Researchers at A*STAR have been comparing data analysis processes to find one that can deliver in terms of speed, quality of analysis and reliability. The winner uses machine learning technique to analyze large, complex biological data sets and provide key relations between parameters in a fraction of the time of the other techniques. This interesting news came to us from Phys.org in their article, “Powerful machine-learning technique enables biologists to analyze enormous data sets.”

Machine learning is a method of data analysis that automates analytical model building. It is a branch of artificial intelligence based on the idea that systems can learn from data, identify patterns and make decisions with minimal human intervention.

Measurements on single cells alone can generate huge data sets that have anywhere from 20 to more than 20,000 parameters. This massive size of data can make it extremely challenging for scientists to uncover meaningful relationships between parameters.

An analysis that might take days using other methods can be done in a few hours using uniform manifold approximation and projection (UMAP), which will allow scientists to investigate larger data sets.

Melody K. Smith

Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.