coefficient

MCE 50K 类药多样库由 50,000 种类药化合物组成。依据谷本相似性（Tanimoto Coefficient）及聚类算法（Bemis-Murcko）对上百万化合物进行筛选以确保结构多样性。优选的 5 万化合物平均谷本相似数为 0.52，共包含 36,857 个化合物簇且每簇仅包含 1-7 个化合物。除此之外，确保每簇化合物具有尽可能多的官能团，从而实现化合物库取代基、官能团、立体化学、骨架多样，占据广泛的“化学空间”。本多样性库具备新颖性、类药性，化合物结构类型多样、化学空间丰富，库中化合物可重复供应，是新药研发的有力工具，可以广泛地应用于高通量筛选（HTS）和高内涵筛选（HCS）。

Cosmetics are complex mixtures formulated through the rational blending and processing of various natural, synthetic, or extracted raw materials. The ingredients used in cosmetics are diverse in type and functionality. Based on their properties and applications, cosmetic ingredients can generally be classified into two main categories: base materials and auxiliary ingredients. The former constitutes the primary component of cosmetics, accounting for a significant proportion in formulations and serving as the key functional substances. Auxiliary ingredients, on the other hand, play roles in shaping the product, ensuring stability, or imparting color, fragrance, and other specific characteristics.Establishing a systematic ingredient database is of great significance for cosmetic research and development. By analyzing the physicochemical properties (such as oil-water partition coefficients and molecular weight distribution), biological activity mechanisms (such as antioxidant pathways and cellular signaling regulation), and compatibility of ingredients, the database can provide precise guidance for formulation design. This approach helps shorten the development cycle of cosmetic/skincare products and reduces trial-and-error costs.

MCE offers 0 types of cosmetic ingredient compounds, including antioxidants, humectants, emulsifiers, film-forming agents, and more.

Cosmetics are complex mixtures formulated through the rational blending and processing of various natural, synthetic, or extracted raw materials. The ingredients used in cosmetics are diverse in type and functionality. Based on their properties and applications, cosmetic ingredients can generally be classified into two main categories: base materials and auxiliary ingredients. The former constitutes the primary component of cosmetics, accounting for a significant proportion in formulations and serving as the key functional substances. Auxiliary ingredients, on the other hand, play roles in shaping the product, ensuring stability, or imparting color, fragrance, and other specific characteristics.Establishing a systematic ingredient database is of great significance for cosmetic research and development. By analyzing the physicochemical properties (such as oil-water partition coefficients and molecular weight distribution), biological activity mechanisms (such as antioxidant pathways and cellular signaling regulation), and compatibility of ingredients, the database can provide precise guidance for formulation design. This approach helps shorten the development cycle of cosmetic/skincare products and reduces trial-and-error costs.

MCE offers 0 types of cosmetic ingredient compounds, including antioxidants, humectants, emulsifiers, film-forming agents, and more.

Natural products are an attractive source with varied structures that exhibit potent biological activities, and desirable pharmacological profiles. The core scaffold of a natural product can also provide a biologically validated framework upon which to display diverse functional groups. Inspired by bioactive natural products, natural product-like compounds, occupying the same chemical space, are ideally suited to explore and to facilitate understanding of biological pathways.

MCE 10K Natural Product-like Compound Library consists of 10,000 natural product-like compounds. Each compound has scaffold of natural products or Tanimoto coefficient >0.6 with natural products. The natural-likeness scoring of these compounds is >-2. What’s more, compounds in the library are drug-like and readily available for re-supply, making it a powerful tool for new drug research and development. It can be widely applied in high-throughput screening (HTS) and high-content screening (HCS).

历史上，天然产物在药物发现中起着关键的作用，特别是在癌症和传染病的治疗领域，其他的治疗领域也包括心血管疾病（如他汀类药物），多发性硬化症（如腺苷酯）等。过去的几十年里，FDA 批准的药物中大约有 40% 是天然产物，其衍生物或与天然产物相关的类似物。

MCE 5K Natural Product-like Compound Library 由 5,000 个类天然产物化合物组成，库中每个分子含有天然产物关键骨架（42个）或者和天然产物的谷本相似系数 >0.6，且 Natural-likeness scoring >-2。该化合物库同时具备类药性和新颖性，库中化合物可重复供应，是新药研发的有力工具，可以广泛地应用于高通量筛选（HTS）和高内涵筛选（HCS）。

MegaUni 库为运用生成式人工智能技术，构建出的兼具新颖性、类药性、多样性、可合成性的超大化合物库。适用于AI药物筛选、大型虚拟筛选等。

MCE 依托强大的计算能力，基于高质量的 40,662 个分子砌块，匹配合适的反应规则，选择最优的化合物生成策略，去除合成难度高、类药性低、PAINS等不利化合物后，进一步分析化合物骨架，优选出类药多样性分子组成虚拟库。随后随机挑选库中分子，进行合成验证，再次剔除合成难度高的分子，经迭代优化后，最终生成含 1000 万可合成类药多样性分子的 MegaUni 10M Virtual Diversity Library。

优选 50,000 个分子组成 MegaUni 50K Virtual Diversity Library。50,000 个分子具有 46,744 种 BMS 分子骨架，每种分子骨架仅包含 1-3 个化合物，化学空间多样，结构新颖，适用于新型先导物发现等。

基于片段的药物开发 (FBDD) 是可应用于科学研究和商业化的药物开发方法，可增强对一些 “不可成药物” 靶点的识别。基于片段的药物开发发现了低分子量配体 (<300Da) 能够与相关大分子结合。这些片段分子可以覆盖广阔的化学空间，易于后期进行结构优化。目前，已经有多种基于片段开发发的药物进入临床试验，其中 Vemurafenib 和 Venetoclax 两种药物已经获得批准上市。

MCE 基于 Tanimoto 系数，使用相似性算法，从大规模的片段分子中精心挑选了 2,298 个高结构多样性的符合 ‘RO3’ 片段分子，可应用于基于片段的药物开发。

基于片段的药物发现（FBDD）作为发现新药的有力方法，已备受制药行业和学术界关注。 在近期上市的药物结构中，sp3 中心和立体中心的比例显著增加，研究者们对高三维度（3D）和富含 Fsp3 中心的片段库颇感兴趣。

MCE 3D 多样片段库由 5,400 个非平面片段分子组成（平均 Fsp3 值为 0.58），超过4,700个片段至少包含一个手性中心。本库设计的关键元素是 3D 结构、多样性、生物反应性等。另，库中化合物在保证高sp3中心和 3D 结构优势的同时，还有效提高了片段潜在生物活性，为基于片段的药物发现提供了更高的片段命中优化概率，增加了找到创新命中的可能性。