npj: 基因型改变与硅藻壳变化—机器学习、大数据分析

来源：知社学术圈

活体生物可在环境温度、压力和pH条件下，用无机原料构建复杂的三维结构，但这种合成物的复杂性和精确性可与现代工业方法相媲美。硅藻的生物矿化，是单细胞藻类使用二氧化硅构建的细胞壁，这种细胞壁虽是微米级的，但其诸多特征性结构是纳米级的，是超过八个数量级的多标量结构（注：百度搜索“硅藻形态”会看到很多硅藻精美结构图片），超过了当前合成方法所能达到的复杂性。认识和利用生物矿物质形成过程，将有助于设计下一代材料，用于光学、传感、过滤和药物递送等领域的合成功能材料。因此，针对这些应用，通过定向遗传修饰实现可控的硅藻结构修改，可制备出复杂定制结构的硅藻壳结构的材料，前途广阔。但首先需要揭示修改的基因型和表达的表型之间的关系。

来自美国橡树林国家实验的Olga S. Ovchinnikova领导的研究团队，通过敲除怀疑可能与硅藻壳形成有关的基因来修改硅藻基因型，并通过扫描电镜表征该基因引起的表型变化。他们使用图像处理和机器学习分类算法（人工NN）来筛选影响硅藻表型的基因，并将野生型硅藻与基因修饰型区分开来。就控制毛孔形态的蛋白检测来说，他们的识别野生型和基因修饰型硅藻的NN，检测准确度为94％。为解释基于NN的分类表观准确率，他们用类激活图（CAM）来突出显示网络使用的图像区域，发现硅藻壳的孔是将野生型硅藻与一种特定的敲低基因表达的藻株分开的稳定特征。随后，他们创建了另一个神经网络，专门针对毛孔并提取其参数。这种自动化特征提取过程使人们能够将遗传修饰与硅藻形态对应关联起来。这一方法确定了由给定的遗传修饰产生的藻壳结构的变化，为生物矿化过程提供了生物学探测能力。

该文近期发表于npj Computational Materials 5: 4 (2019)，英文标题与摘要如下，点击左下角“阅读原文”可以自由获取论文PDF。

Deep data analytics for genetic engineering of diatoms linking genotype to phenotype via machine learning 

Artem A. Trofimov, Alison A. Pawlicki, Nikolay Borodinov, Shovon Mandal, Teresa J. Mathews, Mark Hildebrand, Maxim A. Ziatdinov, Katherine A. Hausladen, Paulina K. Urbanowicz, Chad A. Steed, Anton V. Ievlev, Alex Belianinov, Joshua K. Michener, Rama Vasudevan & Olga S. Ovchinnikova 

Genome engineering for materials synthesis is a promising avenue for manufacturing materials with unique properties under ambient conditions. Biomineralization in diatoms, unicellular algae that use silica to construct micron-scale cell walls with nanoscale features, is an attractive candidate for functional synthesis of materials for applications including photonics, sensing, filtration, and drug delivery. Therefore, controllably modifying diatom structure through targeted genetic modifications for these applications is a very promising field. In this work, we used gene knockdown in Thalassiosira pseudonana diatoms to create modified strains with changes to structural morphology and linked genotype to phenotype using supervised machine learning. An artificial neural network (NN) was developed to distinguish wild and modified diatoms based on the SEM images of frustules exhibiting phenotypic changes caused by a specific protein (Thaps3_21880), resulting in 94% detection accuracy. Class activation maps visualized physical changes that allowed the NNs to separate diatom strains, subsequently establishing a specific gene that controls pores. A further NN was created to batch process image data, automatically recognize pores, and extract pore-related parameters. Class interrelationship of the extracted paraments was visualized using a multivariate data visualization tool, called CrossVis, and allowed to directly link changes in morphological diatom phenotype of pore size and distribution with changes in the genotype.