A systematic approach to identify novel cancer drug targets using machine learning, inhibitor design and high-throughput screening

Jeon, Jouhyun; Nim, Satra; Teyra, Joan; Datti, Alessandro; Wrana, Jeffrey L.; Sidhu, Sachdev S.; Moffat, Jason; Kim, Philip M.

doi:10.1186/preaccept-8096551512514564

Cited by 27 publications

(37 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jeon et al (52) utilized SVM to learn five genomic features from various types of high-throughput data for the genome-wide identification of cancer therapeutic targets. These features include gene essentiality, expression level, mutation, copy number and closeness in a PPI network.…”

Section: Selecting Anticancer Drugs Warmuth Et Al (43) Used Activementioning

confidence: 99%

Applications of Support Vector Machine (SVM) Learning in Cancer Genomics

2018

CGP

582

347

View full text Add to dashboard Cite

Abstract. Machine learning with maximization (support) of separating margin (vector), called support vector machine (SVM) learning, is a powerful classification tool that hasMachine learning (ML) "learns" a model from past data in order to predict future data (1). The key process is the learning which is one of the artificial intelligences. Many different statistical, probabilistic, and optimization techniques can be implemented as the learning methods such as the logistic regression, artificial neural networks (ANN), K-nearest neighbor (KNN), decision trees (DT) and Naive Bayes. There are two main types of ML learning -supervised learning and unsupervised learning. The supervised learning builds a model by learning from known classes (labeled training data). In contrast, unsupervised learning methods learn the common features from unknown class data (unlabeled training data).ML algorithms have been used for key feature training and recognition and for group classification. The strength of ML methods is it could detect hard-to-discern patterns from large, noisy or complex data sets. This capability is particularly well-suited to complex genomic data, especially in cancer studies. For example, ANN and DT have been used in cancer detection and diagnosis for nearly 20 years (2-3). The clinical implication of cancer heterogeneity and various cancer genomic data available motivate the applications of ML for cancer classification using genomic data.SVM learning is one of many ML methods. Compared to the other ML methods SVM is very powerful at recognizing subtle patterns in complex datasets (4). SVM can be used to recognize handwriting, recognize fraudulent credit cards, identify a speaker, as well as detect face (5). Cancer is a genetic disease where the genomic feature patterns or feature function patterns may represent the cancer subtypes, the outcome prognosis, drug benefit prediction, tumorigenesis drivers, or a tumor-specific biological process. Therefore, the Artificial Intelligence of SVM can help us in recognizing these patterns in a variety of applications. SVM ModelSVM is a powerful method for building a classifier. It aims to create a decision boundary between two classes that enables the prediction of labels from one or more feature vectors (6). This decision boundary, known as the hyperplane, is orientated in such a way that it is as far as 41

show abstract

Section: Selecting Anticancer Drugs Warmuth Et Al (43) Used Activementioning

confidence: 99%

Applications of Support Vector Machine (SVM) Learning in Cancer Genomics

2018

CGP

582

347

View full text Add to dashboard Cite

show abstract

“…Chemotherapeutic agents, such as alkylating agents, cytostatic antibiotics, platinum compounds, taxanes and topoisomerase modifiers, have been shown to be effective in EOC. However, so many agents take part in the management of EOC is an indication that none are entirely efficacious or appropriate in all circumstances 5 . Therefore, novel biomarkers with high sensitivity and specificity are urgently required for better diagnostic tools and targeted therapies of EOC 6 .…”

mentioning

confidence: 99%

Overexpression of MAGE-A9 Is Predictive of Poor Prognosis in Epithelial Ovarian Cancer

Wang

Zhang

et al. 2015

Sci Rep

View full text Add to dashboard Cite

The cancer testis antigen, melanoma-associated antigen A9 (MAGE-A9), is expressed in many kinds of different human cancers, and is an important target for immunotherapy. However, the clinicopathologic significance of MAGE-A9 in epithelial ovarian cancer (EOC) is unknown. In this study, real-time PCR (12 carcinomas of high FIGO stage, 12 carcinomas of low FIGO stage, and 20 normal ovary or fallopian tube tissues) and immunohistochemistry by tissue microarrays (128 carcinomas and 112 normal ovary or fallopian tube tissues, benign or borderline ovarian tumor tissues) were performed to characterize expression of MAGE-A9 in EOC. We found that significantly higher MAGE-A9 mRNA expression in EOC tumors than that in normal ovary or fallopian tube tissues (all P < 0.05). Protein expression of MAGE-A9 was significantly associated with FIGO stage, high histological grade, level of CA-125 and metastasis. Consistent with the associated poor clinicopathologic features, patients with MAGE-A9H (high-expressing) tumors had a worse overall survival as compared to patients with MAGE-A9L (low or none-expressing) tumors. Further studies revealed that MAGE-A9 overexpression was an independent prognostic factor for overall survival (OS). Multivariate analysis showed that patients with MAGE-A9 overexpressing tumors had extremely poor OS. These findings indicate that MAGE-A9 expression may be helpful in predicting EOC prognosis.

show abstract

“…Drug dilution and injection into culture wells was performed at the Simple Modular Assay and Robotic Technology (SMART facility; Mount Sinai Hospital, Toronto, ON, Canada). 1 For initial screening, NIH 3T3 cells were plated on collagen grids (size: 0.7 cm × 0.7 cm) at 1.4 × 10 3 cells per well in 200 µL of 10% FBS/DMEM with or without compounds in eight-well chamber slides. Drugs were immediately added to a final concentration of 1, 0.1, or 0.01 µM.…”

Section: Cell Extension Assaymentioning

confidence: 99%

A Screening System for Evaluating Cell Extension Formation, Collagen Compaction, and Degradation in Drug Discovery

Yuda

McCulloch

2018

SLAS Discovery

View full text Add to dashboard Cite

The generation of cell extensions is critical for matrix remodeling in tissue invasion by cancer cells, but current methods for identifying molecules that regulate cell extension formation and matrix remodeling are not well adapted for screening purposes. We applied a grid-supported, floating collagen gel system (~100 Pa stiffness) to examine cell extension formation, collagen compaction, and collagen degradation in a single assay. With the use of cultured diploid fibroblasts, a fibroblast cell line, and two cancer cell lines, we found that compared with attached collagen gels (~2800 Pa), the mean number and length of cell extensions were respectively greater in the floating gels. In assessing specific processes in cell extension formation, compared with controls, the number of cell extensions was reduced by latrunculin B, β1 integrin blockade, and a formin FH2 domain inhibitor. Screening of a kinase inhibitor library (480 compounds) with the floating gel assay showed that compared with vehicle-treated cells, there were large reductions of collagen compaction, pericellular collagen degradation, and number of cell extensions after treatment with SB431542, SIS3, Fasudil, GSK650394, and PKC-412. These data indicate that the grid-supported floating collagen gel model can be used to screen for inhibitors of cell extension formation and critical matrix remodeling events associated with cancer cell invasion.

show abstract

A systematic approach to identify novel cancer drug targets using machine learning, inhibitor design and high-throughput screening

Cited by 27 publications

References 40 publications

Applications of Support Vector Machine (SVM) Learning in Cancer Genomics

Applications of Support Vector Machine (SVM) Learning in Cancer Genomics

Overexpression of MAGE-A9 Is Predictive of Poor Prognosis in Epithelial Ovarian Cancer

A Screening System for Evaluating Cell Extension Formation, Collagen Compaction, and Degradation in Drug Discovery

Contact Info

Product

Resources

About