when we sequenced the human genome,

在 2003 年，

we thought we would have the answer to treat many diseases.

當我們為人類的基因組定序時，

But the reality is far from that,

我們以為會找到許多疾病的治療方法。

because in addition to our genes,

但實際情形卻遠非如此，

our environment and lifestyle could have a significant role

因為除了我們的基因之外，

in developing many major diseases.

生活環境和生活作息

One example is fatty liver disease,

也是引發重大疾病的關鍵因素。

which is affecting over 20 percent of the population globally,

以脂肪肝疾病爲例，

and it has no treatment and leads to liver cancer

全球超過 20% 的人口 受此疾病影響，

or liver failure.

目前沒有任何治療方法 而且最後可發展為肝癌，

So sequencing DNA alone doesn't give us enough information

或是肝臟衰竭。

to find effective therapeutics.

所以只靠基因定序 並不能給我們足夠的訊息，

On the bright side, there are many other molecules in our body.

找出有效的治療方法。

In fact, there are over 100,000 metabolites.

好消息是，我們身體裡 還有許多其他的分子，

Metabolites are any molecule that is supersmall in their size.

事實上，我們身體 有超過十萬的代謝物。

Known examples are glucose, fructose, fats, cholesterol --

代謝物是體積超級小的分子，

things we hear all the time.

已知的例子包括， 葡萄糖、果糖、脂肪、膽固醇——

Metabolites are involved in our metabolism.

我們時常聽到的這些東西。

They are also downstream of DNA,

代謝物會參與新陳代謝活動，

so they carry information from both our genes as well as lifestyle.

它們也是 DNA 的後段，

Understanding metabolites is essential to find treatments for many diseases.

所以它們帶著基因訊息 也透露出我們的生活作息。

I've always wanted to treat patients.

要找出許多疾病的治療方法 就有必要瞭解代謝物，

Despite that, 15 years ago, I left medical school,

我一直都想要醫治好病人，

as I missed mathematics.

但是十五年前，

Soon after, I found the coolest thing:

因爲傾心於數學而離開了醫學院。

I can use mathematics to study medicine.

不久，我發現最酷的事情是：

Since then, I've been developing algorithms to analyze biological data.

我可以用數學來研究醫學，

So, it sounded easy:

從那時起，我就一直開發 演算法用來分析生物數據。

let's collect data from all the metabolites in our body,

這聽起來很簡單：

develop mathematical models to describe how they are changed in a disease

我們收集身體中所有代謝物的數據，

and intervene in those changes to treat them.

然後開發數學模型來描述 它們在疾病中如何變化，

Then I realized why no one has done this before:

並且干預這些變化來進行治療。

it's extremely difficult.

然後，我明白為什麼之前 沒有人做過這件事了：

(Laughter)

因為這實在太困難了。

There are many metabolites in our body.

（笑聲）

Each one is different from the other one.

我們身體中有太多代謝物了，

For some metabolites, we can measure their molecular mass

每一個都不盡相同。

using mass spectrometry instruments.

針對一些代謝物，

But because there could be, like, 10 molecules with the exact same mass,

我們能夠用質譜儀 來測量它們的分子量。

we don't know exactly what they are,

但是具有完全相同的 分子量可能有十種之多，

and if you want to clearly identify all of them,

所以無法知道它們確切是什麼東西，

you have to do more experiments, which could take decades

假如要清楚辨識所有代謝物，

and billions of dollars.

必須要做更多的實驗， 那有可能要花上數十年的時間，

So we developed an artificial intelligence, or AI, platform, to do that.

還要耗費幾十億美元。

We leveraged the growth of biological data

因此，我們開發了一種 人工智慧來做這事。

and built a database of any existing information about metabolites

我們利用生物數據的增長，

and their interactions with other molecules.

然後建立一個資料庫 裡面有代謝物的相關訊息，

We combined all this data as a meganetwork.

包含代謝物與其他分子 相互作用的訊息，

Then, from tissues or blood of patients,

我們把所有數據組合成一個巨大網絡。

we measure masses of metabolites

接著，從患者的器官組織或是血液中，

and find the masses that are changed in a disease.

我們測量到代謝物的分子量，

But, as I mentioned earlier, we don't know exactly what they are.

並且尋找因疾病 而產生變化的代謝物質量。

A molecular mass of 180 could be either the glucose, galactose or fructose.

但是，正如我稍早提過， 我們無法確切知道它們是什麼，

They all have the exact same mass

分子量為 180 可能是葡萄糖， 不然就是半乳糖或是果糖，

but different functions in our body.

它們都擁有相同的質量，

Our AI algorithm considered all these ambiguities.

但在身體中有著不同的功能。

It then mined that meganetwork

我們的人工智慧演算考慮到 這些含糊不清的情形，

to find how those metabolic masses are connected to each other

它會在巨大網絡中挖掘數據，

that result in disease.

找出那些代謝物如何相互連結，

And because of the way they are connected,

才會導致疾病的發生。

then we are able to infer what each metabolite mass is,

而且因為它們連接的方式，

like that 180 could be glucose here,

我們得以推斷出 每個代謝物的分子量是多少。

and, more importantly, to discover

在這裡，分子量 180 的可能是葡萄糖。

how changes in glucose and other metabolites

而且更重要的是，

lead to a disease.

發現葡萄糖和其他代謝物的變化

This novel understanding of disease mechanisms

如何引發疾病。

then enable us to discover effective therapeutics to target that.

這種針對疾病機制的新穎理解，

So we formed a start-up company to bring this technology to the market

讓我們能夠針對疾病 找出有效的治療方法。

and impact people's lives.

所以我們成立了一家新創公司 將這項技術帶入市場，

Now my team and I at ReviveMed are working to discover

對大家的生活帶來正面影響，

therapeutics for major diseases that metabolites are key drivers for,

現在我和團隊 在 ReviveMed 生技公司

like fatty liver disease,

正利用代謝物 努力尋找重大疾病的療法，

because it is caused by accumulation of fats,

像是脂肪肝疾病，

which are types of metabolites in the liver.

這是由於脂肪的堆積引起。

As I mentioned earlier, it's a huge epidemic with no treatment.

而脂肪是肝臟中 不同類型的代謝物組成，

And fatty liver disease is just one example.

我稍早提到這種重大疾病 目前沒有任何治療方式，

Moving forward, we are going to tackle hundreds of other diseases

脂肪肝疾病只是其中一個例子，

with no treatment.

我們接著要解決

And by collecting more and more data about metabolites

其他數百種目前尚無治療方式的疾病。

and understanding how changes in metabolites

藉著搜集更多的代謝物數據，

leads to developing diseases,

並且瞭解這些代謝物的變化

our algorithms will get smarter and smarter

如何引發疾病。

to discover the right therapeutics for the right patients.

我們的演算法會變得愈來愈聰明，

And we will get closer to reach our vision

幫助病患找出正確的治療方法。

of saving lives with every line of code.

而且我們能夠利用每條基因碼

Thank you.

一步步達成拯救生命的願景。

(Applause)

謝謝大家。