Accelerate drug discovery through confidential crowdsourcing data
Accelerate drug discovery through confidential crowdsourcing data
Accelerate drug discovery through confidential crowdsourcing data
Taking advantage of modern automatic and cryptographic learning tools, researchers have developed a new computational protocol that allows researchers from multiple companies and pharmaceutical libraries to share research and collaborate safely in the development of new drugs, without revealing the underlying confidential data belonging to them. to anyone involved.
According to the report, the experimental shared data sets improve the capacity of predictive models, designed to identify drug-receptor interactions (DTI), in order to predict new therapeutic candidates to a pace and scale much greater than the current cutting-edge methods, which could greatly accelerate the development of drugs.
While collaborative efforts between pharmaceutical companies and academic laboratories have proven to be fruitful in the development of new medicines, they are often limited in scope due to concerns about intellectual property and financial interests encountered, and the exchange of data between multiple entities. is restricted by the need to maintain confidentiality.
The multiparty secure computation (MPC) protocols offer a modern cryptographic solution to facilitate collaboration and guarantee data privacy. However, the existing MPC frameworks lack, according to the authors, the ability to perform complex algorithms on the large data sets that are needed to predict new therapeutic drugs.
To address this need, Brian Hie and his colleagues developed a computational protocol for predicting collaborative DTI based on secure MPC, which hides confidential data and divides computational tasks between collaborating groups. The combined safe data set was used to train a neural network model for the prediction of DTI.
According to the results, the protocol allowed the model to produce accurate results in less than four days of training in a wide area network on a data set with more than one million interactions. While the method demonstrates a promising solution for pharmaceutical collaboration, the authors suggest that it could also be used in other areas that are hampered by lack of collaboration due to confidentiality issues. (Source: AAAS)
.
LINK OF THE ORIGINAL SOURCE SCIENCE & TECHNOLOGY NEWS
Related
!function(f,b,e,v,n,t,s)
{if(f.fbq)return;n=f.fbq=function(){n.callMethod?
n.callMethod.apply(n,arguments):n.queue.push(arguments)};
if(!f._fbq)f._fbq=n;n.push=n;n.loaded=!0;n.version='2.0';
n.queue=[];t=b.createElement(e);t.async=!0;
t.src=v;s=b.getElementsByTagName(e)[0];
s.parentNode.insertBefore(t,s)}(window, document,'script',
'https://connect.facebook.net/en_US/fbevents.js');
fbq('init', '369524843414444');
fbq('track', 'PageView');
.
SOURCE LINK ERESVIRAL.COM https://www.beviral.online
Comentarios
Publicar un comentario