How big data and machine learning is revolutionising biological research

#artificialintelligence

Once the three-billion-letter-long human genome was sequenced, we rushed into a new'omics' era of biological research. Scientists are now racing to sequence the genomes (all the genes) or proteomes (all the proteins) of various organisms – and in the process are compiling massive amounts of data. For instance, a scientist can use'omics' tools such as DNA sequencing to tease out which human genes are affected in a viral flu infection. But because the human genome has at least 25,000 genes in total, the number of genes altered even under such a simple scenario could potentially be in the thousands. Although sequencing and identifying genes and proteins gives them a name and a place, it doesn't tell us what they do.


3 Technologies Will Utterly Transform Your World in the Next Decade

#artificialintelligence

Because all of the low-hanging scientific and technological fruit has supposedly been plucked. You can invent broad technologies like electrification, the light bulb, plumbing and sanitation, the telephone, refrigeration, the internal combustion engine, and the digital computer only once. Therefore most new technologies will consist of slight improvements on the old ones and that will not propel future economic growth. But have all broad technologies really been invented already? Below are three core technologies whose elaborations during the next decade will conjure into existence a world with far less transactional friction, amazing cures, and much smarter machines.


Machine Learning Is Helping Us Find The Genetics Of Autism

#artificialintelligence

The genetic cause of autism spectrum disorder is notoriously hard to research. Genetic markers for the disorder are tough to match from patient to patient because they're so rare--one of the most common genetic signifiers is only found in less than one percent of those diagnosed with autism. Even when genetic anomalies are found, they must be checked against family members genomes to ensure it's not attributable to a more commonly inherited mutation that doesn't cause disease. Researchers at Princeton and the Simons Foundation turned the traditional approach on its head, teaching a machine learning algorithm to look for the genetic relationships that could cause autism. The algorithm scoured a digital network of the human genome's interactions, looking for relationships and connections that are similar to those in previously-known markers for autism.


How machine learning helps biologists crack life's secrets

#artificialintelligence

This article is published in collaboration with The Conversation. Once the three-billion-letter-long human genome was sequenced, we rushed into a new "omics" era of biological research. Scientists are now racing to sequence the genomes (all the genes) or proteomes (all the proteins) of various organisms – and in the process are compiling massive amounts of data. For instance, a scientist can use "omics" tools such as DNA sequencing to tease out which human genes are affected in a viral flu infection. But because the human genome has at least 25,000 genes in total, the number of genes altered even under such a simple scenario could potentially be in the thousands.


IBM, Pfizer form research pact to tackle Parkinson's Disease

ZDNet

IBM Research Data Scientist Eric Clark explores wearable technologies that could help monitor and analyze biological data from study subjects on Thursday, April 7, 2016 at IBM's T. J. Watson Research Center in Yorktown, NY. IBM and Pfizer are teaming up in an effort to give Parkinson's Disease research an analytical edge. The tech titan and the pharmaceutical giant plan to utilize non-invasive wearables to collect and monitor real-time patient data. The end goal of the research project is to advance the way neurological diseases are diagnosed and treated while also speeding up clinical trials to bring new drugs to market. The study, which is expected to last up to three years, will glean patient data from a system of sensors, wearables and mobile devices that will monitor patients around the clock, not just episodically.