Dataset Information

Phenotypic Screening Combined with Machine Learning for Efficient Identification of Breast Cancer-Selective Therapeutic Targets.

ABSTRACT: The lack of functional understanding of most mutations in cancer, combined with the non-druggability of most proteins, challenge genomics-based identification of oncology drug targets. We implemented a machine-learning-based approach (idTRAX), which relates cell-based screening of small-molecule compounds to their kinase inhibition data, to directly identify effective and readily druggable targets. We applied idTRAX to triple-negative breast cancer cell lines and efficiently identified cancer-selective targets. For example, we found that inhibiting AKT selectively kills MFM-223 and CAL148 cells, while inhibiting FGFR2 only kills MFM-223. Since the effects of catalytically inhibiting a protein can diverge from those of reducing its levels, targets identified by idTRAX frequently differ from those identified through gene knockout/knockdown methods. This is critical if the purpose is to identify targets specifically for small-molecule drug development, whereby idTRAX may produce fewer false-positives. The rapid nature of the approach suggests that it may be applicable in personalizing therapy.

SUBMITTER: Gautam P

PROVIDER: S-EPMC6642004 | biostudies-literature | 2019 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Phenotypic Screening Combined with Machine Learning for Efficient Identification of Breast Cancer-Selective Therapeutic Targets.

Gautam Prson P Jaiswal Alok A Aittokallio Tero T Al-Ali Hassan H Wennerberg Krister K

Cell chemical biology 20190502 7

The lack of functional understanding of most mutations in cancer, combined with the non-druggability of most proteins, challenge genomics-based identification of oncology drug targets. We implemented a machine-learning-based approach (idTRAX), which relates cell-based screening of small-molecule compounds to their kinase inhibition data, to directly identify effective and readily druggable targets. We applied idTRAX to triple-negative breast cancer cell lines and efficiently identified cancer-se ...[more]

PMID: 31056464

Similar Datasets

Project description:BackgroundSepsis is one of the most lethal diseases worldwide. Pyroptosis is a unique form of cell death, and the mechanism of interaction with sepsis is not yet clear. The aim of this study was to uncover pyroptosis genes associated with sepsis and to provide early therapeutic targets for the treatment of sepsis.MethodsBased on the GSE134347 dataset, sepsis-related genes were mined by differential expression analysis and weighted gene coexpression network analysis (WGCNA). Subsequently, the sepsis-related genes were analysed for enrichment, and a protein‒protein interaction (PPI) network was constructed. We performed unsupervised consensus clustering of sepsis patients based on 33 pyroptosis-related genes (PRGs) provided by prior reviews. We finally obtained the PRGs mostly associated with sepsis by machine learning prediction models combined with prior reviews. The GSE32707 dataset served as an external validation dataset to validate the model and PRGs via receiver operating characteristic (ROC) curves. The NetworkAnalyst online tool was utilized to create a ceRNA network of lncRNAs and miRNAs around PRGs mostly associated with sepsis.ResultsA total of 170 genes associated with sepsis and 13 hub genes were acquired by WGCNA and PPI network analysis. The results of the enrichment analysis implied that these genes were mainly involved in the regulation of the inflammatory response and the positive regulation of bacterial and fungal defence responses. The prolactin signalling pathway and IL-17 signalling pathway were the primary enrichment pathways. Thirty-three PRGs can effectively classify septic patients into two subtypes, implying that there is a reciprocal relationship between sepsis and pyroptosis. Eventually, NLRC4 was considered the PRG most strongly associated with sepsis. The validation results of the prediction model and NLRC4 based on ROC curves were 0.74 and 0.67, respectively, both of which showed better predictive values. Meanwhile, the ceRNA network consisting of 6 lncRNAs and 2 miRNAs was constructed around NLRC4.ConclusionNLRC4, as the PRG mostly associated with sepsis, could be considered a potential target for treatment. The 6 lncRNAs and 2 miRNAs centred on NLRC4 could serve as a further research direction to uncover the deeper pathogenesis of sepsis.

Dataset Information

Phenotypic Screening Combined with Machine Learning for Efficient Identification of Breast Cancer-Selective Therapeutic Targets.

Publications

Phenotypic Screening Combined with Machine Learning for Efficient Identification of Breast Cancer-Selective Therapeutic Targets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets