lwaldron

library(curatedMetagenomicData)
library(dplyr)
library(table1)

dat <- sampleMetadata |>
  select(study_name, body_site, study_condition, age_category, age, BMI)

# labeling is optional, just to make the table nicer
label(dat$body_site) <- "Body Site"
label(dat$study_condition) <- "Study Condition"

lwaldron

library(nabor)

# suppose you have two vectors of propensity scores
propensity_scores1 <- c(0.1, 0.2, 0.3, 0.4, 0.5) #more controls
propensity_scores2 <- c(0.15, 0.25, 0.35) #fewer cases

# use the knn function from the nabor package to find the index of the closest match in propensity_scores2 for each score in propensity_scores1
matches <- nabor::knn(matrix(propensity_scores2), matrix(propensity_scores1), k = 1)$nn.idx

# print the matches

lwaldron

library(curatedMetagenomicData)
library(dplyr)
agecats <- unique(sampleMetadata$age_category) |> na.omit()
sm <- filter(sampleMetadata, study_condition=="control") |>
  filter(disease == "healthy") |>
  filter(body_site == "stool") |>
  filter(!is.na(age_category))

for (agecat in agecats){
  sm1 <- filter(sm, age_category == agecat)

lwaldron

suppressPackageStartupMessages({
  library(lefser)
  library(curatedMetagenomicData)
})
zeller <-
  curatedMetagenomicData("ZellerG_2014.pathway_abundance",
                         counts = TRUE,
                         dryrun = FALSE)[[1]]
zeller <- zeller[, zeller$study_condition != "adenoma"]
zeller <- relativeAb(zeller)

lwaldron

suppressPackageStartupMessages({
  library(curatedMetagenomicData)
  library(mia)
  library(dplyr)
  library(purrr)
})

datasets <- sampleMetadata |>
  group_by(study_name) |>
  count() |>

lwaldron

Before using this script you need to create an OpenAI API key (https://platform.openai.com/api-keys)
and put it in ~/.Renviron:

OPENAI_API_KEY='my_key_here'

# libraries used
library(openai)
library(dplyr)
library(stringr)

lwaldron

library(bugsigdbr)
bsdb <- importBugSigDB(version = "devel")

# Create a stacked barplot of the proportion of Pielou, Shannon, Chao1, Simpson, Inverse Simpson, and Richness as a function of year
library(tidyverse)
bsdb_by_year <- bsdb |>
  filter(Year > 2014) |>
  dplyr::group_by(Year) |>
  dplyr::summarize(
    Pielou = sum(!is.na(Pielou)) / n(),

lwaldron

---
title: "Stepwise treadmill test"
author: "Levi Waldron"
date: "`r Sys.Date()`"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

lwaldron

% \VignetteIndexEntry{Using Affymetrix Probe Level Data}
% \VignetteDepends{hgu95av2.db, rae230a.db, rae230aprobe, Biostrings}
% \VignetteKeywords{Annotation}
%\VignettePackage{annotate}

\documentclass{article}

\newcommand{\Rfunction}[1]{{\texttt{#1}}}
\newcommand{\Rmethod}[1]{{\texttt{#1}}}

lwaldron

suppressPackageStartupMessages(library(curatedMetagenomicData))
zeller <- curatedMetagenomicData::curatedMetagenomicData("Zeller.+relative_abundance", counts = FALSE, dryrun = FALSE)[[1]]
zellercounts <- curatedMetagenomicData::curatedMetagenomicData("Zeller.+relative_abundance", counts = TRUE, dryrun = FALSE)[[1]]

zeller <- zeller[, zeller$study_condition != "adenoma"]
zellercounts <- zellercounts[, zellercounts$study_condition != "adenoma"]

suppressPackageStartupMessages(library(lefser))
res_group <- lefser(zeller, groupCol = "study_condition")
res_group_counts <- lefser(zellercounts, groupCol = "study_condition")