AI Drug Discovery Firm Yulu Qianxing Secures Angel Funding, Files Prospectus for Next-Stage Growth

Investment Circle (ID: pedaily2012) reported that AI pharmaceutical company Divamics completedAngel RoundFinancing, the investor isHangzhou Shileng Investment Management Co., Ltd.This round of financing mainly aims to introduce strategic shareholders to boost the company's business development. It is reported that the company has launched a new fundraising plan, which will be mainly used for team building and the layout of new innovative drug research and development pipelines.

Divamics is positioned as an interdisciplinary technology enterprise driven by molecular simulation and modeling techniques to advance new drug development. Its core technology is a molecular simulation computing platform, including a machine learning-based molecular force field engine and parallelized molecular dynamics simulation technology, aiming to design and optimize lead compounds from the dynamic mechanisms of protein target structures and their interactions with drug molecules, providing a new entry point for drug research and development.

According toDr. Zheng Zheng, Founder of DivamicsIntroduction: International computer-based drug discovery technologies are roughly divided into two technical schools: physics-based methods rooted in first principles and statistics-based methods represented by AI algorithms. The physical models are bottom-up analytical models, characterized by high accuracy, low dependence on known information, but with expensive computational costs. AI algorithms, on the other hand, only require inputting training data into the training model and waiting for the model to converge before application, significantly reducing development costs compared to the former. However, the issue lies in that the model's accuracy is limited by the quality of the training data and the coverage of biological system diversity.

As a result, the development of these two types of algorithms exhibits completely different development models. The former (physical models) often has a long development cycle (several years), with a relatively low frequency of algorithm iteration required after completion, while also being highly challenging to develop. Currently, in China, only a handful of teams possess the capability to develop physical models. The latter (AI models) is characterized by relatively lower development difficulty (currently, the number of AI drug design software products globally is too numerous to count), but with a high iteration frequency, requiring continuous updates and training using new databases. However, their applicability for system expansion beyond the database is poor, and they are highly dependent on the coverage of prior research systems.

To this end, Divamics leverages the development characteristics of AI models and their impact on algorithm development paradigms by strategically integrating AI models into physical engines. These AI models replace the most costly molecular force field component in terms of development expenses. Additionally, by combining AI models with the conformational change features exhibited by different target systems during molecular dynamics simulations, Divamics pre-learns the binding sites and pathways between drugs and their targets to enhance computational speed. In short, by merging AI models with physical models, the approach reduces the development cost of physical models while retaining their adaptability across various biological systems, thereby improving computational efficiency. This preserves the strengths of both technological approaches: high precision with minimal data dependency, as well as rapid processing speeds.

Computer-aided drug design technology, after decades of development, has been deeply integrated into various processes of drug research and development, playing a crucial role in multiple stages primarily involving molecular-level drug design and analysis. Moreover, the industry's main demands for computer-aided drug design technology have gradually expanded from ultra-large-scale virtual screening and lead compound optimization to areas such as exploring drug mechanisms of action and designing complex macromolecular drugs and their delivery systems. This not only places higher demands on the computational efficiency and accuracy of related algorithms but also presents significant challenges to the generalization capability of these algorithms when applied to unknown complex molecular systems.

To this end, Divamics has developed and integrated a drug molecule R&D platform through extensive computational simulation research and testing on various drug-target systems. The platform expands the focus from the binding interface of drugs and targets to the dynamic behavior of target functional conformational changes after binding with drug molecules. By comparing the dynamic behavior of the apo protein (without bound drug) and analyzing the thermodynamic properties during the drug-target binding process, the platform comprehensively evaluates and predicts the in vitro activity of drug molecules.

Specifically, the computational process of its technical platform begins with structural modeling of the target and the restoration of dynamic conformations in physiological processes: by analyzing stable conformational states formed during the conformational changes of the target, potential drug-binding sites are selected for high-speed virtual screening algorithms paired with high-precision molecular simulation algorithms to obtain reliable hit compounds; subsequently, through a combination of dry and wet experiments, the pharmacodynamic mechanisms at the molecular level are clarified, and finally, based on the principle of molecular scaffold hopping, novel lead compound molecular structures are designed.

Based on this technology, one of Divamics' key future development goals is to expand into the market of "difficult-to-drug targets," which account for a larger proportion of known targets. The company aims to leverage its technical advantages to precisely and rapidly simulate the structure and physiological properties of these "difficult-to-drug targets," explore binding sites, and design drug molecules that can effectively bind to them.Dr. Zheng ZhengDivamics stated that turning "difficult drug targets" into "hot targets" represents the broadest application prospect and the most imaginative market space for AI technology in the field of drug development in the future, which is also Divamics' differentiated competitive strategy.

This article is sourced from Pedaily, original text: https://news.pedaily.cn/202207/496482.shtml