肿瘤管线临床进展，英矽智能ISM3412完成首例患者给药

⦿ ISM3412靶向局部晚期和转移性实体瘤治疗，在临床前实验中表现出优异的成药性和良好的安全窗，并在动物模型中表现出低剂量下的良好活性，其分子设计过程由英矽智能自有生成化学引擎Chemistry42赋能。

⦿ 目前，针对ISM3412的I期临床研究正在美国和中国的多个中心开展招募，旨在评估该候选药物在患者群体中的安全性、耐受性、PK/PD特征和初步疗效。

马萨诸塞州剑桥市 – 2025年6月19日 – 由生成式人工智能驱动的临床阶段生物医药科技公司英矽智能（Insilico Medicine）宣布在一项全球多中心临床试验（NCT06414460）中完成了首例患者给药，该试验旨在局部晚期和转移性实体瘤患者群体中评估ISM3412，一款AI赋能、创新结构的潜在“同类最佳”（best-in-class）MAT2A抑制剂。

该项I期临床研究分为剂量递增试验和剂量选择优化两大部分，受试者将每日一次接受ISM3412口服治疗。除针对ISM3412的安全性、耐受性、药代动力学/药效动力学特性和初步抗肿瘤疗效评估外，此项研究还将确定后续研究的推荐剂量。截至目前，该试验已在中国组长单位，即中国医学科学院肿瘤医院完成了首例受试者入组和第一剂量队列的剂量限制性毒性（DLT）观察。

英矽智能联合首席执行官兼首席科学官任峰博士表示，"首例患者给药标志着其从临床前研究到人体内验证的转变，是候选药物研发历程中的关键里程碑。我们很高兴看到AI技术赋能开发的ISM3412有望为晚期或转移性肿瘤患者提供创新的潜力治疗选择，期待更新颖、更高效的治疗策略能为全球患者带来获益。"

ISM3412是一款高口服生物利用度、高选择性的强效MAT2A（甲硫氨酸腺苷转移酶2A）抑制剂，其研发流程由英矽智能自有生成化学平台Chemistry42赋能。该候选药物通过抑制MAT2A，降低S-腺苷甲硫氨酸（SAM）这一细胞功能必需成分的水平，进而针对性杀伤MTAP缺失的癌细胞，同时保护健康细胞。考虑到MTAP缺失突变广泛存在于非小细胞肺癌（NSCLC）、胰腺癌、膀胱癌等多种实体瘤，该策略有望提供创新治疗方案。

以合成致死策略为引，英矽智能采用生成化学引擎Chemistry42基于配体的AI药物设计策略开展创新药物研发，并于2022年5月宣布提名ISM3412为临床前候选化合物。在临床前研究中，ISM3412在临床前研究中显示出优异的成药性、良好的溶解度和渗透性，以及良好的安全性特征与安全窗，并在动物模型中表现出低剂量下的良好活性。相关数据已在2023年AACR（美国癌症研究协会）年会上以摘要和海报形式展示。2024年4月和5月，ISM3412先后获得了美国FDA和NMPA的临床试验批件，为后续研究铺平了道路。

英矽智能首席医学官Sujata Rao博士表示，"在临床前研究中，ISM3412展现出了良好的安全性特征，突显了其优化患者治疗选择的潜力。目前，ISM3412不仅在单药使用时表现出疗效，还在与化疗和PRMT5抑制剂联合使用显示出协同效应。我们期待从正在进行的I期临床研究出发，进一步验证这些结果。"

通过整合先进的AI和自动化技术，英矽智能在实际应用案例中展现出效率提升，为AI驱动的药物研发树立了标杆。与传统药物研发通常需要2.5-4年的时间周期相比，英矽智能在2021至2024年间的自研项目，从立项到提名临床前候选药物（PCC）的平均耗时为12-18个月之间，每个项目仅需合成和测试约60-200 个分子，从 PCC到 IND-enabling阶段的成功率达到 100%。

⦿ ISM3412 was designed with the support of Chemistry42, Insilico’s proprietary generative chemistry engine, for the treatment of locally advanced and metastatic solid tumors. In preclinical studies, ISM3412 has demonstrated excellent drug-likeness, promising safety margin, and good activity at low doses in animal models.

⦿ The Phase I study of ISM3412 is currently recruiting in multiple sites across the United States and China, aiming to evaluate the safety, tolerability, PK/PD profiles and preliminary efficacy in patients.

Cambridge, MA – June 19, 2025 –Insilico Medicine(“Insilico”), a clinical-stage biotechnology company driven by generative artificial intelligence (AI), today announces that the first patient has been dosed in a global multicenter clinical trial (NCT06414460) to evaluate ISM3412, a potentially best-in-class, AI-empowered MAT2A inhibitor with novel structure, in patients with locally advanced and metastatic solid tumors.

The Phase 1 study consists of two parts: dose escalation and dose selection optimization, where participants will receive ISM3412 orally once daily, not only to evaluate the safety, tolerability, pharmacokinetics/pharmacodynamics properties and preliminary anti-tumor efficacy of ISM3412, but also to determine the recommended dose in further studies. To date, the trial has completed enrollment for the first subject and DLT (Dose-Limiting Toxicities) observation for the first dose cohort at Cancer Hospital Chinese Academy of Medical Sciences, the leading site in China.

“The first-in-patient dosing is a critical milestone for any drug candidate, marking its transition from preclinical research into evaluations within human bodies. We are thrilled to see ISM3412 emerging as a potential treatment option, developed with the support of AI—— particularly for patients with advanced or metastatic tumors, who could benefit from novel and more efficient treatment methods.” said Feng Ren PhD, Co-CEO and CSO of Insilico Medicine. “

ISM3412 is an orally bioavailable, highly selective, and potent MAT2A (methionine adenosyltransferase 2A) inhibitor empowered by Insilico’s proprietary generative chemistry platform, Chemistry42. The drug targets cancers with MTAP deletion, a common genetic alteration found in multiple solid tumors, including non-small cell lung cancer (NSCLC), pancreatic cancer, and bladder cancer. MTAP deletions create a synthetic lethality vulnerability that ISM3412 exploits by inhibiting MAT2A, reducing levels of S-adenosylmethionine (SAM)—a molecule essential to cell function—and selectively killing MTAP-deficient cancer cells while sparing healthy cells.

Guided by the synthetic lethality strategy, ISM3412 was designed using ligand-based AI-enabled drug design by Insilico's generative chemistry application, Chemistry42, and was nominated as a preclinical candidate compound in May 2022. In preclinical studies, ISM3412 demonstrated excellent drug-likeness with good solubility and permeability, good activity at low doses in animal models, and a favorable safety profile with promising safety margin in preclinical studies. Relevant data has been presented as abstract and poster on the AACR (American Association for Cancer Research) Annual Meeting 2023. In April and May 2024, ISM3412 received IND clearance from the U.S. FDA and NMPA, paving the way for future clinical studies.

“In preclinical studies, ISM3412 has demonstrated a promising safety profile, highlighting its potential to improve treatment options for patients. Beyond its efficacy as a monotherapy, ISM3412 also exhibited synergistic effects when combined with chemotherapy and PRMT5 inhibitors. We look forward to validating these results in our ongoing phase 1 study in patients.” said Sujata Rao, MD, Chief Medical Officer of Insilico Medicine.

By integrating advanced AI and automation technologies, Insilico Medicine has demonstrated significant efficiency improvements in practical applications, setting a benchmark for AI-driven drug research and development. Compared to the typical 2.5–4 years required in traditional drug discovery, Insilico’s 22 nominated candidate drugs from 2021 to 2024 took only 12–18 months on average to progress from project initiation to nomination of preclinical candidates (PCCs), with each project requiring synthesis and testing of only about 60–200 molecules. The success rate from PCC to IND-enabling stage reached 100%.