Adapting Protein Language Models for Explainable Fine-Grained Evolutionary Pattern Discovery
Adapting Protein Language Models for Explainable Fine-Grained Evolutionary Pattern Discovery
复制标题
DOI：
10.1109/bibm58861.2023.10385976
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Ashley Babjac;Owen Queen;Shawn-Patrick Barhorst;Kambiz Kalhor;Andrew D. Steen;Scott J. Emrich
中科院分区：
文献类型：
--
作者：
Ashley Babjac;Owen Queen;Shawn-Patrick Barhorst;Kambiz Kalhor;Andrew D. Steen;Scott J. Emrich
生活在不同环境中的有机体面临着不同的进化压力。因此，表型更成功的生物体繁殖更频繁，但在生物体水平上作用的不同选择压力会影响基因，从而影响蛋白质。因此，了解蛋白质如何跨环境适应可能有助于为特定环境设计蛋白质，并有助于提高我们对基础生物学的理解。在这项工作中，我们明确地比较了来自不同环境的同源(读作：配对)蛋白质。虽然以前的研究已经探索了这些环境中的一个[11]、[17]中的相关进化压力以及基因组对这些压力的响应[1]、[28]，但先前还没有对它们的蛋白质进行计算研究。我们应用了ESM-2[20]，虽然在我们的阴性对照(两个不同的酵母菌株)中没有预期的信号，但我们对所选的环境梯度-良好的地下生物群与表面生物群-获得了近乎完美的预测精度。我们进一步表明，ESM-2能够在其嵌入空间中捕获相关的细粒度生物模式，即使在其最小的模型中也是如此。值得注意的是，我们证明了这些嵌入可以通过使用可解释的人工智能技术建立的新型可视化管道来解释。
Organisms that live in different environments face different evolutionary pressures. As such, organisms that have more successful phenotypes reproduce more frequently, but differing selective pressures acting at the organismal level can influence genes, and thus proteins. Understanding how proteins adapt across environments may therefore be useful in engineering proteins for specific environments as well as to improve our understanding of basic biology. In this work, we explicitly compare homologous (read: paired) proteins from different environments. While previous studies have explored the relevant evolutionary pressures in one of these environments [11], [17] and genomic responses to those pressures [1], [28], no prior computational study of their proteins has been performed. We apply ESM-2 [20] and although there is no signal in our negative control (two divergent yeast strains) as expected, we obtain near perfect prediction accuracy for our selected environmental gradient–the well-established subsurface vs. surface biome. We further show that ESM-2 is able to capture relevant fine-grained biological patterns in its embedding space, even in its smallest model. Significantly, we demonstrate that these embeddings can be interpreted using a novel visualization pipeline built using explainable AI techniques.