Applying Deep Learning for Hypotheses Generation to Bridge Medicinal Types Ayurveda and
Allopathy using Deep Belief Network in Word Embedding
Arockia Xavier Annie R* and Aishwarya T
Department of Computer Science and Engineering, College of Engineering, Anna University, India
*Corresponding Author: Arockia Xavier Annie R, Department of Computer Science and Engineering, College of Engineering, Anna University, India.
August 04, 2021; Published: 00-00
There is a humongous amount of information available in the biomedical field that leads to opportunities and several open issues. Biomedical research is towards the discovery of new cost efficient and side effects free drugs. Manual processing of this data could consume very high man-hours of labor. Automatic text processing of the abstracts of the research paper enhances the efficiency and could lead to the identification of interesting new hypotheses. Hence, hypotheses generation promises to shrink the number of possible substitutes that a medical researcher has to try in order to get a valid drug for a disease. Therefore, training word embedding using deep learning techniques improves the efficiency in vocabulary discovery and the classification of terms into various classes. The association between different diseases would serve as the base to derive hypotheses of drugs for the diseases. Our proposed work using Deep Belief Network (DBN) trained using the abstracts of the research papers has an accuracy of 82.98% whereas the traditional text processing method of hypotheses generation has an accuracy of 67.8%. Our work has provided symptom-disease, and disease-drug hypothesis that enables new alternatives and bridges between the Allopathy and Ayurveda drugs. It also intensifies and reduces the all possibilities in creation and testing of drugs for a particular disease. The hypothesis helps in reducing this all possibilities of drugs relevant to a disease.
Keywords: Disease-Drug Generation; Ayurveda and Allopathy; Deep Learning; Hypothesis Generation; Query Processing;
- Action L., et al. “Use of a machine learning framework to predict substance use disorder treatment success”. Plos One4 (2017): e0175383.
- Ayyadurai VS. “The control systems engineering foundation of traditional Indian medicine: the Rosetta stone for Siddha and Ayurveda”. International Journal of System of Systems Engineering2 (2014): 125-149.
- Bleecker LG. “Hypothesis-generating research and predictive medicine". Genome Research7 (2013): 1051-1053.
- Camacho DM., et al. “Next-generation machine learning for biological networks”. Cell (2018).
- Chandra S. “Ayurveda research, wellness and consumer rights”. Journal of Ayurveda and Integrative Medicine1 (2016): 6-10.
- Costa FF. “Big data in biomedicine”. Drug Discovery Today4 (2014): 433-440.
- Goetz LH and Stork NJ. “Personalized medicine: motivation, challenges, and progress”. Fertility and Sterility 6 (2018): 952-963.
- Hollinger A and Juridical I. “Knowledge discovery and data mining in biomedical informatics: The future Is in integrative, interactive machine learning solutions”. In Interactive knowledge discovery and data mining in biomedical informatics. Springer, Berlin, Heidelberg (2014): 1-18.
- Jiang Z., et al. “Training word embedding’s for deep learning in biomedical text mining tasks”. In Bioinformatics and Biomedicine (BIBM), 2015 IEEE International Conference on (2015): 625-628.
- Jinn W., et al. “A text mining model for hypothesis generation”. In Tools with Artificial Intelligence, 2007. ICTAI 2007. 19th IEEE International Conference on 2 (2007): 156-162.
- Kang D and Park Y. “Based measurement of customer satisfaction in mobile service: Sentiment analysis and VIKOR approach”. Expert Systems with Applications4 (2014): 1041-1050.
- Lanier WL., et al. “Empiricism and rationalism in medicine: can 2 competing philosophies coexist to improve the quality of medical care?” In Mayo Clinic Proceedings10 (2013): 1042-1045.
- Lee S., et al. “An empirical comparison of four text mining methods”. Journal of Computer Information Systems 1 (2010): 1-10.
- Niehaus KE., et al. “Machine learning for the Prediction of antibacterial susceptibility in Mycobacterium tuberculosis”. In Biomedical and Health Informatics (BHI), 2014 IEEE-EMBS International Conference on (2014): 618-621.
- Niehaus WN., et al. “The PM&R Journal implements a social media strategy to disseminate research and track alternative metrics in physical medicine and rehabilitation”. PM&R5 (2018): 538-543.
- Popova M., et al. “Deep reinforcement learning for de novo drug design”. Science Advances7 (2018): eaap7885.
- Ravi D., et al. “Deep learning for health informatics”. IEEE Journal of Biomedical and Health Informatics1 (2017): 4-21.
- Rifaioglu AS., et al. “Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases”. Briefings in Bioinformatics (2018).
- Sarikaya R., et al. “Application of deep belief networks for natural language understanding”. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)4 (2014): 778-784.
- Schmidhuber J. “Deep learning in neural networks: An overview”. Neural Networks 61 (2015): 85-117.
- Schumacher A., et al. “Changing R&D models in research-based pharmaceutical Companies”. Journal of Translational Medicine1 (2016): 105.
- Shih WJ and Lin Y. “On study designs and hypotheses for clinical trials with predictive biomarkers”. Contemporary Clinical Trials 62 (2017): 140-145.
- Srivastava SR., et al. “Mainstreaming of Ayurveda, Yoga, Naturopathy, Unani, Siddha, and Homeopathy with the health care delivery system in India”. Journal of Traditional and Complementary Medicine2 (2015): 116-118.
- Spangler S., et al. “Automated hypothesis generation based on mining scientific literature”. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining (2014): 1877-1886.
- Terranova N., et al. “Application of Machine Learning in Translational Medicine: Current Status and Future Opportunities”. AAPS Journal 23 (2021): 74 (2021).
- Valka HGG and Mukhopadhyay S. “Hypotheses Generation Pertaining to Ayurveda Using Automated Vocabulary Generation and Transitive Text Mining”. In 2009 International Conference on Network-Based Information Systems (2009) 200-205.
- Versos KM. “Drawing on millions of biomedical journal publications to do predictive biology”. In Big Data and Smart Computing (Big Comp), 2015 International Conference on (2015): 251-253.
- Yao V., et al. “Enabling Precision Medicine through Integrative Network Models”. Journal of Molecular Biology 430 (2018): 2913-2923.
- Yao J., et al. “Predicting clinically promising therapeutic hypotheses using tensor factorization”. BioRxiv (2018): 272740.
- Zhang W., et al. “A comparative study of TF* IDF, LSI and multi-words for text Classification”. Expert Systems with Applications3 (2011): 2758-2765.
- Zhang L., et al. “From machine learning to deep learning: progress in machine Intelligence for rational drug discovery”. Drug Discovery Today (2017).
- Zhao XF., et al. “A novel drug discovery strategy inspired by traditional medicine philosophies”. Science 6219 (2015): S38-S40.
- Zitnik M., et al. “Machine learning for integrating data in biology and medicine: Principles, practice, and opportunities”. Information Fusion 50 (2019): 71-91.
- “Wikipedia, a free encyclopedia”.
- “Pubmed central”.