大型制药公司在三期试验中失败率高达50%。AI可以解决这个问题 | 维恩·辛格，BullFrog AI

这样做的目的是提高临床试验成功的可能性。

The point of this is to increase likelihood that a clinical trial will succeed.

考虑到开发一种新药要花十年到十五年，耗资十亿到二十亿美元，大药企在三期试验中失败率高达百分之五十，这实在令人震惊。

Considering it takes ten to fifteen years and 1 to $2,000,000,000 to develop a drug, it's quite shocking that big pharma fails fifty percent of

三期试验中。

the time in phase three.

你担心大药企也会发现同样的生物驱动因素，从而成为你的竞争对手吗？

Are you concerned about competition from big pharma who may be developing discovered the biological drivers

这些疾病的致病机制吗？

of those diseases?

我们从一个全球独一无二的数据集中，发现了与抑郁症、双相情感障碍和精神分裂症相关的基因。

We believe we've discovered the genes that drive depression, bipolar and schizophrenia from a one of a kind data set that does not exist anywhere in the world.

你们看起来挺像是ZigFrog的收购目标。

It seems that you would be an acquisition target by ZigFrog.

咱们先看看能不能做成一单药物发现或者靶点发现的AI交易吧。

Let's see if we can get one of these drug discovery AI deals done or target discovery deals done.

跟听众们介绍一下你自己，你是怎么来到BullFrog的？

Introduce yourself to listeners how you got to BullFrog.

Craig，谢谢您今天邀请我。

Craig, thanks for having me today.

很高兴能来参加这个节目。

Great to be here.

我叫文·辛格。

So my name is Vin Singh.

我是BullFrog AI的董事长、创始人兼首席执行官。

I'm the chairman, founder and CEO of BullFrog AI.

我们是一家在纳斯达克上市的公司，股票代码是BFRG。

We are a publicly traded company under the symbol BFRG on NASDAQ.

有些事情我确实不能说，有些问题也可能没法回答，但我还是很期待这次交流。

So obviously there are certain things I won't be able to say or questions I might not be able to answer, but looking forward to it.

先简单说说我的背景。

So a little bit about me.

我有将近三十年的行业经验，主要在生命科学和生物技术领域。

I have almost thirty years of industry experience, life sciences, biotech.

我受过生物医学工程的训练。

I'm a biomedical engineer by training.

我三次创办过获得投资支持的公司。

I'm a three time founder of investor backed companies.

其中两家已经上市了。

Two of them have gone public.

我联合创办的第一家公司叫MaxSite，股票代码是MXCT，是一家细胞治疗系统公司。

The first company I co founded is a company called MaxSite, symbol is MXCT, as a cell therapy systems company.

几年前他们在纳斯达克上市时，市值大约是15亿美元。当然，那之后生物技术行业经历了不小的回调。

When they went public on NASDAQ several years ago, I think the market cap was around $1,500,000,000 Obviously, biotech's been beaten down pretty hard over that period of time.

之后我创办了Next Healthcare，那是当时全球首家面向医疗应用的成体皮肤细胞和干细胞银行。

After that, I founded a company called Next Healthcare, which was at the time the world's first adult skin cell and stem cell banking company for return to medicine applications.

这家公司至今仍在运营，也在开展一些新的业务。

And that company is still operating and doing some different things today.

大约八年前，我创办了BullFrog公司。

And then about eight years ago, I founded BullFrog.

我创办这家公司，是因为对晚期临床试验的高失败率感到非常惊讶。

And the reason I founded the company was I was very surprised by the high failure rates in late stage clinical development.

一款药物研发要花上十到十五年，投入十亿到二十亿美元，而大药企在三期临床阶段居然有五成概率失败，这实在让人震惊。

And considering it takes ten to fifteen years and 1 to $2,000,000,000 to develop a drug, it's quite shocking that big pharma fails 50% of the time in phase three.

这在我眼里完全说不通。

It didn't make sense to me.

我也意识到，如果我能做出改变，就会有更多人能用上原本可能无法问世的药物。

I also realized if I could make a difference, there's a lot of people that will benefit from drugs that maybe otherwise wouldn't.

如果成功率提高了，药价整体上也会变得更亲民，这是必然的结果。

And I think the trickle down effect would be drugs would be more affordable in general if you have more success.

因为所有那些失败的成本，最终都得有人买单。

Because somebody is paying for all those failures.

可惜的是，这笔账最后都算在了医疗体系头上。

And unfortunately, it's the healthcare system that's paying for it.

所以我创办了这家公司，最初的想法是：我们能不能试着挽救那些失败的药物？

So, I started the company and the original focus was, why don't we try to rescue failed drugs?

因为这类药物多得像大海一样。

Because there's like an ocean of them out there.

当然，这仍然是我们关注的方向。

Obviously, still something that we're interested in.

但一开始我就意识到，这需要巨额的资金投入。

But when I had started first, I realized, wow, that's going to require a tremendous amount of capital.

那时候的融资环境，跟现在完全不一样，对吧？

And the funding environment is not what it is today, right?

现在可是有几十亿资金到处在找项目，对吧？

Where many billions are just flying around, right?

八年前，那时候情况完全不同。

Back then, eight years ago, A.

我

I.

那时候，人工智能还不是一个广为人知的词。

Artificial intelligence was not really a well known term.

现在呢，地球上几乎每个人都知道这是啥。

Now it's like every human being on Earth knows what it is.

所以我们现在身处一个完全不同的时代。

So, we're in a different world.

于是我创办了这家公司。

So, I started the company.

我意识到，技术才是关键，对吧？

I realized technology is the key here, right?

我和约翰斯·霍普金斯大学一直有联系。

And I had relationships with Johns Hopkins University.

我在那儿拿了MBA，后来还当过驻校导师。

I did my MBA there and I was a mentor in residence as well.

我四处打听，结果发现他们有个下属机构，叫应用物理实验室，简称APL。

I was hunting around and it turned out that they had a subsidiary called the Applied Physics Lab or APL.

事情就这么顺理成章地发展下去，结果我发现，嘿，这个子公司年收入高达数十亿美元，拥有顶尖的技术，还从事高度机密的国防项目。

And one thing led to another and discovered that, hey, this is a multi billion dollar subsidiary that has incredible technology and does very sensitive defense work.

你根本连他们的大楼都进不去。

And you can literally can't even get in any of the buildings there.

我的意思是，那地方确实很了不起。

I mean, it's a pretty impressive place.

他们开发了各种了不起的技术，很多都是普通人可能在电视上或新闻里见过的，比如太空探索、机器人之类的。

So they develop all kinds of amazing technologies, things that the average person's probably read about or seen on TV related to space exploration and robotics and things like that.

早在人工智能还没火起来的时候，他们就已经花了好几年时间打造了一个AI平台，并且在多个领域投入使用了。

And they had spent years developing an AI platform before it was like the thing to do and had deployed it in different sectors.

所以我们顺利拿到了全球独家授权，专门用于药物研发。

So we were able to secure worldwide exclusive licenses for drug development applications.

刚起步的时候，我们就手握顶尖技术。

So right out of the gates, we had blue chip technology.

APL那里有大约五千名工程师和科学家。

APL, they have like 5,000 engineers and scientists there.

这地方规模很大，这项技术还拿过EPL年度创新奖。

This is a big place and this tech won innovation of the year at EPL.

所以我们手上有这么一项了不起的技术。

So we had this tremendous technology.

它最初是为其他用途设计的。

It was originally designed for different applications.

大家都知道，生物医学数据跟自动驾驶数据或者能源数据完全不一样。

And as we know, biomedical data is very different than autonomous vehicle data or energy data.

我们花了一段时间做研发，最后终于打造出我们需要的平台。

So we went through some R and D for a while and then ended up with the platform that we needed.

后来又跟他们合作了一些，再加入我们自己的独家技术。

You know, did some more work with them and then added our own secret sauce.

如今，我们拥有一套独特而强大的技术组合。

And here we are today with a very unique and powerful ensemble of technology and capabilities.

还有，克雷格，人人都说‘我们的技术最棒’。

And, Craig, everybody says, Oh, we have the best technology.

当然，我也会这么说。

And of course, I'll say that too.

但现在我们开始收到反馈了。

But now we're getting feedback.

比如大型药企，他们对行业情况了如指掌。

We're hearing from big pharma, for example, that knows what's out there.

他们有自己的团队，也做过不少合作。

They have their own teams, they've done deals.

他们告诉我们，没人能像你们这样做事，这太棒了。

And they're telling us that nobody can do what you guys can do, which is fantastic.

所以很自然，下一步就是：既然如此，咱们不妨合作吧。

So obviously we want to, next step is, well, let's work together then if that's the case.

这就是我们目前的状况。

So that's where we are.

现在我们顺应市场趋势，这些力量把我们推向了药物靶点发现这个方向。

Now we kind of followed with our market forces and where those forces pushed us was toward drug target discovery.

这是药物发现的第一步。

That's the very first step in drug discovery.

正确的靶点到底是什么？

What is the right target?

而最后一步，是三期临床试验。

And then the last step, late stage clinical trials, phase three.

正是在这些环节，我们的经验和贡献最为突出。

So that's where we have really had our experiences and made a difference.

但我想明确一点，我们的技术完全不挑领域。

But I just want to be clear, Our technology is completely agnostic.

不管处于哪个研发阶段，也不管是什么疾病。

We don't care what stage of development or what disease.

关键在于数据。

The key is the data.

我们很清楚，自己能做出的发现、挖掘的洞见、做出的预测，几乎没人能做到。

And we know that we can make discoveries and uncover insights and make predictions that are very few, if anybody, can do.

这就是整个故事。

That's the story.

我们今天能走到这一步，就是这么来的。

That's how we got where we are today.

明白了。

Okay.

当你提到 BullFrog 的技术时，是指贯穿药物发现和三期临床试验这两个环节吗？

And when you talk about technology of BullFrog's technology, are you talking about on both ends on drug discovery and the phase three trials?

你们提供的是一个平台，还是说你们开发了一些工具，供大型或小型药企在研发新药时使用？

Is it a platform or are they tools that you're making available to either big pharma or a small pharma to this other drugs.

对，咱们就说说这两个环节。

Yeah, just talk about the two ends.

这是一个平台吗？

Is it a platform?

还是说你们提供的是工具？

Are they tools?

那产品到底是什么？

What is the product?

目前它是一个平台，但客户需要把他们的数据发给我们。

So right now it's a platform, but the customer client, they have to send their data to us.

让我给你从整体上讲一讲。

Let me zoom out a little bit for you.

我想聊聊整个平台和所有解决方案。

I want to talk about the whole platform, all the solutions.

现在我们已经能够用人工智能覆盖药物发现与开发的全流程了。

So we are now in a situation where we can address end to end everything that needs to be done using AI for drug discovery and development.

其实昨天我们刚推出了一项新方案。

We launched a new solution yesterday, actually.

关于这个，我们还发了新闻稿。

We put out a press release on that.

几个月前我们推出过一个，不过我先快速给你过一遍，之后你可以提问。

And then we had launched one several months ago, but I'll just walk you through them quickly and then you can ask some questions.

我们最早意识到的是，那些和我们合作的公司，以及行业内普遍的情况，数据都特别杂乱。

So the first thing we realized is the companies that we were working with and we just know in general, there's a lot of messy data out there.

数据是不少，但一团乱麻。

There's a lot of data, but it's a mess.

随着AI的快速普及，像ChatGPT、Claude这些工具层出不穷，我们当时也觉得太棒了。

And with the rapid adoption of AI, with Chad GPT and Claude and all these companies, we're like, wow, that's great.

但没人手里的数据是能直接喂给AI用的。

But nobody really has data that's ready to be ingested by an AI.

这样一来，AI本该带来的价值，你根本提取不出来。

And so you're not going to extract the value that you should be out of the AI.

后来，我们在和一家处于三期临床的胰腺癌公司合作时，亲身经历了一次这样的情况。

And so through one of our experiences working with this phase three stage pancreatic cancer company, we went through this exercise with them.

他们把数据拿给我们看，我们一看就傻了，这到底是什么东西？

They presented their data to us and we were just like, wow, what is this?

几万页的PDF文件，全是手写的笔记。

You had tens of thousands of pages of PDFs with handwritten notes.

说实话，那简直一团糟。

I mean, it was a mess.

所以我们开发了一套算法流程，把所有这些手写笔记和其他数据准确地转换成干净、结构化的信息。

So we developed an algorithm pipelines to accurately convert all of that data, all the handwritten notes and everything into clean, structured data.

通过这次经历，我们意识到，如果连这么混乱的数据都能处理，那几乎任何行业、任何公司都可以，毕竟其他行业的数据比生物医学数据简单多了。

And going through that exercise, we realized that if we can do this with a gigantic mess of data like this, we can literally do this for anybody else, probably in any industry, to be honest, because other industries' data is far simpler than biomedical data.

于是我们决定把这套数据预处理工具叫做 BF Prep。

And we said, all right, we're going to call this BF Prep for data prep.

几个月前，我们就正式推出了这个产品。

So we launched this several months ago.

随着我们做更多调研，发现现在仍有超过六成的企业根本没有准备好能用在AI上的数据。

And as we've done more homework, we realized even now more than 60% of companies out there don't have AI ready data.

但他们已经在把AI解决方案整合进自己的IT系统了。

But they're integrating these AI solutions into their IT systems.

咱们就看看接下来会发生什么吧。

But let's just see what happens.

但他们得先把数据准备好。

But they got to prepare their data.

这一点我们可以帮他们做到。

So we can do that.

这是一款非常强大的AI工具。

That's a very powerful AI tool.

接下来就是数据分析环节。

Then the next step is the analytics.

我们把这个叫做BF Leap。

That's something we call BF Leap.

这其实正是我刚才十几分钟一直在跟你说的内容。

And that's really what I've been telling you for the past ten, fifteen minutes here.

真正的发现就发生在这里。

That's where we make the discoveries.

但有时候你会做出好几个发现。

But sometimes you'll make a number of discoveries.

比如说，你发现了一批药物靶点或者生物标志物，对吧？

Like, let's say you discover a number of drug targets or a number of biomarkers, right?

或者是其他一些预测结果。

Or some other prediction.

这时候我们就推出了BF竞技场。

That's where we just launched BF arenas.

它的作用就是帮你全面评估这些选项，找出最适合我们推进的那个。

The purpose of that is look at all these options and help me figure out what is the best one for us to move forward with.

这一步非常关键——

And that's a really critical-

就分子层面来说，你是这个意思吗？

Just in terms of molecule, is that what?

可能是分子本身。

It could be the molecule.

具体是什么其实没那么重要。

It doesn't really matter what it is.

想想你以前做过定量分析的时候。

Think about any time you've done some quantitative analysis.

比如说你做了一次风险评估，列出了这么多风险。

Let's say you've done a risk analysis and you have all these risks.

然后你随便给它们分配权重，比如这个风险占20%。

You arbitrarily assign weights like, Okay, this risk is worth 20%.

那个占10%。

That's worth 10%.

这个占5%。

This is worth 5%.

这里面其实挺主观的，对吧？

There's a lot of subjectivity in this, right?

然后你就会想，这个风险有多严重？

And it's like, Okay, how severe is the risk?

发生的可能性有多大？

What's the likelihood?

你可能有一些数据。

You may have some data.

但通过 arenas，你可以借助大型语言模型和其他工具，整合海量信息，从而消除主观判断，做出真正正确的决策。

But with arenas, you take that subjectivity out of it by using large language models and other tools and incorporating massive amounts of information so that you can truly make the right decision.

很多这些 AI 工具都是黑箱，直接给你抛出结果，对吧？

A lot of these AI tools are black boxes that spit out answers, right?

你该怎么相信它呢？

How do you trust it?

你怎么知道到底该不该这么做？

How do you know, oh, should I do this or not?

所以我们在这上面加了一层，我们认为这是整个解决方案链条中非常关键的一环。

So we are adding that layer on top, which we think is going to be a fantastic piece of the entire continuum of solutions that we're providing.

综合来看，这说明我们属于 AI 创新者这一类，克雷格。

So with all of this, what this speaks to is we are in the AI innovator category, Craig.

我们不像那些生物技术公司，只是随便加了个 AI，或者外面那些用开源工具套个外壳就自称 AI 的公司。

We're not like these biotechs that have added AI and people, companies out there that are using the open source tools and putting their own wrapper around it.

我们正在创新，对吧？

We are innovating, right?

我们正在推动整个行业向前发展。

We're pushing the industry forward.

我们做的事，几乎每一件别人都做不了。

The things that we are doing, we're pretty sure in almost all cases nobody else can do them.

但我们还是个很小的公司。

But we're still this tiny company.

我们一直很低调。

We're under the radar.

所以现在这种拉扯感一直存在。

So that's sort of the tug of war that's going on.

但我们现在正全力推进和制药公司的合作。

But we're driving toward getting deals done now with pharma.

我们的目标很清楚，就是要成为一家有收入的公司。

Our goal, you know, we want to be a revenue generating company.

我们不是一家生物技术公司。

We're not a biotech.

我们不搞长期的药物研发。

We're not developing drugs for the long term.

那部分交给我们的客户去做。

We leave that to our customers.

没错。

Right.

我想问一下中间那个部分，BF LEAP。

And let me just ask about the middle part, BF LEAP.

我原以为它是专门针对精准肿瘤学的。

I thought that was specifically for precision oncology.

那是其中一个应用方向。

That was one of

应用之一。

the applications.

我可以跟你简单介绍一下BFLEAP是什么。

So I can tell you a little bit about what is BFLEAP.

它的核心其实是叫可扩展图分析技术。

So the core of it, the heart of it is something called scalable graph analytics.

明白吗？

Okay?

这项技术最初来自约翰斯·霍普金斯大学应用物理实验室。

That's what comes from the Johns Hopkins Applied Physics Lab.

后来我们逐步加入了因果人工智能的能力。

We've now over time added causal AI capabilities.

让我来解释一下这是什么意思。

And let me explain what that is.

我觉得你的听众一定会很感兴趣。

I think your audience will be really interested.

通常来说，人工智能是去找那些已经存在的模式和关联。

So typically with AI, you're looking for patterns and relationships that exist.

预测就是这么做的。

That's how the predictions are made.

所以我们现在加入了称为因果人工智能的技术。

So we've added something now called causal AI.

我们自己开发了这套系统，能在三十分钟内生成六百万个模型。

We've developed this ourselves where we can generate 6,000,000 models in thirty minutes.

有了因果人工智能，不仅能发现关系和模式，还能判断这些关系的强弱和方向。

And with causal AI, you can not only identify the relationships and patterns, but you can determine the magnitude and direction of the relationship.

那这对我们的行业来说为什么重要呢？

So why is that important for our industry?

生物系统非常复杂。

Biological systems are very complex.

如果你想知道，比如到底是哪个基因在推动疾病、引发这些病理通路，最终导致疾病，对吧？

So if you want to try to determine, say, hey, what gene is driving a disease, driving these disease pathways and ultimately leading to the disease, right?

拥有这种能力是个很大的优势。

Having that capability is an advantage.

我们用了这个技术，它帮助我们完成了不少工作。

And we've used that and that's helped us do some of the things we've done.

比如，我们和利伯脑发育研究所的合作，让我们能接触到他们所有的数据。

For example, our partnership with the Lieber Institute for Brain Development, we had access to all of their data.

他们拥有数千例精神神经疾病患者的死后脑组织样本。

They have many thousands of postmortem brains for neuropsychiatric patients.

精神神经疾病领域，光靠诊断还不够，药物研发更是难上加难。

And the world of neuropsychiatric, well, only diagnosing, but developing drugs, very challenging space.

这里面主观因素太多了。

A lot of subjectivity there.

靠的都是行为表现和症状，对吧？

It's about behavior and symptoms, right?

通过对这批珍贵数据的分析，我们是唯一能接触到这些资料的团队。

Well, through our analysis of this incredible data, we had exclusive access to it.

我们找到了这些疾病的生物学驱动因素。

We discovered the biological drivers of those diseases.

所以现在把这一点加到行为和症状上，我们就有了针对这些疾病的精准神经精神医学方法。

So now you add that to behavior symptoms, you have a precision neuropsych approach to these.

因此，我们认为已经找到了引发抑郁症、双相情感障碍和精神分裂症的基因。

So we believe we've discovered the genes that drive depression, bipolar and schizophrenia.

这些发现出来之后，我们就开始推向市场了。

So those discoveries now we've gone to market.

现在我们正在和大型制药公司接洽。

Now we're talking to big pharma.

咱们不如一起合作吧。

Hey, let's work together here.

我们已经锁定了药物靶点。

We've discovered the drug targets.

就像我一开始说的——虽然没明讲——选错药物靶点，正是很多药物失败的根本原因。

And like I said in the beginning, I didn't really say it, but getting the wrong drug target is the reason a very significant number of drugs fail.

因为有了这些因果网络，我们能清楚地指出，这才是疾病的根源所在。

Because with these causal networks, we can show it's like the root cause of the disease.

我们其实可以把它展示出来。

We can actually illustrate it.

你看，这个基因没有上游基因。

Hey, this gene has no parents.

所有其他变化都源自它。

Everything is downstream from it.

这才是根本原因。

This is the root cause.

对吧？

Right?

不是说那个在末端的基因，然后它开关调控其他基因导致了问题。

It's not the gene way at the end that then these genes turning on and off causes that.

而是这个根本原因。

It's this root cause.

很多时候，药物靶点是在下游被发现的。

A lot of times when drug targets are discovered, it's downstream somewhere.

这并不是根本原因，所以药物在开发中途就失败了。

It's not the root cause, which is why the drug fails somewhere in the middle of development.

如果从一开始就能选对靶点，能为整个行业节省大量时间和资金。

So being able to pick that right target from the beginning, it's going to save the industry lots of time and lots of money.

因为这不仅能帮助发现新靶点，如果你公司已经认为找到了正确靶点，我们也能帮你确认是不是真的对。

Because not only could you use it to discover new targets, but hey, if you're a company that's already you think you've discovered the right target, well, we can tell you if you did.

我觉得整个行业，连投资者，迟早都会意识到这项技术的价值。

So I think this is something the whole industry is gonna eventually really appreciate and investors too.

你知道生物技术投资的风险有多高吧？

I mean, you know how high risk biotech investing is, right?

是的，当然。

Yeah, sure.

不过有个问题，疾病并不一定都有遗传上的起点。

Just a question about that, but diseases don't have necessarily a root, genetic, starting point.

确实不一定有。

They're not necessarily.

是的。

Yeah.

各种因素组合成的一个矩阵。

A matrix of combinations of different, things.

那怎么来说呢？举个例子吧，我听说你们的时候，特别注意到BFLEAP识别出了胰腺癌的患者亚群，这些患者的平均总生存期提高了近三倍。

So, how, how, how can yeah, maybe take one I'll tell you on the, on, in taking one example, what caught my attention, when I heard about you guys is BFLEAP, has identified patients subgroups with a nearly threefold increase in mean overall survival of pancreatic cancer.

胰腺癌可是那种让人一听就害怕的疾病。

And pancreatic cancer is like one of those boogeymen that people might terrified of.

你能拿这个例子来说明吗？还是说这跟其他情况不太一样？

So could you use that as an example or is that a little different than?

我觉得我们可能在讨论两件不同的事，不过先说一点，我们的平台能整合任何类型的数据——刚才我们聊的是基因表达或基因组数据，但其实它支持的是真正的多模态数据，包括影像、人口统计、环境、实验室数据，还有你能想到的所有组学数据。

Well, I think we're talking about maybe two different things here, but let me first say our platform can ingest any type of data, We were just talking about gene expression or genomics data, but it's true multimodal data, imaging data, demographic data, environmental data, lab data, all the omics data you can imagine.

你说得对，克雷格。

So, you're right, Craig.

在很多情况下，情况远比单纯一个基因要复杂得多，对吧？

In a lot of cases, it's much more complicated than just a gene, right?

正因如此，我们才能整合所有这些信息。

But that's why we're able to bring all that information in.

这就是精准医疗的思路——通过全面分析患者的基因和非基因特征，找出最可能对胰腺癌药物产生良好反应的群体。

And that's the precision medicine approach because then you can really identify the true genetic and non genetic profile of a patient that will maybe in this case best respond to a pancreatic cancer drug.

所以在这个案例中，我们面对海量数据，成功识别出一个患者亚群和相关生物标志物，将总体生存期从两个月延长到了六个月，这对胰腺癌来说意义重大。

So yeah, in that example, that's when we had this mountain of data and we were able to identify a patient subgroup and biomarkers that increased the overall survival from two months to six months, which is for pancreatic cancer, that's a big deal.

这也说明，答案其实就藏在这些数据里。

But it also speaks to the fact that, hey, answer is in there.

这正是精准医疗的核心理念。

That's a precision medicine approach.

如果你的特征匹配这一类群体，这种药就会对你有效。

If you're a patient with this particular profile, this drug will benefit you.

整个行业，尤其是借助人工智能，正被推着朝这个方向走。

The whole industry, especially with AI, it's almost being forced in that direction.

我们谈论精准医疗已经二十多年了，但始终存在一种矛盾：药企往往希望覆盖更广泛的患者群体。

I mean, we've been hearing about precision medicine for twenty But plus there's always that tension because pharma wants wide nets for the patient population.

他们希望覆盖数百万患者。

They want millions of patients.

但如果你想要真正有效的药，那就做不到这一点。

Well, if you want drugs that actually work, you're not going to be able to do that.

你必须采取精准医疗的路径。

You've to take a precision approach.

我认为，随着人工智能的广泛应用，将会极大推动现有的精准医疗发展。

So I think with mass adoption of AI, it's going to turbo boost the precision medicine initiative that's out there.

对。

Yeah.

而且你提到大药企，但现在有很多小型公司和实验室在研发新分子或药物，从一期、二期临床试验一路推进，最后卖给大药企。

And also, you're talking about big pharma, but what's happening are there are smaller companies, labs that are developing molecules or drugs, and they bring them all the way up through phase one, phase two trial and then sell them to big pharma.

这会影响市场的这一部分吗？

Is that affecting that strata of the market?

这些公司虽然不是大药企，但它们专注在精准药物研发上。

Those companies, it's not big pharma, but they're focused on precision drug discovery.

是的，确实如此。

Yeah, it is.

我看到越来越多的生物技术公司从一开始就尝试融入人工智能。

I think what I'm seeing is more and more biotechs now are trying to incorporate AI from the beginning.

对吧？

Right?

他们明白，这只会提升成功的几率。

Mean, they realize it's only going to improve their chances for success.

关键在于能提升多少？

The question is by how much?

但在生物技术这个高风险行业里，从起步到成功的成功率低得可怜，任何一点提升都意义重大。

But still, in this incredibly high risk business of biotech where your chances from start to finish are like low single digit percentages, Any improvement, it's a big deal.

所以，我们确实看到了这种趋势。

So yeah, we are seeing that.

这正变得越来越普遍。如果你看看其他国家，比如中国，他们已经把人工智能全面融入了整个生物技术产业。

That's becoming And then if you look at other countries, China, for example, they've bolted AI into their entire biotech industry.

现在这就像有了电一样普遍。

It's like having electricity at this point.

美国在生物技术领域可能在这方面跟进得慢了一些。

Think US has been slower probably on the biotech end to adopt that.

制药行业过去十年早就明白了其中的价值。

Pharma has understood the value for the past ten years.

所以他们才一直在做各种合作交易。

That's why they've been doing all these deals.

现在他们开始收购人工智能公司，因为他们想拥有自己的模型。

And now they're starting to make acquisitions in AI because they want to own their own models.

他们不想只是跟别人合作。

They don't want to partner on them.

他们想要完全掌控。

They want to own them.

所以他们要么直接收购，要么像礼来那样，跟科技巨头合作，打造超算能力，开发自己的模型等等。

So they're making acquisitions or they're doing what Eli Lilly did and say, hey, we're going to partner with big tech and build supercomputing capabilities and develop our own models and so forth.

总之，这些就是目前正在发生的一些变化。

Anyway, that's sort of the some of the changes that are occurring.

但对我们来说，一切都朝着正确的方向发展。

But it's all in the right direction for us.

一切都挺好的。

It's all good.

对。

Yeah.

所以你们的意思是，你们不针对特定疾病或靶点，对吧？

And so you guys, you're saying you're disease or target agnostic.

是的。

Yeah.

我们对疾病和阶段都不设限。

We are disease and stage agnostic.

对。

Yeah.

那企业具体是怎么用的呢？咱们来聊聊这三个平台。

So how does a company use, and let's talk about the three platforms.

它们的使用流程是怎样的？或者说，进阶的路径是什么？

How do they, what's the progression?

我的意思是，大致来说

I mean, sort

就是给大家

of give

给我一个案例，比如那个神经精神方面的案例，Happy非常

me a use case, maybe that neuropsychiatric use case Happy is very

去做这件事。

to do it.

我的意思是，首先我们会跟一家公司沟通，基本上是对他们的数据进行审计。

I mean, so the first thing is we talk to a company, we basically audit their data.

好的。

Okay.

你们的数据状况怎么样？

What kind of condition is your data in?

我们有BF预处理服务。

And we have BF prep.

我们可以帮你们处理这些数据。

We can prepare that data.

这对我们来说是个很好的切入点。

So it's a great door opener for us.

即使他们之后不想继续合作，我们也能看出他们的数据有问题，这就是第一步。

Even if they don't want to work with us beyond that, we know they got problems with their data, So that's the first step.

接下来，我们可以帮他们整理、清洗和结构化数据。

Then we can basically prepare, clean and structure their data.

原本需要一个团队花几个月才能完成的事，

So we can do what would take a team months.

我们有时几个小时就能搞定，最迟几天内一定能把数据准备好。

We can do it sometimes in hours, but certainly in days we can prepare that data.

接下来，你要从这些数据里找出哪些关键问题的答案？

Then the next step is, what questions do you want answers to in this data?

我们能帮你发现什么？

What can we help you find?

这时候，BF Leap 和数据分析就派上用场了。

And that's where BF Leap and the analytics comes into play.

没错。

Right.

基于这些分析，我们就能构建出这些关系网络。

So out of that, we're able to build these networks.

这些网络能揭示数据中的关联，比如找出疾病通路之类的。

These networks show the relationships that exist in the data, or you can identify disease pathways and things like that.

然后，系统会做出一系列预测。

Then let's say a number of predictions are made.

就像我之前举的例子，药物靶点。

And like an example I gave earlier was drug targets.

假设有一组基因，我们认为它们是导致这种疾病的关键因素。

And let's say there's a series of genes that we think they're the drivers of a disease.

那么在这十个关键基因中，我们应该优先关注哪一个呢？

Okay, which one should we go after out of those 10 driver genes?

这时候，BF Arenas 就派上用场了。

And that's where we layer on BF arenas.

BF Arenas 会把每一个候选都拿出来比拼，这才是真正的核心所在。

So BF arenas effectively takes each of those selections and creates a competition between them, which is that's really the secret sauce.

这就是我们的方法。

That's the approach.

同时整合了大量其他相关信息。

And brings in lots of other information.

最终你会得到一个更有把握的推荐结果。

And then what you're presented with is a recommendation that you can have a lot more confidence in.

BF Arena 的原理也是一样的。

BF Arena is the same.

先选目标一，然后是六，再是九。

Go for target one and then six and then nine.

这就像是一个优先级排序。

So it's like a priority ranking.

我觉得在AI时代，这一点至关重要。

And I think that's going to be critical in this world of AI.

首先，你得相信AI给出的结果。

First of all, you have to trust what the AI is telling you.

这时候，可解释性就很重要了。

And that's where explainability is important.

我们的平台从一开始就是可解释的。

Our platform's always been explainable from the very beginning.

它不是个黑箱。

It's not a black box.

但就算能解释清楚，也得帮我们做决定。

But then even with explainability, okay, help me make a decision.

总之，我们认为我们的位置非常独特。

Anyway, I think we're uniquely positioned.

我们虽然是个小公司，但在创新方面却走在最前沿。

We're a small company but super high on the innovative end of things.

所以现在我们认为，我们拥有三项对行业至关重要的核心优势，能带来真正的改变。

So now we think we got three really valuable pieces for the industry that are going to make a difference.

对。

Yeah.

在刚才那个阶段，你说不同的目标彼此竞争时，你们是不是在用进化型AI？就是多个模型分别输出结果，然后选出最好的再组合起来？

At the last stage there, when you said then you have these these different targets competing with each other, are you using evolutionary AI where where you're different models produce an output and then you take the best and combine those models?

是的，我们确实会评估多个模型。

Yeah, so we're looking at different models.

就像我说的，凭借我们的因果AI能力，几分钟内就能生成数百万个模型。

And like I said, with our causal AI capabilities, for example, we can generate millions of models in a matter of minutes.

这正是它的精妙之处。

But that's the beauty of it.

你是在把大量信息、多个模型和各种结果整合在一起。

Like you're bringing lots of information together, lots of models, lots of outputs.

然后你试图找出其中的共同点，从而更有信心做出选择。

And then you're trying to find sort of where that common thread is to give you confidence in what selection to make.

你之前提到一个有意思的观点，说你们在考虑分析那些失败的药物，因为临床试验失败很多时候跟药物本身没关系。

You said an interesting thing earlier that you were considering looking at failed drugs because clinical trials fail oftentimes for reasons that have nothing to do with the underlying drug.

但这一切的核心，不就是提高临床试验成功的概率吗？

But the point of all this is to increase the likelihood that a clinical trial will succeed, right?

我的意思是，归根结底。

I mean, ultimately

这正是目标。

That's the goal.

这一直是目标。

That is the goal.

从一开始我们就想降低药物研发的风险，提高成功率，缩短时间和减少投入。

That's been the goal from the beginning to de risk drug development, improve the odds of success, shrink the timelines and investment.

这一直都是目标。

That's always been the goal.

就像我之前说的，我们有机会在早期和后期介入。

And like I said, we've had opportunities to get involved at the beginning, at the end.

希望未来我们能更多地参与到中间阶段。

Hopefully in the future, we'll get more involved in the middle stages.

我觉得这正是人工智能的整体目标，对吧？

And I think that's the goal of AI in general, right?

不管你身处哪个行业都是这样。

It doesn't matter what industry you're in.

目的就是提升效率，对吧？

It's to improve efficiencies, right?

是的。

Yeah.

这三个平台分别是：BF prep 负责生成、清洗和准备数据；BF leap 做因果分析；还有 BF arenas，用来决定该聚焦哪些方向。

So these three platforms, BF prep that makes the data, cleans the data, prepares the data, and then the causal analysis that's BF leap, and then, the sort of decisions on what to focus on that's BF arenas.