Example for the current prioritization function in the IDBac "prioritizer" branch

example_prioritize.R

library(remotes)
remotes::install_github("chasemc/IDBacApp@prioritizer")
library(IDBacApp)
library(here)

# connect_to_idbac_database
pool <- IDBacApp::idbac_connect('VNBacterialLibrary_db-2_0_0', # name of sqlite database
                                here::here('data')) # directory containing sqlite database

# get_protein_peaks
peak_data <- IDBacApp::idbac_get_peaks(pool = pool,
                                       sampleIDs = NULL,
                                       minNumber = 2,
                                       lowerMassCutoff = 3000L,
                                       upperMassCutoff = 15000L,
                                       minSNR = 6,
                                       tolerance = 0.002,
                                       type = 'protein',
                                       mergeReplicates = TRUE)

# use_maldiqaunt_binning
peak_dist <- IDBacApp::mquant_bin(massStart = 3000,
                                  massEnd = 15000,
                                  massList = lapply(peak_data, function(x) x@mass),
                                  intensityList = lapply(peak_data, function(x) x@intensity),
                                  method = 'strict',
                                  tolerance = 0.002)

# create_dendrogram
peak_dend <- idbac_dendrogram_creator(bootstraps = 0L,
                                      distanceMethod = 'euclidean',
                                      clusteringMethod = 'ward.D',
                                      proteinMatrix = peak_dist)

# run_idbac_prioritizer
z <- IDBacApp::prioritizer(pool = pool,
                           dendrogram = peak_dend$dendrogram,
                           h = 340,
                           k = NULL,
                           fractionMetabolitePeaksToRetain = 0.75,
                           minFrequency = 0,
                           minNumber = 2, 
                           smallMolLowerMassCutoff = 200,
                           smallMolUpperMassCutoff = 2000,
                           smallMolSnr = 6,
                           tolerance = 2,
                           method = "strict")