Integrated QSAR study for inhibitors of hedgehog signal pathway against multiple cell lines:a collaborative filtering method

Abstract

BackgroundThe Hedgehog Signaling Pathway is one of signaling pathways that are very important to embryonic development. The participation of inhibitors in the Hedgehog Signal Pathway can control cell growth and death, and searching novel inhibitors to the functioning of the pathway are in a great demand. As the matter of fact, effective inhibitors could provide efficient therapies for a wide range of malignancies, and targeting such pathway in cells represents a promising new paradigm for cell growth and death control. Current research mainly focuses on the syntheses of the inhibitors of cyclopamine derivatives, which bind specifically to the Smo protein, and can be used for cancer therapy. While quantitatively structure-activity relationship (QSAR) studies have been performed for these compounds among different cell lines, none of them have achieved acceptable results in the prediction of activity values of new compounds. In this study, we proposed a novel collaborative QSAR model for inhibitors of the Hedgehog Signaling Pathway by integration the information from multiple cell lines. Such a model is expected to substantially improve the QSAR ability from single cell lines, and provide useful clues in developing clinically effective inhibitors and modifications of parent lead compounds for target on the Hedgehog Signaling Pathway.ResultsIn this study, we have presented: (1) a collaborative QSAR model, which is used to integrate information among multiple cell lines to boost the QSAR results, rather than only a single cell line QSAR modeling. Our experiments have shown that the performance of our model is significantly better than single cell line QSAR methods; and (2) an efficient feature selection strategy under such collaborative environment, which can derive the commonly important features related to the entire given cell lines, while simultaneously showing their specific contributions to a specific cell-line. Based on feature selection results, we have proposed several possible chemical modifications to improve the inhibitor affinity towards multiple targets in the Hedgehog Signaling Pathway.ConclusionsOur model with the feature selection strategy presented here is efficient, robust, and flexible, and can be easily extended to model large-scale multiple cell line/QSAR data. The data and scripts for collaborative QSAR modeling are available in the Additional file 1.

When drug discovery meets web search: Learning to Rank for ligand-based virtual screening

“…LOR can be categorized to the idea of multi-targets based QSAR modeling for VS. Our group has previous tested other three multiple targets based QSAR schemas [ 24 , 25 ] such as multi-task learning based QSAR modeling [ 26 ], collaborative filtering based QSAR modeling [ 27 ] and Proteochemometric Modeling (PCM) [ 28 , 29 ]. Compared to traditional VS methods, essentially all these methods can be used to integrate multiple target information rather than the single one.…”

“…Only human protein targets are considered; (2) The redundancy of protein targets are eliminated; (3) The protein targets are selected to cover as many protein families as possible, and the proteins from the same family are avoid to be selected again as much as possible once other members in this family were selected; (4) To keep the data balanced, only targets with non-redundant ligands record number between 500 and 1,500 are considered; and (5) The affinity distribution of the compounds associated with a given target should be even. Taking pIC50 value as the affinity measurement, normally a compound is considered to be active if its pIC50 value is higher than 6 (pIC50 ≥ 6) [ 27 ], and inactive vise verse. The affinity was roughly graded into 5 categories as 0 (pIC50 < 6), 1 (6 ≤ pIC50 < 7), 2 (7 ≤ pIC50 < 8), 3 (8 ≤ pIC50 < 9), 4 (9 ≤ pIC50) according to reported literatures and we required that the associated compound affinity value should cover these 5 grades evenly.…”

Improving Phylogenetic Tree Accuracy through Recommending Missing Metabolic pathways: A Collaborative Filtering Approach

“…When an entity participates in several relations, Collective Matrix Factorization Model (CMFM) can simultaneously factorize multiple matrices which share parameters among factors, that is, with multiple relations, formatted into matrices. CMFM attempt to exploit information from observed relations to predict unknown ones (Gao, et al, 2012;Singh & Gordon, 2008). …”

A desirability-based multi objective approach for the virtual screening discovery of broad-spectrum anti-gastric cancer agents

“…Multi-species QSAR models can achieve high retrieval rates (72–85%) and moderately low false-fit rates (15–28%) [ 8 ]. More recently, multi-target QSAR models have been developed that incorporate data from several cell lines by a sort of multi-species strategy [ 13 ]. According to the authors of the study, the integration of experimental data from multiple cell lines into the QSAR pipeline provided several advantages compared to single cell line QSAR modeling.…”

“…According to the authors of the study, the integration of experimental data from multiple cell lines into the QSAR pipeline provided several advantages compared to single cell line QSAR modeling. Among the advantages, authors mentioned that the use of data from multiple cell lines resulted in i) better handling the inherent noise of experimental activity measurements and ii) reducing the detrimental effects that arise from the relatively small number of training data that is commonly available for a single cell line [ 13 ].…”