首页
论文
新闻
招聘
职业生涯
活动
官方微信
发布职位
登录 / 注册
目前收录职位
1
9
4
7
4
论文导读
1
8
0
1
0
学术会议
2
3
6
热门搜索:
今天的科技头条《环球科学》杂志社科学60秒Cell人工智能Science博士后科研助理nature
快速浏览
×
管理网站
展示网站
网站名称
网址
热门网站推荐(点击添加)
百度学术
ScienceDirect
Web Of Science
APS
PubMed
必应学术
IEEE
Wiley
google scholar
springer link
ScienceMag
Mendeley
aMiner
arXiv
T&F
BMJ
EBSCO
The Lancet
nature.com
NCBI
中国知网
未登录
您需要先登录才能添加更多网站
查看更多
论文
按学科查找
速度提高100万倍:哈佛医学院提出可预测蛋白质结构的新型深度模型
Highlights• Neural network predicts protein structure from sequence without using co-evolution• Model replaces structure prediction pipelines with one mathematical function• Achieves state-of-the-art performance on novel protein folds• Learns a low-dimensional representation of protein sequence spaceSummaryPredicting protein structure from sequence is a central challenge of biochemistry. Co-evolution methods show promise, but an explicit sequence-to-structure map remains elusive. Advances in deep learning that replace complex, human-designed pipelines with differentiable models optimized end to end suggest the potential benefits of similarly reformulating structure prediction. Here, we introduce an end-to-end differentiable model for protein structure learning. The model couples local and global protein structure via geometric units that optimize global geometry without violating local covalent chemistry. We test our model using two challenging tasks: predicting novel folds without co-evolutionary data and predicting known folds without structural templates. In the first task, the model achieves state-of-the-art accuracy, and in the second, it comes within 1–2 Å; competing methods using co-evolution and experimental templates have been refined over many years, and it is likely that the differentiable approach has substantial room for further improvement, with applications ranging from drug discovery to protein design.Graphical Abstract
查看更多
招聘
按学科查找
河北大学光信息技术创新中心
博士
面议
博士
河北保定
研究方向:1、光学相干断层扫描(OCT)技术在医疗诊断和材料检测的应用; 2、分布式光纤传感技术及应用(包括可调频窄线宽激光光源等使能技术研究); 3、基于分布式光纤传感的智能蒙皮技术及应用; 4、微波光子学研究; 5、光纤电流电压互感器技术及其在智能电网中的应用。
查看更多
合作伙伴
中国自动化学会
中国科学院物理研究所
中国科学院高能物理研究所
青岛海洋科学与技术国家实验室
浙江大学学术委员会
云南中科灵长类生物医学重点实验室
瑞典皇家理工学院
Cell Research
国家科学评论
中国科学院院刊
北京知识产权运营管理有限公司
赛伯乐投资集团
联系我们
电话:010-85321181
邮箱:help@linkresearcher.com
工作日:周一至周五 9:00-17:30
关注科研圈微信公众号
友情链接
www.linkresearcher.com 领研©京ICP备14007358号-1 / 京公网安备11010802014104号 / Powered by © 2008-2017