Home»R&D»AI, deep learning systems could transform Big Pharma

AI, deep learning systems could transform Big Pharma

June 2016

Print This Post

Insilico Medicine will unveil a newly-developed Artificial Intelligence (AI) drug discovery engine at the Re-Work Machine Intelligence Summit in Berlin, Germany, to be held June 29-30, 2016.

The AI engine is capable of predicting therapeutic use, toxicity, and adverse effects of thousands of molecules. Insilico says that this drug-discovery engine has the potential to transform the pharmaceutical industry and double the number of drugs on the market by “developing multi-modal deep-learned and parametric biomarkers as well as multiple drug-scoring pipelines for drug discovery and drug repurposing, and hypothesis and lead generation.”


By using AI coupled with a deep understanding of pharmaceutical R&D processes, Insilico hopes to overcome hurdles to drug discovery, such as failure rates due to irreproducible experiments with poor choices of animal models and the inability to translate the results from animal models directly to humans. Researchers point, however, to the overarching slow pace and bureaucratic culture of the industry as well as the number and variety of different diseases, and communication difficulties between scientists, managers, venture capitalists, pharmaceutical companies and regulators.

Up until now, Insilico has dealt mainly with nutraceuticals and cosmetics, signing an exclusive agreement with Life Extension, a vendor of major nutraceutical products, to develop a set of geroprotectors, which are natural products that mimic a young, healthy state in multiple old tissues. Geroprotectors have been shown to increase rejuvenation rates and slow down, or even reverse, the aging process.

The company’s next step will be to announce a cancer immunology concomitant drug discovery engine that will help boost the response rates to checkpoint inhibitors in immuno-oncology. Insilico has currently narrowed down thousands of hypotheses to 800 strong molecule-disease predictions with efficacy, toxicity, adverse effects, and bioavailability among other parameters. Partnering with various institutions has allowed Insiloco to partner with other institutions in order to validate their predictions in vitro and in vivo.

Source: Could deep-learning systems radically transform drug discovery? | KurzweilAI

Previous post

Not your father’s workplace: millennials and the future of employment

Next post

Family of 4 Healthcare costs tripled since 2001 - but 2015-2016 rise lowest increase yet

No Comment

Leave a reply