GenEpi / 0-Abstract
===
###### tags: `基因體/三級分析/GenEpi`
###### tags: `基因體`, `SNP`, `dbSNP`, `Variant`, `GenEpi`, `ML`, `生物資訊`

<br>

## [#034] [Abstract(摘要)](https://www.biorxiv.org/content/10.1101/421719v6)
> Genome-wide association studies (GWAS) provide a powerful means to identify associations between genetic variants and phenotypes.

全基因組關聯研究（GWAS）提供了一種有效的方法，來識別遺傳變異和表現型之間的關聯。

> However, GWAS techniques for detecting epistasis, the interactions between genetic variants associated with phenotypes, are still limited.

然而，用於檢測上位作用的 GWAS 技術，即與表現型相關的遺傳變異之間之相互作用，仍然是有限的。

> We believe that developing an efficient and effective GWAS method to detect epistasis will be a key for discovering sophisticated pathogenesis, which is especially important for complex diseases such as Alzheimer’s disease (AD).

我們相信，開發一種「有效率」且「有效果」的 GWAS 方法來檢測上位作用，將是發現複雜發病機制的關鍵。這對複雜疾病，如阿茲海默症（AD），尤其重要。

> In this regard, this study presents GenEpi, a computational package to uncover epistasis associated with phenotypes by the proposed machine learning approach.

在這方面，本研究提出了 GenEpi，這是一種藉由所提出的機器學習方法，來揭示與表現型相關的上位作用之計算套件。

> GenEpi identifies both within-gene and cross-gene epistasis through a two-stage modeling workflow.

GenEpi 經由兩階段的模型工作流程，來識別「基因內」和「跨基因」的上位作用。

> In both stages, GenEpi adopts two-element combinatorial encoding when producing features and constructs the prediction models by L1-regularized regression with stability selection.

在兩個階段中，GenEpi 在產生特徵時採用雙元素組合編碼，並藉由具有穩定性選擇的 L1 正規化回歸來建構預測模型。

> The simulated data showed that GenEpi outperforms other widely-used methods on detecting ground-truth epistasis.

模擬數據顯示，GenEpi 在檢測「有[標準答案 (真實案例) ](https://www.itread01.com/content/1546727252.html)的上位作用」優於其他廣泛使用的方法。

> As real data is concerned, this study uses AD as an example to reveal the capability of GenEpi in finding disease-related variants and variant interactions that show both biological meanings and predictive power.

就真實數據而言，本研究以 AD 為例，揭示 GenEpi 在尋找疾病相關變異和變異相互作用方面的能力，同時顯示生物學意義和預測能力。

> Availability: GenEpi is an open-source python package and available free of charge only for non-commercial users.

可用性：GenEpi 是一個開源 python 套件，僅供非商業用戶免費使用。

> The package can be downloaded from https://github.com/Chester75321/GenEpi, and has also been published on The Python Package Index.

該套件可以從 https://github.com/Chester75321/GenEpi 下載，也已發佈在 Python Package Index 上。