Deep neural networks, and combinations of supervised, semi-supervised and unsupervised learning techniques, are increasingly being used to solve difficult problems in medical image analysis, medical diagnosis, and analysis of biomarkers.
Deep learning is a branch of machine learning and often refers to artificial neural networks (“ANN”) that are composed of many layers. Broadly speaking, the goal of deep learning is to model complex, hierarchical features in data. It involves feeding a computer system a lot of data, which it can use to make decisions about other previously unseen data. Deep learning is about learning to predict in ways which can involve more complex dependencies between the input features.
In layman terms, neural networks are essentially computational models that attempt to mimic the action potential cascades that typify biological data processing (i.e. like our brain). So artificial neurons essentially act as little processors. ANNs are generally presented as systems of interconnected "neurons" which exchange messages between each other. These networks ask a series of binary true/false questions, or extract a numerical value, of every bit of data which pass through them, and classify it according to the answers received. The connections have numeric weights that can be tuned based on experience, making neural nets adaptive to inputs and capable of both supervised and unsupervised learning.
Thirty or forty years ago, neural networks were only two or three layers deep as it was not computationally feasible to build larger networks. Today it is common to have neural networks with 10+ layers and even 100+ layer ANNs are not unheard of. In fact, our DeepNEU models currently have thousands of layers.
Enter 123Genetix and DeepNEU
DeepNEU is our big data solution specifically engineered to empower rare diseases researchers. This highly novel deep learning computational platform combines (1) extensive and publicly available rare diseases gene network data with (2) modified Neutrosophic Logic, and (3) features of deep ANNs and Support Vector Machines.
The current version (v2.1) of DeepNEU continues to undergo testing and has been used to generate beta versions of several rare disease models for which the underlying genetics and clinical features are reasonably well characterized. A few examples of such well characterized diseases are Cystic Fibrosis, Duchenne Muscular Dystrophy and Sickle Cell Disease. These system biology models are easily customized to meet individual researchers’ needs. The purpose of these advanced models is to empower rare disease researchers to: (1) develop new disease hypotheses; (2) design and run experimental simulations to test those hypotheses; (3) write better grants and (4) identify potential disease specific biomarkers.
While DeepNEU itself is not a drug discovery engine, the identification of novel biomarkers should drive future research towards new and effective therapies where none exist now.
Over 300 million people are affected by about 7000 rare diseases around the world. Sadly, there are tremendous resource limitations and challenges in driving research and drug development for rare diseases. Innovative approaches to these challenges are needed.
Welcome to our blog. We intend to use this space to help you get to know our organization, our team and our mission, as well as to create more awareness for rare diseases and the limitations their researchers face.
We hope that this is the beginning of a defining time for rare disease research. We are thrilled to have you as a reader and we hope to make you a supporter. To keep up to date on what we're doing here at 123Genetix, we invite you to follow us on Facebook and/or Twitter. You can also connect with us on LinkedIn, and to ensure you never miss any of our future blog posts, you can subscribe to our RSS feed.
Thanks for visiting.
Today marks the Phase 1 launch of 123Genetix, a new non-profit organization created to advance rare disease research and transform the lives of those affected by rare diseases around the globe. 123Genetix is introducing its proprietary predictive computer models of rare disease biology to empower medical researchers to discover potential new research directions that may identify disease specific biomarkers that can lead to new and effective treatments for various rare diseases. The company’s advanced deep learning technology will be made available free of charge to not-for-profit researchers and organizations.
“We passionately believe the time is right for our transformative platform technology and a novel approach to empower rare disease research and improve the lives of families affected by rare diseases. At this time we are looking to create awareness for 123Genetix and our technology solution as we continue to forge relationships with relevant medical researchers and organizations. Our Phase 1 launch includes our website and blog at www.123genetix.com, as well as the use of Twitter and Facebook. I urge anyone interested in rare disease research to follow our social media accounts. A more formal launch of our not-for-profit technology solution will take place in about three months.” - Dr. Wayne Danter, Chief Science Officer and founder
The Unmet Need: A rare disease is generally a disease that affects a small percentage of the population. However, rare diseases are more common than you might think. There are more than 7,000 known rare diseases affecting over 300 million people worldwide. That’s almost the size of the population of the United States. In North America, rare diseases affect 8% to 10% of the population. About 80% of rare diseases have a genetic basis and 50% of rare diseases affect children. Unfortunately, less than 50% of known rare diseases have organizations to advocate on behalf of patients and their families. Compounding this ongoing problem is the ever increasing competition for limited and diminishing resources supporting rare diseases research.
Our Solution: DeepNEU is 123Genetix’s novel systems biology platform capable of evolving complex editable rare disease specific computer models. These models can be individualized by rare disease researchers to: (1) develop new hypotheses; (2) design and run experimental simulations to test those hypotheses; (3) write better grants; and, (4) discover potential biomarkers.