天才冲冲冲

谷歌Gemma下载量破10亿次 AI深度探索癌症治疗新机制_我的网站

A |     　　当地时间8月20日，谷歌宣布，其开源端侧模型家族Gemma的总下载量已突破10亿次。这款由谷歌DeepMind推出的开源大模型，自发布以来，全球开发者基于它衍生出超10万个定制变体，形成名为“Gemmaverse”的开源生态。
　　谷歌列举了多个Gemma家族应用场景：从太空本地图像分析、医疗报告标准数字化、癌症创新治疗方案再到动物语言识别，Gemma家族模型正实实在在地应用到各个垂直行业。    As we mark the 101st birth anniversary of Raj Kapoor, it feels like the perfect moment to look back at one of the most memorable chapters in Filmfare history, a night that celebrated the artistry, emotion, and timeless appeal of the showman of Indian cinema. Let’s travel back to May 1961, when the 9th Filmfare Awards unfolded as a landmark evening. Raj Kapoor was honoured with the Filmfare Best Actor award for his unforgettable performance in Jis Desh Mein Ganga Behti Hai, a role that beautifully captured his deep-rooted connection with Indian culture and storytelling.                was awarded the Filmfare Best Actor for his spectacular performance in Jis Desh Men Ganga Behti Hai at the 9th Filmfare awards. ❤️Witness the magic once again as we return to Gujarat for the… pic.twitter.com/9C1AXn6S3s     — Filmfare (@filmfare) September 14, 2025                    That year, Raj Kapoor took home the Best Actor trophy for Jis Desh Mein Ganga Behti Hai. The film led the night with 10 nominations, followed closely by Gunga Jumna with 7. Interestingly, though released in 1960, Jis Desh Mein Ganga Behti Hai was not considered for the 8th edition but went on to dominate the 4th Filmfare Awards with 4 wins, including Best Film and Best Actor.     Another highlight from the evening was Shubha Khote’s double nomination in the Best Supporting Actress category for her roles in Gharana and Sasural. However, the award eventually went to Nirupa Roy for her powerful performance in Chhaya.                                                                 View this post on Instagram          A post shared by Filmfare (@filmfare)                         From legends like Dilip Kumar, Raj Kapoor, and Nargis in the early decades to the unmatched charisma of Amitabh Bachchan, Rekha, and Rishi Kapoor, every generation has left a timeless stamp on the Filmfare stage. More recently, Shah Rukh Khan’s witty hosting, Salman Khan’s high-energy acts, Aishwarya Rai Bachchan’s poise, Deepika Padukone’s elegance, Priyanka Chopra’s dynamism, and Ranveer Singh’s infectious energy have kept the magic alive.Also Read: Filmfare Flashback: Looking Back at Dilip Kumar and Nutan’s Wins for Devdas and Seema。　　其中，以Gemma为基座的模型在生物医药科研领域产出了多项标志性成果。谷歌一方面推出面向医疗场景的垂直模型MedGemma，支撑医疗报告结构化、医学影像辅助分析等应用；另一方面联合科研机构，依托Gemma底座攻坚癌症机制研究。　　其中最受行业关注的是谷歌DeepMind、谷歌研究院与耶鲁大学合作开发的Cell2Sentence-Scale 27B（C2S-Scale）模型。　　传统的癌症疫苗治疗思路，是让免疫系统通过识别身份标签来识别敌人。

B | 但这面临一个“瞄准困境”：一般来说，肿瘤的“身份标签”取自肿瘤本身,但很多肿瘤细胞表面缺少能被免疫T细胞识别的、独特的“身份标签”（即肿瘤特异性抗原），同时，它们还主动穿上“防护服”（如高表达PD-L1蛋白），成为所谓的“冷肿瘤”。

C | 结果就是，对于“冷肿瘤”，免疫系统即使大军压境，也像得了“脸盲症”，看不见敌人，或者看见了也被强行抑制，导致治疗无效。　　针对免疫治疗难以起效的“冷肿瘤”难题，C2S-Scale按活跃程度排序，将单细胞基因表达数据转化为类文本的“基因句子”，让大语言模型能直接“读”懂细胞。随后，该模型完成4000余种药物的虚拟筛选，预测出silmitasertib联合低剂量干扰素的用药组合。

D | 　　C2S-Scale锁定的候选药物中，仅10%-30%在过往文献中被提及，其余与筛选目标无已知关联。最终被选中的是silmitasertib（CX-4945），一种CK2激酶抑制剂。

E | 　　这一AI提出的全新治疗假说，后续在人源活细胞实验中得到验证，研究团队用模型训练时从未见过的人类神经内分泌细胞进行实验，结果是单独用药无效果，单用低剂量干扰素只有轻微提升，两者联用后抗原呈递提升约50%，证实联用方案可显著提升抗原呈递水平，属于少数AI产出全新癌症治疗机制并获得实验室验证的案例，有望提升肿瘤细胞抗原呈递能力，把冷肿瘤转化为对免疫治疗敏感的热肿瘤。　　该模型相关成果已对外开源，可供全球科研团队继续拓展研究。需要注意的是，该发现目前仅停留在体外细胞实验阶段，尚未进入临床。　　随着下载量冲高，Gemma证明开源大模型不再局限对话生成，能够直接介入原始生物数据挖掘，深度探索癌症治疗新机制，为AI医药科研提供低成本的技术底座。（文章来源：科创板日报）。

Current article:http://t23q1d.yindabobiehonggaonumiao.bond/bmi6853/7b7.html

Published on:21:45:58