Caffeine Project
Project Overview
For this project I worked with Brad and a fellow student, Will Fox, to determine the caffeine levels in different samples of coffee. Our original goal was to determine whether a lighter or darker roast of coffee would have a higher concentration of caffeine. We then branched out to a few other questions involving the caffeine levels in the green coffee beans, the caffeine levels in decaf coffee, and how much caffeine the coffee maker we have extracted through each run of the coffee grounds. This page includes procedures for making the standards and samples, as well as procedure for running the HPLC.
Making the Samples
Caffeine Standards
For this project we had to make caffeine standards to compare the samples to. The following link describes how we made these standards.
L0 and L5 Samples - Trial 1
To make the coffee for the samples, 2.6 oz of beans were weighed out. These beans were then grinded, and 38 g of the beans were placed into a pourover filter. Then, 640 g of boiling hot water were poured over the grounds, using the chemex, allowing the grounds to bloom as needed. This process was done with both L0 and L5 beans.
L0 and L5 Samples (and Green Beans) - Trial 2
After this first round of coffee, we discovered that the coffee samples were too concentrated for our standards, so we cut the amount of beans to 30 g of L0 and L5. This round we also made a sample of 15 g of the green coffee beans with 320 g of boiling water. We used a 0.45 micron filter and syringe to put this solution into the HPLC vials to ensure there was no particulate matter present.
Final Results for Preparation of L0 and L5 Samples (and Green Beans)
After looking at the data from the second round of coffee, we discovered that the concentrations of caffeine in our samples were still too high for our standards. We tested L0 and L5 again, diluting 50% (400 microliters of the sample and 400 microliters of RO water). We also tested L0 samples through the traditional coffee maker, running the grounds through three separate times to analyze how the concentrations of caffeine were affected by extraction. This test was also done with green coffee beans as well.
Trigonelline and Nicotinic Acid
Once the data for this trial was analyzed, we decided to run L0 samples three times through the coffee maker again to validate our previous results. In this trial, we also tested standards for 300 ppm trigonelline and 10 ppm nicotinic acid, which are both also found in coffee. The trigonelline standard was made by mixing 0.03 g of trigonelline and 100 mL of water. The nicotinic acid sample was made by mixing 0.001 g of nicotinic acid and 100 mL of water.
Decaf Samples
After all of these trials, we decided to test the amount of caffeine in decaf coffee. 2.6 oz of decaf coffee beans were weighed out and grinded. We then ran these grounds through the coffee maker three times. These samples were not diluted because we already expected the concentrations of caffeine to be fairly low.
Instrumentation
After making the standards, we tested the standards using the HPLC to see where the peaks were for the different concentrations of caffeine. The following link goes into more depth about working with the HPLC.
Once the standards were tested, another HPLC trial was done including the L0 and L5 coffee samples.
An additional HPLC trial was done with coffee that had been diluted. This set included L0, L5, and the green coffee bean samples.
The HPLC trials with decaf coffee were not diluted due to the small amounts of caffeine in the samples.
What the HPLC Tells Us
We ran these samples through the HPLC at the wavelength of 273 nm, which is the lambda max for caffeine. Running the samples at this wavelength tells us how much the samples absorb at this wavelength.
Data Analysis
To analyze the HPLC data, the data was exported as an arw file. This file was then loaded into Igor, and further analyzed from there. This allowed us to make chromatograms to gain a better understanding of the how each concentration of caffeine absorbs at 273 nm. We used the information from the chromatograms to make standard curves in excel. The slopes of the standard curves gave us an equation we could use to find the concentration of a sample using the absorbance.
Equation
The following equation was used to find the concentration of caffeine in our samples. The equation is solved for x, which is concentration, then the absorbance is plugged in for y and solved.
y = 0.0041x + 0.0071
R² = 1
Data Summary
From the data we collected, we found that the L5 roast had slightly more caffeine than the L0 roast. The green beans had more caffeine than the L0, but not the L5. We also found that if L0 is run through our coffee maker three times, the second run through will have the most caffeine. However, this was not true for the decaf and green bean runs through the coffee maker. These followed the more expected result of the first run having the most caffeine, followed by the second run and the third run having the least amount of caffeine. That being said, small amounts of caffeine were found in the decaf coffee.
Caffeine in a Standard Cup of Coffee
Starbucks Nutritional Value PDF
References
Journal of Chemical Education Article about the Chemistry of Coffee