"In a new paper a team of researchers from Insilico Medicine present a new model called GENTRL (https://github.com/insilicomedicine/GENTRL) for molecule generation. This algorithm, given a protein target, has generated 6 viable compounds in 21 days, and after 25 more days of synthesis and testing, 4 passed the preliminary tests; the most potent one was tested on live mice, and its predicted biological and chemical properties were confirmed."



https://www.nature.com/articles/s41587-019-0224-x

AI Can Detect Coronavirus Infections Far Faster Than Humans
https://www.freethink.com/articles/detect-coronavirus
https://news.1rj.ru/str/ArtificialIntelligenceArticles

Mark Zuckerberg :
As part of our response to the coronavirus outbreak, our team at the Chan Zuckerberg Initiative is working with UCSF and Stanford to quadruple the Bay Area's testing and diagnostics capacity. We're funding the acquisition of state-of-the-art FDA approved COVID-19 diagnostic machines that will significantly increase the Bay Area's ability to test and diagnose new cases. We're also bridging connections between clinical labs at Stanford and UCSF to help distribute the testing load throughout the area.

And following up on my post last week about the IDSeq (Infectious Disease Sequencing) tool we developed at the Chan Zuckerberg Initiative, researchers in Cambodia recently published how they were able to sequence the virus that causes COVID-19 and confirm the country's first case. You can view this data on the IDseq website at http://public.idseq.net. This new data is continuing to provide scientists with valuable insights into the transmission and spread of the virus, and could hopefully unlock new discoveries that could lead to treatments.

More to come soon.

Why AI expert Haven't do something for coronavirus?
I was thinking there should be a way to find a treatment or something for this virus using machine learning and AI. Why we haven't seen anything yet? It's killing many people all around the world and the number is growing like mad. I expect the AI community to make a great effort on this and solve this problem.

——————-

Usually nobody asks them. Like, there was really good expert system in 80s that could determine what kind of bacterial infection patient had, better then doctors. Why is that important? Well you can use specific antibiotic to kill that bacteria and reduce chances of making one super bacteria that will kill us all before you say corona (https://www.youtube.com/watch?v=xZbcwi7SfZE) and also, you would save much of good bacteria but as much as I know they never put it in practices and proceeded to go with overkills all the time.

Medicine is slow and very inert.

Also, this was fun: https://www.youtube.com/watch?v=EVoZMRmtBkY

Natural Language QA Approaches using Reasoning with External Knowledge. http://arxiv.org/abs/2003.03446

Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restorat... http://arxiv.org/abs/2003.03440

How does the non-conscious become conscious?
https://www.cell.com/current-biology/fulltext/S0960-9822(20)30033-6
https://news.1rj.ru/str/ArtificialIntelligenceArticles

Introducing the TensorFlow Developer Certificate!
https://blog.tensorflow.org/2020/03/introducing-tensorflow-developer-certificate.html

#Job PhD position in Cryptography and Machine Learning: Chalmers University of Technology, Sweden https://iacr.org/jobs/item/2164

PhD position now open.

Are you interested in evolution? Can you work with global data sets? Do you want to develop machine learning techniques? Are you excited by the global underground?

Evolutionary Biogeography of Microbial Networks

https://workingat.vu.nl/ad/evolutionary-biogeography-of-microbial-networks/v9ydfv

Google releases millions of free datasets. (from January 23rd, 2020)
https://blog.google/products/search/discovering-millions-datasets-web/
https://news.1rj.ru/str/ArtificialIntelligenceArticles

Sebastian Raschka

STAT 453 -- Introduction to Deep Learning and Generative Models (Spring 2020)

http://pages.stat.wisc.edu/~sraschka/teaching/stat453-ss2020/

https://github.com/rasbt/stat453-deep-learning-ss20/blob/master/L06-pytorch/code/adaline-with-autograd.ipynb

Fast and Easy Infinitely Wide Networks with Neural Tangents
Blog by Samuel S. Schoenholz and Roman Novak: https://ai.googleblog.com/2020/03/fast-and-easy-infinitely-wide-networks.html
#ArtificialIntelligence #MachineLearning #DeepLearning

MIT’s deep learning found an antibiotic for a germ nothing else could kill | ZDNet
https://www.zdnet.com/article/mits-deep-learning-found-an-antibiotic-for-a-germ-nothing-else-could-kill/

A great opinion piece by Robert M. Sapolsky.

https://edition.cnn.com/2020/03/13/opinions/coronavirus-neuroscience-brain-decisions-sapolsky/index.html

Clinical predictors of mortality due to COVID-19 based on an analysis of data of 150 patients from Wuhan, China
https://link.springer.com/article/10.1007/s00134-020-05991-x