Merge pull request #87 from xueweic/main

Add animation

Author: xueweic

_pkgdown.yml

@@ -36,6 +36,7 @@ articles:
     desc: "Advanced topics and special cases in colocalization and fine-mapping analysis."
     contents:
     - Partial_Overlap_Variants
+    - ColocBoost_Update
     - ColocBoost_Wrapper_Pipeline
     - LD_Free_Colocalization
     - Ambiguous_Colocalization

man/figures/ColocBoost_update.gif

@@ -0,0 +1,33 @@
+---
+title: "Animation Example: Proximity Gradient Boosting Algorithm"
+output: rmarkdown::html_vignette
+vignette: >
+  %\VignetteIndexEntry{Animation Example: Proximity Gradient Boosting Algorithm}
+  %\VignetteEngine{knitr::rmarkdown}
+  %\VignetteEncoding{UTF-8}
+---
+
+```{r, include = FALSE}
+knitr::opts_chunk$set(
+  collapse = TRUE,
+  comment = "#>"
+)
+```
+
+
+
+This vignette visualizes the iterative process of proximity gradient boosting proposed in ColocBoost from an extensive simulation example.
+
+
+- **Red point**: the standard gradient boosting update for only the best single-effect variant $j_k^*$ in each iteration.
+- **Blue points**: the proximity gradient boosting update, where it probabilistically incorporates the LD proxies of $j_k^*$ by applying a convex relaxation to the gradient.
+
+The animation below demonstrates how ColocBoost iteratively updates across multiple rounds. 
+Observe how the blue points (proxies) distribute around the selected best update, showing the algorithm's ability to capture LD structure during optimization.
+
+```{r, out.width="80%"}
+knitr::include_graphics("../man/figures/ColocBoost_update.gif")
+```
+
+
+See more details in the [ColocBoost Manuscript](https://www.medrxiv.org/content/10.1101/2025.04.17.25326042v1) and the [GitHub repository](https://github.com/StatFunGen/colocboost).