GenoML is a Python package automating machine learning workflows for genomics (genetics and multi-omics) with an open science philosophy. Genomics data require significant domain expertise to clean, pre-process, harmonize and perform quality control of the data. Furthermore, tuning, validation, and interpretation involve taking into account the biology and possibly the limitations of the underlying data collection, protocols, and technology. GenoML's mission is to bring machine learning for genomics and clinical data to non-experts by developing an easy-to-use tool that automates the full development, evaluation, and deployment process. Emphasis is put on open science to make workflows easily accessible, replicable, and transferable within the scientific community. Source code and documentation is available at https://genoml.com.
翻译:GenoML是一个Python软件包,使基因组(遗传学和多组学)的机器学习工作流程自动化,具有开放的科学理念;基因组数据需要大量的领域专门知识来清理、预处理、统一和进行数据质量控制;此外,调试、验证和解释需要考虑到生物因素,并可能考虑到基本数据收集、协议和技术的局限性;GenoML的使命是通过开发一种方便使用的工具,将基因组学和临床数据的机器学习带给非专家,使全面开发、评价和部署过程自动化;强调开放科学,使工作流程在科学界内容易获得、复制和可转让;资料来源代码和文件见https://genoml.com。