This directory contains tests to verify Taxoniq's compatibility with the requirements identified in BugSigDB issue #248.
BugSigDB was considering migrating from direct NCBI API calls to Taxoniq for improved performance and reliability. The issue documents known divergences between Taxoniq and the NCBI API, particularly around:
superkingdom to domaink__Bacteria (2) vs NCBI's newer kingdom ranks
| bioc_repos <- BiocManager::repositories()[["BioCsoft"]] | |
| pkgs <- rownames(utils::available.packages(repos = bioc_repos)) | |
| #pkgs <- head(pkgs, 100) # for testing | |
| stats <- bioC.logs::bioC_downloads(pkgs, from = "08-2025", to = "09-2025") | |
| names(stats) <- pkgs | |
| stats.df <- Reduce(rbind, stats) | |
| rownames(stats.df) <- pkgs | |
| write.csv(stats.df, file = "bioc-pkg-downloads.csv") |
| -- 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' | |
| ); |
| # 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")) |
| --- | |
| title: "F. prausnitzii in PD" | |
| author: "Levi Waldron" | |
| date: "`r Sys.Date()`" | |
| output: html_document | |
| --- | |
| ```{r setup, include=FALSE} | |
| knitr::opts_chunk$set(echo = TRUE) | |
| ``` |
| --- | |
| title: "pMDstudies" | |
| author: "Levi Waldron" | |
| date: "`r Sys.Date()`" | |
| output: html_document | |
| --- | |
| ```{r, message=FALSE, warning=FALSE, echo=FALSE} | |
| library(parkinsonsMetagenomicData) | |
| library(dplyr) |
| suppressPackageStartupMessages(library(parkinsonsMetagenomicData)) | |
| #> Set default bucket name to 'metagenomics-mac' | |
| packageVersion("parkinsonsMetagenomicData") | |
| #> [1] '0.0.0.9000' | |
| colnames(sampleMetadata) |> sort() | |
| #> [1] "Adhesive removal (s)" | |
| #> [2] "age" | |
| #> [3] "Age" | |
| #> [4] "AGE" | |
| #> [5] "age_group" |
| library(curatedMetagenomicData) | |
| library(dplyr) | |
| library(table1) | |
| dat <- sampleMetadata |> | |
| select(study_name, body_site, study_condition, age_category, age, BMI) | |
| # labeling is optional, just to make the table nicer | |
| label(dat$body_site) <- "Body Site" | |
| label(dat$study_condition) <- "Study Condition" |
| library(nabor) | |
| # suppose you have two vectors of propensity scores | |
| propensity_scores1 <- c(0.1, 0.2, 0.3, 0.4, 0.5) #more controls | |
| propensity_scores2 <- c(0.15, 0.25, 0.35) #fewer cases | |
| # use the knn function from the nabor package to find the index of the closest match in propensity_scores2 for each score in propensity_scores1 | |
| matches <- nabor::knn(matrix(propensity_scores2), matrix(propensity_scores1), k = 1)$nn.idx | |
| # print the matches |
| 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) |