What is Bioinformatics?
The explosion of data from high throughput biological experiments like sequencing and micro-arrays has led to the science called Bioinformatics. Bioinformatics is the interdisciplinary science which is similar to Data Science for solving biological problems.
According to Wikipedia “Bioinformatics is an interdisciplinary science, ultimately aiming to understand biology”.
Bioinformatics is an interdisciplinary field that develops and applies computational methods to analyse large collections of biological data, such as genetic sequences, cell populations or protein samples, to make new predictions or discover new biology. The computational methods used include analytical methods, mathematical modelling and simulation.
Our human body can be break down into small machineries of cells which is involved in complex processes. These cells are controlled by the central processing unit called DNA (De-oxyribo Nucleic Acid). Understanding DNA can reveal a lot about the organism as well as the chances of diseases in future. Current technologies including NGS (Next Generation Sequencing) has generated large amount of data. These big data (Genome, Transcriptome, Proteome and Metabolome) should be organised into databases and must be analysed. The outcomes of analysis these large data (termed as Big Data) are utilized in healthcare, preventive medicine and drug discovery.
Application of machine learning in bioinformatics has given rise to a lot of application from diseases prediction, diagnosis and survival analysis. Data Science has changed a lot in bioinformatics from dimensionality reduction of large datasets to data visualisation.
Machine Learning in Biology
Presently a large list of bioinformatics tools and softwares are available which are based on machine learning. The twin of Bioinformatics, called Computational Biology have emerged largely into development of softwares and application using machine learning and deep learning techniques for biological image data analysis. Recently Google’s Deep Learning library called TensorFlow was shown how it can be used in computational biology. Application of machine learning and deep learning in biology need to be explored further for building AI’s which can be used for disease diagnosis and prediction.
According to the Science Daily news, biologist are increasingly turning into Data Scientist as Bioinformatics Data Scientist or Genomic Data Scientist. The market of bioinformatics and career needs in bioinformatics is increasing each year. It is predicted that in the near future, there will be a huge need for people having bioinformatics skills.
Here is a video by Maria Nattestad on “What is Bioinformatics?” Where she explains the similarities between Bioinformatics and Data Science. She also explains the three approaches in bioinformatics.
Bioinformatics has become an essential interdisciplinary science for life science and biomedical sciences. However there is a huge demand in education and training in bioinformatics. I believe the MOOC’s by edX, Coursera and Udacity will help people to make foundations in the field.
- Contribute your suggestions to the Curated Directory for Bioinformatics🔗
- Join the Bioinformatics Data Science Group at Data Science Central🔗
- Join the Bioinformatics Innovation Lab🔗
