2−3…, 214, 215 and γ = 2−15, 2−14….24, 23), which gave us best parameters (C = 22 and γ = 2−2) with cross-validation accuracy of 80.99% (Fig 3). The parameters with cross-validation accuracy of over 80.5% are distinctly marked with green color in grid space of Fig 3, we next focused on fine grid search in this region.


Potential Compounds for Oral Cancer Treatment: Resveratrol, Nimbolide, Lovastatin, Bortezomib, Vorinostat, Berberine, Pterostilbene, Deguelin, Andrographolide, and Colchicine.

Bundela S, Sharma A, Bisen PS - PLoS ONE (2015)

Coarse Grid Search for C and γ for parameter estimation.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4633227&req=5

pone.0141719.g003: Coarse Grid Search for C and γ for parameter estimation.
Mentions: In the current study, we performed an exhaustive grid—search on C and γ using 5-fold cross-validation. After feature extraction and data transformation of the benchmark dataset (see section Feature Extraction), we first did a coarse grid search for finding best C and γ using 5-fold cross-validation. We first started with coarse grid search with an exponentially growing sequence of C and γ (C = 2−5, 2−4, 2−3…, 214, 215 and γ = 2−15, 2−14….24, 23), which gave us best parameters (C = 22 and γ = 2−2) with cross-validation accuracy of 80.99% (Fig 3). The parameters with cross-validation accuracy of over 80.5% are distinctly marked with green color in grid space of Fig 3, we next focused on fine grid search in this region.

Bottom Line: The molecular targets of the predicted anti-cancer compounds were mined from reliable sources like experimental bioassays studies associated with the compound, and from protein-compound interaction databases.The majority of the compounds in this list are natural products, which are well-tolerated and have minimal side-effects compared to the synthetic counterparts.Some of the potential therapeutic compounds identified in the current study are resveratrol, nimbolide, lovastatin, bortezomib, vorinostat, berberine, pterostilbene, deguelin, andrographolide, and colchicine.

View Article: PubMed Central - PubMed

Affiliation: Defence Research Development Establishment, Defence Research Development Organization, Ministry of Defence, Govt. of India, Gwalior, Madhya Pradesh, India.

ABSTRACT
Oral cancer is one of the main causes of cancer-related deaths in South-Asian countries. There are very limited treatment options available for oral cancer. Research endeavors focused on discovery and development of novel therapies for oral cancer, is necessary to control the ever rising oral cancer related mortalities. We mined the large pool of compounds from the publicly available compound databases, to identify potential therapeutic compounds for oral cancer. Over 84 million compounds were screened for the possible anti-cancer activity by custom build SVM classifier. The molecular targets of the predicted anti-cancer compounds were mined from reliable sources like experimental bioassays studies associated with the compound, and from protein-compound interaction databases. Therapeutic compounds from DrugBank, and a list of natural anti-cancer compounds derived from literature mining of published studies, were used for building partial least squares regression model. The regression model thus built, was used for the estimation of oral cancer specific weights based on the molecular targets. These weights were used to compute scores for screening the predicted anti-cancer compounds for their potential to treat oral cancer. The list of potential compounds was annotated with corresponding physicochemical properties, cancer specific bioactivity evidences, and literature evidences. In all, 288 compounds with the potential to treat oral cancer were identified in the current study. The majority of the compounds in this list are natural products, which are well-tolerated and have minimal side-effects compared to the synthetic counterparts. Some of the potential therapeutic compounds identified in the current study are resveratrol, nimbolide, lovastatin, bortezomib, vorinostat, berberine, pterostilbene, deguelin, andrographolide, and colchicine.

No MeSH data available.


Related in: MedlinePlus