SBIR Phase I: Advanced Deep Learning Technologies for Designing Humanized Antibody

这个小企业创新研究（SBIR）第一阶段项目的更广泛的影响/商业潜力是通过开发专有的计算方法来加速抗体设计和工程。与通常冗长、昂贵和低效的传统抗体药物开发方法相比，这种创新可能提供更有效和更具成本效益的替代方案。所提出的方法旨在创造更好的治疗级抗体，同时解锁新的抗体设计可能性。该技术所带来的市场机会是巨大的，因为到2028年，全球癌症和传染病治疗抗体市场预计将达到2350亿美元。该项目有可能改变抗体发现领域，并为患者提供新的治疗选择。这个小型企业创新研究（SBIR）第一阶段项目旨在开发一个基于人工智能（AI）的平台，有效地设计具有可能较低毒性和免疫原性风险的新型抗体候选药物。该研究将涉及开发新颖和专有的基于AI的模型，以创建一流的抗体疗法，并通过最先进的计算机实验对其进行验证。为了成功完成这一I期项目，该公司计划：a）开发一种新的计算模型来设计抗体命中序列，B）证明所提出的计算模型在设计针对不同靶标的抗体命中序列中的可扩展性，c）评估计算模型预测的抗体命中序列的生物学价值。预期的技术成果涉及更快速和有效的治疗性抗体设计过程，从而降低开发费用并更快地进入市场。人工智能技术有可能在数月而不是数年内设计出最有前途的治疗性抗体，用于治疗传染病和癌症，从而减少治疗性抗体的临床前开发所需的时间和资源。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact / commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to accelerate antibody design and engineering through the development of proprietary computational approaches. Compared to conventional antibody drug development approaches that are often lengthy, costly, and inefficient, this innovation may offer a more efficient and cost-effective alternative. The proposed approach aims to create better therapeutic-grade antibodies while unlocking novel antibody design possibilities. The market opportunity addressed by the proposed technology is significant, as the global therapeutic antibody market for cancer and infectious diseases is projected to reach $235 billion by 2028. This project has the potential to transform the field of antibody discovery and provide new therapeutic options for patients. This Small Business Innovation Research (SBIR) Phase I project aims to develop an artificial intelligence (AI)-based platform that efficiently designs novel antibody drug candidates with possible lower toxicity and immunogenicity risks. The research will involve developing novel and proprietary AI based models to create best-in-class antibody therapeutics and validate them through state-of the-art in-silico experiments. To successfully complete this Phase I project the company plans to: a) develop a novel computational model to design antibody hit sequences, b) demonstrate the scalability of the proposed computational model in designing antibody hit sequences against diverse targets, c) assess biological values of the antibody hit sequences predicted by the computational model. The expected technical outcomes involve a more rapid and efficient process for designing therapeutic antibodies, resulting in lower development expenses and a quicker path to market. The AI technologies have the potential to design the most promising therapeutic antibodies to treat infectious diseases and cancer in months rather than years, reducing the time and resources needed for the pre-clinical development of therapeutic antibodies.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.