Project Grant R44OD037625

A COMPUTER-VISION GUIDED AUTOMATED MICROINJECTION SYSTEM WITH INCREASED ROBUSTNESS, THROUGHPUT, AND GENERALIZABILITY TO DIVERSE SPECIES - PROJECT SUMMARY OBJECTIVE BIOTECHNOLOGY IS A SPIN-OUT FROM THE UNIVERSITY OF MINNESOTA THAT IS PIONEERING THE USE OF MACHINE VISION GUIDED ROBOTS FOR AUTOMATING PRECISE PROCEDURES SUCH AS MICROINJECTION. A KEY CHALLENGE IN BIOLOGICAL RESEARCH IS THE BOTTLENECK OF GENERATING TRANSGENIC AND MUTANT ANIMALS. TRADITIONALLY, TRANSGENESIS AND GENE EDITING EXPERIMENTS INVOLVE SKILLED TECHNICIANS PERFORMING INTRICATE AND PRECISE MICROINJECTION PROCEDURES REPEATEDLY. OBJECTIVE BIOTECHNOLOGY INC. HAS INTRODUCED AN INNOVATIVE SOLUTION; A MACHINE VISION GUIDED ROBOT DESIGNED TO AUTOMATE THE MICROINJECTION PROCESS FOR DROSOPHILA EMBRYOS. THIS TECHNOLOGY CAN ALSO BE READILY ADAPTED FOR USE WITH VARIOUS OTHER ORGANISMS. THIS ROBOT ELIMINATES THE NEED FOR MANUAL MICROINJECTION PROTOCOLS, WHICH ARE OPERATOR-DEPENDENT, TIME-CONSUMING, AND REQUIRE SIGNIFICANT TRAINING. THE ROBOT USES MACHINE LEARNING (ML) MODELS TRAINED TO DETECT INDIVIDUAL EMBRYOS ON AGAR PLATES AND GUIDES MICROINJECTION NEEDLES TO PERFORM MICROINJECTIONS AT SPECIFIC LOCATIONS IN EACH DETECTED EMBRYO. THIS ROBOT CAN BE OPERATED BY INDIVIDUALS WITH NO PRIOR EXPERIENCE AND SURPASS HUMAN CAPABILITIES IN TERMS OF MICROINJECTION SPEED AND ACCURACY. OBJECTIVE BIOTECHNOLOGY WAS PREVIOUSLY AWARDED AN SBIR PHASE I GRANT TO DEVELOP A PRE-COMMERCIAL VERSION OF THE AUTOINJECTOR. THIS PHASE II SBIR PROPOSAL WILL BUILD OFF THAT WORK AND ENGINEER A FULLY AUTONOMOUS MICROINJECTION ROBOT FOR COMMERCIAL DISSEMINATION. IN AIM 1 OF THIS PROPOSAL, WE WILL DEVELOP HARDWARE AND SOFTWARE TO ENABLE THE AUTOINJECTOR TO AUTOMATICALLY CHANGE PIPETTES WHEN CLOGGING OR OTHER ISSUES ARE DETECTED. THIS, TOGETHER WITH MULTI-DISH CAPABILITIES, WILL ALSO ALLOW EXPERIMENTERS TO PERFORM MULTIPLEXED EXPERIMENTS WHERE THERE ARE MULTIPLE CONSTRUCTS THAT NEED TO BE INJECTED WITHIN THE SAME INJECTION SESSION. IN AIM 2 WE WILL ROBUSTLY TEST THESE IMPROVEMENTS OVER THE COURSE OF MORE THAN 500 INJECTION EXPERIMENTS IN PARTNERSHIP WITH DROSOPHILA RESEARCHERS AT BAYLOR COLLEGE OF MEDICINE. WE WILL INCORPORATE FEEDBACK FROM THIS BETA TESTING SITE TO REFINE AND IMPROVE THE SYSTEMS DEVELOPED IN AIM 1. IN AIM 3, WE WILL DEVELOP SOFTWARE TOOLS TO ENABLE USERS TO TRAIN NEW MACHINE LEARNING MODELS TO TARGET NEW SPECIES OR STRUCTURES. ACCOMPLISHING THESE AIMS WILL PROVIDE US WITH TOOLS THAT WILL ALLOW US TO ACCESS ADDITIONAL MARKETS AND OPTIMIZE THE IMPROVED INSTRUMENT FOR COMMERCIAL LAUNCH AT THE END OF PHASE II.