MAR 16, 2021 2:38 AM PDT

Machine Learning Speeds Up Drug Discovery

WRITTEN BY: Nouran Amin

How do drugs work? Well, they work when they stick to their target protein. Of course, there is much more complicated process than simply put—but it notes the importance of ‘stickness’ in the therapeutic process.

With this in mind, research his now addressing the key hurdle associated with the drug ‘stickiness’ by combining chemistry and machine learning through a new technique called ‘DeepBAR’.

"Our method is orders of magnitude faster than before, meaning we can have drug discovery that is both efficient and reliable," says Bin Zhang, the Pfizer-Laubach Career Development Professor in Chemistry at MIT, an associate member of the Broad Institute of MIT and Harvard, and a co-author of a new paper describing the technique.

DeepBAR calculates the binding affinities between a drug candidate and their targets.

A lower binding free energy means the drug can better compete against other molecules," says Zhang, "meaning it can more effectively disrupt the protein's normal function."

Findings were published in the Journal of Physical Chemistry Letters.

The "BAR" in DeepBAR stands for "Bennett acceptance ratio," which is used in decades-old calculations of binding free energy.

"These models create a reference state for each endpoint, the bound state and the unbound state," says Zhang. These two reference states are similar enough that the Bennett acceptance ratio can be used directly, without all the costly intermediate steps.

"It's basically the same model that people use to do computer image synthensis," says Zhang. "We're sort of treating each molecular structure as an image, which the model can learn. So, this project is building on the effort of the machine learning community."

"These models were originally developed for 2D images," says Ding. "But here we have proteins and molecules -- it's really a 3D structure. So, adapting those methods in our case was the biggest technical challenge we had to overcome."

Learn more about how drugs are taken up in the body:

DeepBAR is "a really nice computational work" with a few hurdles to clear before it can be used in real-world drug discovery, says Michael Gilson, a professor of pharmaceutical sciences at the University of California at San Diego, who was not involved in the research.

"This research is an example of combining traditional computational chemistry methods, developed over decades, with the latest developments in machine learning," says Ding. "So, we achieved something that would have been impossible before now."

Source: Science Daily

About the Author
  • Nouran is a scientist, educator, and life-long learner with a passion for making science more communicable. When not busy in the lab isolating blood macrophages, she enjoys writing on various STEM topics.
You May Also Like
NOV 09, 2021
Microbiology
Can This Cat Parasite Become a Tumor Treatment?
NOV 09, 2021
Can This Cat Parasite Become a Tumor Treatment?
You may have heard of Toxoplasma gondii because it is so common. Cats carry this parasite, and anyone that cleans a litt ...
NOV 22, 2021
Microbiology
Researchers Solve the Structure of the HIV Capsid, May Be a New Drug Target
NOV 22, 2021
Researchers Solve the Structure of the HIV Capsid, May Be a New Drug Target
Though treatments are available, there is no cure or vaccine from HIV, which impacts about 38 million people worldwide. ...
NOV 30, 2021
Cannabis Sciences
To Trust or Not to Trust the Process: Bioreactive Chemical Variation in Cannabis Extracts Based on Extraction Method
NOV 30, 2021
To Trust or Not to Trust the Process: Bioreactive Chemical Variation in Cannabis Extracts Based on Extraction Method
With cannabis legislation becoming increasingly less restrictive over the past 20 years, consumers have found themselves ...
JAN 01, 2022
Cannabis Sciences
Pharmacological Effects of Cannabis: To Be or Not To Be... Carboxylated?
JAN 01, 2022
Pharmacological Effects of Cannabis: To Be or Not To Be... Carboxylated?
Results from a new study published in Nature’s Scientific Reports suggest that the carboxylated (i.e., acidic) for ...
JAN 06, 2022
Health & Medicine
New Hope for Hair Regrowth in Alopecia Areata
JAN 06, 2022
New Hope for Hair Regrowth in Alopecia Areata
Two recently completed phase 3 clinical trials showed the drug baricitinib leads to hair growth for alopecia areata pati ...
JAN 20, 2022
Immunology
Researchers Stumble Upon Cancer Drug While Studying Flesh-Eating Bacteria
JAN 20, 2022
Researchers Stumble Upon Cancer Drug While Studying Flesh-Eating Bacteria
  Scientists studying a neglected tropical disease have made a chance discovery—a promising therapeutic targe ...
Loading Comments...