gemelli - Gemelli是用于运行Robust Aitchison的工具箱

项目说明

Gemelli

Gemelli is a tool box for running Robust Aitchison PCA (RPCA), Joint Robust PCA (Joint-RPCA), TEMPoral TEnsor Decomposition (TEMPTED), and Compositional Tensor Factorization (CTF) on _sparse_ compositional omics datasets.

RPCA can be used on cross-sectional datasets where each subject is sampled only once. CTF can be used on repeated-measure data where each subject is sampled multiple times (e.g. longitudinal sampling). TEMPTED is specifically designed for longitundal (time series) repeated measure studies, especially when samples are irregularly sampled across subjects. Joint-RPCA allows for the exploration of multiple omics datasets with shared samples at once. All these methods are _unsuper and aim to describe sample/subject and the biological features that separate them.

The preprocessing transform for both RPCA and CTF is the robust centered log-ratio transform (rlcr) which accounts for sparse data (i.e. many missing/zero ). Details on the rclr can be found here and a interacti into the transformation can be found here. In short, the rclr log transforms the observed (nonzero) before centering. RPCA and CTF then perform a matrix or tensor factorization on only the obser after rclr transformation, similar to Aitchison PCA performed on dense data. If the data also has an associated phylogeny it can be incorporated through the phylogenetic rclr, details can be found here.

Installation

To install the most up to date of gemelli, run the following command

# pip (only supported for QIIME2 >= 2018.8)
pip install gemelli

Note: that gemelli is not compatible with python 2, and is compatible with Python 3.4 or later.

Documentation

Gemelli can be run standalone or through QIIME2 and as a python API or CLI.

Cross-sectional / multi-omics study (i.e. one sample per subject) with RPCA

If you have a cross-sectional study design with only one sample per subject then RPCA is the appropriate method to use in gemelli. For examples of using RPCA we provide tutorials below exploring the microbiome between body sites.

Joint-RPCA allows for the exploration of those feature that seperate jointly across sample groupings and the potential interactions of those features.

Tutorials

#### Tutorials with QIIME2

* RPCA QIIME2 CLI
* Phylogenetic RPCA QIIME2 CLI
* Joint-RPCA QIIME2 CLI
* Joint-RPCA QIIME2 API

#### Standalone tutorial outside of QIIME2

* RPCA Python API & CLI
* Joint-RPCA API & CLI

Repeated measures study (i.e. multiple sample per subject) with CTF & TEMPTED

Tutorials

If you have a repeated measures study design with multiple samples per subject over time or space then CTF is the appropriate method to use in gemelli. For optimal results CTF requires samples for each subject in each time or space measurement. If that is not the case and your study has irregular time sampling, then TEMPTED should be used. TEMPTED also allows for the projection of new data into an existing factorization which is necessary for machine learning. For examples, explore the tutorials below.

#### Tutorials with QIIME2

* CTF QIIME2 CLI
* CTF QIIME2 API
* Phylogenetic CTF QIIME2 CLI
* Phylogenetic CTF QIIME2 API
* TEMPTED QIIME2 CLI
* TEMPTED QIIME2 API

#### Standalone tutorial outside of QIIME2

* CTF Standalone Python API
* TEMPTED R implementation - Intallation and tutorials

Performing parameter optimization and QC on results

For an introduction to these QC methods see the tutorial here. Examples are also provided in the RPCA tutorials here (RPCA QIIME2 CLI) & here (RPCA Python API & CLI). Users are encrouaged to report the QC/C for thier data.

Citations

If you found this tool useful please cite the method(s) you used:

Citation for CTF

Citation for RPCA

Citation for Phylogenetic RPCA

Citation for TEMPTED

Citation for Joint-RPCA

Other Resources

项目信息

开发语言：Python

Star 数：92

技术要点

该项目属于CTF思路方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕Gemelli is a tool box for running Robust Aitchison PCA (RPCA), Joint Robust Aitchison PCA (Joint-RPCA), TEMPoral TEnsor Decomposition (TEMPTED), and Compositional Tensor Factorization (CTF) on sparse compositional omics datasets.展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。