linkstream2 microblog

Please find the article at link:
https://www.pharma-iq.com/informatics/articles/is-big-pharma-really-on-cusp-of-ai-shake-out-0

Is big pharma really on cusp of AI shake-out?

By: Pharma IQ
Posted: 07/14/2017

QT:{{”

The promises of “disruptive technologies” have failed to live up to expectations in the past. For example, the development of ‘high throughput screening’ – a process that employs robotics to conduct millions of chemical, genetic and pharmacological tests in rapid time – in the 1990s failed to significantly reduce R&D inefficiencies and offered sporadic success rates.

“The major cost in drug R&D is last-phase clinical trials,” said Dr Mark Gerstein, professor of biomedical informatics at Yale University. “It is not clear whether AI can be as useful for these as it has been in target selection for the initial phases.”

“One of the first principles of data mining is that history is a good predictor of the future. AI has a track record of not living up to its expectations and therefore caution about how great its impact will be in the healthcare industry is now warranted.”
“}}

UCB & @BitmarkInc partner to bring data donation to public health
studies https://Medium.com/@bitmark/uc-berkeley-and-bitmark-partner-to-bring-data-donation-to-public-health-studies-3e9a17891432 Using #blockchain to control one’s data

Tomasetti & Volgenstein

Science 2 January 2015:
Vol. 347 no. 6217 pp. 78-81
DOI: 10.1126/science.1260825

It’s a correlation between aggressiveness, mutations and cell division http://www.sciencemag.org/content/347/6217/78

The discovery of integrated gene networks for autism and related disorders

Fereydoun Hormozdiari
Osnat Penn
Elhanan Borenstein
Evan E. Eichler

Published in Advance November 5, 2014, doi:10.1101/gr.178855.114 Genome Res. 2015. 25: 142-154

QT:{{”
Motivated by this observation, we have developed a novel method that simultaneously integrates information from both PPI and coexpression networks to identify highly connected modules in both types of networks that are also enriched in mutations in cases and not in controls. We call this method MAGI, short for merging affected genes into integrated networks. MAGI is based on a combinatorial
optimization algorithm that aims to maximize the number of mutations in the modules while accounting for gene length and distribution of putative LoF and missense mutations in cases and controls. MAGI is generic and can be applied to any disease, given a list of de novo mutations in cases and relevant coexpression information. Using neurodevelopmental RNA-seq data from the BrainSpan Atlas
(http://www.brainspan.org/), we have applied it to exome sequence data generated from ASD, ID, epilepsy, and schizophrenia, providing a comprehensive comparison of common and specific gene modules for these diseases.
“}}

Speak text with ios…
http://9to5mac.com/2014/10/04/ios-8-how-to-have-your-ios-device-read-text-for-you/

DUX4 binding to #retroelements creates promoters that are active… Highlights #chipseq binding sites in #repeats
http://www.plosgenetics.org/article/info%3Adoi%2F10.1371%2Fjournal.pgen.1003947 http://www.ncbi.nlm.nih.gov/pubmed/?term=24278031
PLoS Genet. 2013 Nov;9(11):e1003947. doi:
10.1371/journal.pgen.1003947. Epub 2013 Nov 21.
DUX4 binding to retroelements creates promoters that are active in FSHD muscle and testis.
Young JM, Whiddon JL, Yao Z, Kasinathan B, Snider L, Geng LN, Balog J, Tawil R, van der Maarel SM, Tapscott SJ.

http://julialang.org/