This article is brought to you by Congress Bookers, a reliable accommodation partner for lead pharma companies worldwide.
In order to better understand the meaning of deep learning, we first need to take a look at big data.
New technologies such as the internet of things (IoT) and genomics generate huge data sets in a completely unstructured manner which are referred to as big data. These data sets are so large and so complex that they can’t be analysed using traditional apps and software. Therefore, new applications emerge. One of the biggest players in the field is Palantir Technologies, a company which helps make sense of all this big data. While storing this data is one thing, analyzing it is something completely different and it takes us to the concept of deep learning.
Deep learning involves teaching a computer to make sense of all the unstructured big data using various methods like “artificial neural networks” which mimic the way the human brain works. What it does is use algorithms to search for complex relationships in all that “big data.”Those algorithms are constantly refined and improved.
Cognitive computing refers to a computer’s ability to learn more over time based on experience, much like the human brain does. You’ve probably read some articles on IBM’s Watson cognitive computing platform that uses deep learning for translation, speech-to-text, and text-to-speech. Deep learning or cognitive computing is a form of artificial intelligence.
Deep Learning & Drug Discovery
As explained so far, deep learning is a way to analyse big data and find relationships within huge data sets that would take years and years for humans to discover and process on their own.
If we see this in the context of the drug discovery industry, many years of research are needed to identify a drug compound that might be effective in combating a disease prior to seeking FDA approval. The FDA approval process is actually more like the cherry on top, it comes after huge research and extended trials. All this translates into billions spent by the pharmaceutical industry
on R&D with the aim of discovering compounds that treat specific diseases. Unfortunately, the path is long and rocky leading to only a fraction of all that research translated into commercial drugs.
Deep learning could make things faster and much more efficient by analysing a wide spectrum of already effective molecular compounds and use the findings to develop new drugs to combat diseases.
Some companies have turned to deep learning in an attempt to shorten the drug discovery cycle by building platforms that enable the discovery of new drug compounds, while predicting their likely success.
Founded in 2012, US-based deep learning company Atomwise is the creator of AtomNet, the first deep learning technology for novel small molecule discovery, characterized by its unprecedented speed, accuracy, and diversity. The company has worked with companies like Merck and has been involved in Ebola treatment research.
Founded in 2014, Insilico Medicine raised USD 10M in a venture round in February 2017. The company is dedicated to finding novel solutions for cancer, aging and age-related diseases using advances in genomics and big data analysis. They provide services like advanced deep learning, custom drug and biomarkers discovery, aging research tools to academia, pharma and cosmetics companies.
Berg Health is a Boston-based biopharma company founded in 2006. They use their “Berg Interrogative Biology™ discovery platform” to reduce the time, and expense, of drug development. Berg focuses on three distinct areas: diagnostics, pharmaceutical research and development and health care analytics.
Founded in 2014, twoXAR is “an artificial intelligence-driven drug discovery company.” Using its computational platform, twoXAR identifies promising drug candidates, lowers risks through preclinical studies, and progresses drug candidates to the clinic through industry and investor partnerships. Their DUMA Drug Discovery platform evaluates enormous datasets to identify and rank high probability drug-disease matches in minutes rather than years.
Using deep learning for drug discovery is still in its early stages but it definitely shows great promise. By teaching a computer how to learn, relationships between vast data sets are uncovered thus helping scientists and researchers learn more about how to treat diseases whether they’re new or have been around for decades.
Congress Bookers provides a whole range of services needed to organize a group for a medical congress. On our website, you will find a full list of hotel allotments for the most important medical congresses in 2017, regardless of their location. The biggest congresses next year are:
- EHA 2017 – 445 rooms in fourteen 4-star hotels
- ESMO 2017 – 440 rooms in ten 4-star hotels
- EURETINA 2017 – 160 rooms in five 4-star hotels
- EASD 2017 – 423 rooms in thirteen 4-star hotels
- EAACI 2017 – 688 rooms in fourteen 4-star hotels