Towards full sequence design of functional chromosomes by AI

目前合成基因组学的进展意味着我们设计和构建DNA的规模正在迅速增加。与此同时，支持AI的工具正在加速我们设计基因编码部件以实现所需规格的能力。因此，我们应该期待“未来的生物设计师”使用人工智能来帮助编写定制的DNA序列，这些DNA序列可以组装成驱动细胞执行所需任务的完整染色体和基因组。在这个项目中，我们计划看看我们已经离人工智能主导的人工合成酵母染色体的全序列设计有多近。在设计、构建和测试酵母染色体的人工智能写入区域时，我们将了解目前缺少哪些基因组知识和人工智能设计能力，这些知识和能力将在未来十年内实现定制的染色体设计。我们计划开发解决方案来解决这些目前的差距，这样到项目结束时，我们就可以使用人工智能来生成合成染色体臂的全序列，只为人工智能提供一个要包含的基因列表，这些基因的肽序列，他们的目标表达水平和他们所需要的任何调节。该项目将利用我们两个研究小组在酵母中构建和测试合成染色体区域的现有工作（Ellis），以及为工程生物学设计人工智能驱动的工具（Stan）。重要的是，它将建立在现有成功的关键已发表的人工智能工具的基础上，这些工具使用GAN和CNN来编写合成酵母启动子[1]，5'UTR [2]和3'UTR [3]以规范。这3个遗传部分共同占酵母染色体中非编码DNA的>85%。

Current progress in synthetic genomics means that the scale at which we design and build DNA israpidly increasing. In parallel, AI-enabled tools are accelerating our capabilities to designgenetically-encoded parts to achieve desired specifications. It is logical, therefore, that we shouldexpect the 'biodesigner of the future' to be using AI to help write custom DNA sequences that canbe assembled to build whole chromosomes and genomes that drive cells to perform desired tasks.In this project, we plan to see how close we already are to AI-led full sequence design of asynthetic yeast chromosome. In designing, building and testing AI-written regions of yeastchromosomes, we will learn what genomic knowledge and AI design capabilities are currentlymissing that would enable bespoke chromosome design in the next decade. We plan to developsolutions to these current gaps, so that by the end of the project we can use AI to generate the fullsequence of a synthetic chromosome arm, providing the AI with only a list of genes to be included,the peptide sequences of these, their target expression levels and any regulation they require.The project will leverage existing work in our two research groups on building and testingsynthetic chromosome regions in yeast (Ellis), and in designing AI-driven tools for engineeringbiology (Stan). Importantly, it will build on the existing success of key published AI tools that useGANs and CNNs to write synthetic yeast promoters [1], 5'UTRs [2] and 3'UTRs [3] to specification.These 3 genetic parts together account for >85% of non-coding DNA in a yeast chromosome