Learning Instead of Programming means that the Singularity is Near

Australian physicists have used an online optimization process based on machine learning to produce
effective Bose-Einstein condensates (BECs) in a fraction of the time it would normally take the
researchers.

As robots become more pervasive in society, humans will want them to do chores like cleaning house
or cooking. But to get a robot started on a task, people who aren’t computer programmers will have to
give it instructions. “So we needed to provide a way for everyone to train robots, without
programming,” said Matthew Taylor, Allred Distinguished Professor in the WSU School of Electrical
Engineering and Computer Science.

Mixed-up metals make for stronger, tougher, stretchier alloys
Materials scientists are creating next-generation mixtures with remarkable properties.

Aiding his team is Duane Johnson, a theorist at Ames who, in 1995, developed an algorithm to predict
the properties of conventional alloys before they are made8. In 2015, he expanded the code to work
for high-entropy alloys9. Johnson's algorithm assesses how much one element is attracted to or
repelled by another, and then using that information to predict whether a mixture of elements will
form a compound, a solid solution or a mixture of both. That enables Kramer's team to identify which
alloys might be worth investigating. The experimental results are then fed back into the algorithm to
validate and improve the code.
http://www.nature.com/news/mixed-up-metals-make-for-stronger-tougher-stretchier-alloys-1.19942

Sharing genetic information from millions of cancer patients around the world could revolutionize
cancer prevention and care, according to a paper in Nature Medicine by the Cancer Task Team of the
Global Alliance for Genomics and Health (GA4GH). Hospitals, laboratories and research facilities
around the world hold huge amounts of this data from cancer patients



Abstract of Deep learning applications for predicting pharmacological properties of drugs and drug
repurposing using transcriptomic data

Deep learning is rapidly advancing many areas of science and technology with multiple success stories
in image, text, voice and video recognition, robotics and autonomous driving. In this paper we
demonstrate how deep neural networks (DNN) trained on large transcriptional response data sets
can classify various drugs to therapeutic categories solely based on their transcriptional profiles. We
used the perturbation samples of 678 drugs across A549, MCF-7 and PC-3 cell lines from the LINCS
project and linked those to 12 therapeutic use categories derived from MeSH. To train the DNN, we
utilized both gene level transcriptomic data and transcriptomic data processed using a pathway
activation scoring algorithm, for a pooled dataset of samples perturbed with different
concentrations of the drug for 6 and 24 hours. When applied to normalized gene expression data for
“landmark genes,” DNN showed cross-validation mean F1 scores of 0.397, 0.285 and 0.234 on 3-, 5-
and 12-category classification problems, respectively. At the pathway level DNN performed best with
cross-validation mean F1 scores of 0.701, 0.596 and 0.546 on the same tasks. In both gene and
pathway level classification, DNN convincingly outperformed support vector machine (SVM) model on
every multiclass classification problem. For the first time we demonstrate a deep learning neural net
trained on transcriptomic data to recognize pharmacological properties of multiple drugs across
different biological systems and conditions. We also propose using deep neural net confusion matrices
for drug repositioning. This work is a proof of principle for applying deep learning to drug discovery
and development.






Next