包括细菌、真菌、寄生虫和病毒在内的耐药微生物正日益成为全球性威胁。2021年，约500万人的死亡与细菌抗微生物药物耐药性相关（在新窗口中打开）——预计到2050年，这一年度死亡人数将大致翻倍。找到有可能成为抗微生物药物的分子可能需要数年时间。研究人员正在利用人工智能加速这一早期发现阶段。
“在我看来，抗微生物药物耐药性是人类面临的最大生存威胁之一，”生物工程师塞萨尔·德拉富恩特（在新窗口中打开）说，他的跨学科实验室正在寻找抗微生物药物候选分子。“然而，我们已经50年没有新的抗生素类别了。”
现代抗微生物药物研发大多集中于修改现有药物或搜索熟悉的化学类别。但这种方法带来的回报正在递减。
德拉富恩特的实验室从某个远未被充分探索的地方入手：生命的代码。这项工作背后的核心思想是，生物学是一个信息系统。“构成DNA的核苷酸，以及构成蛋白质和多肽的氨基酸，有点像一种字母表，”德拉富恩特说。“把生物学视为信息，使我们能够开发出一些方法，开始破译那些产生了功能性分子的生命组织原则。”
该实验室的深度学习模型经过训练，可以识别生物序列中的模式，从而使它们能够搜索庞大的基因组和蛋白质数据集，以寻找潜在的抗微生物药物。这种方法可以将候选分子的初步搜索从数年缩短到数小时。
除了自己的人工智能模型外，该实验室还使用ChatGPT和Codex来集思广益提出假设、编写和优化代码、处理数据集、分析结果，并连接跨学科的科学思想。
探索生物学中未被读取的空间
基因组中只有一小部分具有被清楚理解的功能，而其中编码能够对抗感染性微生物的分子的部分更少。挑战在于识别使分子具有功能性或生物活性的模式，然后确定哪些模式具有对抗感染性微生物的潜力。
长期以来，科学家一直在植物、动物、微生物、昆虫、水和土壤中寻找抗微生物药物。他们收集样本，分离或预测候选分子，并在一个可能耗时数年的迭代过程中对其进行测试。
如今，数字基因组和蛋白质数据库使科学家能够跨越生命之树搜索新化合物，极大地扩展了可供探索的数据库广度。但信息的丰富也带来了自身挑战：如何在数量庞大的可能性中找到有前景的信号。
人工智能特别适合这种大海捞针的任务。它可以扫描庞大的数据集，识别研究人员可能难以发现的模式，并优先筛选出一组数量可控、可供实验测试的候选物。
但识别出一个有前景的候选物，并不一定意味着它会成为有效药物。
科学家必须首先确认候选分子能够杀死目标微生物，确定其有效所需剂量，并测试它对人类细胞的影响。化学家随后可能会对其进行优化，以提高其有效性、安全性或稳定性。
进一步的测试会评估候选物在何种剂量下会产生毒性、微生物对其产生耐药性的难易程度，以及候选物如何在体内移动。团队还会确定一种可靠的分子制造方法。通过这些关卡的候选物在作为获批抗微生物药物到达患者手中之前，仍要面临监管审查和临床试验。
对德拉富恩特来说，这就是为什么人工智能和实验室生物学必须共同进步。“真实实验对于验证人工智能预测至关重要，”他说。“如果我们想继续触及我们对生物学理解的表层，这在未来数年的生命科学中将至关重要，因为生物学是世上最复杂的事物。”
一个不断进化的合作者
他的实验室探索现存和已灭绝生物的基因组，以寻找候选分子。搜索这些基因组、理解其编码蛋白质如何形成和运作，并确定这些分子有什么作用，需要跨越多个领域的专业知识。
“我们是一个高度跨学科的团队，所以我们有来自生物学、化学、计算机科学和工程学的人，”德拉富恩特说。一些实验室成员是优秀的程序员，但对生物学或化学了解较少，反之亦然。Codex和ChatGPT帮助弥合这些差距，使生物学家能够构建程序，也使程序员能够处理生物学问题。从这个意义上说，人工智能降低了科学学科之间的壁垒。
它帮助实验室成员复习他们跨学科工作所需的不熟悉主题，澄清术语，比较不同领域的方法，并组织药物发现的想法。其他人则使用人工智能下载、整理和预处理大型基因组数据集。ChatGPT还使实验室成员能够用母语工作，从而降低障碍，加速他们的工作流程。
德拉富恩特将ChatGPT用作头脑风暴伙伴。他继续与同事一起发展想法，但他看重人工智能帮助他塑造假设的能力。他也喜欢自己只需点击按钮就能获取世界上的信息。
“我们的ChatGPT工作空间接收来自所有这些不同人的输入，他们对我们要解决的问题有着不同的思考方式，”德拉富恩特说。实验室成员把自己的好主意和坏主意都输入其中，使它成为一种协作式的意见反馈板。
但他告诫不要只依赖人工智能。“显然，你必须始终核对准确性，”德拉富恩特说。
尽管如此，他仍然赞赏人工智能帮助研究人员探索科学学科边界的能力。“突破正等待着在那里被发现。它们本质上位于很少有人涉足的领域边缘。”
他把这项工作视为更悠久科学传统的一部分。“我们一直依赖工具和机器来理解周围的世界，”德拉富恩特说。“望远镜照亮了宇宙，显微镜揭示了不可见的世界。”如今，机器帮助研究人员理解、预测和工程化生物学。“这就是我们工作的全部意义，”他说。
Drug-resistant microbes including bacteria, fungi, parasites, and viruses are a growing global threat. About five million deaths in 2021 were associated(opens in a new window) with bacterial antimicrobial resistance—an annual toll projected to roughly double by 2050. It can take years to find molecules with the potential to become antimicrobials. Researchers are using AI to accelerate this early stage of discovery.
“Antimicrobial resistance is one of the greatest existential threats to humanity in my opinion,” said César de la Fuente(opens in a new window), a bioengineer whose cross-disciplinary lab searches for antimicrobial candidates. “And yet, we haven’t had a new class of antibiotics for 50 years.”
Much of modern antimicrobial development focuses on modifying existing medicines or searching familiar classes of chemicals. But that approach offers diminishing returns.
De la Fuente’s lab starts somewhere far less explored: the code of life. The central idea behind the work is that biology is an information system. “The nucleotides that make up DNA, and the amino acids that make up proteins and peptides are sort of like an alphabet,” said de la Fuente. “Thinking about biology as information enabled us to develop methods that can begin to decipher the organizing principles of life that gave rise to a functional molecule.”
The lab’s deep-learning models are trained to recognize patterns in biological sequences, allowing them to search vast genome and protein datasets for potential antimicrobials. The approach can reduce the initial search for candidate molecules from years to hours.
Alongside its own AI models, the lab uses ChatGPT and Codex to brainstorm hypotheses, write and refine code, process datasets, analyze results, and connect ideas across scientific disciplines.
Exploring biology’s unread spaces
Only a fraction of a genome has a clearly understood function, and fewer still encode molecules that can fight infectious microbes. The challenge is to identify patterns that make a molecule functional, or biologically active, then determine which have the potential to combat infectious microbes.
Scientists have long searched for antimicrobials in plants, animals, microbes, insects, water, and soil. They collect samples, isolate or predict candidate molecules, and test them in an iterative process that can take years.
Digital genome and protein databases now let scientists search across the tree of life for new compounds, dramatically expanding the breadth of databases available for exploration. But that abundance of information comes with its own challenges: finding promising signals among an enormous number of possibilities.
AI is particularly well suited to this needle-in-a-haystack task. It can scan huge datasets, identify patterns that might be difficult for researchers to spot, and prioritize a manageable set of candidates for experimental testing.
But identifying a promising candidate doesn’t necessarily mean that it will become an effective medicine.
Scientists must first confirm that a candidate molecule kills the target microbe, determine the amount needed in order to be effective, and test how it affects human cells. Chemists may then optimize it to improve its effectiveness, safety, or stability.
Further tests assess the dose at which the candidate becomes toxic, how readily microbes develop resistance to the molecule, and how the candidate moves through the body. Teams also determine a reliable way to manufacture the molecule. Candidates that clear these hurdles still face regulatory review and clinical trials before they can reach patients as approved antimicrobial drugs.
For de la Fuente, this is why AI and laboratory biology must advance together. “Ground-truth experiments are essential to validate AI predictions,” he said. “This will be critical in the life sciences in the years to come if we are to continue scratching the surface of our understanding of biology, which is the most complex thing out there.”
A continually evolving collaborator
His lab explores the genomes of living and extinct organisms for candidate molecules. Searching those genomes, understanding how their encoded proteins form and function, and determining what those molecules do requires expertise spanning several fields.
“We’re a highly transdisciplinary group, so we have people from biology, from chemistry, from computer science, from engineering,” said de la Fuente. Some lab members are strong programmers but know less about biology or chemistry and vice versa. Codex and ChatGPT help bridge those gaps, allowing biologists to build programs and programmers to tackle biological problems. In that sense, AI lowers barriers between scientific disciplines.
It helps lab members review unfamiliar topics that they need for their cross-disciplinary work, clarify terminology, compare methods across fields, and organize ideas for drug discovery. Others use AI to download, organize, and pre-process large genome datasets. ChatGPT also lets lab members work in their native languages, lowering barriers to accelerate their workflows.
De la Fuente uses ChatGPT as a brainstorming partner. He continues to develop ideas with colleagues, but he values AI’s ability to help him shape a hypothesis. He also likes that he can access the world’s information with a click of a button.
“Our ChatGPT workspace is receiving input from all these different people that think differently about the problems that we’re trying to tackle,” said de la Fuente. Lab members feed it their good and bad ideas, making it a kind of collaborative sounding board.
But he cautions against relying on AI alone. “Obviously you have to always double-check for accuracy,” de la Fuente said.
Still, he appreciates AI’s ability to help researchers explore the boundaries between scientific disciplines. “That’s where the breakthroughs are waiting to be discovered. They’re essentially at the edges between fields where very few people go.”
He sees this work as part of a much longer scientific tradition. “We have always relied on tools and machines to understand the world around us,” said de la Fuente. “The telescope illuminated the cosmos, and the microscope revealed the world of the invisible.” Machines now help researchers understand, predict, and engineer biology. “That is what our work is all about,” he said.
本文内容采集自官方网站，排版和翻译可能与原页面存在差异。
阅读官方全文