Machine learning reveals metabolic pathways disrupted by the drugs, offering new targets to combat resistence

Most antibiotics work by interfering with critical functions such as DNA replication or construction of the bacterial cell wall. However, these mechanisms represent only part of the full picture of how antibiotics act.

In a new study of antibiotic action, MIT researchers developed a new machine-learning approach to discover an additional mechanism that helps some antibiotics kill bacteria. This secondary mechanism involves activating the bacterial metabolism of nucleotides that the cells need to replicate their DNA. Exploiting this mechanism could help researchers to discover new drugs that could be used along with antibiotics to enhance their killing ability, the researchers say.

Many other researchers have used machine-learning models to analyze data from biological experiments, by training an algorithm to generate predictions based on experimental data. However, these models are typically "black-box," meaning that they don't reveal the mechanisms that underlie their predictions.

To get around that problem, the MIT team took a novel approach that they call "white-box" machine-learning. Instead of feeding their data directly into a machine-learning algorithm, they first ran it through a genome-scale computer model of E. coli metabolism that had been characterized by Palsson's lab. This allowed them to generate an array of "metabolic states" described by the data.

Because the researchers already knew the experimental conditions that produced each state, they were able to determine which metabolic pathways were responsible for higher levels of cell death.