bio-metabolomics-targeted-analysis

name	bio-metabolomics-targeted-analysis
description	Targeted metabolomics analysis using MRM/SRM with standard curves. Covers absolute quantification, method validation, and quality assessment. Use when quantifying specific metabolites using calibration curves and internal standards.
tool_type	mixed
primary_tool	skyline

Targeted Metabolomics Analysis

Skyline Data Export Processing

library(tidyverse)

# Load Skyline export
skyline_data <- read.csv('skyline_export.csv')

# Expected columns: Replicate, Peptide/Molecule, Area, Concentration (for standards)
colnames(skyline_data)

# Filter to quantifier transitions
quant_data <- skyline_data %>%
    filter(Quantitative == TRUE | is.na(Quantitative))

# Pivot to matrix format
intensity_matrix <- quant_data %>%
    select(Replicate, Molecule, Area) %>%
    pivot_wider(names_from = Replicate, values_from = Area)

Standard Curve Fitting

# Standard curve data
standards <- data.frame(
    concentration = c(0, 1, 5, 10, 50, 100, 500, 1000),  # nM
    area = c(100, 5000, 25000, 50000, 240000, 480000, 2300000, 4500000)
)

# Linear regression (log-log for wide range)
fit_linear <- lm(area ~ concentration, data = standards)
fit_loglog <- lm(log10(area) ~ log10(concentration +  data  standards


fit_weighted  lmarea  concentration data  standards
                   weights    standardsconcentration  


summaryfit_linearr.squared
summaryfit_weightedr.squared


ggplotstandards aesx  concentration y  area 
    geom_pointsize   
    geom_smoothmethod   se   
    scale_x_log10 
    scale_y_log10 
    theme_bw 
    labstitle   x   y  

Calculate Concentrations

calculate_concentration <- function(area, fit, method = 'linear') {
    if (method == 'linear') {
        coef <- coef(fit)
        conc <- (area - coef[1]) / coef[2]
    } else if (method == 'loglog') {
        coef <- coef(fit)
        conc <- 10^((log10(area) - coef[1]) / coef[2]) - 1
    
    pmaxconc   



samples  data.frame
    sample  paste0 
    area           


samplesconcentration  calculate_concentrationsamplesarea fit_weighted


dilution_factor  10
samplesconcentration_original  samplesconcentration  dilution_factor

Internal Standard Normalization

# Data with internal standard
data_with_istd <- data.frame(
    sample = paste0('Sample', 1:10),
    analyte_area = c(12000, 45000, 8000, 120000, 35000, 78000, 22000, 95000, 41000, 63000),
    istd_area = c(50000, 52000, 48000, 51000, 49000, 53000, 47000, 50000, 51000, 49000)
)


data_with_istdresponse_ratio  data_with_istdanalyte_area  data_with_istdistd_area


istd_conc  100  
data_with_istdconcentration  calculate_concentration
    data_with_istdresponse_ratio  istd_conc
    fit_weighted

Method Validation Metrics

# Accuracy and precision from QC samples
qc_data <- data.frame(
    level = rep(c('Low', 'Medium', 'High'), each = 6),
    nominal = rep(c(10, 100, 500), each = 6),
    measured = c(
        c(9.5, 10.2, 11.1, 9.8, 10.5, 10.0),
        c(98, 102, 95   
             
    



validation_metrics  qc_data 
    group_bylevel nominal 
    summarise
        mean  meanmeasured
        sd  sdmeasured
        cv_percent  sdmeasured  meanmeasured  
        accuracy_percent  meanmeasured  nominal  
        bias_percent  meanmeasured  nominal  nominal  
        .groups  
    

printvalidation_metrics

Limit of Detection/Quantification

# LOD/LOQ from standard curve
# LOD = 3.3 * (SD of response / slope)
# LOQ = 10 * (SD of response / slope)

# Residual standard deviation
residuals_sd <- sd(residuals(fit_weighted))
slope <- coef(fit_weighted)[2]

LOD <- 3.3 * residuals_sd / slope
LOQ <- 10 * residuals_sd / slope

cat('LOD:', round(LOD, 2), 'nM\n')
cat('LOQ:', round(LOQ, 2), 'nM\n')

# Signal-to-noise based LOD (from blank samples)
blank_areas <- c(100, 120, 95, 110, 105
LOD_SN  meanblank_areas    sdblank_areas

Multi-Compound Analysis

# Multiple analytes with individual standard curves
analytes <- c('Glucose', 'Lactate', 'Pyruvate', 'Citrate', 'Succinate')

# Store calibration curves
calibrations <- list()
for (analyte in analytes) {
    std_data <- standards_all[standards_all$analyte == analyte, ]
    calibrations[[analyte]] <- lm(area ~ concentration, data = std_data,
                                   weights = 1 / (std_data$concentration + 1)^2)
}

# Quantify all samples
quantify_sample <- function(sample_data calibrations 
    results  data.frameanalyte  calibrations
    resultsconcentration  sapplycalibrations a 
        area  sample_dataareasample_dataanalyte  a
        calculate_concentrationarea calibrationsa
    
    results

Python Workflow

import pandas as pd
import numpy as np
from scipy import stats
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt

# Load data
data = pd.read_csv('targeted_data.csv')

# Standard curve fitting
def fit_standard_curve(concentrations, areas, weighted=True):
    X = np.array(concentrations).reshape(-1, 1)
    y = np.array(areas)

    if weighted:
        weights = 1 / (np.array(concentrations) + 1)**2
        model = LinearRegression()
        model.fit(X, y, sample_weight=weights)
    else:
        model = LinearRegression()
        model.fit(X, y)

    r2 = model.score(X, y)
    return model, r2

model, r2 = fit_standard_curve(standards['concentration'], standards['area'])
print(f'R² = {r2:.4f}')

# Calculate concentrations
def calculate_conc(areas, model):
    return (np.array(areas) - model.intercept_) / model.coef_[0]

samples['concentration'] = calculate_conc(samples['area'], model)

# Validation metrics
def calc_cv(values):
    return np.std(values) / np.mean(values) * 100

 ():
     np.mean(measured) / nominal * 


fig, axes = plt.subplots(, , figsize=(, ))


axes[].scatter(standards[], standards[])
x_line = np.linspace(, (standards[]), )
axes[].plot(x_line, model.predict(x_line.reshape(-, )), )
axes[].set_xlabel()
axes[].set_ylabel()
axes[].set_title()


axes[].bar(samples[], samples[])
axes[].set_xlabel()
axes[].set_ylabel()
axes[].set_title()

plt.tight_layout()
plt.savefig(, dpi=)

Quality Control

# QC sample tracking
qc_chart <- function(qc_values, target, warning_sd = 2, action_sd = 3) {
    mean_val <- mean(qc_values)
    sd_val <- sd(qc_values)

    ggplot(data.frame(run = 1:length(qc_values), value = qc_values)) +
        geom_point(aes(x = run, y = value), size = 3) +
        geom_line(aes(x = run, y = value)) +
        geom_hline(yintercept = target, color = 'green' linetype   
        geom_hlineyintercept  target  warning_sd  sd_val color   linetype   
        geom_hlineyintercept  target  warning_sd  sd_val color   linetype   
        geom_hlineyintercept  target  action_sd  sd_val color   linetype   
        geom_hlineyintercept  target  action_sd  sd_val color   linetype   
        theme_bw 
        labstitle   x   y  

Export Results

# Final results table
results_final <- data.frame(
    sample = samples$sample,
    concentration_nM = round(samples$concentration, 2),
    concentration_uM = round(samples$concentration / 1000, 4),
    cv_percent = round(samples$cv, 1),
    qc_flag = ifelse(samples$cv > 20, 'FAIL', 'PASS')
)

write.csv(results_final, 'targeted_results.csv', row.names = FALSE)

Related Skills

• xcms-preprocessing - Peak detection for targeted features
• normalization-qc - QC-based normalization
• statistical-analysis - Group comparisons