PolyU develops big data analysis platform to unveil gene interactions in cancer

The Hong Kong Polytechnic University (PolyU) has achieved a breakthrough in the cancer genomics by developing a novel big data analysis platform for analysing the interactions among genes.

Maybe this is the start of some really great analyses of genomics research as it can be repeated for other areas now.

SQLFool makes their scripts open source and has loaded them onto Github

Due to a change in focus she has put all her scripts onto Github and made the open source so others can benefit from all her hard work over the years.  The announcement is here and the scripts are here. An incredibly kind and community spirited act.

WEBINAR: Big Data, Big Deal: Turning Unstructured Information into Structured Data - July 9, 2015

Big Data, Big Deal: Turning Unstructured Information into Structured Data

Complimentary Web Seminar
July 9, 2015
2 pm ET/11 am PT

Brought to you by Information Management

We’ve all read about Big Data in books, magazines and news articles – we need to do something about analytics and big data. Organizations that embed analytics within all parts of their business to make faster decisions and improve decision making, planning and forecasting have a distinct competitive advantage.

This complimentary webinar will highlight recent market research on big data and what organizations are doing with it and highlight the different approaches to take using text analytics to transform your unstructured data into meaning that business can use to make decisions.

Featured Presenters:

Moderator:

Eric Kavanagh – Host of DM Radio

Speakers:

Shawn Rogers – Chief Research Officer, Dell Software
Danny W. Stout, Ph.D. - Senior Analytics Consultant, Dell Software

Sponsored by:

Register here

Document Clustering with Python

Great tutorial showing how to cluster a set of documents using Python. Includes a Github repo with interactive notebook.  From Brandon Rose.

How Data Science Shaped This Teen-Counseling-By-Text Service

Two years after its launch, Crisis Text Line is swimming in data. But data for data's sake is meaningless. This is a great story about finding value in large datasets - both for the organization involved and for the people doing the analysis work.  Great article from Fast Company.

10 R packages for Machine Learning

Needless to say, R is one of the most efficient and effective tools for analysing and manipulating data for statistical purpose. To add to that, R being both inexpensive and beautiful, embellishes both the art of programming and proliferating the skill set of the programmer.

Great list from Big Data Made Simple.  I've only used e1071 and rpart from the list myself, but having recently learnt about it still prefer the caret package as it can be central to so many different models.  You can find some information about caret here.  If you look at Train Model List that tells you the different models you can get from using the caret package.

Even doctors will be Data Scientists

An interesting discussion abut all the data that is created today but not just doctors and how tools to analyse that data are increasingly available for us to analyse our own data.  Article from Big Data Made Simple.