AI Predicts Patient Phenotypes that Will Develop Drug Resistance

139
Freenome’s artificial intelligence (AI) genomics platform

Investigators at Duke University have shown in a new study that different strains of the same bacterial pathogen can be distinguished by a machine learning analysis of their growth dynamics alone, which can then also accurately predict other traits such as resistance to antibiotics.

Findings from the new study—published recently in PNAS through an article titled “Temporal encoding of bacterial identity and traits in growth dynamics”—could point to methods for identifying diseases and predicting their behaviors that are faster, simpler, less expensive, and more accurate than current standard techniques.

“Microbiology has traditionally been defined by the study of the phenotypic traits of microorganisms,” the authors wrote. “While some traits can be easily explained with a direct genetic basis, most are a result of complex interactions between the organism and its environment.”

Bacterial identification has relied on growing cultures and analyzing the physical traits and behaviors of the resulting bacterial colony. It wasn’t until recently that scientists could simply run a genetic test. Yet, genetic sequencing isn’t universally available and can often take a long time. Even with the ability to sequence entire genomes, it can be difficult to tie specific genetic variations to different behaviors in the real world.

For example, even though researchers know the genetic mutations that help shield/protect bacteria from beta-lactam antibiotics—the most commonly used antibiotic in the world—sometimes the DNA isn’t the whole story. While a single resistant bacterium usually can’t survive a dose of antibiotics on its own, large populations often can.

The Duke researchers wondered if a new twist on older methods might work better. Maybe they could amplify one specific physical characteristic and use it to not only identify the pathogen but to make an educated guess about other traits such as antibiotic resistance.

We thought that the slight variance in the genes between strains of bacteria might have a subtle effect on their metabolism,” explained senior study investigator Lingchong You, PhD, a professor of biomedical engineering at Duke. “But because bacterial growth is exponential, that subtle effect could be amplified enough for us to take advantage of it. To me, that notion is somewhat intuitive, but I was surprised at how well it actually worked.”

How quickly a bacterial culture grows in a laboratory depends on the richness of the media it is growing in and its chemical environment. But as the population grows, the culture consumes nutrients and produces chemical byproducts. Even if different strains start with the same environmental conditions, subtle differences in how they grow and influence their surroundings accumulate over time.

In the study, the research team took more than 200 strains of bacterial pathogens, most of which were variations of E. coli, put them into identical growth environments, and carefully measured their population density as it increased. Because of their slight genetic differences, the cultures grew in fits and starts, each possessing a unique temporal fluctuation pattern. The researchers then fed the growth dynamics data into a machine learning program, which taught itself to identify and match the growth profiles to the different strains.

We demonstrated, in clinical and environmental bacterial isolates, that growth dynamics in standardized conditions can differentiate between genotypes, even among strains from the same species,” the authors penned. “We found that for pairs of isolates, there is little correlation between genetic distance, according to phylogenetic analysis, and phenotypic distance, as determined by growth dynamics. This absence of correlation underscores the challenge in using genomics to infer phenotypes and vice versa. Bypassing this complexity, we show that growth dynamics alone can robustly predict antibiotic responses.”

You added that “using growth data from only one initial condition, the model was able to identify a particular strain with more than 92% accuracy. And when we used four different starting environments instead of one, that accuracy rose to about 98%.”

Taking this idea one step further, the researchers then looked to see if they could use growth dynamic profiles to predict another phenotype—antibiotic resistance.

Once again, they loaded a machine learning program with the growth dynamic profiles from all but one of the various strains, along with data about their resilience to four different antibiotics. They then tested to see if the resulting model could predict the final strain’s antibiotic resistance from its growth profile. To bulk up their dataset, they repeated this process for all of the other strains.

The results showed that the growth dynamic profile alone could successfully predict a strain’s resistance to antibiotics 60–75% of the time.

“This is actually on par or better than some of the current techniques in the literature, including many that use genetic sequencing data,” said You. “And this was just a proof of principle. We believe that with higher-resolution data of the growth dynamics, we could do an even better job in the long term.”

The researchers also looked to see if the strains exhibiting similar growth curves also had identical genetic profiles. As it turns out, the two are entirely uncorrelated, demonstrating once again how difficult it can be to map cellular traits and behaviors to specific stretches of DNA.

Moving forward, You plans to optimize the growth curve procedure to reduce the time it takes to identify a strain from two to three days to perhaps 12 hours. He’s also planning on using high-definition cameras to see if mapping how bacterial colonies grow in space in a Petri dish can help make the process even more accurate.

This site uses Akismet to reduce spam. Learn how your comment data is processed.