Bhattacharjee Kamanasish, Idris Adi
Department of Analytics, School of Computer Science and Engineering (SCOPE), Vellore Institute of Technology, Vellore, Tamil Nadu, India.
Centre for Immunology and Infection Control, School of Biomedical Sciences, Queensland University of Technology, Brisbane, Queensland, Australia.
J Microbiol Biol Educ. 2025 Aug 22:e0013925. doi: 10.1128/jmbe.00139-25.
The use of artificial intelligence (AI) in biologics drug design is interlaced into the fabric of the drug discovery pipeline for many in the biotechnology industry. The use of AI tools in RNA therapeutic drug design has gained traction in recent years to develop more effective therapeutics in a short period of time, revolutionizing rapid-response therapeutics. Indeed, machine learning (ML) and deep learning (DL) are streamlining RNA therapeutic design in ways we never thought were possible just a decade ago. These advances are accompanied by a plethora of new AI tools for drug design that continue to barrage the research space at unprecedented speed. As biology educators, we bear the responsibility for keeping up with technological advances in the biotechnology space, as it is up to us to prepare and equip the next generation of scientists with the use of AI platforms in this space. Small interfering RNA (siRNA) therapeutic design remains a complex challenge, despite several of them being currently in clinical use for various genetic diseases. The application of AI and ML models can predict potent and longer-lasting siRNA drug candidates for therapeutic development. Additionally, it is imperative that siRNA candidates are screened for their propensity to form secondary structures, as this can reduce targeting efficacy and result in unwanted immune responses. Though siRNA technology is commonly taught at the undergraduate level across life sciences disciplines, there remains a disconnect between the use of AI and siRNA design in the teaching curriculum. We previously described an innovative approach for teaching students the use of a generative AI tool called Biomod AI to design siRNAs. Here, we designed an inquiry-based non-wet-lab workshop for students to explore the use of an automated DL-based RNA 3D structure prediction tool called trRosettaRNA to determine the secondary structures of siRNAs. Importantly, the interdisciplinary design of this activity amalgamates both AI and RNA science concepts in a simplified format in a single workshop tailored for first-year health sciences undergraduate students.
在生物制药设计中，人工智能（AI）的应用已融入许多生物技术行业从业者的药物发现流程。近年来，人工智能工具在RNA治疗药物设计中的应用越来越受到关注，其目的是在短时间内开发出更有效的治疗方法，从而彻底改变快速反应疗法。事实上，机器学习（ML）和深度学习（DL）正在以前所未有的方式简化RNA治疗设计，而这在仅仅十年前是我们从未想象过的。这些进展伴随着大量用于药物设计的新型人工智能工具，它们以前所未有的速度不断冲击着研究领域。作为生物学教育工作者，我们有责任跟上生物技术领域的技术进步，因为培养下一代科学家在这个领域使用人工智能平台的任务落在了我们身上。尽管目前有几种小干扰RNA（siRNA）已用于多种遗传疾病的临床治疗，但siRNA治疗设计仍然是一项复杂的挑战。人工智能和机器学习模型的应用可以预测出用于治疗开发的高效且持久的siRNA候选药物。此外，必须对siRNA候选药物形成二级结构的倾向进行筛选，因为这可能会降低靶向效果并引发不必要的免疫反应。虽然siRNA技术在生命科学各学科的本科教学中普遍讲授，但在教学课程中，人工智能的使用与siRNA设计之间仍然存在脱节。我们之前描述了一种创新方法，用于教授学生使用名为Biomod AI的生成式人工智能工具来设计siRNAs。在此，我们为学生设计了一个基于探究的非湿实验室工作坊，以探索使用名为trRosettaRNA的基于深度学习的自动化RNA三维结构预测工具来确定siRNAs的二级结构。重要的是，这项活动的跨学科设计以简化的形式，在一个为健康科学专业一年级本科生量身定制的单一工作坊中，融合了人工智能和RNA科学概念。
