AI and the Future of Drug Discovery: A Conversation with Isomorphic Labs President Max Jaderberg
打开互动全文版(中英对照 + 朗读 + 问答)→Isomorphic Labs 总裁 Max Jaderberg 探讨如何利用 AI 在临床试验前将生物学理解搬上计算机,从而变革药物发现。
Isomorphic Labs President Max Jaderberg discusses how AI can transform drug discovery by bringing biological understanding onto computers before clinical trials.
今天我们请到了 Max Jaderberg。Max 是 Isomorphic Labs 的总裁,也是创始团队成员之一。Isomorphic 由 Alphabet 和多家其他投资方支持,目标是攻克所有疾病,这个话题非常令人兴奋。我们会聊一聊 AI 在生物制药的未来、人类健康和长寿中扮演的角色。Max 当然有机器学习的背景,在这个方向读了博士,研究机器视觉,后来把一家公司卖给了 Google DeepMind,在那里一路晋升,现在是 Isomorphic 的总裁。非常期待这次对话。Max,非常感谢你今天来参加。
We're joined by Max Jaderberg. Max is the President and part of the founding team of Isomorphic Labs. Isomorphic is backed by Alphabet and a variety of other investors, and its goal is to solve all disease, which is a very exciting topic. We're going to talk a little bit about the role of AI in the future of biopharma, human health, and longevity. And Max, of course, has a background in machine learning. He has a PhD in the topic, working on machine vision, eventually sold a company to Google DeepMind, rose up the ranks there, and now is President of Isomorphic. So very excited to have this conversation. Max, thank you so much for joining us today.
不,能来这里非常荣幸。谢谢你。
No, it's such a pleasure to be here. Thank you.
我觉得 Isomorphic 是当下整个科技界最引人入胜的公司之一。Alphabet 是主要股东,也算赞助方。Demis 在 DeepMind 和其他地方开创了很多模型——我记得你之前把公司卖给了他——他确实在公司的最初构想、搭建以及现在的运营上帮了很多。而你们在攻克人类剩下要解决的最大问题之一,也就是人类健康。能不能讲讲你是怎么参与到这家公司的,以及创立它的驱动力是什么?
Isomorphic, I think, is one of the more fascinating companies right now in technology in general. Alphabet is a major shareholder and sort of sponsor. Demis, who pioneered a lot of models at DeepMind and other places — and I believe you sold your company to him before — really helped with the inception and setup and now running of the company. And you folks are tackling one of the biggest problems left for humanity to tackle, which is human health. Could you tell me a bit about how you came to work on this company and what was the motive force to starting it?
我是 Isomorphic Labs 创始团队的一员。在那之前我在 DeepMind 待了很久。就我个人而言,我早期做的是生成模型、语言模型、深度强化学习,还有那些大型博弈类挑战问题。那些是我的拿手好戏——比如 AlphaGo、AlphaStar。后来就到了一个阶段,我们在攻克当时那些所谓的“不可能问题”。大概是 2018、2019 年。
I was part of the founding team of Isomorphic Labs. I was at DeepMind for a long time beforehand. Personally, I was working on the early days of generative models, language models, deep reinforcement learning, all of the big game-playing challenge problems. Those were my jam — like AlphaGo, AlphaStar. And it got to the point where we were going after these, you know, quote-unquote impossible problems at that point in time. This is probably 2018, 2019.
比如游戏对局,AI 能不能打败电子游戏?
Like gameplay and can AI beat video games?
没错。那时候我们还在努力向世界证明 AI 本身是成立的,对吧?所以我们在攻克这些不可能的问题,而我能亲眼看到怎么系统性地把它们解决掉。对我个人来说,就到了这样一个节点:好吧,我们确实还没到 AGI,但我们显然已经拥有了深度学习、强化学习这一整套了不起的技术。那我们真正该把这些东西聚焦在哪些问题上?我一直在想这些,Demis 当然也一直在想这些。与此同时,我们看到了 AlphaFold 的成果,最初的火苗开始出现,我们真的开始看到——对我们来说,这是第一个概念验证:你可以得到一个在生物学中有意义的空间里具备泛化能力的深度学习模型。正是这个概念验证给了我们信念:现在正是时候去追求这个宏大的使命,改变我们对人类健康的思考方式,去攻克所有疾病。而这需要非常巨大的投入,值得拥有一家自己的公司、自己的文化,让不同学科的具体人才聚到一起,并且能够在这件事上跑得非常快。这就是 Isomorphic Labs 大约在 2021 年诞生的由来。
Exactly. At that point in time, we were still trying to prove to the world that AI was even a thing, right? And so we were going after these impossible problems, and I could see firsthand how to just systematically solve these. And it got to the point for me personally where it's like, okay, sure, we're not at AGI yet, but we clearly have this amazing set of technologies in deep learning and reinforcement learning. And what are the problems we really need to be focusing this stuff on? And I was thinking all of this, of course, and Demis was thinking all of this. At the same time we're seeing the AlphaFold results, the first embers of that starting to emerge, and really starting to see — for us this was the first proof of concept that you could get a deep learning model that generalizes in a meaningful space in biology. And so that was really the proof of concept that gave us conviction that actually now is the right time to go after this big mission of changing the way that we think about human health, going after solving all disease. And that's going to take a really substantial effort, and that warrants its own company, its own culture, specific people of different disciplines coming together for this, and the ability to run really fast on that. So that was the genesis of Isomorphic Labs in about 2021.
哦,太厉害了。你的背景其实更多是从深度学习和 AI 建模这一侧起步的,我记得你把一家公司卖给了 DeepMind——是 2014 年吗?
Oh, amazing. Your background really started off more on the deep learning side and AI modeling side, and I believe you sold a company to DeepMind — was it 2014?
对,没错。
Yeah, that's right.
所以相当早。我是说,你在这件事被大家意识到有多重要之前就已经在做它了,或者说在很多人意识到它有多重要之前。能不能多讲讲你走过的这段旅程,你是怎么走到那里的?最初是什么让你对它产生兴趣的?
So quite early. I mean, you were at this stuff before people realized how important it was, or many people realized how important it was. Could you tell me a little bit more about the journey you took, how you got there? What got you interested in it to begin with?
好,我出身工程背景。几乎是阴差阳错地去读了计算机视觉的博士,而这其实正好赶上一个转折点。我想我是在 AlexNet 之前开始读博的。
Yeah, I come from an engineering background. I ended up almost by accident doing a PhD in computer vision, and this was actually just at the turning point. I think I started my PhD pre-AlexNet.
哦,因为 AlexNet 是 2012 年,对吧?
Oh, because AlexNet was 2012, was it?
对,没错。然后我看到了它的出现。我当时想,哇,这太棒了。我记得和 Yann LeCun 聊卷积神经网络,我说我们得把它引入到我们在牛津做的核心计算机视觉领域。后来我们确实开发出了所有这些方法。我们最终做出了 2014 年 ImageNet 夺冠的网络——最佳物体识别、文本检测,诸如此类。我在这个领域创办了一家公司,做计算机视觉即服务,想融资。而那时候 Demis 和 DeepMind 刚把公司卖给 Google。所以想融资,非常非常快地就变成去跟 Demis 聊,请他做天使投资,结果他说,那你干脆来 DeepMind 解决 AGI 吧。我说,AGI 是什么?就这样开始了在 DeepMind 的旅程和那里的一切。
Yeah, exactly. And then I saw that emerge. I was like, wow, this is awesome. I remember speaking to Yann LeCun about convolutional neural networks, and I was like, we need to translate this into the core computer vision space that we're working on in Oxford. And yes, ended up developing all of these methods. We ended up having the ImageNet-winning network of 2014 — best object recognition, text detection, all of this sort of stuff. And I had built a company in this space, computer vision as a service, and trying to raise money. And at that point in time, Demis and DeepMind had just sold to Google. So trying to raise money, very very quickly ended up just speaking to Demis, asking for angel investment, and he was like, well, why don't you just come to DeepMind to solve AGI. I was like, what's AGI? But so began the journey into DeepMind and everything there.
嗯,太厉害了。你现在的重心基本上是一家垂直整合的公司,从模型一直做到生物学。思路是找到能帮助人们的药物,覆盖人类健康的不同方面。如果你看制药行业,我觉得有一件事非常触目惊心——我以前画过这张图——就是每年新药获批的数量大致是平的。但这是在知识爆炸的背景下。所有那些科学论文,论文数量是指数级增长的。在那段时间里,数量涨了 10 倍、20 倍。新模态的数量、你能做的新药类型也增加了。有抗体类药物、小分子、蛋白质、多肽,有所有这些新的治疗方式。而成本却一路飙升,对吧?从每款药几亿美元涨到了 15 亿美元。
Yeah. Amazing. And your focus now is basically a vertically integrated company that's doing everything from models to the biology. And the idea is to find drugs that can help people, different aspects of human health. And so if you look at the pharma industry, one of the things that I think is really striking — like I've graphed this out in the past — where if you look at the number of new drug approvals per year, it's roughly flat. But that's despite an explosion in knowledge. So all these scientific papers have sort of exponentiated in terms of the number of papers. You know, the numbers have gone up 10, 20x during that period. The number of new modalities, the type of new drugs that you can do has gone up. So there's antibody-based drugs, there's small molecules, there's proteins, there's peptides, there's all these new ways you can treat drugs. The price has gone way up, right? It went from a few hundred million dollars per drug to 1.5 billion.
制药行业很大一部分是一个高度依赖经验的流程。真正出问题的地方是在临床阶段,因为我们直到把药用到病人身上之前都看不到问题,然后我们说:“糟了,有我们没考虑到的毒性。”所以真正巨大的机会,是在进入病人之前就获得多得多的这种理解。我们怎么把所有这些药物发现的工作搬到计算机上?怎么走出真实世界?如果快进哪怕 5 年,对疾病生物学的预测性理解没有发生巨大的跃变,我会非常失望。
The large part of the industry makes medicines is this very empirically driven process. Where things really fail is in the clinic, because we never could see the problems until we get to the point where we put these drugs in patients and we say, "Oh no, there's toxicity that we didn't account for." And so the really big opportunity is to have much more of that understanding before you go into patients. How can we bring all of that drug discovery work onto a computer? So how can we get out of the real world? I'd be really disappointed if we fast forward even 5 years' time and the predictive understanding of disease biology has not step-changed in a massive way.
研发时间从八九年延长到了 15 年。所以每项指标都在恶化,而产出数量却停滞不前。知识库爆炸式增长,你能处理的分子类型也增多了。为什么会这样?为什么在其他方面都取得了那么多进展,这个领域却如此停滞?
It went from eight or nine years to 15 years. So every metric has gotten worse while the number of things have gotten flat. The knowledge base has exploded. The number of types of molecules that you can do has gone up. Why is that? Why has it been so static despite all that progress in other ways?
是啊,看到研发新药越来越难、越来越贵、耗时越来越长,真是令人难以置信。我认为这背后可能有多种原因。我经常思考的一点是,整个行业乃至人类一直以来制药的方式,都是一个非常非常经验驱动的过程。最初,那是很久以前,大概一百年前,我们发明的药物都是偶然发现的。我们只是碰巧遇到了某种东西,人们意识到它有生理效应,然后就采用了。后来变得稍微复杂一些,更多是经验性的试错。
Yeah, it's crazy to see just how it keeps getting harder and harder to make new medicines, more and more expensive, longer and longer. And I think there's probably a number of reasons behind this. The thing that I really think quite a lot about is that the way that we actually make medicines in general in the industry and as a species forever has been a very, very empirical process. Right at the very beginning, it was—and this was a long time ago, like a hundred years ago—the medicines that we came up with came about by chance. We just happened to stumble upon something that people realized has a physiological effect, and people adopted it. Things got a bit more sophisticated. It's a bit more empirical trial and error.
是啊。很多药物我们只是猜的,对吧?比如阿司匹林——我想很长一段时间我们都不知道它怎么起效。
Yeah. A lot of medicines we just guessed, right? Like aspirin—I think for a long time we had no idea how it worked.
阿司匹林我们不知道它怎么起效,扑热息痛我们也不知道它怎么起效。我们一直以来制药的方式,以及大部分行业仍然在用的方式,就是这种非常经验驱动的过程。经验性是指你对疾病可能如何运作有一个假设,对什么是好的分子设计有一个假设,但你必须把它制造出来并在真实世界中测试,而且得非常迭代地进行。
Aspirin we didn't know how it worked. Paracetamol we didn't know how it worked. And the way we've been making medicines and still how the large part of the industry makes medicines is this very empirically driven process. Empirical as in you have a hypothesis on how a disease might work. You have a hypothesis on what a good molecule design could be, but you have to make it and test it in the real world and do this very iteratively.
那很慢。
That's slow.
从中获取信号真的非常非常困难。生物学的空间真的非常庞大和复杂。这些就像巨大而复杂的——细胞是一个巨大复杂的混沌系统。
It's really really difficult to get signal out of that. And the space of biology is really really big and complex. These are like big complex—the cell is a big complex chaotic system.
超高维的。
Super high-dimensional.
然后是分子设计,无论是小分子、抗体还是多肽,它们真的又是非常高维的对象,是组合上巨大的设计问题。而我们唯一可用的工具基本上就是试错筛选过程。
And then molecule design, whether it's small molecules, antibodies, peptides, they're really again really high-dimensional objects, combinatorially large design problems. And the only tools we've got available to us is basically trial and error screening processes.
所以在我看来,这限制了你在有限时间内或投入有限资金进行经验性工作时所能找到的解决方案的复杂度。
And so that limits to me the complexity of solution that you can find in a finite period of time or finite amount of money that you spend on that empirical work.
所以我认为,随着时间的推移,你能看到的是,通过我们这种经验性的药物设计过程能够找到的低垂果实正在被摘取。我们正在找到低垂的果实,但之后要提升复杂度、找到那些经验过程无法触及的东西就越来越难了。
And so I think what you've seen over time is that the low-hanging fruit of medicines that can be found with our empirical process of designing medicines are being found. We're finding the low-hanging fruit, but then it's getting harder and harder to ratchet up the complexity and find things that are out of reach from this empirical process.
这很有趣。但你不觉得吗?如果我看任何其他行业,经常发生的是行业的年龄会影响其变化速度。换句话说,行业越老,行动越慢。事情变得更官僚化,有更多的监管俘获等等。我想上一次有生物制药公司估值超过 500 亿美元——除了 Moderna,而我认为 Moderna 几乎是新冠的意外产物——是在 1980 年代,我想是 Regeneron。
That's interesting. But don't you think so? If I look at any other industry, often what happens is the age of the industry impacts the rate of change in it. In other words, the older the industry, the slower it moves. Things become more bureaucratic. There's more regulatory capture etc. I think the last time there was a biopharma company that was worth over $50 billion—besides Moderna, and I think Moderna was almost an accident of COVID—was the 1980s I think, with Regeneron.
是的。
Yeah.
所以自从我们建立起一家新的价值数百亿美元的生物技术公司以来,已经快 40 年了。
And so it's been almost 40 years since we've had a new tens of billions of dollar biotech built.
是的。Regeneron、Vertex,这些你知道——
Yeah. Regeneron, Vertex, these you know—
安进也是那个时代,80 年代初。
Amgen was that era too, early '80s.
那么你认为有多少只是监管问题或官僚组织,或者只是那种自然的衰老?我认为这到处都会发生——你知道,汽车行业在特斯拉之前就是这样。
And so how much do you think is just like regulatory issues or bureaucratic organizations or just like that natural aging? I think that happens everywhere—you know, that was automotive until Tesla.
我们谈到了科学方面。我认为还有一个很大的文化层面,就是作为一个行业,你如何持续创新,如何保持非常非常快的行动速度。我还认为——这与科学和技术部分相关——是哪些机制真正能在创新侧、在研发侧给你带来规模经济。所以如果你针对某个特定的药物靶点,试图制造某种药物,而你是制药公司或生物技术公司,你会全力以赴。你从中学习到什么,能帮助你更快地研发下一种药物,然后下一种药物更快?因为如果你能随着时间的推移实现学习的复利,你也许就能获得规模效益,作为一家公司建立起真正了不起的庞大事业。但我认为很多技术以及我们研发药物的方式——或者说行业研发药物的方式——实际上是把每一个都当作一个分割的、定制的前沿科学项目。你对那个项目了解了很多,但可能没有太多可以转移到下一个项目——当然,不同疾病领域有很多很多不同的经验。我认为这就是 AI 和机器学习世界可能发生很大转变的地方:如果你在下面有这样一个平台来研发这些药物,让你能够真正吸收和理解这些经验,并帮助影响你对疾病生物学的核心基础理解,以及如何设计好的分子并精巧地工程化这些药物,那么你就有希望随着研发的药物越多,真正获得复合式的改进。
We talked about maybe the science side of it. I think there's a big cultural aspect of just how can you keep innovating as an industry, how can you keep moving really really fast. And I think as well—and this is related to the sort of science and technical part—is what are the mechanisms that actually give you economies of scale on the innovation side, on the research and development side. So if you go after a particular drug target and you're trying to make a particular medicine, and you're a pharma company or biotech, you're going all in on that. What do you learn from that that helps you work on the next medicine much quicker, and then the next medicine even quicker after that? Because if you could get that compounding of learnings over time, you could maybe get the benefits of scale and build something really amazing and big as a company. But I think a lot of the techniques and the way we go after medicines—or the industry goes after medicines—is really treating each one as a segmented, bespoke frontier science project. And you learn so much about that project, and there's maybe not so much that's transferable to the next—like there's of course many many different learnings of disease areas. And this is I think where things can shift quite a lot in the world of AI and machine learning, where if you have this platform underneath going after these medicines that allow you to really suck up and understand the learnings and help impact your core foundational understanding of disease biology and how to design good molecules and exquisitely engineer these medicines, then you can hope to actually get compounding improvements the more medicines you go after.
因为我想,深度学习和我们当前所处的基础模型时代出现的一个引人注目的事情是,其中一些东西随着规模扩大而具有泛化能力。所以听起来,也许在生物学中也是如此,如果你有足够的规模和足够深思熟虑的方法,你可以泛化一些以前是定制的问题。你们采取什么方法?
Because I guess one of the striking things that has emerged from deep learning and the foundation model era that we're in right now is the generalizability of some of these things with scale. So it sounds like perhaps in biology as well, if you have sufficient scale and a sufficiently thoughtful approach, you can generalize some of these problems that were bespoke before. What approach are you all taking?
嗯,我认为这就是我们在 Isomorphic 所采取的重大转变,相比——我们并不是第一批尝试用 AI 改变药物设计和药物发现方式的人。
Well I think that's the big shift that we're taking with Isomorphic compared to—we're not the first people to try and change the way we do drug design and drug discovery with AI.
Isomorphic 真正迷人的一点是,你们有非常多样化的人才空间,大家为了共同的事业一起工作,而且往往来自非常不同的背景。你能多谈谈你们雇佣什么样的人吗?他们的背景是什么?你们目前正在寻找谁?
One of the things that's really fascinating about Isomorphic is the degree to which you have a very diverse space of people all working together towards a common cause, often who come from backgrounds that are very disparate. Can you tell me more about what sort of people you hire? What are their profiles? Who you're looking for currently?
是的,这是一个有趣的空间,因为前沿 AI 与药物发现、化学、生物学的融合并没有存在很长时间。
Yeah, I mean it's an interesting space because the mashup of frontier AI and drug discovery, chemistry, biology hasn't really existed for very long.
所以你不能直接去外面说:“嘿,我想聘请 AI 药物发现领域的世界级专家。”因为他们基本上不存在。即使存在,他们也不是在使用我们的模型,而是在用不同的技术。所以我们考虑的是直接寻找核心 AI 和深度学习领域最顶尖的人才,他们可能甚至没有生命科学、生物学或化学的背景,但非常希望看到他们在深度学习上的工作能转化为对人类的巨大影响。所以我们只招聘 AI 核心人才。我们也有生物学和化学的核心人才,他们可能对 AI 接触不多,然后我们在内部努力建设一种文化,让每个人都能互相交流和学习的文化,然后在内部培养出这些跨学科的专家科学家,这真的非常令人兴奋。
So you can't kind of go out into the world and say, 'Hey, I want to hire the world experts at AI for drug discovery.' Because they basically don't exist. And if they do exist, they're not using our models, they're using different techniques. So we think about going after literally just the best people in core AI and deep learning who maybe don't even have a background in life sciences or biology or chemistry, but really want to see their work on deep learning translate into amazing impact for humanity. So we hire just core people in AI. We have core people in biology and chemistry maybe who haven't had much exposure to AI, and then we work hard internally to build that culture that everyone talks and learns from each other, and then internally we get these sort of cross-disciplinary expert scientists emerging, which has been really exciting to see.
你如何看待这些比例?很久以前我创办了一家叫 Color 的公司,头几年我是 CEO。现在我的联合创始人接手已经十年了。所以这是很久以前的事了,我们基本上是将机器学习和数据科学应用于基因组学,我们在构建这些基因组管道,我们发现你可以有大约五个机器学习人员,然后一个来自传统领域的研究科学家,这大概就是我们采用的比例。现在情况如何,或者你认为一个团队中每个学科最优的人数是多少?
How do you think about the ratio of those things? So I started a company a long time ago called Color and I was CEO for the first couple years. My co-founder took over a decade ago now. So this was a long ways back and we were basically using ML and data science as applied to genomics and we were building these genomic pipelines and what we found is you could have like five ML people and then one research scientist from the traditional field and that was kind of the ratio-ish that we adopted. What is it like now or how do you think about how many people of each discipline do you optimally have in a pod working on a problem?
是的,对于一些核心 AI 超级项目,即 AI 建模项目,我认为其实没有太大区别。你有核心建模人员,比如工程师、AI 科学家,然后你只需要一些关键领域专家,真正理解应用、数据细微差别的人,比如指标意味着什么?确保我们不是在追逐虚假指标,这些是真正能转化为实际制药的东西。所以是的,那种比例,五分之一,我觉得这非常符合我们团队的情况。
Yeah, for some of these core AI superpower projects, the AI modeling projects, I think that's actually not too dissimilar. You have your core modelers like engineers, AI scientists, and then you just need some key domain experts, people who really understand the application, the nuances of the data, like what do the metrics mean? Make sure that we're not chasing smoke metrics and these are real things that are going to translate into actually making medicines. So yeah, those sort of ratios, one in five, like that I think those resonate quite a lot for what our teams look like.
目前你们有在积极招聘的具体职位吗,还是全面招聘?
And are there specific roles that you're actively hiring for currently or just across the board?
我的意思是,我们希望最优秀的 AI 研究人员加入 Isomorphic,帮助我们推进这一使命。我认为在核心模拟模型(如 AlphaFold++)以及核心推理模型(如将所有前沿模型和开源模型适配到我们的领域)上,确实有很多工作要做。所以我认为这是我们招聘的一个非常重要的领域。
I mean, we want the best AI researchers coming into Isomorphic and helping us push on this mission. And I think there's literally so much work to do on the core simulation models like AlphaFold++, but also on the core reasoning models like taking all of the frontier models and open source models and adapting them to our space. So that's I think a really important area for us to be hiring on.
你们处理哪些组成部分,或者你们在 approach 新药时主要关注哪些领域?你们有自己的实验室吗?你们运行机器人进行移液吗?我们采取的方法是什么?
What are the components that you tackle or what are the main areas that you all are focused on in terms of how you approach new drugs? Do you have your own labs? Do you run robots that do pipetting? Like what is the approach we're taking?
是的。所以如果你进入我们的核心 AI 团队,我们的北极星和真正试图实现的目标是,如何将所有的药物发现工作、所有的药物设计工作、对疾病生物学的理解都搬到计算机上。所以我们如何摆脱现实世界?我知道很多人在构建与真实世界高效交互的方式,以便可以进行大量的真实世界迭代。这很好,而且是互补的,但根本上,最大的时间瓶颈、最大的成本瓶颈是合成真实原子,然后在真实的试验和实验中测试它们。正如我们看到几乎所有其他工程领域都转向计算机辅助设计场景,这改变了我们设计的方式,改变了我们可以工程化的东西。我们希望在这个领域做同样的事情。
Yeah. So if you go into our core AI team, our north star and the thing that we're really trying to achieve is how can we bring all of that drug discovery work, all of that drug design work, understanding of disease biology onto a computer. So how can we get out of the real world? I know a lot of people are building ways to interface with the real world really efficiently so you can do lots and lots of real world iteration. That's great and it's complementary, but fundamentally the big time bottleneck, the big cost bottleneck is synthesizing real atoms and then testing them out in real assays and experiments. And just like we've seen pretty much every other area of engineering move into a computer-aided design scenario, and that's just changed the way that we can design, changed what we can engineer. We want to do the same thing in this space.
所以,当我们考虑核心 AI 药物设计引擎开发方面时,这真正聚焦于我们如何为我们的模拟模型、我们的世界模型实现实验精度。如果你能获得一个预测模型,让我们以 AlphaFold 为例。AlphaFold 关注结构预测,蛋白质的结构以及它们如何相互作用。通常这需要数月或数年进行 X 射线晶体学并得出结构。如果你能用像 AlphaFold 这样的模拟模型做到这一点,那么你就不必进入现实世界去做那件事。你节省了数月的时间。药物发现是许多许多不同的非常困难的科学问题和工程问题的组合,如果你能创建预测模型而不是在现实世界中进行,那么你节省了大量的时间。所以在内部,我们所有的排行榜上都有一条虚线,那就是实验精度,而我们试图创建的所有这些超级能力的目标是达到实验精度。到那时,你不需要进入现实世界。你可以在计算机上进行更多的设计和迭代。这样当你进入现实世界时,当你制造分子时,当你测试你的科学假设时,成功的概率比传统方式要高得多。因此,你不必像在现实世界中那样进行多次尝试,事情实际上变得更快,问题更容易解决。
And so really, when we think about the core AI drug design engine development side, this is really focused on how can we achieve experimental accuracy for our simulation models, our world models. If you can get a predictive model, let's use AlphaFold as an example. AlphaFold looks at structure prediction, the structure of proteins and how they interact with each other. Normally that takes months or years to do X-ray crystallography and get a structure out. If you can do that with a simulation model like AlphaFold, then you don't have to go into the real world and do that. You save months and months of time. And drug discovery is a combination of many, many different really hard scientific problems and engineering problems, and if you can create predictive models instead of the real world, then you're saving tons and tons of time. So internally we have a dotted line on all of our leaderboards that is experimental accuracy, and the goal of all of these superpowers that we're trying to create is to get to a point where it's experimental accuracy. At that point, you don't need to go into the real world. You can do so much more design and iteration on a computer. So that when you do go into the real world, when you make your molecules, when you test out your scientific hypothesis, the probability of success is much, much higher than it would have been traditionally. And so you don't have to do as many turns as the real world and things actually become quicker and problems fall easier.
嗯,所以当我观察药物开发时,我认为现在大约是一个 15 年的过程。它花费 15 亿美元。我的感觉是,小分子和体外工作,即组织培养和小鼠工作,基本上大约两到三年,然后大约 5000 万美元的数量级,然后其他的 14.5 亿美元和大约 12 年是临床试验和不同阶段以及安全性,你认为其中有多少可以真正在计算机中封装?
Well, so when I look at drug development, I think it's about a 15-year process now. It costs $1.5 billion. My sense is the small molecule and the in vitro work, the tissue culture and mouse work is basically say two to three years and then it's say $50 million of that order of magnitude and then the other 1.45 billion and 12 years-ish is the clinical trial and the different phases and safety and how much of that do you think you can actually encapsulate in a computer?
你知道,你有发现阶段。所以你从想法到认为你有一个好的分子可以用于患者,或者在此之前你必须做临床前动物研究以确保安全并按预期工作。这又需要一年。然后你进入临床研究。你有一期、二期、三期逐步升级。所以,当你观察时间线,当你观察失败率时,我认为这些是真正加剧平均成本的事情,对吧?为什么东西这么贵?是因为很多东西失败了。然后事情真正失败的地方是在临床阶段。
You know, you have the discovery phase. So where you go from idea to you think you've got a good molecule that you could put in patients or before that point you have to do pre-clinical, animal studies to make sure that this is safe and working as intended. That takes another year. Then you go into clinical studies. You have phase one, phase two, phase three ratchets up. And so, when you look at the timeline and when you look at the failure rates, and I think these are the things that really exacerbate the costs on average, right? Why do things cost so much? It's because so many things fail. Then where things really fail is in the clinic.
它们在临床阶段失败,是因为我们一直看不到问题,直到真正落地、把这些药物用在病人身上,我们才说:“糟了,有我们没预料到的毒性。”
They fail in the clinic because we never could see the problems until we get to the point where the rubber meets the road and we put these drugs in patients, and we say, "Oh no, there's toxicity that we didn't account for."
或者我们有一个分子,它确实命中了我们设计它要命中的靶点,但它也命中了别的东西,而那会带来非常负面的影响。
Or we have a molecule and it hits the thing that we've been designing it to hit, but it hits something else, which is a really negative effect.
又或者你确实命中的那个靶点,我们以为它能治好这个疾病——也许它确实治好了,但它本身却带来了非常负面的影响。
Or the thing that you do hit, we thought it's going to solve the disease. Maybe it does even, but it actually has a really negative effect in and of itself.
所以人们只有在开始把它用到病人身上、用到真实病人身上时,才会了解到这些问题。
And so people only learn about those problems when they start introducing it to patients, to real patients.
所以真正巨大的机会,是在进入病人之前就获得多得多的这种理解。
And so the really big opportunity is to have much more of that understanding before you go into patients.
所以如果你对疾病生物学、对细胞如何运作有更好的理解,你也许就能理解你试图命中并调控的那个东西究竟是如何参与其中的。所以你实际上是在对所有这些其他组成部分建模,而不只是“什么分子会结合什么”。
So if you have a better understanding of disease biology, how cells work, you can maybe understand how the thing you're trying to hit and modulate is really implicated. So you're actually modeling all these other components and not just what molecule will bind to what.
正是如此,我们在对所有这些组成部分建模。
Exactly, we're modeling all of these components.
那你怎么获得数据来对这些东西建模?这个数据集是从哪来的?
How do you get the data to model those things? Like where does that data set come from?
我们有一套全面得离谱的数据战略。数据到处都是,但我认为过去 5 年我们从根本上学到的是:自己生成这些数据有很大的机会。
We have this ridiculously comprehensive data strategy. There's data all over the place, but I think fundamentally what we've learned over the last 5 years is there's a lot of opportunity to generate this data yourself.
当然有大型的数据仓库。有时候这对深度学习非常有用。但很多时候,这些数据仓库——无论是公开的、在药企里的,还是在公司里的——都是多年被动数据收集的副产品,来自做药这件事本身。所以它们可能非常非常有偏。
There's of course big repositories of data. Sometimes that's really good for deep learning. Oftentimes these repositories of data, whether they're public or in pharma or in companies, they've been the byproduct of many years of passive data collection from doing the activity of making medicines. So they can be very, very biased.
如果你想要一个通用的药物发现解决方案,这往往帮不上什么忙。如果你真的在意这些模型的泛化能力,你需要的可能是另一种分布的数据。所以我们自己去生成这些数据,结果我们看到了非常非常惊人的数据缩放定律。
Which often doesn't really help you if you're trying to make a general solution to drug discovery. If you really care about generalization out of these models, there's maybe a different distribution of data you need. So we go out and generate this ourselves, and we've seen some really, really amazing data scaling laws as a result.
那你怎么衡量这些东西是否会有这些副作用?因为归根结底有句老话——我有生物学博士学位,以前在多个领域工作过,癌症、神经科学等等。在癌症领域,我们在小鼠身上治愈癌症几百次了,而那些分子却无法转化到人身上。
How do you measure whether some of these things will have these side effects? Because ultimately there's the old saying — I have a PhD in biology and I used to work in a variety of fields, cancer, neuroscience, etc. And on the cancer side we cured cancer in mice hundreds of times, and those molecules wouldn't translate into people.
所以你真正需要的很多数据,必须在人体临床试验中生成。你打算怎么生成那些真正能提供信息的数据?因为如果你用动物模型,出来的数据相对于人类生物学往往是不准确的。
And so a lot of the data you actually needed, you had to generate in human clinical trials. How do you go about generating that data that actually informs it? Because if you're using animal models, often the data that comes out of that is incorrect relative to human biology.
正是如此。听起来你亲身经历过很多这种事。这非常痛苦。
Well, exactly. It sounds like you experienced a lot of this firsthand. It's very painful.
非常痛苦。
It's very painful.
你知道,如果你想想毒性、毒性的来源——要通过监管机构,你需要达到的金标准是证明你的分子在大鼠和其他动物身上没有毒性。但即便如此,即使东西获批了、在大鼠身上被证明了,它们最终在人类身上往往还是有毒性。
And you know, if you think about toxicity, sources of tox — the gold standard that you need to get through for regulators is you need to prove that your molecules aren't toxic on rats and other animals. But still, even when things are approved and they've been proved on rats, they end up being, you know, often toxic in humans.
那为什么呢?好吧,大鼠其实不是人。它其实预测性并不高。我觉得,具体看研究,但大鼠对人类临床毒性的预测性大约只有 30%。
And well, why is that? Well, okay, a rat isn't actually a human. It's not actually very predictive. I think, you know, choose your study, but it's about 30% predictive of human clinical tox in a rat.
你知道,如果我的一位 AI 科学家或工程师走过来对我说:“嘿,我们有个很棒的模型,预测准确率 30%。”
And you know, if one of my AI scientists or engineers came up to me and said, "Hey, we've got this amazing model. It's 30% predictive."
你就会说:“好吧,也许再做好一点吧。”
You're like, "Okay, maybe do a bit better than that."
对。所以我认为有很大的机会去真正重新思考——人类临床毒性的那些预测终点是什么?别管动物了,它们过去 50、70 年一直是个代理指标。
Yeah. And so I think there's a lot of opportunity to actually rethink how we — like what are those predictive endpoints for human clinical tox? Like forget animals, you know, they've been a proxy for the last 50, 70 years.
但我们也许能做得更好。我们可以做得更好,办法是把体外终点——也就是在实验室里很容易测量的东西——与 AI 预测模型结合起来,同时也与一些惊人的新实验技术结合起来,这些技术出现在类器官、器官芯片领域,比如合成人体组织,
But we can maybe do better. We can do better by bringing together in vitro endpoints — so things you could measure quite easily in the lab — together with AI predictive models, also together with some amazing new experimental technologies coming out in the space of organoids, organs on a chip, like synthetic human tissues,
它们某种程度上近似并创造出人体器官的微型环境。
which sort of approximate and create these little microcosm environments of human organs.
所以你可以想象,大概有机会把这一切整合起来,然后直接尝试对人类临床毒性建模。不过这方面数据不多,因为已开展的临床试验数量是有限的。但我认为我们现在有一些非常好的方法。
And so you can imagine there's probably an opportunity to bring all of this stuff together and then directly try and model human clinical tox. Now there's not much data on that side because there's only a finite number of clinical trials that have been run. But I think we have some really good methods now.
那对于这类方法或技术,你倾向于合作吗?还是把它们引入内部?我有点好奇,作为一家公司,你们是怎么运作的——因为能做的事情太多了。
And for these sorts of approaches or techniques, do you tend to partner for them? Do you bring them in house? I'm a little bit curious as a company how you operate relative to — because there's so much that could be done.
我也有点好奇,你们有多想只强调计算机科学这一侧;而在生物学这边,人们常用所谓的 CRO,也就是合同研究组织。可惜这类器官模型的产出质量往往参差不齐——我就是有点好奇,你们对外部方的依赖相对于内部有多大。
And a little bit curious how much you want to just emphasize the computer science side, and then, you know, biology often there's these things called CRO, or these contract research organizations that people use. Unfortunately, the quality tends to be pretty mixed in terms of the output of these types of organ — I'm just a little curious like how much you depend on external parties versus internal.
好。比如打造我们的药物设计引擎、所有 AI 模型,这些我们全部在内部做。我们也看到生成专有数据并自己拥有这些数据的巨大机会。但生物学和这类实验平台非常复杂、长尾,而且这里有一些了不起的人在打造一些极棒的平台。
Yeah. So like making our drug design engine, all of the AI models, we do that all in house. And we see a big opportunity in generating proprietary data and owning that ourselves. But biology and experimental platforms like this are really complex and long-tailed, and there's some amazing people working on some fantastic platforms here.
所以我们和全世界合作——无论是我们自己做的、合同研究组织 CRO,还是其他创新公司——来帮我们生成驱动模型的数据。
So we work with the whole world — whether that's stuff we do ourselves, contract research organizations, CROs, other innovative companies — to actually help us create the data that is powering our models.
是这样。
So yeah.
挺酷的。
That's cool.
Anthropic 最近宣布他们要在旧金山建一个湿实验室。不用什么特别的知识,光看公开论文、读读字里行间,就感觉他们可能在搭建某种机器人系统或闭环系统。总的来说,如果你看 AI 模型——你比我更懂——你会想要闭环系统来快速迭代。换句话说,如果你能获得快速反馈,比如写代码时能立刻测试,那你就有了快速检验模型是否好用的方法。在生物学中,一个问题是你设计一个实验,等三周,拿到结果,还得解读——这是一个大循环。这拖慢了在数据上迭代的进度。搭建这些机器人平台或其他东西可能会加速这个过程。你如何应对这个问题?或者你认为这是你们会追求的一部分解决方案吗?
Anthropic recently announced that they're doing a wet lab in San Francisco. Reading between the lines without any special knowledge, just reading external papers, it kind of looks like there's some potentially robotic system or closed-loop system they're trying to build. In general, if you look at AI models, as you know better than me, you want closed-loop systems to be able to iterate quickly. In other words, if you can get rapid feedback—like if you're writing code and it can instantly get tested—then you have a fast way to test if the model's working well or not. In biology, one of the issues is you set up an experiment, you wait 3 weeks, then you get the results, you have to interpret them—there's a big loop. That slows down progress in the ability to iterate on data. Building these robotic platforms or other things may expedite that. How do you approach that problem, or do you think that's part of the solution that you all will be pursuing?
是的,看到这些自动化实验室——这些用于实验的机器人解决方案——变得好多了,真是令人兴奋。我们与这类自动化实验室合作已经很久了。大家都应该如此,我们应该继续缩短与现实世界迭代的时间。从根本上说,我想摆脱现实世界,对吧?我们真的能做到吗?因为总有一天你会碰到物理定律的极限。比如合成一个分子需要多久?有时候你只能等待反应发生,反应需要那么长时间。培养一个细胞需要多久?有时候你只能等那些天,让细胞达到合适的状态才能测试。所以是的,我认为我们可以做很多工作,也应该做,而且我们作为一个物种正在做,在改进自动化、改进方式——
Yeah, I mean it's been really exciting to see how much better these automated labs—how much better these robotic solutions for experimental labs have been getting. We've been working with these sorts of automated labs for a long time now. Everyone should, and we should keep driving down that iteration time with the real world. And fundamentally I want to get out of the real world, right? Can we actually—because you're going to hit the finite laws of physics at some point. Like how long does it take to synthesize a molecule? At some point you have to just wait for the reaction to happen, and that's how long the reaction takes. How long does it take to culture a cell? At some point you just have to wait those days for the cell to get to the right state before you can test things on that. So yes, I think we can do a lot of work and we should, and we are as a species, on improving automation and improving the way—
听起来你想把它带到计算机模拟中。
You want to bring it in silico, it sounds like.
但我认为我们也应该大力推动在计算机上以硅基方式实现,这样我们可以减少现实世界的时间,在计算机上做更多预测性工作,这样当我们进入现实世界时——
But I think we should also be driving really hard at bringing that in silicon on a computer, so that we can reduce the amount of real-world time, so that we can do much more predictive work on a computer, so that when we do go into the real world—
是的,看起来我们进入现实世界是为了验证——
Yeah, it looks like we go into the real world to validate—
不一定是去学习和迭代。我们仍然需要进入现实世界来验证,因为我们提出新的科学假设,最终要在人身上测试。所以你必须确保它们有效且安全。因此你必须进入现实世界来验证。但问题是,你能把进入现实世界做实验和迭代的时间减少多少?
Not necessarily to learn and iterate. We still need to go into the real world to validate because we're coming up with novel scientific hypotheses and we want to test them out in people at the end of the day. So you have to make sure that they work and they're safe. So you have to go into the real world to validate. But the question is, how much can you reduce the amount of time you go into the real world to experiment and to iterate?
你们的方法有多少是专注于与现有制药公司合作,而不是开发自己的药物?
How much of your approach is focused on partnering with existing pharma companies versus developing your own drugs?
我们在内部构建 AI 药物设计引擎,而且我们实际上不卖模型。我们不出售模型许可,不以那种方式卖 token。我们在内部用它来制药。我们通过两种方式来做。我们有完全拥有、自己资助、自己推进的药物发现项目——我们的内部管线。然后我们也有与优秀制药公司、生物技术公司合作的项目,我们在这些项目上合作。这些也非常令人兴奋,因为那些公司和团队通常在特定疾病领域有惊人的想法和专业知识。所以他们带着最困难的问题来找我们——也许是他们研究了 10 年、20 年都没什么进展的问题——然后我们一起使用我们的药物设计引擎,可以取得巨大进展。
We make the AI drug design engine in-house, and then we actually don't sell the model. We don't license out the model. We don't sell tokens in that way. We use it internally to make medicines. And then we do that in two ways. We have programs, drug discovery programs that we fully own and fund ourselves and work on ourselves—our internal pipeline. And then we have programs that we work on with amazing pharma companies, biotech, where we partner on these projects. And those are really exciting as well because often those companies and those teams have amazing ideas and amazing expertise in specific disease areas. So they come to us with—these are the hardest problems, maybe problems that they've been working on for sometimes 10, 20 years not making much progress—and then together using our drug design engine we can make a huge amount of progress.
你们专注于哪些适应症领域或人类健康领域?
What are the indication areas or areas of human health that you all are focused on?
在内部,我们更专注于肿瘤学、免疫学和炎症。但酷的是,药物设计引擎和所有模型都是通用的。它们与疾病无关,与靶点类别无关,与模态无关。所以它们适用于多种模态。
Internally, we're focused much more on oncology, immunology, and inflammation. But the cool thing is the drug design engine, all the models, they're general. They're disease-agnostic. They're target-class-agnostic. They're modality-agnostic. So they work across multiple modalities.
你们是从癌症开始,还是自身免疫疾病或其他?
You're starting with like cancer and is it autoimmune disease or something else?
是的。免疫学和炎症通常密切相关,所以是那个领域。当我们在内部攻克这些问题时——无论是肿瘤学、癌症还是炎症——我认为有很大机会去解决一些根节点问题。这类问题如果找到解决方案,可能会积极影响大量不同患者的不同下游适应症。举个例子:如果你考虑癌症,这是一种非常复杂的长尾疾病,在患者身上以许多不同方式表现出来。但我们也知道有一些核心驱动机制是许多不同情况共有的。今年早些时候我们看到了一个惊人的例子:Daraxonrasib 和 RAS,一种 KRAS 抑制剂,在一个大型癌症会议上获得起立鼓掌,大幅改善了 Revolution Medicines 的晚期胰腺癌患者的生活。再次,这是攻克某种根节点的绝佳例子。
Yeah. So immunology and inflammation they're often quite related, so it's that sort of space. And when we go after these things internally—whether it's oncology, cancer, inflammation—I think there's a big opportunity to go after some of these root-node problems. The sorts of things that could positively affect—if you have a solution—could affect lots and lots of different patients for different downstream indications. An example: if you think about cancer, this is a really complex and long-tail disease, and it shows itself up in patients in many different ways. But we also know there are some core driving mechanisms that are common to many different things. We saw this amazing example earlier this year: Daraxonrasib and RAS, a KRAS inhibitor, standing ovation at a big cancer conference, drastically improving the lives of late-stage pancreatic cancer patients from Revolution Medicines. And again, a great example of going after some sort of root node.
我明白了。是的,RAS 在癌症文献中出现了大约 30 年、20 年。但从药物发现和设计的角度来看,这些问题极其困难。
I see. Yeah, RAS has been popping up in the cancer literature for like 30 years, 20 years. But these problems are devilishly hard from a drug discovery and design point of view.
而且它也有天然功能。所以能够调节——
And also has a natural function. So being able to modulate—
正是如此。所以你真的——当然,在癌症中,突变非常快。所以你以为有了解决方案,但临床上却行不通,因为它会绕过解决方案突变。这其实是个有趣的观点,因为对于许多不同的药物、许多不同的健康领域,HIV 也是如此,对吧?最终你采用鸡尾酒疗法,这实际上才能抑制艾滋病或 HIV。在癌症中,类似地,许多药物是作为单一药物开发的,而不是鸡尾酒。正如你所说,通常在一个肿瘤内,有一系列突变,如果你真想治愈,就需要同时抑制它们,否则它会在细胞分布中存在的突变基质下进化出来。
Exactly. So you really—and of course then in cancer things mutate very quickly. So you think you've got a solution but actually clinically it doesn't work out because it just mutates around the solution. It's actually an interesting point because for a lot of different drugs, for a lot of different areas of health, this also was HIV, right? You end up with a cocktail of drugs that you give eventually and that's actually what allows you to suppress AIDS or HIV. In cancer, similarly, a lot of drugs are developed as individual drugs versus cocktails. And to your point, often within a tumor, you have a spectrum of mutations that you need to suppress simultaneously if you really want to cure the thing because otherwise it'll evolve out given the substrata of mutations that exist in a distribution across the cells.
你们是否在考虑那些更复杂的方法,比如鸡尾酒疗法或多药联合疗法?
Are you thinking about those more complex approaches of cocktails or multi-drug approaches?
那么为什么我们不更多地使用鸡尾酒药物呢?问题在于,这些分子往往有效,但有一些毒性,或者对肝脏有影响,以至于如果你同时服用多种这样的分子药物,它们会产生药物相互作用,对患者非常有害。所以,正是因为我们不擅长设计精妙的分子和药物,这意味着我们无法以对患者安全的方式将它们组合在一起。因此,我们可能限制了其应用范围。
So why aren't we giving more cocktail drugs? Well, the problem is often these molecules work but they have some toxicity or they exhibit some effect on the liver, such that if you're taking multiple of these molecules, these medicines at the same time, they have these drug-drug interactions that can be really harmful for patients. And so it's actually because we're not great at engineering exquisite molecules and medicines that means that we can't combine them together in a safe way for patients. And so we're maybe limiting the surface of applicability.
是的,我想你只能招募那么多患者参加临床试验,所以从临床试验的角度来看,组合数学的问题也会累积起来。
Yeah, I guess you only have so many patients to enroll in a clinical trial and so the combinatorics of it my sense is also kind of adds up in terms of the clinical trial side.
尤其是当这些药物如何组合存在很多风险和不确定性时,所以这就是我们看到的机会。是的,如果你能更精确地设计这些分子,使其安全,不对肝脏产生这些影响,不以不良方式相互作用,那么你实际上就有可能——我真的希望——想出一些相当复杂的组合,这些组合可以同时调节不止一个靶点,而是跨越这些非常复杂的生物通路的整个靶点向量,从而对疾病产生更好的效果。
Especially when there's a lot of risk and uncertainty about how these things will combine and so that's where we see an opportunity. Yeah. If you can actually much more accurately engineer these molecules to be safe, to not have these effects on the liver, to not interact with each other in bad ways, then you can feasibly come up with actually, I would really hope some quite complex combinations that can modulate not just a single target at a time, but a whole vector of targets that span these very complex biological pathways at the same time and so have a better effect on disease.
有一个很好的 YouTube 视频,讲的是创办杨森制药的杨森。该公司最终被强生收购,他是药物开发和制药领域的先驱之一,我认为他拥有最高产的制药公司之一,就实际推出的药物而言。在视频中,他强烈表达的观点是,药物开发的主要制约因素是对安全性的过度强调,监管机构限制了进展。他指出,在第二次世界大战期间,丘吉尔试图在战场上找到治疗士兵某种性病的方法。于是他们重新发现了抗生素,因为青霉素在 20 年代由弗莱明发现,然后被搁置遗忘了。然后在 9 个月的时间里,他们从头重新发现并商业化了青霉素,专门用于治疗这种疾病,这是因为他消除了所有监管障碍。所以这是杨森指出的一个例子,有人可能会说新冠疫苗在能够快速推进方面也是类似的。嗯,你认为在多大程度上对安全性的强调过度了?就像杨森的观点是,这关乎风险与回报。你需要做出权衡,不能单一地说只考虑安全性。你还应该说,嗯,这关乎收益,在某些情况下也应该承担风险。你怎么看?
There's a very good YouTube video of this guy Jansen who started Jansen Pharmaceuticals. It was acquired eventually by J&J and he was one of the big pioneers of drug development and pharma and I think he was one of the um they had one of the most productive pharma companies in terms of actual drugs launched and in it he his view that he expresses pretty strongly is that the main constraint on drug development is an overemphasis on safety and that regulators kind of curtail progress. And he pointed out how during World War II when St. Churchill tried to find a cure for soldiers of some venereal disease uh in the field. And so they they rediscovered um antibiotics because penicillin was discovered in the 20s by Fleming and then kind of put on a shelf and forgotten. And then in a 9-month period they rediscovered and um commercialized uh penicillin from scratch specifically to treat this and it was because he removed all regulatory obstacles. So that was an example that Jansen pointed to one could argue the COVID vaccine was similar in terms of being able to rush it. Um, how much do you think there's too much of an emphasis on safety? Like Jensen's point was it's about risk-reward. You know, you need to make trade-offs and you can't just monolithically say it's only safety. You should also say, well, it's about benefit and in some cases risk should be taken as well. Like how do you think about that?
我认为始终把患者安全放在心上至关重要,说实话。嗯,但然后你需要理解患者面临的风险和他们的风险偏好,这可能因不同适应症而异。你知道,新冠就是一个很好的例子,由于它如此普遍和危险,患者的风险偏好发生了巨大变化,我认为这改变了对稍微不同做法的需求和动力。你甚至在不同疾病领域也能看到这一点。
I think it's like centrally important to just always have patient safety in mind to be honest. Um, and but then you need to understand like what are the risks and the appetites of patients and that can be different for different indications. uh you know COVID's a good example where the risk appetite for patients because it was so pervasive and so dangerous just changed dramatically and that changed I think the demand and the force for doing things slightly differently. You even see this across different disease areas.
如果患者患有晚期癌症,面前没有太多选择,他们的风险偏好就非常不同。
If patients have you know late-stage cancer and not many options in front of them there's a very different risk appetite.
是的,相比于治疗慢性低度炎症等适应症。所以我认为,我们继续关注患者安全实际上非常非常重要,但我们可以根据患者的需求来调节这一点。所以最终,我们希望患者过上更健康的生活,并尽快接受治疗。
Yeah. compared to if you're trying to treat a chronic low-level, you know, uh, inflammation um, uh, indication. And so I think it's actually really really important that like we keep focusing on patient safety, but that we can modulate that, you know, depending on what the patient need is. So ultimately, you know, ultimately we want patients who are living healthier lives and they're receiving that treatment as quickly as possible.
嗯。
Mhm.
你知道,我们与这里的监管机构,比如 FDA,以及世界各地的监管机构有很多交流,我认为一个共同点是,你们真的希望为患者提供最好的药物和最好的解决方案。嗯,我确实认为,随着时间的推移,我们会看到差异,当分子设计时对其工作原理有更多理解,我们能够搜索设计空间来设计出比经验驱动过程好得多的东西,成功率 and 安全性特征会有所不同。我希望随着时间的推移证明这在统计上非常不同,并且我认为这将改变我们对监管和将药物带给患者的思考方式。
And you know we speak a lot to regulators here, you know FDA here but also all over the world and I think the one thing in common is like you people really want to get patients the best drugs and the best solutions possible. Um and I do think that over time we will see a difference in our you know the success rates and the safety profiles of molecules coming out when they're designed with much more understanding about how they work with you know we're be able to search the design space to engineer something you know much better than you could do from an empirical empirically driven process and I hope to prove out over time that this is very statistically different and that will change the way that we think I think about regulation and getting drugs to patients.
你认为你们何时会进行首次临床试验?
When do you think you'll have your first clinical trial?
我很想给你一个确切的日期。这真的是非常困难的前沿科学。嗯,我们有一些非常令人兴奋的药物正在研发中。嗯,这些进展非常顺利。所以我们正在努力尽快将这些药物带给患者。我们一直在建立我们的临床开发团队。所以我们正在为此做准备。
I would love to give you like a hard day. This is like really hard frontier science. Um we've got some really exciting um medicines in the works. Um and these are going really well. So we're pushing really hard to get these to patients as quickly as possible. We've been building up our clinical development team. So we're getting ready for this.
你有没有——我知道这些总是无法回答的问题。你对例如 80% 的人类癌症将可治疗的时间有预测吗?或者你知道其他一些指标来说明为什么这对世界如此重要?
Do you have a I know these are always impossible questions. Do you have a prediction on when you think for example 80% of human cancers will be treatable or you know some other metric of why this is so important for the world?
如果我们快进,你知道,甚至五年后,如果我们还没有基础工具,比如对疾病生物学的预测性理解没有大幅提升,我会非常失望。嗯。我们设计更精确、毒性更低的分子的能力没有大幅提升,以至于药物发现和开发仍然需要数年时间——这会随着时间的推移而减少,但现在需要数年。嗯,但我们应该有工具来真正开始以不同的方式攻克这些大部分疾病。嗯,如果你从社会中消除癌症和心脏病,我认为统计数据表明,平均人将多活——我不确定是五年还是七年。所以对两个最大杀手的寿命影响,在某种意义上是相当大的,从另一个角度看则较小。有许多公司试图将衰老或长寿作为一个更普遍的过程来关注,这似乎明显是基因编程的。对吧?如果你在秀丽隐杆线虫、果蝇或小鼠中敲除某些基因,它们会多活 20% 到 30%。
I'd be really disappointed if we fast forward, you know, even five years time, if we don't have the base tools like the predictive understanding of disease biology has not step changed in like a massive way. Mhm. Um our ability to design molecules that are much more precise, much less toxic, has not step changed in such a massive way that you know still drug development, discovery and development takes years and that'll reduce over time but it takes years now. Um but we should have the tools in place to really start be like start cracking these large large portions of disease in a different way. um if you remove uh if if you removed cancer from society and heart disease, I think the stats suggest that the average person would live I can't if it's five or seven years longer. And so the actual impact to longevity for two of the biggest killers um is on some in some sense quite large and another point of view is kind of small. Uh there's a number of companies that have tried to focus on aging or longevity as a more general process which seems to clearly be genetically programmed. Right? If you knock out certain genes in seaggans or drosophila or in mice, they'll live 20 to 30% longer.
或者在秀丽隐杆线虫(C. elegans)这种情况下,这些小蠕虫会活三倍长,对吧?如果你敲除某些通路中的特定基因。我博士期间其实研究过那些通路。
Or in the case of C. elegans, the little worms, they'll live three times longer, right? If you knock out certain genes in certain pathways. I actually worked on those pathways as part of my PhD.
太棒了。
Amazing.
真的很有趣。嗯,你如何从人类寿命的角度来思考这个问题?比如我们最终是否会达到一个点,让人们活三倍、五倍长?就像你如何在药物开发和所有这些即将出现的工具的背景下思考长寿?
It was really fun. Um, how do you think about that in the context of human lifespan? Like should we just hit a point eventually where people live three times longer, five times? Like how do you think about longevity in the context of drug development and you know all these tools that will now exist?
是的。不,这很有趣。就像有些重大疾病困扰着很多人,如果我们能开始对它们产生影响,那将对人们的寿命产生具体的影响。我认为即使除了癌症和心脏病之类的事情,你也有那种与衰老相关的慢性疾病开始累积,而根本原因就是衰老。换句话说,根本原因是你允许这些系统随着时间的推移而退化。
Yeah. No, it's interesting. Like there are some of these major diseases that afflict so many people that if we could start to make impact on those, that would have a concrete impact on how long people are living. I think even outside of things like cancer and heart disease, you just have the sort of chronic afflictions of aging that start to add up and the root cause is literally aging. In other words, like the root cause is the fact that you're allowing these systems to degrade over time.
很好。还有干细胞区室。
Great. And stem cell compartments.
是的。它们以某种方式结合,意味着人们的,你知道,即使人们活到 80 或 90 岁的可爱长寿,他们生命的最后 10 年甚至 20 年可能并不像本来可以的那样好,因为他们,你知道,因为你的骨骼开始退化,肌肉开始退化,比如你摔了一跤,突然你就不能,你不再像你希望的那样灵活。那对你的心理健康有影响,突然你的生活质量急剧下降。你可能还会再活 10 年。
Yeah. And they combine in a way that means that people's, you know, even if people live to a lovely long age of 80 or 90, like they maybe the last like 10 years of their life or even 20 years of their life isn't necessarily as great as it could be because they've, you know, because of, you know, your bones start to degrade, your muscles start to degrade, like you have a fall and suddenly you can't, you're not as mobile as you want to be. That has impacts on your mental health and suddenly your quality of life has dropped dramatically. You still might live another 10 years.
在衰老研究领域,他们将其称为寿命与健康寿命的对比。
In the aging community, they talk about that as lifespan versus health span.
正是如此。所以我们对此思考很多。而且所有的衰老模型,如果你干预衰老并延迟它,健康寿命也会随之延长。换句话说,如果一个生命延长三倍,它实际上作为健康成年人的时间也延长三倍。然后它在最后崩溃。但你实际上同时延长了两者。
Exactly. So, we think a lot about that. And but all the aging models, if you impinge on aging and you delay it, the health span goes with it. In other words, if a life is three times longer, it's actually a healthy adult for three times longer. It's and then it crashes out at the end. But you actually have extended both simultaneously.
所以我有点好奇你如何看待寿命延长和你知道的那类事情。
So, I'm a little bit curious how you think about like life extension and you know that kind of stuff.
我认为看到大家在这方面努力会非常有趣,而且正如你所说,我认为我们可以从各个不同角度来攻克这个问题,对吧?我们可以考虑改善困扰我们的事情,帮助最大化我们的健康寿命,同时也尝试解决衰老以及身体、细胞和器官退化的根本原因,以便我们实际上也能随着时间的推移延长寿命。而且,我的意思是,这个领域有如此令人兴奋的工作正在进行,是的,看看这会如何发展将会很有趣。
I think it's going to be really fun to see everyone working on this and, as you said, I think we can attack this from every different angle, right? We can think about improving the things that afflict us and help maximize our health span and also be trying to hit some of the root causes of aging and degradation of our bodies and cells and organs so that we actually can actually extend that over time as well. And I there's yeah, I mean there's such exciting work happening in this space and yeah, it'll be interesting to see how this pans out.
太棒了。非常感谢你今天加入我们。不,这是一次迷人的对话。
Amazing. Thank you so much for joining us today. No, it's been a fascinating chat.
在 Twitter 上找到我们,账号是 no prior pod。如果你想看到我们的脸,请订阅我们的 YouTube 频道。在 Apple Podcasts、Spotify 或你收听的地方关注节目。这样,你每周都会收到新的一集。并在 no-bers.com 注册电子邮件或找到每集的转录。
Find us on Twitter at no prior pod. Subscribe to our YouTube channel if you want to see our faces. Follow the show on Apple Podcasts, Spotify, or wherever you listen. That way, you get a new episode every week. And sign up for emails or find transcripts for every episode at no-bers.com.