Data and code underlying the publication: Machine Learning-Assisted Pathway Optimization in Large Combinatorial Design Spaces: a p-Coumaric Acid Case Study

This repository consists of the code necessary for reproduction of results in the paper Machine Learning-Assisted Pathway Optimization in Large Combinatorial Design Spaces: a p-Coumaric Acid Case Study. The data consists of :NMR screening data of ~3000 engineered S. cerevisiae strains (in code_mlassisted_pca.zip, data/raw/CycleTUD/), and follow-up DBTL cycle (data/raw/CycleTUDValidation)DNA sequencing data (.fasta format, in 4tu_mlassisted_pca_fasta) and coverage per contig files. Processed count matrices and numerical matrices that were downstream-processed from the DNA sequencing data files using .gff biobricks files.<br>Code is also available on the github repository https://github.com/AbeelLab/ml-assisted-p-coumaric-acid-optimization

本仓库包含复现论文《大规模组合设计空间中机器学习辅助通路优化：对香豆酸（p-Coumaric Acid）案例研究》所需的全部代码。本数据集包含以下内容：约3000株工程化酿酒酵母（S. cerevisiae）菌株的核磁共振（Nuclear Magnetic Resonance，简称NMR）筛选数据，存储于code_mlassisted_pca.zip、data/raw/CycleTUD/路径下；后续设计-构建-测试-学习（Design-Build-Test-Learn，简称DBTL）循环的相关数据（存储于data/raw/CycleTUDValidation路径）、.fasta格式的DNA测序数据（存储于4tu_mlassisted_pca_fasta路径）以及各重叠群覆盖度文件；基于上述DNA测序数据文件、使用通用特征格式（General Feature Format，简称GFF）生物砖（BioBricks）文件进行下游处理后得到的处理后计数矩阵与数值矩阵。相关代码亦可在GitHub仓库https://github.com/AbeelLab/ml-assisted-p-coumaric-acid-optimization获取。