KEY TAKEAWAYS<\/p>\n
\tA team led by HHMI Investigators Eric Gouaux and Michael Rosen is creating new AI tools to enhance cryo-electron tomography (cryo-ET), a microscopy technique that images cells and complex biochemical reconstitutions in three dimensions.\u00a0 Biologists are generally not fancy people, but when it comes to cryo-electron tomography, it can help to add a little bling. \u00a0<\/p>\n Cryo-electron tomography (cryo-ET) images cells in their native environment in three dimensions, providing 3D views of biological structures at nanometer resolution. The technique does a great job at revealing large structures, like cellular organelles, but is more complex to use for distinguishing the individual molecules that make them up \u2014 information that scientists use to understand how the larger structures function. \u00a0<\/p>\n To overcome this, researchers add small gold nanoparticles that attach to the molecules they want to see. But finding these small gold particles in the noisy images can be difficult and time-consuming. \u00a0<\/p>\n HHMI Investigator<\/a> Eric Gouaux<\/a> likens it to Sherlock Holmes and Doctor Watson searching for Professor Moriarty on a dark, foggy night on a crowded London street \u2014 they can track Moriarty\u2019s lantern, but the signal is faint and it\u2019s hard to discern the criminal mastermind\u2019s features. \u00a0<\/p>\n Now, unlike Holmes and Watson, scientists can enlist artificial intelligence for help. \u00a0<\/p>\n Using AI\u00a0to\u00a0Uncover\u00a0Molecular\u00a0Details\u00a0in Cryo-ET\u00a0<\/p>\n Gouaux, who leads a lab at Oregon Health and Science Universityexternal link, opens in a new tab<\/a>, and HHMI Investigator Michael Rosen<\/a> at UT Southwestern Medical Centerexternal link, opens in a new tab<\/a> are leading a project to use AI to transform cryo-ET from its traditional use in imaging big things \u2014 like cells and the structures inside them \u2014 to a technique that can also be used to examine small things \u2013 like the molecules making up these cellular structures. \u00a0<\/p>\n Understanding where these molecules are and how they\u2019re organized allows biologists to uncover how the larger structures work and what happens when they go awry. \u00a0<\/p>\n For Rosen, understanding how chromatin \u2014 densely packed DNA \u2014 is organized in the nucleus helps his team uncover how it contributes to functions like gene expression. Studying the organization of molecules in synapses \u2014 the sites where messages are passed between neurons \u2014 allows Gouaux and his team to understand how signal transmission happens. \u00a0<\/p>\n \u201cUltimately, we are really interested in: Does Moriarity have a knife? Does he have a gun? How can we figure that out?\u201d Gouaux says. \u201cAnd so, with respect to these assemblies, we really want to know how they are fitting together so we can understand, in detail, what\u2019s going on.\u201d\u00a0<\/p>\n Training AI\u00a0Models to\u00a0Find\u00a0Molecules\u00a0\u00a0<\/p>\n Using cryo-ET data obtained by the researchers, the team plans to develop and train AI models to quickly and accurately recognize gold nanoparticle labels of different shapes and brightnesses, ramping up the speed and sensitivity of the process beyond what the human eye can capture.\u00a0<\/p>\n The researchers also want to increase the amount of gold nanoparticle labels they can use and employ different types of labels that can be used with other imaging techniques, both of which could reveal additional molecular details, says HHMI Investigator Elizabeth Villa<\/a>, who is collaborating on the project. <\/p>\n Tomography is the highest resolution imaging tool biologists have but it is hard to identify molecules of interest, so improving these labeling methods and making them easier to use will be a game changer for researchers, Villa says. <\/p>\n \u201cI can\u2019t think of a single person that uses tomography right now that wouldn\u2019t want a plug-and-play version of this and I can think of a lot of people that are not experts in tomography that would love to use tomography,\u201d she says. <\/p>\n The team also plans to create and train AI models on biochemical reconstitutions of dense chromatin as well as molecular simulations of chromatin created by Rosen\u2019s collaborator Rosana Collepardo-Guevara at the University of Cambridge. Information from the biochemistry and simulations will help improve the model\u2019s predictions of where the chromatin is in the tomograms, how different elements are connected to each other, and how changes, like mutations, disease, and aging, can affect its mechanics and function.\u00a0<\/p>\n These AI-powered methods both improve the quality of the cryo-ET images \u2014 providing better reconstruction of the molecules and structures in the sample \u2014 and the analysis, enabling more information to be obtained from the data, says Magdalena Schneider, a Machine Learning Researcher with the AI@HHMI Initiative at HHMI\u2019s Janelia Research Campusexternal link, opens in a new tab<\/a>, who is collaborating on the project. \u00a0<\/p>\n \u201cWe can see things that we haven\u2019t seen before in the natural environment of the cell,\u201d she says. \u00a0<\/p>\n Taking\u00a0Tomography to the\u00a0Next\u00a0Level\u00a0\u00a0<\/p>\n Ultimately, the team hopes to design AI tools that can be used by biologists in labs worldwide to understand many different types of molecular structures beyond synapses and chromatin. \u00a0\u00a0<\/p>\n \u201cIf the AI can produce a generalizable approach to labeling multiple objects differently, and then rapidly identifying where they are and determining their structures, that will be transformative in a lot of different areas,\u201d Rosen says.<\/p>\n
\n\tThe team is combining AI with innovative techniques like labeling molecules with gold nanoparticles to improve the interpretation of cryo-ET images. This will enable scientists to identify molecules that make up larger structures like tightly wound strands of DNA and sites where neurons communicate. \u00a0
\n\tUnderstanding where these molecules are located and how they\u2019re organized allows researchers to better understand how the larger structures they make up function and what happens when they go awry. \u00a0
\n\tThe project is part of AI@HHMIexternal link, opens in a new tab<\/a>, the institute\u2019s $500 million initiative to support AI-driven projects and embed AI systems throughout the scientific process.\u00a0<\/p>\n