These silicon scientists are executing thousands of experiments, searching for life-saving

這些硅科學家正在執行成千上萬的實驗，尋找拯救生命的方法。

drugs and building synthetic organisms -- all with virtually no human intervention.

藥物和建立合成生物體 -- -- 所有這些幾乎都不需要人類干預。

It's part of a industry-wide push to move away from time-intensive manual benchwork

這是整個行業推動擺脫時間密集型手工工作的一部分。

and towards automation.

並走向自動化。

This has the potential to transform how we develop new therapies, and could fundamentally

這有可能改變我們開發新療法的方式，並可能從根本上。

reimagine scientific discovery.

重塑科學發現。

The life sciences are really underserved by automation and technology in general.

生命科學領域的自動化和技術確實普遍服務不足。

If you go into a lab, you'll see humans doing a lot of labor intensive work.

如果你走進實驗室，你會看到人類在做很多勞動密集型的工作。

There's a joke that sort of PhD students are free labor for professors.

有一個笑話說，那種博士生是教授的免費勞動力。

When I was doing my PhD, that's actually when I first started using Strateos' robotic cloud

當我在讀博士的時候，其實就是我第一次開始使用Strateos的機器人云的時候。

lab myself.

我自己的實驗室。

The concept was that you could log into a web application, design an experiment with

這個概念是，你可以登錄到一個網絡應用，設計一個實驗，與

code, and then have it executed for you by robots remotely via the internet.

代碼，然後由機器人通過互聯網遠程為你執行。

I got really excited and so I signed up, and then I actually started running experiments.

我真的很興奮，所以我註冊了，然後我真的開始跑實驗。

I remember being sat on the couch in my apartment and just sort of watching this experiment

我記得當時我坐在公寓的沙發上 看著這個實驗... ...

execute while I was just relaxing, and I thought, "Well, this is the future of life science."

執行，而我只是放鬆， 我想，"嗯，這是生命科學的未來。"

This is really about helping humans focus more on the creative aspects of hypothesis

這其實是幫助人類更專注於假說的創造性方面。

generation and scientific interpretation, then the moving of small amounts of liquid

生成和科學解釋，然後將少量液體移動到一個地方。

around or shining lasers at them.

或用脈衝光照射他們。

Not only does offloading experimental work onto robots have the potential to save enormous

將實驗工作卸載到機器人身上，不僅有可能節省大量的費用，而且還可以節省時間。

amounts of time, it could also mean more reliable results.

的時間量，也可能意味著更可靠的結果。

Often when you look at a protocol that a human is executing, there's very ambiguous steps

通常，當你看到一個人類正在執行的協議，有非常模糊的步驟。

like incubate overnight, which is not a set period of time, or shake until the solution

如孵化過夜，這不是一個固定的時間段，或搖動，直到溶液。

is cloudy.

是多雲。

There's no real definition of cloudy or how much you should shake that sample.

沒有真正意義上的濁度定義，也沒有真正意義上的應該搖動多少樣本。

Every experiment that Strateos has executed is actually defined by code. And so, when

Strateos所執行的每一個實驗，其實都是由代碼定義的。所以，當

I want my colleagues to replicate an experiment that I've performed, I can just give them

我想讓我的同事複製我所做的實驗，我可以直接給他們。

access to that code, and they can just click Go and it runs exactly the same way.

訪問該代碼，他們只需點擊 "Go"，就能以同樣的方式運行。

So the first step in getting robots to do your scientific bidding?

那麼，讓機器人為你科學競價的第一步是什麼？

Log on to a website.

登錄網站。

You actually see a whole menu of different scientific processes that you can choose from.

實際上，你看到的是一個完整的菜單，你可以選擇不同的科學過程。

After you've put in all your parameters of the experiment, and you've also chosen your

當你輸入了所有的實驗參數，並且你也選擇了你的

samples as well, you click Launch and then our system actually automatically checks that

樣品，你點擊啟動，然後我們的系統實際上會自動檢查。

you're not trying to pipette a crazy amount of liquid, or you're trying to use something

你不是想用移液器移取大量的液體，也不是想用什麼東西。

dangerous.

危險的。

If it's all good, our system automatically dispatches the work down to the robots.

如果一切正常，我們的系統就會自動把工作調度下來給機器人。

We're inside one of our work cells here.

我們在這裡的一個工作間裡。

This is the robotic arm, you can see it's coming towards us.

這是機械臂，你可以看到它正向我們走來。

This arm has been told to move around some inventory on this plate in particular, so

這隻手臂已經被告知，要在這個板塊上特別移動一些庫存，所以。

there's experiments all in this little plate.

有實驗都在這個小板塊。

And once that comes out, this plate is actually then going to go to an analytical device.

而一旦出來，這塊板子其實就會被送到一個分析設備上。

Meanwhile, the robot is then going to go off and do some other experiments for a different

同時，機器人還要去做一些其他的實驗，為不同的。

user.

用戶。

Once it's done, the user gets a notification via their email and they can just go in and

一旦完成，用戶就會通過他們的電子郵件收到通知，他們可以直接進入和

fetch their results.

取其結果。

At optimal conditions, a single workcell could execute 190,000 experiments in a day, and

在最理想的條件下，一個工作單元一天可以執行19萬次實驗，而在最理想的條件下，一個工作單元一天可以執行19萬次實驗。

Strateos currently has 23 workcells in operation.

Strateos目前有23個工作單元在運行。

We really believe that this is going to go more and more towards the types of scale that

我們真的相信，這將會越來越多地走向規模化的類型。

cloud computing has reached.

雲計算已經達到。

You could picture a huge warehouse type of facility packed full of robotics and inventory

你可以想象一個巨大的倉庫式的設施，裡面裝滿了機器人和庫存。

and storage equipment for samples.

和樣品的儲存設備。

And then thousands of scientists all using that equipment and infrastructure simultaneously

然後數千名科學家同時使用這些設備和基礎設施。

and remotely via the internet.

並通過互聯網遠程。

Faster, easier, and more reliable experimental results would be a game changer across industries,

更快、更簡單、更可靠的實驗結果將改變各行業的遊戲規則。

but one that could benefit most is drug discovery.

但其中最能受益的是藥物發現。

The process of developing drugs has become extremely difficult.

開發藥物的過程變得非常困難。

We start by identifying a target that we're looking to develop a drug or some other therapy

我們首先要確定一個我們正在尋找開發藥物或其他療法的目標。

for.

為：

We design an assay that will tell you whether or not the activity of that particular target

我們設計了一種檢測方法，可以告訴您該特定靶點的活性是否存在。

has been inhibited or not, and then screen that over many, many possible compounds, many

抑制或不抑制，然後在很多很多可能的化合物中進行篩選，很多的

possible drugs.

可能的藥物。

It can take years of experiments and cost billions of dollars to develop a single drug.

開發一種藥物可能需要多年的實驗，花費數十億美元。

And often, after all of that, it could fail before getting to market.

而往往在經歷了這些之後，在進入市場之前可能會失敗。

Using a cloud lab could help drug developers streamline that process.

使用雲實驗室可以幫助藥物開發者簡化這一過程。

But we're really excited that we've been able to work with Eli Lilly and actually add synthetic

但我們真的很興奮，我們已經能夠與禮來合作，並實際添加合成的。

chemistry to the platform.

化到平臺。

What that means is that entirely via the cloud users will be able to design molecules, have

這意味著，完全通過雲端用戶將可以設計分子，有。

them made and purified, and then ran through those biological assays so they can get that

然後通過這些生物測試，這樣他們就可以得到這些東西

whole process from their idea to data.

從他們的想法到數據的整個過程。

It's not just large pharma and biotech that have access to this.

不僅僅是大型製藥和生物技術公司有機會獲得這些。

This platform basically offers state-of-the-art equipment that's typically only been accessible

這個平臺基本上提供了最先進的設備，通常只有在這個平臺上才能獲得

to the big guys and actually makes it easier for either startups or academics to have access to this.

到大佬，其實無論是創業公司還是學術界都更容易獲得這些。

COVID has been a really interesting time for Strateos.

對於Strateos來說，COVID是一個非常有趣的時代。

The number of people that have reached out to us saying, "Hey, my lab is suddenly closed,

有多少人找到我們說："嘿，我的實驗室突然關閉了。

I need to keep this work going over this time."

我需要在這段時間裡把這項工作繼續下去。"

I think people have seen the need to work remotely.

我想大家已經看到了遠程工作的必要性。

Science should be able to continue without physical access to a lab.

科學應該能夠在沒有實際進入實驗室的情況下繼續進行。

Automating the execution of experiments is a huge step towards more efficient and accessible

自動執行實驗是朝著更高效、更便捷的方向邁出的一大步。

scientific discovery, but some want to go even further to develop robots that actually

科學發現，但有些人想更進一步，開發出真正的機器人。

design their own experiments.

自己設計實驗。

A key concept in automated science is the idea of a closed loop for experimentation.

自動化科學的一個關鍵概念是實驗閉環的概念。

Closed loop experimentation starts with execution of some set of experiments.

閉環實驗是從執行某組實驗開始的。

The second step is to build a model from that data, and then the third step is to decide,

第二步是根據這些數據建立一個模型，然後第三步是決定。

"What experiments should I do next in order to optimally improve that model?"

"為了優化改進該模型，我接下來應該做哪些實驗？"

This loop relies on the union of robotics, machine learning and artificial intelligence.

這個循環依靠的是機器人、機器學習和人工智能的結合。

And getting it right could completely upend how we find life-saving drugs.

而正確的做法可能會徹底顛覆我們尋找救命藥的方式。

So you can think of this like playing the game of Battleship.

所以，你可以把這當成是玩戰艦遊戲。

You've got x and y coordinates, x being the drugs and y being the targets.

你有x和y的座標，x是藥物，y是目標。

We're playing the game by doing A1, B1, C1, D1, and if anybody's ever played Battleship

我們玩遊戲的方法是做A1、B1、C1、D1，如果有人玩過《戰艦》的話

you know that's not a winning strategy.

你知道這不是一個成功的策略。

What we really need is to explore the board, and then build a model as you're doing that

我們真正需要的是探索板塊，然後建立一個模型，因為你在做這個事情。

and use that in order to make your next choice.

並以此來進行下一步的選擇。

That's where automated science comes in is to tackle the creation of a full predictive

這就是自動化科學的作用，就是要解決建立一個完整的預測性的

model for the experimental space of drugs and targets.

藥物和靶點的實驗空間模型。

In the future, this same method could be expanded to build predictive models for the complex

在未來，同樣的方法可以擴展到建立複雜的預測模型。

interactions within our bodies, giving us a much clearer understanding of how they work

我們的身體內部的相互作用，讓我們更清楚地瞭解它們是如何工作的。

and what to do when they don't.

以及當他們不這樣做時該怎麼做。

But there's still a ways to go.

但還有一段路要走。

Moving towards the future of automated science, one of the challenges of course is a technical

朝著自動化科學的未來前進，當然，挑戰之一是技術上的。

one.

一。

How do we implement this for many different kinds of experimental spaces for different

對於多種不同類型的實驗空間，我們如何實現對不同的

cells, for tissues, for whole organisms.

細胞、組織、整個生物體。

And so that, of course, is going to take an enormous amount of work.

是以，這當然需要大量的工作。

But there is a real bottleneck there in the adoption of this automated science approach

但是，在採用這種自動化科學方法時，確實存在一個瓶頸。

by scientists.

由科學家。

I thought that a good place to start would be by building a Master's program in automated

我想，一個好的開始是建立一個自動化的碩士課程。

science.

科學。

The first class just finished their first year.

第一班剛上完一年級。

Those are going to be some of the most productive scientists around because they'll be able

這些將是一些最富有成效的科學家，因為他們將能夠

to scale their experiments through code and automation, and also be able to scale the

通過代碼和自動化來擴大他們的實驗規模，也能夠擴大他們的實驗規模。

actual data analysis piece as well.

實際的數據分析片以及。

A lot of people ask me, "What's the role for humans if you've eliminated humans from the

很多人問我："如果你把人類淘汰了，人類的作用是什麼？

loop?"

跑？"

I think that one answer to that kind of question is the same answer that's been given to automation

我想，這種問題的一個答案，也就是對自動化的一個答案了

for hundreds of years which is that automation doesn't replace the need for people.

數百年來，這就是自動化並不能取代對人的需求。

It changes the jobs that people do.

它改變了人們的工作。

Now a PhD student themselves could be their own PI of all of these different robots doing

現在一個博士生自己就可以成為自己的PI，所有這些不同的機器人都在做

experiments for them.

為他們做實驗。

So they can actually have much grander aspirations of the hypotheses that they want to evaluate,

所以，他們對自己想要評估的假說，其實可以有更宏大的願望。

and the scale of experimentation they want to accomplish.

以及他們想要完成的實驗規模。