Search

OBJECTIVES/GOALS: This work aims to explore how citizen science serves as a transformative frame work to bridge scientific knowledge, focusing on its potential to enhance transdisciplinary learning in artificial intelligence (AI) biomedical and clinical sciences by facilitating near-peer mentoring. METHODS/STUDY POPULATION: Our group of eight friends comprise a multicultural and multidisciplinary cohort including students from the USA, Philippines, Indonesia, and Guatemala pursuing PhD degrees in electrical and computer engineering, epidemiology, physics, and MD, PharmD, and DMD degrees. We engage in shared online courses, collaborative projects, and abstract submissions. Employing our collective knowledge, we design interactive learning experiences, support each other’s initiatives, and collaboratively develop lectures and presentations. We in tend to expand collaborations in biomedical AI education while fostering principles of experiential and collaborativelearning, constructivism, and authentic inquiry. RESULTS/ANTICIPATED RESULTS: Our recent successes include submittedconference abstracts on data science and AI education in pharmacy and the facilitation of a guest lecture in health informatics. Additionally, we are currently collaborating on seven biomedical machine learning projects in radio frequency engineering, aiming for conference submissions. Moving forward, our goal is to expand our group, support the formation of similar communities, and promote data science and AI literacy in biomedical and clinical contexts. We aspire to extend this knowledge to families, classmates, and eventually patients, facilitating a broader understanding of the role of AI in healthcare. DISCUSSION/SIGNIFICANCE: We believe diverse expertise and pedagogical theories can help demonstrate the potential of citizen science to democratize scientific experience. By nurturing collaborative networks our efforts aim to bridge gaps between disciplines and enhance the broader public’s understanding of AI in healthcare.

Myosin VI, found in organisms from Caenorhabditis elegans to humans, is essential for auditory and vestibular function in mammals, since genetic mutations lead to hearing impairment and vestibular dysfunction in both humans and mice. Here, we show that a missense mutation in this molecular motor in an ENU-generated mouse model, Tailchaser, disrupts myosin VI function. Structural changes in the Tailchaser hair bundles include mislocalization of the kinocilia and branching of stereocilia. Transfection of GFP-labeled myosin VI into epithelial cells and delivery of endocytic vesicles to the early endosome revealed that the mutant phenotype displays disrupted motor function. The actin-activated ATPase rates measured for the D179Y mutation are decreased, and indicate loss of coordination of the myosin VI heads or 'gating' in the dimer form. Proper coordination is required for walking processively along, or anchoring to, actin filaments, and is apparently destroyed by the proximity of the mutation to the nucleotide-binding pocket. This loss of myosin VI function may not allow myosin VI to transport its cargoes appropriately at the base and within the stereocilia, or to anchor the membrane of stereocilia to actin filaments via its cargos, both of which lead to structural changes in the stereocilia of myosin VI-impaired hair cells, and ultimately leading to deafness.

OBJECTIVES/GOALS: Computational pathology is an emerging discipline that resides at the intersection of engineering, computer science, and pathology. There is a growing need to develop innovative pedagogical approaches to train future computational pathologists who have diverse educational backgrounds. METHODS/STUDY POPULATION: Our work proposes an iterative approach toward teaching master’s and Ph.D. students from various backgrounds, such as electrical engineering, biomedical engineering, and cell biology the basics of cell-type identification. This approach is grounded in the active learning framework to allow for observation, reflection, and independent application. The learners are trained by a team of an electrical engineer and pathologist and provided with eight images containing a glomerulus. They must then classify nuclei in each of the glomeruli as either a podocyte (blue), endothelial cell (green), or mesangial cell (red). RESULTS/ANTICIPATED RESULTS: A simple web application was built to calculate agreement, measured using Cohen’s kappa, between annotators for both individual glomeruli and across all eight images. Automating the process of providing feedback from an expert renal pathologist to the learner allows for learners to quickly determine where they can improve. After initial training, agreement scores for cells scored by both the learner and the expert were high (0.75), however, when including cells not scored by both the agreement was relatively low (0.45). This indicates that learners needed more instruction on identifying unique cells within each image. This low-stakes approach encourages exploratory and generative learning. DISCUSSION/SIGNIFICANCE: Computation medical sciences require interdisciplinary training methods. We report on a robust approach for team-based mentoring and skill development. Future implementations will include undergraduate learners and provide opportunities for graduate students to engage in near-peer mentoring.