Medicine Open Source

Cancer fighters invited to take part in open source machine learning project

Scientists at the Georgia Institute of Technology have put in motion an initiative that aims to help cancer fighters by giving them predictive analysis of effectiveness of drugs via machine learning and raw genetic data.

Researchers say that they have built a program that is open source and will enable cancer fighters to take it for free, or even just swipe parts of their programming code. Scientists hope that they will be able to attract researchers who will bring to the table their own cancer, machine learning and computer expertise to improve upon the existing program and thereby help save more lives.

Researchers wanting to participate can start by reading a new study about the software published on October 26, 2017, in the journal PLOS One. There they will find links to download the software from GitHub and to access the code. They will then use the current program that has been about 85 per cent accurate in assessing treatment effectiveness of nine drugs across the genetic data of 273 cancer patients. This particular program uses proven machine learning mechanisms and also normalizes data. The latter allows the machine learning to work with data from varying sources by making them compatible. And the researchers have reduced human bias about which data are important for predicting outcomes.

The researchers also want the project to pool large amounts of anonymous patient treatment success and failure data, which will help the program optimize predictions for everyone’s benefit. But that doesn’t mean some companies can’t benefit, too.

But hopefully, most players will catch the spirit of kindness.

Get Free Sample Copy of Report

About the author

Sonia Javadekar

Sonia Javadekar

I am a postgraduate of Mass Communication but my interest lies in writing. I like writing on varied topics from politics, technology, science, health and so on. I would be glad if you could leave your feedback after reading my blog !

Add Comment

Click here to post a comment