Shengqiao Gao1, Lu Han1, Dan Luo1, Gang Liu1, Zhiyong Xiao1, Guangcun Shan2, Yongxiang Zhang3, Wenxia Zhou4. 1. Beijing Institute of Pharmacology and Toxicology, State Key Laboratory of Toxicology and Medical Countermeasures, Beijing, 100850, China. 2. School of Instrumentation Science and Opto-Electronics Engineering and Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, Beihang University, Beijing, 100083, China. 3. Beijing Institute of Pharmacology and Toxicology, State Key Laboratory of Toxicology and Medical Countermeasures, Beijing, 100850, China. zhangyx@bmi.ac.cn. 4. Beijing Institute of Pharmacology and Toxicology, State Key Laboratory of Toxicology and Medical Countermeasures, Beijing, 100850, China. zhouwx@bmi.ac.cn.
Abstract
BACKGROUND: Querying drug-induced gene expression profiles with machine learning method is an effective way for revealing drug mechanism of actions (MOAs), which is strongly supported by the growth of large scale and high-throughput gene expression databases. However, due to the lack of code-free and user friendly applications, it is not easy for biologists and pharmacologists to model MOAs with state-of-art deep learning approach. RESULTS: In this work, a newly developed online collaborative tool, Genetic profile-activity relationship (GPAR) was built to help modeling and predicting MOAs easily via deep learning. The users can use GPAR to customize their training sets to train self-defined MOA prediction models, to evaluate the model performances and to make further predictions automatically. Cross-validation tests show GPAR outperforms Gene set enrichment analysis in predicting MOAs. CONCLUSION: GPAR can serve as a better approach in MOAs prediction, which may facilitate researchers to generate more reliable MOA hypothesis.
BACKGROUND: Querying drug-induced gene expression profiles with machine learning method is an effective way for revealing drug mechanism of actions (MOAs), which is strongly supported by the growth of large scale and high-throughput gene expression databases. However, due to the lack of code-free and user friendly applications, it is not easy for biologists and pharmacologists to model MOAs with state-of-art deep learning approach. RESULTS: In this work, a newly developed online collaborative tool, Genetic profile-activity relationship (GPAR) was built to help modeling and predicting MOAs easily via deep learning. The users can use GPAR to customize their training sets to train self-defined MOA prediction models, to evaluate the model performances and to make further predictions automatically. Cross-validation tests show GPAR outperforms Gene set enrichment analysis in predicting MOAs. CONCLUSION: GPAR can serve as a better approach in MOAs prediction, which may facilitate researchers to generate more reliable MOA hypothesis.
Entities:
Keywords:
Deep learning; Gene expression profiles; L1000; MOA
Authors: Nehme El-Hachem; Deena M A Gendoo; Laleh Soltan Ghoraie; Zhaleh Safikhani; Petr Smirnov; Christina Chung; Kenan Deng; Ailsa Fang; Erin Birkwood; Chantal Ho; Ruth Isserlin; Gary D Bader; Anna Goldenberg; Benjamin Haibe-Kains Journal: Cancer Res Date: 2017-03-17 Impact factor: 12.701
Authors: Murat Iskar; Monica Campillos; Michael Kuhn; Lars Juhl Jensen; Vera van Noort; Peer Bork Journal: PLoS Comput Biol Date: 2010-09-09 Impact factor: 4.475
Authors: Diego Carrella; Francesco Napolitano; Rossella Rispoli; Mario Miglietta; Annamaria Carissimo; Luisa Cutillo; Francesco Sirci; Francesco Gregoretti; Diego Di Bernardo Journal: Bioinformatics Date: 2014-02-20 Impact factor: 6.937
Authors: David R Boulware; Matthew F Pullen; Ananta S Bangdiwala; Katelyn A Pastick; Sarah M Lofgren; Elizabeth C Okafor; Caleb P Skipper; Alanna A Nascene; Melanie R Nicol; Mahsa Abassi; Nicole W Engen; Matthew P Cheng; Derek LaBar; Sylvain A Lother; Lauren J MacKenzie; Glen Drobot; Nicole Marten; Ryan Zarychanski; Lauren E Kelly; Ilan S Schwartz; Emily G McDonald; Radha Rajasingham; Todd C Lee; Kathy H Hullsiek Journal: N Engl J Med Date: 2020-06-03 Impact factor: 91.245