Realizing private and practical pharmacological collaboration.
Realizing private and practical pharmacological collaboration.
复制标题
DOI:
10.1126/science.aat4807
复制
发表时间:
2018-10-19
期刊:
影响因子:
--
通讯作者:
Berger B
中科院分区:
文献类型:
--
作者:
Hie B;Cho H;Berger B
While combining data from multiple entities could power life-saving breakthroughs, open sharing of pharmacological data is generally not viable due to data privacy and intellectual property concerns. To this end, we leverage modern cryptographic tools to introduce a computational protocol for securely training a predictive model of drug-target interactions (DTI) on a pooled dataset that overcomes barriers to data sharing by provably ensuring the confidentiality of all underlying drugs, targets, and observed interactions. Our protocol runs within days on a real dataset of more than a million interactions, and is more accurate than state-of-the-art DTI prediction methods. Using our protocol, we discover novel DTI that we experimentally validated via targeted assays. Our work lays a foundation for more effective and cooperative biomedical research. A computational protocol enables collaborative drug discovery by securely combining private pharmacological data.
登录
查看更多内容
影响因子:
5.6
作者:
Cobanoglu MC;Liu C;Hu F;Oltvai ZN;Bahar I
通讯作者:
Bahar I
影响因子:
5.8
作者:
Wang, Wenhui;Yang, Sen;Li, Jing
通讯作者:
Li, Jing
影响因子:
5.8
作者:
Mei, Jian-Ping;Kwoh, Chee-Keong;Zheng, Jie
通讯作者:
Zheng, Jie
影响因子:
9.3
作者:
Simmons, Sean;Sahinalp, Cenk;Berger, Bonnie
通讯作者:
Berger, Bonnie
影响因子:
14.9
作者:
Szklarczyk D;Santos A;von Mering C;Jensen LJ;Bork P;Kuhn M
通讯作者:
Kuhn M