本文节选自外刊《自然》,内容如下:
DeepMind’s AI for protein structure is coming to the masses
DeepMind的蛋白质结构人工智能正在走向大众
The structure of human interleukin-12 protein bound to its receptor, as predicted by machine-learning software. Credit: Ian Haydon, UW Medicine Institute for Protein Design
人白介素12蛋白与其受体结合的结构——由机器学习软件预测。来源:Ian Haydon, UW Medicine Institute for Protein Design
Machine-learning systems from the company and from a rival academic group are now open source and freely accessible.
DeepMind公司和一个对手团队的机器学习系统现已全部开源,并可免费获取。
protein蛋白质;朊
the masses群众;广大群众;大众
machine机械装置;机器;自动售货机;机械;机构;权力组织;机械般工作的人;用机器加工;用机器操作;用缝纫机缝制;用缝纫机加工
rival竞争对手;敌手;可与…匹敌的人;可与之相比的人;与… 竞争;努力赶上;与…匹敌;比得上
academic学术的;教育和学问的;不切实际的;纯理论的;大学的;学校的;学院的;偏重理论的;非技术教育的;不注重实践教育的;大学教师;学者
open source开放源码;开放资源;开放源
freely自由地;随心所欲地;坦率地;自愿地;大量地;不受限制(或干扰)地;丰富地;直爽地;心甘情愿地
accessible可到达的;可进入的;平易近人的;易懂的;易得到的;易使用的;可以理解的;残疾人可以到达(进入或使用)的
It’s protein-structure prediction for the people. 全民可用的蛋白质结构预测来了。
Software that accurately determines the 3D shape of proteins is set to become widely available to scientists.能够精准解析蛋白质三维结构的软件将供科学家广泛使用。
On 15 July, the London-based company DeepMind released an open-source version of its deep-learning neural network AlphaFold 2 and described its approach in a paper in Nature.
7月15日,总部位于伦敦的公司DeepMind发布了其深度学习神经网络AlphaFold 2的开源版本,并在《自然》杂志的一篇论文中描述了其方法。
The network dominated a protein-structure prediction competition last year.
该网络在去年的蛋白质结构预测竞赛中占据了主导地位。
Meanwhile, an academic team has developed its own protein-prediction tool inspired by AlphaFold 2, which is already gaining popularity with scientists. 与此同时,一个学术团队在AlphaFold 2的启发下开发了自己的蛋白质预测工具,该工具已经受到科学家的欢迎。
That system, called RoseTTaFold, performs nearly as well as AlphaFold 2, and is described in a Science paper also published on 15 July.
该系统被称为RoseTTaFold,性能几乎和AlphaFold 2一样好,该团队7月15日在《科学》发表了一篇论文阐释了这个系统。
determines决定;判决;限定;判定;(determine的第三人称单数);终止;[主用于法律]了结;结束
proteins蛋白质;(protein的复数)
set to开始起劲地干;与舞伴相对而舞
open-source源代码开放的
in nature自然界中;本质上,事实上
dominated支配;控制;(dominate的过去式和过去分词);受控的
inspired by受到...启发;灵感来自...;由...所启发
gaining获得;得到;增加;收益;获利;(gain的现在分词)
popularity受欢迎,讨人喜欢的状态;普及,流行
performs执行任务;完成...;实施行动;履行职责;演出;表演;(perform的第三人称单数)
The open-source nature of the tools means that the scientific community should be able to build on the advances to create even more powerful and useful software, says Jinbo Xu, a computational biologist at the University of Chicago in Illinois, who was not involved in either effort.
这两个工具的开源意味着科学界现在能在这些成果的基础上,创造出更强大、更有用的软件,未参与这两项研究的伊利诺伊州芝加哥大学的计算生物学家徐金波(音译)说。
open-source源代码开放的
scientific community科学界;科学共同体;科研社区
build on基于, 依赖, 指望
advances(使)前进;预付;提出;(advance的第三人称单数);上涨;进展;前进;预付款;增长;(advance的复数)
even more甚至
powerful强大的;强有力的;大功率的;效力大的;有影响力的;影响大的;非常;很
useful有用的;实用的;有效的;胜任的;有能力的
computational使用计算机的;计算机的;计算的
biologist生物学家;生物学者
involved in卷入;参与;包含
Structure to function从结构到功能
Proteins are made of strings of amino acids that, when folded into 3D shapes, determine the function of those proteins in cells.
蛋白质是由氨基酸链组成的,折叠成三维结构的氨基酸链决定了细胞内蛋白质的功能。
For decades, researchers have used experimental techniques such as X-ray crystallography and cryo-electron microscopy to determine protein structures.
数十年来,研究人员一直在用X射线晶体学和冷冻电镜这类实验技术解析蛋白质结构。
But such methods can be time-consuming and costly, and some proteins are not amenable to such analysis.
但是,这类方法存在费时耗钱的问题,对一些蛋白也不适用。
strings线;弦;一串;绳子;(string的复数);(用线)串;挂;系;扎;串起;连成一串;(string的第三人称单数)
amino acids氨基酸;氨基酸类
folded折叠的;对折的;折叠;抱住;笼罩;合拢;(fold的过去式和过去分词);彻底失败;折叠起来
shapes形状;身材;模型;外形;(shape的复数);塑造;使符合;决定…的形成;(shape的第三人称单数);形成;摆好姿势
crystallography晶体学
electron microscopy电镜术;电镜成像;电子显微镜分析
time-consuming耗费时间的;旷日持久的
costly贵重的;昂贵的;损失惨重的;代价大的
amenable to服从;顺从;经得起
DeepMind sent shock waves through the scientific world last year, when it showed that its software could accurately predict the structure of many proteins using the sequence of the proteins alone (which is determined by DNA).
去年,DeepMind在科学界掀起了轩然大波,它的软件仅凭蛋白质的序列(由DNA决定)就能准确预测其结构。
Researchers had been working on this challenge for decades, and AlphaFold 2 performed so well in a biennial protein-prediction exercise called CASP that the competition’s co-founder declared that “in some sense the problem is solved”.
学界在这方面的攻关已经进行了几十年,看到AlphaFold 2在两年一度的“蛋白质结构预测比赛”(CASP)上表现如此优异,以至于该比赛的创始人之一直呼其“在某种程度上攻克了该问题”。
shock令人惊愕的事件;撞击;震动;颤抖;禾束堆;蓬乱(或浓密)的头发;冲击;休克;震惊;惊愕;使惊讶;使惊愕;猛烈碰撞;把…堆成禾束堆;感到震惊;受惊;冒犯…的道义情感;激起…的义愤;使生理休克;使受电击
accurately predict准确地预测;准确预测
working on工作;做…工作
decades十年;十;十年期;(decade的复数)
biennial首脑会议通常两年举行一次;二年生的;二年生植物;两年举办一次的活动
co-founder共同创立者;联合发起人
declared断言;宣称;申报;宣布结束赛局;叫(牌)定约;求爱;宣布参选;宣告;宣布;宣告(或宣布)…为;(declare的过去式和过去分词);公然的;公开宣布的;公告的
solved解决;解答;作解答;溶解;(solve的过去式和过去分词)
DeepMind — which has a reputation for being cagey about its work — described AlphaFold 2 in a brief presentation at CASP on 1 December.
12月1日,DeepMind在CASP一次简短演示中介绍了AlphaFold 2,该公司一直对其讳莫如深。
It promised to publish a paper outlining the network in more detail and to make the software available to researchers, but said little else.
它承诺发表一篇论文,更详细地描述这个网络并向研究人员免费开放整个软件,但具体细节并未展开。
“Among academics, there was a fair amount of doom and gloom,” says David Baker, a biochemist at the University of Washington in Seattle whose team developed RoseTTaFold.
西雅图华盛顿大学的生物化学家David Baker说:“在学术界,有相当多的悲观情绪。”他的团队开发了RoseTTaFold。
“If someone has solved the problem you’re working on but doesn’t disclose how they did it, how do you continue working on it?”
“如果有人已经解决了你正在研究的问题,但不肯告诉你解决方法,你还怎么研究下去呢?”
“I felt like I lost my job at the time,” says computational chemist Minkyung Baek, a member of Baker’s team.
“我当时觉得自己失业了。”Baker团队的成员、计算化学家Minkyung Baek说。
But DeepMind’s presentation also spurred new ideas that Baek couldn’t wait to explore.
但是DeepMind的演讲也激发了Baek迫不及待想要一探究竟。
So she, Baker and their colleagues started brainstorming ways to replicate AlphaFold 2’s success.
于是,她和Baker还有他们的同事开始集思广益,寻找复制AlphaFold 2成功的方法。
cagey吞吞吐吐的;不愿透露的
in more detail更详细;更详细地;细节问题上
fair amount相当金额;相当数量;公允的数额
doom and gloom悲观失望的氛围
biochemist生物化学家
Seattle西雅图
continue working继续工作;持续工作
chemist药房;药店;化学家;化学研究员;化学实验师;药剂师
spurred装有马刺的;有花距的;鞭策;(spur的过去分词)
They identified several key advances, including how the network uses information about proteins that are evolutionarily related to the targets researchers are trying to predict, and how the predicted structures of one part of a protein can influence how the network handles sequences corresponding to other parts of the molecule.
他们确定了AlphaFold 2的几大关键性进展,包括如何利用与预测目标在演化上相关的蛋白的信息,以及预测出的一个蛋白的部分结构如何影响AlphaFold 2对该分子其他部位对应序列的处理。
RoseTTaFold not only performed nearly as well as AlphaFold 2 — but also much better than other CASP entries (including some from the Baker lab). RoseTTaFold的预测能力毫不逊于AlphaFold 2,而且还远超其他CASP参赛团队的预测结果(包括一些来自Baker实验室的预测结果)。
It’s not yet clear why it couldn't equal AlphaFold 2, but one possibility is DeepMind’s expertise, says Baek.
现在还不清楚它比AlphaFold 2差在哪里,一个可能是DeepMind拥有的专业能力,Baek说。
“We don’t have any deep-learning engineers in our lab.” Xu is impressed by the efforts of Baek, Baker and their collaborators, and suspects that DeepMind’s success was down to its access to engineering expertise and superior computing power.
“我们实验室没有深度学习工程师。”徐(音译)很佩服Baek、Baker和他们合作者的工作,并猜测DeepMind的厉害之处在于其工程方面的专业知识和独一无二的算力。
handles操作;处理;应付;触;拿;搬动;控制;操纵;驾驶;买卖;(handle的第三人称单数);柄;把手;提梁;有…柄;(handle的复数)
sequences连续;一组镜头;一系列;一连串;顺序;次序;片段插曲;(sequence的复数);按顺序排列好;安排顺序;测定(基因或分子成分的)序列;[生化]确定…的顺序;确定…的化学结构序列;(sequence的第三人称单数)
corresponding to相当于…;与…一致;对应
molecule分子;摩尔
much better than远好于;远胜过;比...强得多
entries入口;条目;(entry的复数)
impressed给...深刻印象;(impress的过去式和过去分词);印象深刻的;了不起的
collaborators合作者;通敌者;(collaborator的复数)
suspects疑有;觉得;怀疑;感觉有问题;不信任;怀疑某人有罪;(suspect的第三人称单数);嫌疑犯;嫌疑分子;可疑对象;(suspect的复数)
Speedy structures
加速结构解析
DeepMind has also streamlined AlphaFold 2. Whereas the network took days of computing time to generate structures for some entries to CASP, the open-source version is about 16 times faster, says AlphaFold lead researcher John Jumper. It can generate structures in minutes to hours, depending on the size of the protein. That’s comparable to the speed of the RoseTTaFold.
DeepMind 还对AlphaFold 2进行了优化。虽然这个网络在预测CASP比赛中的一些结构时,在计算上用了好几天的时间,但最新的开源版本比这个速度快了约16倍,AlphaFold首席研究员John Jumper说。取决于蛋白质的大小,AlphaFold 2能在几分钟到几小时内预测出结构。这和RoseTTaFold的速度差不了多少。
Although the source code for AlphaFold 2 is freely available — including to commercial entities — it might not yet be particularly useful for researchers without technical expertise. DeepMind has collaborated with select researchers and organizations, including the non-profit Drugs for Neglected Diseases initiative headquartered in Geneva, Switzerland, to predict specific targets, but it hopes to broaden access, says Pushmeet Kohli, head of AI for science at DeepMind. “There is a lot more we want to do in this space.”
虽然AlphaFold 2的源代码现可免费获取——包括商业公司在内,但对不懂技术专业知识的研究人员可能不是特别有用。DeepMind 已经在与一些研究人员和组织合作,预测特定的蛋白质,合作对象包括总部位于瑞士日内瓦的“被忽略疾病药物”(Drugs for Neglected Diseases)非营利性组织,但 DeepMind希望能进一步开放技术,DeepMind的科学AI主管Pushmeet Kohli说。“我们在这个领域还有很多想做的尝试。”
As well as making the code for RoseTTaFold freely available, Baker’s team has set up a server into which researchers can plug a protein sequence and get a predicted structure. Since it was launched last month, the server has predicted the structure of more than 5,000 proteins submitted by around 500 people, says Baker.
除了让RoseTTaFold的代码免费公开,Baker的团队还搭建了一个服务器,研究人员只要插入一个蛋白质序列,就能得到预测好的结构。Baker说,自上个月上线以来,这个服务器已经预测了约500人提交的5000多种蛋白质的结构。
With code now freely available for both RoseTTaFold and AlphaFold 2, researchers will be able to build on both advances, says Xu, and perhaps make the techniques amenable to protein structures that AlphaFold 2 has so far struggled to predict. Two areas of intense interest are predicting the structure of complexes of multiple interacting proteins and applying the software to the design of new proteins.
徐(音译)说,现在RoseTTaFold和AlphaFold 2的代码都可以免费获得,研究人员将能够在这两个进展的基础上再接再厉,并可能使这些技术适用于AlphaFold 2迄今难以预测的蛋白质结构。人们最感兴趣的两个领域是预测多种相互作用蛋白质复合物的结构,以及将该软件应用于新蛋白质的设计。
speedy迅速完成的;快速移动的
streamlined精简;使效率更高;使合理化;把…做成流线型;组织使成流线型;(streamline的过去式和过去分词);流线型的;改进的;最新型的
open-source源代码开放的
lead researcher首席研究员;研究员领导者;研究带头人
comparable to相若;可比于;相当
technical expertise专业技术知识;专门技术知识;技术专长
collaborated合作;通敌;勾结;(collaborate的过去式和过去分词)
non-profit非赢利的;非营利的;非营利机构
headquartered以…为总部所在地的;设立总部于;(headquarter的过去式和过去分词)
基于多年的语言学习实践,发现,随着社会的飞速发展,英语、汉语等重要语言也在不断的与时俱进。这个时候,我们以不变应万变的方法之一,可以是阅读主流刊物。
针对英语而言,无论是为了提高英语水平还是备考任何英语考试,英美外刊都应该是列为首选的最重要的学习资料。当我们真正深入去精读过英美外刊,不仅可以了解英语国家的文化,增长我们的见识,对于英语学习来说,还能够积累以英语为母语者的常用词汇,短语和句型。
建议大家在阅读本文时:第一遍快速阅读,领悟文章重点,了解大意;第二遍开始精读,每看完一段,要仔细体会其中每一句在段落中的功能,各句之间的联系,这一段是如何衔接上下文的,它在整个语篇中的地位,以提高你猜测词义和推理上下文能力;第三遍可以查看中英翻译,继续从微观到宏观地理解原文,学会区分重点和次要信息(这对考试时的阅读非常重要),总结词汇,搭配和句型,并且最好独自翻译一遍原文,以进一步加强理解。
最后建议大家要学以致用,利用从文章中学到的词汇,搭配,句型以及长难句结构进行造句,提高英文写作能力。
学习路径建议:金句记忆——关键词学习——拓展词汇训练——触类旁通——举一反三。
温馨提示:阅读完看着中文译文自己动手翻译出英文,然后将您译的英文与原文进行对比,以此来提升英文表达和句子结构的准确性和地道性。
,