Nanyang Biologics
Của Nanyang BiologicsNanyang Biologics (NYB) is redefining bioactive discovery through Vecura (previously DTIGN), its proprietary AI engine developed to solve one of the most complex problems in drug and ingredient innovation: selecting the right compound from nature’s vast chemical space. NYB focuses on high-value compounds derived from plants, fungi, and marine organisms with potential for both therapeutic and consumer health applications.
- Giai đoạn
- Đang thí điểm
- Ngành
- Công nghệ
- Y tế
Giá trị mang lại
An AI-first discovery platform finds natural bioactive compounds faster and with higher hit rates than conventional screening: a 40% hit rate for AI-prioritized candidates.
Nature has shaped medicine for centuries, yet much of Earth's biodiversity remains untapped for healing. This is especially true in Southeast Asia, where our team originates, a region rich in traditional wisdom but overlooked in modern drug discovery. Meanwhile, developing new medicines remains slow, risky, and expensive, often taking up to 15 years, requiring $4.5 billion, and facing a 90 percent failure rate. Motivated by Southeast Asia’s extraordinary natural resources and the urgent need for faster solutions, NYB created Vecura. By blending deep biological knowledge with frontier AI, Vecura is designed to decode the hidden interactions between molecules and the body, bringing nature’s therapeutic potential to light faster than ever before.
Đang mở deck…
Trang 1
Khách hàng tiêu biểu đang trả phí
- Under NDA terms, we can't share the names
Vecura differentiates itself from existing AI-driven drug discovery solutions by addressing key limitations in compound screening and generative compound design approaches. While many competitors focus on isolated aspects of drug discovery, Vecura offers a more comprehensive and biologically informed approach to drug-target interaction prediction that improves candidate selection and clinical viability. 1. Compound screening competitors Many AI-driven compound screening platforms, such as Enveda Biosciences and Atomwise, primarily rely on binding affinity prediction, often overlooking critical biological factors that influence bioactivity. These models use ligand-based or structure-based screening, which fails to account for signaling pathways, reaction environments, pharmacokinetics, and species-specific variations. As a result, they generate high false-positive rates and struggle with clinical translation. Vecura addresses this gap by incorporating a broader range of biological and chemical parameters, leading to more accurate bioactivity predictions and a higher likelihood of identifying effective compounds. 2. Generative compound design competitors Platforms like Insilico Medicine and Schrödinger focus on generating novel molecular structures and predicting their potential activity. However, many AI-designed compounds are not synthesizable or fail to meet essential drug-like properties, making them impractical for real-world applications. Vecura takes a different approach by prioritizing naturally occurring bioactive compounds, which have higher synthesizability, bioavailability, and clinical viability.