LaberLabs Day 1 – 05/24/2021

Today, we were introduced to Dr. Laber, a professor at Duke and the head of Laber Labs, a research lab that researches different questions, mainly related to medicine, and uses methods like statistics and reinforcement learning to solve them.

Pictured below is an outreach project where Reinforcement Learning was used to “teach” a computer to play the Laser Cat game.

A Demonstration of Q Learning in the Laser Cat Game

For the rest of the day, we’ll be working on simulating something called the Monty Hall Problem. Basically, there are 3 doors. Two have something you don’t want and the third has something you do want. You choose one door and another one is eliminated, leaving you to choose to either open your current door or switch to the other remaining one. What we’re doing is building a dataset to see how often you win when you switch doors and if there is a correlation between switching doors and winning.

ILS Day 1

If you drove past Integrated Laboratory Solutions, you wouldn’t be able to tell that the unassuming facade in quiet Southern Pines was actually a state-of-the-art testing facility. So color me a shade of suprised when our guide for the day, Dr. Sean Zhong, whisked us through rooms brimming with humming and whirring machines that I still can’t probably pronounce the names of.

After, of course, donning personal protective equipment–lab coats and glasses–we embarked on our first adventure for the day: a high performance liquid chromatogarphy (HPLC) machine. Dr. Zhong explained that this fine invention is utilized to process urine samples from patients, separating the constituent parts and checking them with a list of common prescription medications. This process is twofold: one, it can make sure that complex compounds are being metabolized and excreted correctly; two, it can ensure that certain addictive medications like opiates aren’t being abused, leading to patient accountability. At the same time, we stared in awe at the fully automated process–the robot arm of the HPLC could even close the drawer filled with patient samples!

Our second quest involved scrutinizing the mass spectrometer (MS), which was a big box with tubes entering and exiting like the veins and arteries of the heart, along with a dashboard of blinking lights. It really seemed like something out of Star Wars. Dr. Zhong performed a demonstration some hemp samples on hand–ILS also works in conjunction with Integrated Hemp Solutions to create medical hemp products–and pointed out how the MS calculates the proportion of compounds within a given hemp oil sample.

After a quick lunch at a local bakery, courtesy of the Dr. Zhong and the other great folks at ILS, we headed back to our workstations as the mass spectrometer was finishing up. Fortunately, the sample we saw being tested was legal because the MS detected a less than 0.3%–the legal threshold–of THC, or the part of the cannabis plant that leads to the “high.” Dr. Zhong pulled up some linear regression curves to model the compound concentrations, which I understod thanks to what I learned this year in ADV Stats (shoutout to Mr. Lazarski)!

I had a great first day and I’m looking forward to what will unfold in the next 3 days! Dr. Zhong had to leave today for a conference in California, but I’m sure we’ll meet some more awesome scientists over the coming few days.

Skip to toolbar