latest posts
category
Newsletter
April 18, 2017
Pythia 3.0
The newest version of PYTHIA, our in silico platform for polypharmacology and mode-of-action studies, is now available for licensing!   In a matter of seconds PYTHIA combines molecular similarity calculation based fingerprints with experimental activity data to identify biological and off-targets of an active compound. Default activity data come f...
February 20, 2017
Deep Neural Networks for drug discovery
Deep Neural Networks (DNNs) have been in the spotlight for last couple of years. This technique has been applied with great success to traditional Machine Learning problems such as Image and Speech recognition. Moreover, it has been applied to other learning problems such as mastering the game of Go being able to beat a human professional of this game for the ...
January 31, 2017
Improving drug discovery: the Human-On-Chip project
In our sector it is well known that the process of drug development takes on average 10-15 years to be completed, and it costs over $1 billion to finally launch a successful drug onto the market. Around 60-80% of drug discovery projects are unsuccessful: many drugs fail once they enter the clinical stages of the drug development process.   These f...
December 7, 2016
Are biosimilars the new generic drugs?
Biologics are, mostly, large proteins derived from living organisms or cells and manufactured through a highly complex biotechnological process. Although these drugs are very efficacious, their cost is a major issue for patients and reimbursement agencies. A biosimilar, is the alternative to the original biologic, which shares highly similar, but not identical...
March 12, 2013
Data Science
Almost everybody have probably heard that this is the era of “Big Data” and some stories about using data to personalize adverts, medicine, bank credits, etc. But how does one turn data into this type of insight? The answer is using data science which is the intersecition of math/statistics, computer science and data domain knowledge because the go...