32 Cancer cells differ from healthy cells in ways that allow them to grow rapidly and evade normal quality controls. Researchers at Rice University, led by Natasha Kirienko, are seeking to identify and exploit those differences to improve cancer treatments. In a paper published in the journal Leukaemia, the team described a new screening method that identified drugs capable of targeting vulnerabilities unique to cancer cells while largely sparing healthy ones. “We developed a screening method to identify potential drugs against acute myeloid leukaemia,” said Kirienko, a professor of biosciences and corresponding author. “This method uses machine learning to essentially work backwards from the traditional drug screening approach. With it, we identified not only new potential drug compounds but a new drug target specific to AML cells.” The team began by identifying three functions shared by successful drugs from earlier wet-lab screens tested against Acute Myeloid Leukaemia (AML) cells. They then applied machine-learning software to select compounds most likely to perform those three functions. The programme evaluated more than four million drug compounds and found fewer than 100 that met the criteria. “We were looking for compounds that caused increased cell death, or apoptosis, increased organellar recycling, or autophagy, and that inhibited a protein called glutathione reductase,” said Bernadetta Meika, a graduate student and co-author of the paper. “Our computer models identified just under a hundred molecules that could do these functions. We picked the best 20 to test in the lab.” “In a typical in silico, or computer-based, screening process, the researcher tells the programme exactly what to target,” Meika said. “In this process, we told it to look for functions that identified potential drugs and allowed us to define a target.” Closer examination of glutathione reductase revealed that inhibiting the protein exploits a vulnerability particular to cancer cells. Leukaemia cells have high energy demands and rely heavily on mitochondria. As mitochondria generate energy, they also produce harmful reactive oxygen species, or ROS, that must be neutralised. Glutathione reductase proteins play a key role in that process. When the proteins are inhibited, a cell’s ability to neutralise ROS drops significantly. Healthy cells can fall back on secondary neutralisation methods. In AML cells, the high energy requirements produce more ROS than the backup systems can manage. The excess ROS then damages and kills the cell. When the researchers tested the leading compounds in AML cell lines and cancer cells donated by AML patients, the compounds selectively targeted the AML cells. The new compounds also worked in combination with existing AML drugs and produced a synergistic effect. The combination killed 95%–97% of the cancer cells while affecting only 5% of healthy blood cells. The results are notable given that acute myeloid leukaemia remains an aggressive blood cancer with high relapse rates under standard treatments. “Collaborating with chemists, biologists, computational biologists, and clinicians enabled us to develop this pipeline and identify a promising new target with potential drug candidates,” Kirienko said. “Now, we can use this pipeline to look for new compounds and targets in other cancers.” Key collaborators included Scott Gilbertson, a medicinal chemist from the University of Houston, and Simona Colla and Steven Kornblau from The University of Texas MD Anderson Cancer Center, who provided access to patient samples from MD Anderson’s Leukaemia Sample Bank. The research was funded by the National Institutes of Health’s National Institute of General Medical Sciences (R35GM129294, T32GM139801), the National Cancer Institute (R21CA280500, 3R21CA280500-01A1S1), and the Cancer Prevention and Research Institute of Texas’ High Impact/High Risk Research programme (RP250573). Further development and testing will be needed before any clinical application, although the pipeline itself provides a reusable framework for identifying similar vulnerabilities in other cancers.