Sonidegib Phosphate

Basal Cell Carcinoma CSR Highlights CX-4945 Monotherapy: Progression-free survival (PFS) exceeded 21 months in two patients. Optimal Treatment Response: Three patients achieved partial response (PR), while ten patients had stable disease (SD). Tolerability & Disease Control Rate: Shows potential superiority over current first- and second-line therapies. Unmet Medical Need: Enrolled patients with refractory or recurrent disease who had no remaining treatment options. TAIPEI and SAN DIEGO, April 2, 2025 /PRNewswire/ -- Senhwa Biosciences, Inc. (TPEx: 6492), a new drug development company focusing on first-in-class therapeutics for oncology, rare diseases, and infectious diseases, today announced that the completion of Clinical Study Report (CSR) for Phase 1/Dose Expansion Trial of Silmitasertib (CX-4945) in the Treatment of Basal Cell Carcinoma(BCC), with positive data outcomes. The study included patients who had relapsed after standard therapies and had no other treatment options. Among them, three patients experienced over 30% tumor reduction (PR), and two patients had a progression-free survival (PFS) exceeding 21 months. CX-4945 significantly prolonged survival in advanced cancer patients, marking a major milestone for both the patients and Senhwa. Compared to current first- and second-line therapies, CX-4945 demonstrated superior tolerability and disease control potential. Therefore, Senhwa will actively pursue licensing possibilities while carefully evaluating CX-4945's potential as a monotherapy or in combination with the second-line immunotherapy Libtayo. The company aims to explore further indications and potential as a first-line treatment, offering better options for patients. Clinical Trial Overview The trial enrolled 25 patients with locally advanced BCC (laBCC, 20 patients) and metastatic BCC (mBCC, 5 patients). The primary objective was to determine the recommended Phase 2 dose (RP2D) and optimal dosing regimen for CX-4945. Among 22 patients eligible for efficacy analysis: Three laBCC patients achieved partial response (PR). Ten patients had stable disease (SD), including 2 mBCC and 8 laBCC patients. Disease control rates: mBCC patients: 80% (4 patients with complete/partial response or stable disease). laBCC patients: 65% (11 patients with complete/partial response or stable disease). Further data analysis showed that: Median progression-free survival (PFS): laBCC: 9.2 months mBCC: 3.7 months Median duration of disease control (DDC): laBCC: 10.3 months mBCC: 7.5 months CX-4945 exhibited promising anti-tumor efficacy and disease stabilization potential in this indication. Additionally, CX-4945 has a lower study drug discontinuation rate of 24% due to AEs, compared to first-line treatments including Vismodegib and Sonidegib, suggesting superior tolerability. Future Prospects This trial is particularly noteworthy as it evaluated CX-4945 monotherapy in patients who had already failed first-line HHIs. Notably, 27.3% (6 patients) had also failed second-line PD-1 inhibitors such as Libtayo or Keytruda. Among the enrolled patients, two advanced-stage patients achieved a progression-free survival (PFS) of over 21 months, lasting 653 days and 667 days, respectively. Notably, the primary lesion of the former patient was almost undetectable by visual inspection. Given the significant potential of CX-4945 as a monotherapy, Senhwa is now actively pursuing regional licensing to accelerate commercialization through strategic partnerships, ultimately benefiting more patients. SOURCE Senhwa Biosciences, Inc. WANT YOUR COMPANY'S NEWS FEATURED ON PRNEWSWIRE.COM? 440k+ Newsrooms & Influencers 9k+ Digital Media Outlets 270k+ Journalists Opted In GET STARTED

小分子的化学合成，一直是科学研究中的一项挑战。近年来，深度学习模型在逆合成领域展现出了独特的优势，这些技术能够很好的解决化学家在逆合成设计中的遇到的一些问题。然而，大多数基于AI的逆合成模型都缺乏可解释性，无法阐明逆合成设计中的内在逻辑。 2025年1月18日，西北工业大学生命学院施建宇教授团队在《Nature Communications》上发表文章Single-step retrosynthesis prediction via multitask graph representation learning。 这项研究介绍了一种革命性的方法--Retro-MTGR，该方法能够深度挖掘逆合成反应中的化学逻辑，让药物合成的逆向推理变得更加智能和精准。 逆合成推理 逆合成推理是从目标药物的分子结构出发，逆向推理出合成该药物的化学反应物。与传统的正向合成不同，逆合成推理让科学家们能够更高效地设计药物合成路线，极大地提高药物研发的效率。 Retro-MTGR：AI如何精准预测药物合成路径 施建宇教授团队提出的Retro-MTGR框架（如图1所示），是基于先进的“多任务图表示学习”的AI模型。通过深入学习分子结构中的图信息，Retro-MTGR框架能够同时完成多个任务，具体包括两个主要任务和一个辅助任务： 识别反应中心：判断分子中最容易发生化学反应的部分（主要任务）； 识别离去基：确定在反应中会“离开”分子的部分（主要任务）； 优化原子嵌入：为化学反应提供更加精准的原子表示（辅助任务）。 通过完成这三个任务，Retro-MTGR不仅帮助科学家们更好地理解化学反应机制，还能精准预测药物合成路径，为药物研发提供强大支持。 图1. Retro-MTGR的工作流程图 研究亮点：从键能到分子电性，AI揭示药物合成的深层规律 这项研究的最大亮点之一，在于通过学习分子化学键的结构，键能等属性，揭示了哪些化学键可能成为反应中心，哪些则可能只是普通的化学键（图2）。具体来说： 高键能（>=360 kJ/mol）的化学键，如双键和三键，通常是普通键； 低键能的单键（如C-N、C-O等）可能是反应中心，也可能是普通键，这取决于周围分子的结构； 反应中心的原子通常具有相反的电性，而普通键的原子则具有相似的电性。 不仅如此，Retro-MTGR还通过联合嵌入空间分析了合成子和离去基的电性分布，揭示了反应过程中的关键规律（如图3所示），这包括：反应中的两个合成子总是具有相反的电性并且彼此相距甚远；属于同一个反应物的合成子和离去基通常具有相反的电性并且彼此靠近；反应中同时出现的两个离去基经常具有相反的电性并且彼此相距甚远。 图2.化学键嵌入空间的展示 图3.合成子和离去基的联合嵌入空间展示 实验验证：准确预测药物合成路径 为了验证这一创新框架的有效性，研究团队通过预测两种药物Sonidegib和Acotiamide的逆合成路线，并与实际合成路线进行了对比。 图4. 对于两种药物的预测逆合成路线和真实化学合成路线展示 结果表明，Retro-MTGR推断出的合成路线与实际结果高度一致（如图4所示），这无疑证明了其在药物研发中的巨大潜力。 总结和展望 为了开发一个高度可解释的判别模型来揭示化学合成机制，本文提出了一个Retro-MTGR框架。基于分子图，在Retro-MTGR中同时考虑了三个相关任务，其中两个主要的监督判别任务负责识别反应中心和识别LGs，而一个辅助的自监督任务负责生成更好的原子嵌入。 与16种最先进的方法进行比较的结果，证明了Retro-MTGR的优越性。此外，在RTU和RTK场景中，不同的训练测试策略和不同大小的数据集验证了它的稳健性和可扩展性。涉及两种新药的实验验证结果表明，Retro-MTGR推断的逆合成路线与化学合成测定获得的逆合成路线一致。 Retro-MTGR是一个优秀的单步逆合成推断模型。未来，研究团队将在Retro-MTGR的基础上整合其他化学合成因子（例如反应产率，反应条件等）来开发一个可靠的多步逆合成模型以解决复杂分子逆合成路线规划的任务。 参考资料： Zhao, PC., Wei, XX., Wang, Q. et al. Single-step retrosynthesis prediction via multitask graph representation learning. Nat Commun 16, 814 (2025). https://doi.org/10.1038/s41467-025-56062-y. --------- End --------- 感兴趣的读者，可以添加小邦微信加入读者实名讨论微信群。添加时请主动注明姓名-企业-职位/岗位或姓名-学校-职务/研究方向。