New Antibiotics Are Desperately Needed: Machine Learning could Help

As the threat of antibiotic resistance looms, microbiologists aren’t the only ones thinking up new solutions. James Zou, PhD, assistant professor of biomedical data science at Stanford, has applied machine learning to create an algorithm that generates thousands of entirely new virtual DNA sequences with the intent of one day creating antimicrobial proteins.

The algorithm, called Feedback GAN, essentially acts as a mass producer of different DNA snippets. And while these sequence attempts are somewhat random, the algorithm isn't working blindly. It’s basing the new possible peptides, or small groups of amino acids, on previous research that lays out the DNA sequences most likely to align with antimicrobial properties.

For now, these templates, which don't exist in nature, are theoretical, generated on a computer. But in the face of rising concerns about microbe resistance, Zou said it's critical to think about solutions that don't already exist.

"We chose to pursue antimicrobial proteins because it's a very important, high-impact problem that's also a relatively tractable problem for the algorithm," Zou said. "There are existing tools that we incorporate into our system that evaluate if a new sequence is likely to have the properties of a successful antimicrobial protein."

Feedback GAN builds on that, working to incorporate just the right balance of random chance and precision.

A paper describing the algorithm was published online Feb. 11 in Nature Machine Learning. Anvita Gupta, a student in computer science, is the first author; Zou is the senior author.

Self-refining

Gupta and Zou's algorithm doesn't just churn out new combinations of DNA. It also actively refines itself, learning what works and what doesn’t through a feedback loop: After the algorithm spits out a wide range of DNA sequences, it runs a trial-and-error learning process that sifts through the peptide suggestions. Based on their resemblance to other known antimicrobial peptides, the “good” ones get fed back into the algorithm to inform future DNA sequences generated from the code, and to get refined themselves.

"There's a built-in arbiter and, by having this feedback loop, the system learns to model newly generated sequences after those that are deemed likely to have antimicrobial properties," Zou said. "So the idea is both individual peptide sequences and the generation of the sequences get better and better."

Zou has also considered another core component of hypothetical proteins: protein folding. Proteins contort into very specific structures linked to their functions. An algorithm could create the perfect sequence, but unless it can fold up, it's useless - like the cogs of a clock strewn on a table.

Zou can tweak the algorithm so that instead of analyzing a propensity for antimicrobial properties, it determines the likelihood of correct folding.

"We can actually do these two things in parallel where we look at antimicrobial properties of one sequence and folding likelihood of another," said Zou. "We run both so that we’re optimizing either the antimicrobial properties or its ability to fold."

Next, Zou hopes to merge the two variations of the algorithm to create peptide sequences that are optimized for both their microbe-killing abilities and their ability to fold into a genuine protein.

Demo, instructions and code for FBGAN are available at https://github.com/av1659/fbgan.

Anvita Gupta, James Zou.
Feedback GAN for DNA optimizes protein functions.
Nature Machine Intelligence, 1, 105-111 (2019). doi: 10.1038/s42256-019-0017-4.

Most Popular Now

Researchers Find Telemedicine may Help R…

Low-value care - medical tests and procedures that provide little to no benefit to patients - contributes to excess medical spending and both direct and cascading harms to patients. A...

AI Revolutionizes Glaucoma Care

Imagine walking into a supermarket, train station, or shopping mall and having your eyes screened for glaucoma within seconds - no appointment needed. With the AI-based Glaucoma Screening (AI-GS) network...

AI may Help Clinicians Personalize Treat…

Individuals with generalized anxiety disorder (GAD), a condition characterized by daily excessive worry lasting at least six months, have a high relapse rate even after receiving treatment. Artificial intelligence (AI)...

Accelerating NHS Digital Maturity: Paper…

Digitised clinical noting at South Tees Hospitals NHS Foundation Trust is creating efficiencies for busy doctors and nurses. The trust’s CCIO Dr Andrew Adair, deputy CCIO Dr John Greenaway, and...

Mobile App Tracking Blood Pressure Helps…

The AHOMKA platform, an innovative mobile app for patient-to-provider communication that developed through a collaboration between the School of Engineering and leading medical institutions in Ghana, has yielded positive results...

AI can Open Up Beds in the ICU

At the height of the COVID-19 pandemic, hospitals frequently ran short of beds in intensive care units. But even earlier, ICUs faced challenges in keeping beds available. With an aging...

Can AI Help Detect Cognitive Impairment?

Mild cognitive impairment (MCI) can be an early indicator of Alzheimer's disease or dementia, so identifying those with cognitive issues early could lead to interventions and better outcomes. But diagnosing...

Customized Smartphone App Shows Promise …

A growing body of research indicates that older adults in assisted living facilities can delay or even prevent cognitive decline through interventions that combine multiple activities, such as improving diet...

New Study Shows Promise for Gamified mHe…

A new study published in Multiple Sclerosis and Related Disorders highlights the potential of More Stamina, a gamified mobile health (mHealth) app designed to help people with Multiple Sclerosis (MS)...

AI Model Predicting Two-Year Risk of Com…

AFib (short for atrial fibrillation), a common heart rhythm disorder in adults, can have disastrous consequences including life-threatening blood clots and stroke if left undetected or untreated. A new study...

Patients' Affinity for AI Messages …

In a Duke Health-led survey, patients who were shown messages written either by artificial intelligence (AI) or human clinicians indicated a preference for responses drafted by AI over a human...

New Research Explores How AI can Build T…

In today’s economy, many workers have transitioned from manual labor toward knowledge work, a move driven primarily by technological advances, and workers in this domain face challenges around managing non-routine...