lwaldron

-- Install and load the httpfs extension to read from GCS
install httpfs;
load httpfs;

-- Create a secret for accessing Google Cloud Storage using a JSON key file
CREATE SECRET metagenomics_mac (
    TYPE GCS,
    KEY_FILE '/path/to/your/gcp-credentials.json'
);

lwaldron

# Title: Benchmark Query Performance on Sorted vs. Unsorted Parquet Files
# Description: This script first creates a new Parquet file sorted by the
#              '# Gene Family' column. It then uses the 'microbenchmark'
#              package to compare the query speed for a specific gene
#              family between the original, unsorted file and the new,
#              sorted file.

# --- 1. SETUP: Load necessary libraries ---
# Ensure you have these packages installed:
# install.packages(c("duckdb", "dplyr", "arrow", "microbenchmark"))

lwaldron

---
title: "F. prausnitzii in PD"
author: "Levi Waldron"
date: "`r Sys.Date()`"
output: html_document
---

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

lwaldron

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

```{r, message=FALSE, warning=FALSE, echo=FALSE}
library(parkinsonsMetagenomicData)
library(dplyr)

lwaldron

suppressPackageStartupMessages(library(parkinsonsMetagenomicData))
#> Set default bucket name to 'metagenomics-mac'
packageVersion("parkinsonsMetagenomicData")
#> [1] '0.0.0.9000'
colnames(sampleMetadata) |> sort()
#>   [1] "Adhesive removal (s)"                                           
#>   [2] "age"                                                            
#>   [3] "Age"                                                            
#>   [4] "AGE"                                                            
#>   [5] "age_group"                                                      

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() |>