Claude 如何设计出针对蝎毒神经毒素的蛋白质结合体

摘要：作为我们探索 Claude 如何加速药物发现工作的一部分，我们请一个内部研究模型针对蝎毒神经毒素设计迷你结合蛋白（能够紧密附着于目标的小型蛋白质）。Claude 根据我们的提示和四轮后续指示开展工作，这些内容由我们与金融投资研究公司 Citrini Research 合作制定。Adaptyv Bio 和 Twist Bioscience 的团队对 211 个设计进行了结合实验测试，其中 17 个符合我们的标准。我们现将全部 211 个设计及其数据公开，供该领域使用。Summary: As part of our work experimenting with how Claude can help accelerate drug discovery, we asked an internal research model to design minibinders (small proteins that attach tightly to a target) against scorpion neurotoxins. Claude worked from our prompt and four follow-ups, which we developed in collaboration with the financial investment research firm Citrini Research. Teams at Adaptyv Bio and Twist Bioscience experimentally tested 211 designs for binding. Of these, 17 met our criteria. We’re releasing all 211 designs and their data as a resource for the field.

8 月，我们展示了 Claude 如何在只收到一个提示词的情况下设计蛋白质微型结合体。在我们公布这些成果的一个月前，Citrini Research 的一个团队向我们提出了一个有趣的问题：Claude（以及更广义上的 AI 药物发现）能否帮助一群有热情的非专业人士解决一个真正的人类健康问题？我们的生命科学研究团队着手寻找答案，首先与 Claude 一起头脑风暴，探讨可以解决的问题。最终，我们决定请 Claude 协助设计针对蝎子神经毒素的新型蛋白质结合体，希望有朝一日能用它们来开发蝎毒抗血清。In August, we showed how Claude designed protein minibinders after being given a single prompt. A month before we released those results, a team from Citrini Research had approached us with an interesting question: could Claude (and AI drug discovery more generally) enable a group of motivated nonexperts to tackle a genuine problem in human health? Members of our life science research team set out to answer this, first by brainstorming problems with Claude. We landed on asking for Claude’s help designing novel protein binders against scorpion neurotoxins, with the hope that they could one day be used to develop a scorpion antivenom.

蝎子每年蜇伤至少120万人，造成超过3250人死亡，其中大多数是医疗服务有限地区的儿童。新疗法研发成本高昂，而且很可能无法收回开发成本。由于投资极少，蝎毒中毒被称为一种被忽视的热带病。Scorpions sting 1.2 million people or more every year, resulting in more than 3,250 deaths, mostly among children in parts of the world with limited access to medical care. New treatments are expensive to make, and are also unlikely to earn back the cost of developing them. With so little investment, scorpion envenomation has been described as a neglected tropical disease.

我们首先向 Claude 提供了与此前蛋白质结合剂研究中相同的提示词，只是在用 Citrini 对其进行修改后才使用。接下来的 64 小时里，一个在 Claude Science 中运行的内部研究模型主要以自主方式开展工作，尽管我们通过四次后续指示引导了它的工作。在我们的监督下，Claude 分析了研究数据、生成了图表，并起草了最终报告。We started by giving Claude the same prompt we’d used in our earlier protein-binder study, after modifying it with Citrini.¹ Over the next 64 hours, an internal research model, operating within Claude Science, worked mainly autonomously, although we directed its work with four follow-ups. Under our supervision, Claude analyzed the research data, generated the figures, and drafted the final report.

Claude 的设计项目产生了 17 种蛋白质结合体，它们分别能与四种已知对人类有害的蝎神经毒素中的一种结合。在整个过程中，Claude 生成了 318,484 种蛋白质设计，并从中挑选了 180 种进行测试。在 Claude 的帮助下，我们的团队又增加了 31 种。我们的合作伙伴 Adaptyv Bio 和 Twist Bioscience 是两家合同研究组织（CRO），他们在实验室中测试了全部 211 种设计，以确认它们是否会与各自针对的毒素结合，其中 17 种设计符合我们对结合体的标准。我们尚未确认这些结合体能否在细胞环境中中和蝎毒，因此不会声称已经研制出抗蝎毒药物。Claude’s design campaign produced 17 protein binders that each bind to one of four scorpion neurotoxins that are known to be dangerous to humans. Throughout the process, Claude generated 318,484 protein designs and selected 180 of them for testing. Our team added 31 more, with Claude’s help. Our partners at Adaptyv Bio and Twist Bioscience, two contract research organizations (CROs), lab-tested all 211 designs to see if they would bind to the toxins they were designed against, and 17 designs met our criteria for a binder. We have not confirmed whether these binders neutralize scorpion venom in a cellular environment, so we do not claim to have produced an antivenom.

我们将 Claude 的工作交给了两位外部专家 Susana Vázquez Torres 和 Timothy P. Jenkins 审阅。他们表示，认为这项工作是一个很有希望的起点。如果 AI 如今能在几天内设计出针对多种难以靶向的毒素、且可信度较高的结合蛋白，并能在几周内通过实验室验证，那么理论上，这或许能加快针对毒液中毒及其他被忽视疾病的研究发现。和以往一样，挑战在于如何将这些结合蛋白转化为安全、价格可负担且广泛可及的药物。We sent Claude’s work to two outside experts, Susana Vázquez Torres and Timothy P. Jenkins, who said they felt this work was a promising first step. If AI can now design credible binders against several hard-to-target toxins in days and they can be confirmed in the lab within weeks, this could, in theory, speed up discovery for envenomation and other neglected diseases. The challenge, as always, is turning those binders into safe, affordable, and widely accessible drugs.

我们在技术报告中分享了更多细节，并将公开全部 211 种设计及其数据。We share more detail in our technical report, and are making all 211 designs and their data available.

苏萨娜·巴斯克斯·托雷斯，博士后研究员，结构生物学项目，西班牙国家癌症研究中心（CNIO），西班牙马德里。Susana Vázquez Torres, Postdoctoral Researcher, Structural Biology Programme, Spanish National Cancer Research Centre (CNIO), Madrid, Spain.

针对四种蝎子的五种毒素进行从头结合蛋白设计Designing de novo binders against five toxins from four species of scorpions

蝎毒含有多种蛋白质神经毒素。最可能伤害或杀死人类的神经毒素会附着在钠通道上。钠通道是嵌入神经细胞膜中的大型蛋白质，使神经细胞能够放电。钠通道受到干扰时，神经会在错误的时机放电，释放大量应激性化学物质，例如肾上腺素。严重情况下，这可能导致心力衰竭和肺部积液，偶尔会造成死亡。Scorpion venom contains multiple protein neurotoxins. The neurotoxins that are most likely to harm or kill humans attach to sodium channels, large proteins embedded in the membranes of nerve cells that allow them to fire. When sodium channels are disrupted, nerves fire at the wrong time—this releases large amounts of stress chemicals, like adrenaline. In severe cases, this can cause heart failure and excess fluid buildup in the lungs, occasionally resulting in death.

目前有一些可用于治疗蝎子蜇伤的抗毒血清。它们通常由经过免疫的动物的抗体制成，而这一过程可能需要数月。研究人员从数千只蝎子身上采集毒液，用来给马匹免疫；随后再从马血中提纯由此产生的抗体。传统抗毒血清若能及早使用，通常会有效，但往往只对少数几种神经毒素有效。此外，这类抗毒血清生产成本高，在许多地区价格昂贵或供应短缺。There are some antivenoms available for scorpion stings. They’re generally made using the antibodies of immunized animals, a process that can take months. Venom is milked from thousands of scorpions and used to immunize horses; scientists then purify the resulting antibodies from the horses’ blood. Traditional antivenoms can work when given early, but they’re usually effective for only a small number of neurotoxins. They’re also expensive to produce, and in many regions are costly or in short supply.

从头设计提供了一种潜在的解决方案。结合剂是一种能够与特定靶标紧密结合的分子；抗体就是一个天然的例子。原则上，若结合剂能够靶向神经毒素中与钠通道结合的部位，就可以阻止毒素接触钠通道。在从头设计中，针对特定靶标的蛋白质结合剂从零开始生成。这些结合剂通过计算进行设计，并可针对效力和稳定性等类药物特性进行优化，从而有望更便于在最常发生蜇伤的地区供应。De novo design offers a potential solution. A binder is a molecule that attaches tightly to a specific target; antibodies are one natural example. In principle, a binder that targets the part of a neurotoxin that latches onto sodium channels could stop the toxin from reaching the channel. In de novo design, protein binders are generated from scratch against a specific target. These binders are designed computationally and can be optimized for druglike properties such as potency and stability, which could make them easier to supply in regions where stings most often occur.

我们的研究思路受到一项早期研究的启发：该研究从头设计了能够中和蛇类神经毒素并保护小鼠的蛋白质。据我们所知，针对蝎类神经毒素的从头设计结合蛋白尚未见报道。Our approach was inspired by an earlier effort that designed de novo proteins that neutralized snake neurotoxins and protected mice. To our knowledge, no de novo-designed binders against scorpion neurotoxins have been described.

在这次研究中，我们选择针对分布于四个地区的五种蝎毒神经毒素：墨西哥（Cn2）、巴西（Ts1）、北非（AaH I 和 AaH II）以及中东（LqhIII）。我们还决定让设计方案靶向每种毒素的通道结合位点。Claude 通过搜索蛋白质数据库（PDB）和 AlphaFold 数据库（AFDB），选出了用于设计的毒素结构。针对每种毒素，它都选定了五个热点，即毒素上的特定氨基酸位置，设计的结合体旨在与这些位置结合。For this campaign, we chose to target five scorpion-venom neurotoxins across four regions: Mexico (Cn2), Brazil (Ts1), North Africa (AaH I and AaH II), and the Middle East (LqhIII). We also chose to aim the designs at each toxin’s channel-binding site. Claude picked the toxin structures to use for design by searching the Protein Data Bank (PDB) as well as the AlphaFold database (AFDB). For each toxin, it selected five hotspots, specific amino acid positions on the toxin that its binder designs were meant to latch onto.

我们主要想知道 Claude 是否能够针对单种毒素设计结合蛋白。不过，我们也想了解 Claude 是否能够设计出可靶向多种毒素的结合蛋白。尝试设计多毒素结合蛋白有其现实意义：这能减少通用抗蛇毒血清鸡尾酒所需的分子种类，而这种鸡尾酒将是最具成本效益、且不受地域限制的治疗方案。我们选取了这五种蝎毒素（Cn2、Ts1、AaH I、AaH II 和 LqhIII）作为多毒素设计的一项严峻测试：它们的蛋白质整体形状具有相同的折叠结构，但任意两种毒素的氨基酸序列一致性仅为 26% 至 62%。We were primarily wondering if Claude could design binders against individual toxins. But we were also curious if Claude could design binders that targeted multiple toxins. There’s a practical reason for trying to design multitoxin binders, namely that it would reduce the number of molecules needed for a universal antivenom cocktail—which would be the most cost-effective and regionally neutral treatment. We selected these five scorpion toxins (Cn2, Ts1, AaH I, AaH II, and LqhIII) as a challenging test of multitoxin design: they share one fold for the overall shape of the protein, but any two are only 26% to 62% identical in their amino acid sequences.

为了了解 Claude 能做到什么程度，我们让它设计四类结合蛋白：分别针对五种毒素中每一种的结合蛋白；靶向 β 家族毒素 Ts1 和 Cn2 的结合蛋白；靶向 α 家族毒素 AaH II、AaH I 和 LqhIII 的结合蛋白；以及能够同时靶向全部五种毒素的结合蛋白。To see how far Claude could go, we asked it to design four kinds of binders: binders against each of the five toxins individually; binders that targeted the β-family toxins Ts1 and Cn2; binders that targeted the α-family toxins AaH II, AaH I, and LqhIII; and binders that targeted all five toxins simultaneously.

蒂莫西·P·詹金斯，丹麦技术大学副教授。Timothy P. Jenkins, Associate Professor, Technical University of Denmark.

Claude 凭借相当大的自主权开展了这场设计活动。Claude ran the design campaign with considerable autonomy

我们的初始提示词定义了神经毒素靶标、蛋白质设计和折叠工具，以及新颖性、评分和筛选规则。除了选择结构和氨基酸热点外，Claude还设定了设计必须达到的质量门槛，决定对每种可用设计工具的依赖程度，并制定了针对多种毒素设计结合蛋白的策略。Our initial prompt defined the neurotoxin targets, the protein design and folding tools, and the rules for novelty, scoring, and filtering. Beyond choosing the structures and amino acid hotspots, Claude also set the quality thresholds a design had to clear, decided how much to lean on each available design tool, and developed the strategies for designing binders against multiple toxins.

最终，Claude 使用 12 种设计工具生成了 318,484 个设计，并筛除了任何与毒素或已知蛋白质相似的设计。Claude 对 553,052 组设计-毒素配对进行了共同折叠和筛选，将每组配对的结构预测为一个复合物。在我们向 Claude 提供初始提示 64 小时后，它生成了最终的 180 个设计清单。此次研究活动耗用了约 10,000 个 GPU 小时。2Ultimately, Claude used 12 design tools to generate 318,484 designs, filtering out any that resembled a toxin or a known protein. Claude co-folded and screened 553,052 design-toxin pairs, predicting each pair’s structure as one complex. Sixty-four hours after we gave Claude our initial prompt, it produced its final list of 180 designs. The campaign used on the order of 10,000 GPU hours.²

在我们发出第一条提示后，Claude 自主工作了 24 小时。它的成果促使我们继续提示 Claude 推进这项工作，并寻找更好的设计。后续提示主要是引导 Claude 设计一种多毒素结合蛋白。直到我们第三次追加提示后，Claude 才选出了 180 个设计中的大多数，其中包括我们最强的结合蛋白（Cn2-B1）。应我们的要求，Claude 将蛋白质序列发送给了 Twist Bioscience（邮件中注明这些邮件由 Claude 撰写），由该公司合成蛋白质，以便测试它们与毒素的结合能力。之后，我们又与 Claude 合作新增了 31 个设计，使总数达到 211 个：针对单一毒素的 60 个设计（每种毒素 12 个），针对两种 β 家族毒素的 30 个设计，针对三种 α 家族毒素的 30 个设计，以及针对全部五种毒素的 91 个设计。Claude worked autonomously for 24 hours following our first prompt. Its results encouraged us to prompt Claude to continue its campaign and look for better designs. Our follow-up prompts were mainly focused on directing Claude to design a multitoxin binder. Claude selected most of the 180 designs—including our strongest binder (Cn2-B1)—only after our third follow-up. At our request, Claude sent the protein sequences to Twist Bioscience (in emails indicating they were written by Claude), which produced the proteins in order to see how well they would bind to the toxins. We later worked with Claude to add another 31 designs, increasing the total to 211 designs: 60 designs against a single toxin (12 per toxin), 30 designs against the two β-family toxins, 30 designs against the three α-family toxins, and 91 designs against all five toxins.

在我们的团队评估的 211 个设计中，有 17 个符合我们的结合剂标准，且每个设计都只针对一种毒素。针对多种毒素设计的方案中，没有一个符合针对一种以上毒素的标准。（除了受当前能力限制之外，Claude 在这项任务中表现不佳可能有很多原因，包括我们的提示方式、可用设计工具的局限性，甚至多毒素设计在生物学上是否可行。）其中，7 个设计是针对 Cn2 的结合剂，4 个针对 AaH II，4 个针对 AaH I，2 个针对 LqhIII。在 60 个针对单一毒素的设计中，有 11 个是结合剂（18%）。这一比例与典型的蛋白质设计项目一致，包括我们此前的工作。Of the 211 designs our teams assessed, 17 met our criteria for a binder, each against a single toxin. None of the designs made against multiple toxins met our criteria for more than one. (Beyond being limited by its current capabilities, there could be many explanations for why Claude struggled with this, including our prompting, the limitations of available design tools, and even the biological feasibility of multitoxin design.) Seven designs were binders against Cn2, four against AaH II, four against AaH I, and two against LqhIII. Among the 60 single-toxin designs, 11 were binders (18%). This rate is consistent with typical protein design campaigns, including our previous work.

在实验室测试 Claude 的设计方案Testing Claude's designs in the lab

完成这轮设计后，我们将设计方案发送给 Adaptyv Bio 和 Twist Bioscience，以测试它们的结合能力。两家机构都在各自的实验室中制备了这些设计，但采用的形式不同。Adaptyv Bio 使用无细胞系统表达这些设计，该系统利用从细菌中提取的蛋白质合成机制，而非活细胞。Twist Bioscience 则在哺乳动物细胞（本例中为人肾细胞）中表达这些设计，并将它们与 Fc（抗体的柄部）融合。这两种方式可以互为补充，用于测量底层的结合过程；我们将它们结合起来，以提高结果的可信度。After completing the campaign, we sent the designs to Adaptyv Bio and Twist Bioscience to test them for binding. Each group produced the designs in their labs, but in different formats. Adaptyv Bio expressed them in a cell-free system, which uses protein-making machinery extracted from bacteria rather than living cells. Twist Bioscience expressed the designs in mammalian cells (in this case, human kidney cells) as fusions to Fc, the stem of an antibody. These are complementary ways to measure the underlying binding process, and we combined them in order to improve confidence in our results.

两个实验室都使用表面等离子体共振（SPR）测量结合情况：毒素流经设计分子表面时，SPR仪器会实时追踪毒素与其结合及解离的速度。由此得到的曲线称为传感图，可用于测量解离常数（KD），这是衡量结合强度（或亲和力）的指标。KD越低，结合越紧密。Both labs measured binding by surface plasmon resonance (SPR), in which a toxin flows over the design while the SPR instrument tracks in real time how quickly a toxin binds to and detaches from it. The resulting trace, called a sensorgram, produces a measurement known as the dissociation constant (KD), which is a measurement for binding strength (or affinity). The lower the KD, the tighter the binding.

在评估最终设计时，我们制定了严格标准，用于判定某个设计是否能结合毒素。该设计必须在两个实验室都被判定为命中³——也就是说，在每次重复实验中都必须有证据表明它能结合该毒素，并且每个 KD 都必须达到 1 µM 或更高的亲和力。我们还要求该设计对 CLEC12A 不显示任何信号；CLEC12A 是一种无关的人类蛋白，用于测量脱靶结合或“黏性”。When it came to evaluating the resulting designs, we set out strict criteria for labeling a design a binder against a toxin. The design needed to be a hit at both labs³—that is, it needed to show evidence of binding against that toxin in every replicate, and every KD needed to be 1 µM or tighter. We also required that the design show no signal against CLEC12A, an unrelated human protein used to measure off-target binding or “stickiness.”

Claude 的 Cn2 结合体可能与一种毒素中和抗体结合于同一位点。Claude’s Cn2 binders likely bind the same site as a toxin-neutralizing antibody

抗体和纳米抗体仍是从头设计需要超越的标准。已有三种此类分子被报道对 Cn2 或 AaH II 的亲和力（KD）低于 1 nM（纳摩尔），并且已证明它们能够保护小鼠免受蝎毒侵害。Antibodies and nanobodies remain the standard for de novo designs to beat. Three such molecules have reported affinities (KD) below 1 nM (nanomolar) against Cn2 or AaH II, and they have been shown to protect mice from scorpion toxins.

我们称为 Cn2-B1 和 Cn2-B2 的两种最强结合分子，靶向 Cn2——一种来自墨西哥毒蝎 Centruroides noxius 的神经毒素。它们在 Adaptyv Bio 和 Twist Bioscience 的测试中均能与 Cn2 紧密结合，亲和力（KD）达到个位数纳摩尔范围。Our two strongest binders, which we call Cn2-B1 and Cn2-B2, target Cn2, a neurotoxin from the Mexican scorpion Centruroides noxius. They each bound Cn2 tightly at both Adaptyv Bio and Twist Bioscience, with affinities (KD) in the single-digit nanomolar range.

要确定两个分子（例如抗体和微型蛋白）是否结合靶标上的同一位点，可以进行竞争实验，测试两种结合分子能否同时附着在靶标上。如果一种分子的存在降低了另一种分子的结合能力，那么它们很可能是在争夺同一个结合位点。One way to find out whether two molecules (e.g., an antibody and a miniprotein) bind the same site on a target is with a competition experiment, which tests whether both binders can attach to the target at the same time. If the presence of one molecule reduces the other molecule’s binding, then they likely compete for the same binding site.

我们的竞争实验表明，每种 Cn2 结合剂都结合在与一种名为 LR 的抗体相同或相近的表位（结合位点）上。据报道，LR 能在小鼠体内中和 Cn2。LR 的结合位点覆盖了 Cn2 上与钠通道结合并导致神经信号异常放电的部分。我们尚未在细胞环境或活体动物中测试过效力最强的结合剂 Cn2-B1 和 Cn2-B2，但它们能与 LR 竞争这一事实表明，它们很可能也能中和 Cn2。Our competition experiments suggest our Cn2 binders each attach on or near the same epitope (binding site) as an antibody called LR, which has been reported to neutralize Cn2 in mice. LR’s binding site covers the part of Cn2 that attaches to the sodium channel and causes nerves to misfire. We have not tested our strongest binders, Cn2-B1 and Cn2-B2, in a cellular environment or in live animals, but the fact that they compete with LR suggests that they will likely neutralize Cn2.

结合剂只是开发抗蛇毒血清的第一步。A binder is only the first step to developing an antivenom

我们的结果仅显示了对重组毒素的结合。这些毒素是在实验室中根据各自的基因制备的，而不是从蛇毒中纯化得到的。本研究有两项最大的局限：我们没有测试任何设计在体外（针对实验室培养的细胞）是否具有中和作用，也没有测试其在体内（活体动物，如小鼠）是否有效。Our results show binding only against recombinant toxins, which are grown in the lab from each toxin’s gene rather than purified from venom. The two biggest limitations of this study are that we didn’t test any design for neutralization in vitro (against cells grown in the lab) or for efficacy in vivo (in living animals, such as mice).

如果要将一种设计推进为疗法，Cn2-B1 将是我们最有力的候选之一。不过，首先我们需要确认，这种设计也能结合从毒液中纯化出的毒素。随后，我们会通过膜片钳记录在体外评估其功能（膜片钳可测量流经钠通道的电流），以判断它能否阻止毒素作用于通道。接下来，我们还需要在小鼠身上测试这种结合剂，看看它是否确实能起到保护作用。治疗除了要中和毒素，还必须安全、稳定、价格可负担，并能在发生蜇伤的地区供应。要让患者用上这种疗法，还需要临床医生、资助方和政策制定者通力合作。If we were to advance one design toward a therapy, Cn2-B1 would be one of our strongest candidates. First, though, we would need to confirm the design also binds toxin purified from venom. We would then assess it for function in vitro with patch-clamp recordings (which can measure the electrical current passing through sodium channels) to see whether it stops the toxin from acting on the channel. Then, we would need to test the binder in mice to see whether it actually protects them. Beyond neutralizing the toxin, a treatment must also be safe, stable, affordable, and available where stings occur. Reaching patients will also take cooperation from clinicians, funders, and policymakers.

我们将公开全部 211 种设计及其结合数据，以便其他研究人员在我们的工作基础上继续开展研究。我们希望，这次对 Claude 能力的展示以及我们发布的数据，能够推动抗蛇毒血清设计领域的进一步研究。We are releasing all 211 designs and their binding data so that other researchers can build on our work. We hope this demonstration of Claude’s capabilities, along with the data we are releasing, will help accelerate further research into antivenom design.

延伸阅读Further reading

以下资源提供了更深入的技术内容，以及有关上述结果的更多详细信息：The following resources provide further technical depth and more detailed information about the results described above:

• 技术报告；
  Technical report;
• 数据发布：全部 211 个设计、其预测结构和评分，以及实验数据；
  Data release: all 211 designs, their predicted structures and scores, and experimental data;
• 我们此前关于蛋白质设计和令人振奋的生物分子建模的文章。
  Our previous posts on protein design and uplifting biomolecular modeling.