Machine Learning in Biological Sciences

This book gives an overview of applications of Machine Learning (ML) in diverse fields of biological sciences, including healthcare, animal sciences, agriculture, and plant sciences. Machine learning has major applications in process modelling, computer vision, signal processing, speech recognition, and language understanding and processing and life, and health sciences. It is increasingly used in understanding DNA patterns and in precision medicine. This book is divided into eight major sections, each containing chapters that describe the application of ML in a certain field. The book begins by giving an introduction to ML and the various ML methods. It then covers interesting and timely aspects such as applications in genetics, cell biology, the study of plant-pathogen interactions, and animal behavior. The book discusses computational methods for toxicity prediction of environmental chemicals and drugs, which forms a major domain of research in the field of biology.

It is of relevance to post-graduate students and researchers interested in exploring the interdisciplinary areas of use of machine learning and deep learning in life sciences.

Autorentext

Dr. Shyamasree Ghosh is working as a Scientific Officer at the NISER Bhubaneswar, India. She has worked and published extensively in the domain of glycobiology, sialic acids, immunology, stem cells, nanotechnology, and computational immunology. She has graduated from the prestigious Presidency College Kolkata in 1998, and was awarded the prestigious National Scholarship from the Government of India. She completed her masters in Biotechnology from Calcutta University in 2000, ranking second in the University. She did her PhD from the Indian institute of Chemical Biology (IICB) Kolkata, CSIR, India in glycobiology, sialic acids, immunology, and Cancer Biology. She did her Post Doctoral Research in Indian Association for the Cultivation of Sciences (IACS), India on nanotechnology, stem cells and Cancer Biology. She has served as faculty and Chair (2005-2009) of Dept. Her work has been recognised and accepted globally and she has been awarded by different scientific bodies in India. She is a member of different National Science Bodies and is Editorial Board member in Scientific Societies.

Dr. Rathi Dasgupta, has been working in the computer science based industry since the last 25 years and is currently the SVP, Intelliswift Software Inc., Newark, CA, USA. He did his bachelor in Science with Major in Physics, St. Xavier's College, University of Calcutta, Calcutta, India, (Integrated MTech), radio physics & electronics, Institute of Radio Physics and Electronics, Master of Science (MS), Nuclear & Particle Physics, University College of Science & Technology, doctoral research, in theoretical physics, Saha Institute of Nuclear Physics, University of Calcutta and has been adjunct Faculty, Mathematics & Computer Science at MS in CSE & EE Class, Alliance University, visiting faculty, Computer Information Science, MBA Class, Indian Institute of Management, Bangalore and Associate Visiting Professor, Computer Science & Mathematics, Xavier Institute of Management & Entrepreneurship,. He also have few US provisional and full patents in Machine Learning.

Inhalt

1. Overview of machine learning applications in biology

2. Machine Learning Methods

   I. Associations,

   II. Classification,

   III. Regression,

   IV. Unsupervised learning,

   V. Reinforcement learning,

Introduction to the Machine Learning Models

3. Model selection and generalization,

4. Multivariate Methods,

5. Dimensional Reduction,

6. Clustering (K-means, Adaptive Resonance Theory, Self Organizing Maps),

7. Kernel Machines,

8. Hidden Markov Model (HMM)

9. Neural nets and Deep Learning

10. Bayesian Theory for machine learning,

11. Ethics in machine learning and artificial intelligence

Using Machine learning methods in Life Sciences

12. Different Machine learning models and their appropriate usages

13. Machine learning and its use in understanding Life Sciences,

    14. Supervised and unsupervised learning, neural networks and deep learning methods in Biology

14. Recognizing phenotypes using machine learning

15. Reinforcement learning and Support vector machines and random forests in Biological processes Machine Learning: Software and Applications used in Biology and Medicine

16. The Cloud, Microsoft, Google, Facebook applications in healthcare

17. Applications and software of machine learning and artificial intelligence in medical knowledge in One Health

18. Medical Health Approaches cloud set up,

19. Life Sciences in Azure and Amazon Web Services

Application of ML in detection of Toxicity

21. Toxicity: An Introduction (drug toxicity and molecule-molecule interactions)

22. Machine learning and Toxicity Studies

    Application in Human life

23. Applications of machine learning in study of cell biology,

24. Genetics using unsupervised learning methods such as KNN,

25.. Cell Fate analysis using PCA or similar dimensionality reduction methods,

26. Detection of disease through biomarker data and image analysis

    Application in Animal sciences

27. Animal Behaviour: An Introduction

28. Study of animal behaviour by conventional methods and bottlenecks and advantages of machine learning

29. Machine learning and study of precision animal agriculture and animal husbandry

30. Machine learning in the study of animal health and veterinary sciences

31. Machine learning in identification of animal viral reservoirs.

    Application in Plants

32. Problems in Plant Biology that are yet to be tackled

33. Machine learning in agriculture,

34. Machine learning in understanding of plant pathogen interactions,

35. Machine learning in plant disease research.

    Challenges and Road Ahead

36. BioRobotics

    A. An Introduction

    B. BioRobots in detection, identification, prevention and treatment of disease at molecular level

37. The challenges to application of machine learning in biological sciences

38. The future of machine learning