Introduction
It is the era of data generation and data analytics with the help of technology. There is a huge data available at public domain databases. The data has to be analysed and further can be used for prediction of gene, protein function through advanced technology like Machine learning (ML) and Artificial Intelligence (AI). Our research group is working on various application of ML and AI in medical bioengineering field.
Nowadays, technology is changing faster than ever. To meet the market's current opportunities, we should know AI, Machine Learning, Deep Learning, and Data Science. AI and ML helping to the individual human by simplifies many critical works, the business communities to improve their revenue.
Ongoing Projects:
1. Recent developments in machine learning have made significant impact in the detection and diagnosis of neurological diseases. Attention Deficit Hyperactivity Disorder (ADHD) is a neuro-developmental disorder noticed in children of school age which is mostly identified by their behavioural changes rather than scientific means. In this study we are using several machine learning approaches for improved diagnosis of the ADHD.
2. Cancer has been characterized as a heterogeneous disease consisting of many different subtypes. The early diagnosis and prognosis of a cancer type have become a necessity in cancer research, as it can facilitate the subsequent clinical management of patients. The importance of knowing biomarkers for disease identification is important. In our study we are using machine learning approach to predict biomarkers in cancer.
3. We are working on creating Data repository for biological data which are not available . .For this will need to integrate data from available data repositories then using ML or AI can propose conclusions from that data to draw significant inferences in health sector.
Publications:
1. Tiwary, S., Naniwadekar, M., Sonolikar, R., Bapat, S., Yerudkar, A., Kamble, S. P., &Tambe, S. S. (2018). Prediction of Rate Constants of Photocatalytic Degradation of Pharmaceutical Pollutants by Artificial Intelligence based Genetic Programming Formalism. Current Environmental Engineering, 5(1),58-67.DOI : 10.2174/2212717805666180124152718
2. Vyas, R., Bapat, S., Karthikeyan, M., Tambe, S., & Kulkarni, B. D. (2016) Application of Genetic Programming (GP) formalism for building disease predictive models from protein- protein interactions (PPI) data. Transactions on computational biology andBioinformatics.[PMID: 28113781]
3. Vyas,R.,Bapat,S.,Jain,E.,Karthikeyan,M.,Tambe,S.,&Kulkarni,B.D.(2016).Buildingandanalysis of protein-protein interactions related to diabetes mellitus using support vector machine, biomedical text mining and network analysis. Computational Biology and Chemistry, 65, 37-44. [PMID: 27744173]
4. Goel, P., Bapat, S., Vyas, R., Tambe, A., &Tambe, S. S. (2015). Genetic programming based quantitative structure–retention relationships for the prediction of Kovats retention indices. Journal of Chromatography A, 1420,98-109.[PMID: 26460075]
5. Vyas, R., Bapat, S., Jain, E., S Tambe, S., Karthikeyan, M., & D Kulkarni, B. (2015). A Study of Applications of Machine Learning Based Classification Methods for Virtual Screening of Lead Molecules. Combinatorial chemistry & high throughput screening, 18(7),658-672. [PMID: 26138573]
Computational tools used: RapidMiner, Eureqa Formulize
