Ask HN：DNA能否在AI模型中被表示为“一个嵌入”？
3 分•作者: greenmoonx•大约 2 个月前
其中每个数组元素是一个数值，对应于 DNA 链螺旋横杆上 TCAG 化学物质的顺序？<p>是否有人以这种方式模拟了许多 DNA 链？<p>如果这样做，假设我们可以模拟任何已知的 DNA 并预测几代人的情况，我们可以利用人工智能解决哪些问题？<p>-----<p>我猜至少有几种选择：<p>1) 将整个 DNA 链建模为一个模型，其中每个基因（DNA 的一部分）是一个向量。这样，你就会有一个例如秀丽隐杆线虫的模型。你可以在人工智能沙盒中对该物种进行操作。<p>2) 模拟所有 DNA（就像我们模拟所有语言一样），最终得到一个“DNA 人工智能”，它可以生成任何类型的链（也许会生成不存在但可能存在的基因）。这样你就拥有了一个生物学沙盒，你可以在其中发明新的生物，或者预测人类的未来状态，用于测试药物和其他东西（我猜？）<p>你认为什么可行？
查看原文
Where each Array element is a numerical value that corresponds to the order of TCAG chemicals on the crossbar of the helix of a DNA strand?<p>Has anyone modeled many DNA strands in this way?<p>If it was done, what kinds of problems could we solve using AI - assuming we could model any known DNA, and predict out generations?<p>-----<p>I guess there are at least a couple options:<p>1) Model an entire DNA strand as 1 model, with each gene (section of DNA) being a vector. So you'd have, say, a <i>C. elegans</i> model. You could play with that species in an AI sandbox.<p>2) Model all of DNA (the way we model all of language) to end up with a "DNA AI" that can produce any kind of strand (perhaps inventing genes that don't exist, but could). So here you have a biology sandbox, where you can invent perhaps new creatures, or predict out future states of humans, to test drugs and other things (I guess?)<p>What do you think, what's possible?