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 from the ChEMBL database but in principle any activity source, either public or proprietary, can be introduced.PYTHIA is specifically designed to be used by medicinal chemists and researchers without any in silico background: it integrates the ChemAxon’s Marvin JS sketcher to easily draw any compound and few parameters must be set up to run a polypharmacology prediction. For any query molecule predicted targets are calculated and ranked by MoA Score which a function of similarity and activity. The predicted targets are then compared to those of approved drugs in order to suggest possible therapeutic indications of the query molecules.
18/04/2017 | Tags:
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 first time in history.A DNN is a system made of biologically-inspired neurons that are organized in layers with increasing levels of abstraction. Take for instance a DNN trained to classify paintings by their author. In such system the first layers will be in charge of detecting colors and edges. Subsequent layers will use that information to assess more complex patterns such as shapes, and recurring motives. Finally, the last layers will take all that information into consideration in order to predict the artist that produced a given painting.DNNs' ability to extract information at different levels of abstraction can also be used to perform creative tasks. For instance, work has been done to use DNNs for speech synthesis, the design of new encryption algorithms, and to apply a given pictorical style to an image.
20/02/2017 | Tags:
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 failures have multiple causes, a very important one being the unreliable extrapolation from in vitro and animal model results to humans. The inherent differences between cell-biology and organ level physiology is one of the key challenges of the drug development industry.
31/01/2017 | Tags:
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, safety, and efficacy profiles. Biosimilars may represent a more economical alternative to the costly biological agents already on the market.
07/12/2016 | Tags:
1 of 10