BIOSEEKI INTELLIGENCE · DAILY SIGNAL

每天过滤噪音,留下值得科研人员看的进展。

聚焦精准医疗、肿瘤生物学、AI 药物发现、组学、结构生物学与 AI for Science。每一天的入选结果独立归档,论文发表日期和快讯入选日期分开记录。

最近一期 · 2026/10/0236 条精选自动快讯保留 21 天
按主题
按时间

最新一期

2 条 · 2026-10-03
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
基因组与单细胞· 预印本AISK / 78

Feasibility of an AI-Simulated Patient Encounter Delivered in Group and Individual Learning Formats for First-Year Medical Students: A Two-Cohort Pilot Study

Europe PMC · 论文发布 2026-09-30

Abstract Background Generative artificial intelligence (AI) and large language model (LLM)–based simulated patients are being evaluated for problem-based learning and case-based learning in undergraduate medical education, but delivery form…

为什么值得关注关注点在于 AI 是否能从高维组学数据中提取可解释、可复现的生物学信号,并在独立数据集上保持稳定。
AI
查看原始来源 ↗

上一期

2 条 · 2026-10-02
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 方法/模型AISK / 83

Augmenting the hypnotic imagination: practical applications of artificial intelligence for clinical hypnosis.

Europe PMC · 论文发布 2026-09-30

Artificial intelligence (AI), particularly large language models (LLMs), offers clinical hypnotists a powerful and immediately accessible set of tools for enhancing practice. Despite growing interest at the intersection of AI and mental hea…

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI药物发现
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 方法/模型AISK / 78

Critical Thinking, Human Judgment, and Artificial Intelligence in Combat Casualty Care: Implications for Military Medical Education and Practice.

Europe PMC · 论文发布 2026-09-28

Artificial intelligence (AI) is rapidly transforming healthcare through advances in machine learning, predictive analytics, and large language models. These technologies offer substantial opportunities to improve diagnostic support, informa…

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI蛋白/结构
查看原始来源 ↗

本周

3 条 · 2026-10-01 — 2026-09-30
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 方法/模型AISK / 80

Using Sydney Triage to Admission Risk Tool With Artificial Intelligence (START-AI) to Predict Inpatient Admitting Specialty for Emergency Department Patients: Single Centre Deep Learning Analysis.

Europe PMC · 论文发布 2026-10-01

Objective To investigate whether the Sydney Triage to Admission Risk Tool with Artificial Intelligence (START-AI) model could be used to predict specific inpatient admitting teams based on clinical notes. Methods This was a pre-trained lang…

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
AI for Science· 综述AISK / 77

Introduction to Concepts in Artificial Intelligence and Machine Learning for Pharmacoepidemiologists: Large Language Models.

Europe PMC · 论文发布 2026-10-01

Large language models (LLMs) represent a type of generative artificial intelligence (GenAI) that generate and interpret text, with some LLMs able to process multimodal content (e.g., images, audio, video), and can be deployed as part of age…

为什么值得关注关注点在于该方法是否把 AI 从辅助分析推进到可验证的科研工作流,并带来可重复的效率或发现增益。
AI药物发现
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
AI 药物发现· 方法/模型AISK / 82

AnewDDE: An Agentic Drug Discovery Engine for Biomolecular Interaction Modelling and Closed-Loop Design

Europe PMC · 论文发布 2026-09-25

Accurate modelling of biomolecular interactions is fundamental to drug discovery, yet current artificial intelligence (AI) workflows remain fragmented across structure prediction, affinity estimation, molecular design, and experimental deci…

为什么值得关注关注点在于 AI 是否真正提升靶点发现、分子筛选或研发决策效率,以及关键结果是否得到数据或实验验证。
AI蛋白/结构药物发现
查看原始来源 ↗

历史快讯

29 条 · 2026-09-26 — 2026-06-16
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
蛋白质与结构生物学· 方法/模型AISK / 77

Agentic campaign control for high-throughput de novo binder design

Europe PMC · 论文发布 2026-09-23

Progress in artificial intelligence has produced a rapidly growing ecosystem of methods for de novo protein design. With access to many specialized and often complementary tools, how does one use them effectively, especially with a finite c…

为什么值得关注关注点在于 AI 是否提升结构解析、功能预测或蛋白设计能力,以及预测结果能否经实验验证。
AI蛋白/结构
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 综述AISK / 76

Exploring young adult cancer survivors' perspectives on generative AI chatbots for symptom support.

Europe PMC · 论文发布 2026-09-23

Young adult cancer survivors (ages 18-39) often experience persistent treatment-related symptoms that negatively affect daily functioning, psychosocial well-being, and quality of life, yet report unmet educational needs for symptom manageme…

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI蛋白/结构
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 综述AISK / 81

Practical Considerations for Adopting AI Clinical Decision Support Tools and Large Language Models in Dermatology.

Europe PMC · 论文发布 2026-09-21

Artificial Intelligence (AI) in dermatology is a rapidly evolving field, offering promising advancements in the diagnosis and management of skin cancers. As global skin cancer incidence rises, tools like machine-learning based systems and l…

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
蛋白质与结构生物学· 方法/模型AISK / 78

Evaluating Artificial Intelligence, Peer, and Instructor Feedback Across Scientific Communication Assignments in Undergraduate Biology.

Europe PMC · 论文发布 2026-09-20

Generative artificial intelligence (AI) has emerged as a potential source of formative feedback for student writing. However, relatively little is known about how AI-generated feedback compares with instructor and peer feedback across diffe…

为什么值得关注关注点在于 AI 是否提升结构解析、功能预测或蛋白设计能力,以及预测结果能否经实验验证。
AI蛋白/结构
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
AI 药物发现· 方法/模型AISK / 82

From Answers to Agents: What Must Change Before Generative and Agentic AI Become Clinical Infrastructure in Hematology.

Europe PMC · 论文发布 2026-09-21

Generative artificial intelligence in hematology is entering a new phase. The dominant question, whether large language models are accurate enough for clinical decision support, is being overtaken by a harder one, as systems shift from answ…

为什么值得关注关注点在于 AI 是否真正提升靶点发现、分子筛选或研发决策效率,以及关键结果是否得到数据或实验验证。
AI蛋白/结构
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
AI 药物发现· 预印本AISK / 78

AF-RECAL: Multi-Modal Structural Recalibration of AlphaFold 3 Hallucinations in Intrinsically Disordered Human Disease Targets

Europe PMC · 论文发布 2026-09-21

AlphaFold 3 (AF3) has transformed structural bioinformatics through generative diffusion modeling of biomolecular assemblies. However, intrinsically disordered regions (IDRs)—which comprise over 30% of the human proteome and mediate essenti…

为什么值得关注关注点在于 AI 是否真正提升靶点发现、分子筛选或研发决策效率,以及关键结果是否得到数据或实验验证。
AI单细胞/空间组学蛋白/结构
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 方法/模型AISK / 74

Potential clinical utility of a KDIGO 2021-based clinical decision support system for glomerular diseases: a retrospective two-center pilot study.

Europe PMC · 论文发布 2026-09-18

Purpose Glomerulopathies are a heterogeneous group of diseases characterized by complex immunopathogenesis and wide clinical variability. A wide range of laboratory and histopathological tests is used to assess glomerular diseases. However,…

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
蛋白质与结构生物学· 综述AISK / 76

Artificial intelligence in toxicology: current advances, challenges and future directions.

Europe PMC · 论文发布 2026-09-17

Toxicology has traditionally relied on in vivo animal studies and in vitro assays to assess the safety of drugs, chemicals and environmental contaminants. These approaches are constrained by cost, duration, ethical concerns and difficulties…

为什么值得关注关注点在于 AI 是否提升结构解析、功能预测或蛋白设计能力,以及预测结果能否经实验验证。
AI蛋白/结构药物发现
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 方法/模型AISK / 78

Clinicians vs. Artificial Intelligence in Predicting 28-Day ICU Mortality: A Vignette Study.

Europe PMC · 论文发布 2026-09-18

The surprise question (SQ) is an intuition-based tool for identifying patients who may benefit from palliative care, but its short-term prognostic performance in critical illness remains uncertain. Large language models may offer standardiz…

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 综述AISK / 76

Artificial intelligence in otolaryngology: current applications, limitations, and future perspectives.

Europe PMC · 论文发布 2026-09-16

Purpose Artificial intelligence (AI) is increasingly integrated into modern otolaryngology practice and has emerged as one of the most rapidly evolving technologies in contemporary medicine. Recent advances in machine learning, deep learnin…

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI蛋白/结构药物发现
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
AI 药物发现· 方法/模型AISK / 88

Artificial Intelligence-Driven Precision Bisphosphonate Therapy in Osteoporosis: Mechanisms, Clinical Applications, Risks, and Future Directions.

Europe PMC · 论文发布 2026-09-17

Bisphosphonates remain the pharmacological standard of care for osteoporosis; however, their clinical efficacy is limited by significant diagnostic gaps, heterogeneous therapeutic responses, and persistent concerns regarding long-term safet…

为什么值得关注关注点在于 AI 是否真正提升靶点发现、分子筛选或研发决策效率,以及关键结果是否得到数据或实验验证。
AI蛋白/结构药物发现
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 方法/模型AISK / 88

Multimodal large language models for bladder tumor detection in cystoscopy: a retrospective benchmarking study.

Europe PMC · 论文发布 2026-09-17

Purpose Cystoscopic assessment is central to bladder cancer diagnosis, yet visual interpretation remains variable. Existing artificial intelligence approaches often depend on data-intensive models that are often difficult to deploy in routi…

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
基因组与单细胞· 方法/模型AISK / 82

Selective reproduction of spatial–emotional mappings in large language models

Europe PMC · 论文发布 2026-09-16

The vertical-valence metaphor refers to the association between emotional valence and vertical space, whereby positive and negative emotions are linked to upward and downward directions, respectively. While this mapping has been robustly ob…

为什么值得关注关注点在于 AI 是否能从高维组学数据中提取可解释、可复现的生物学信号,并在独立数据集上保持稳定。
AI单细胞/空间组学
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
基因组与单细胞· 方法/模型AISK / 77

From "Who Knows Anatomy Best?" to "What Does 'Best' Mean?": Strengthening Validation Standards for Large Language Models in Anatomy Education.

Europe PMC · 论文发布 2026-09-15

Large language models (LLMs) are increasingly benchmarked against professional examination questions and interpreted as indicators of educational competence. A recent study comparing four LLMs on publicly available anatomy multiple-choice q…

为什么值得关注关注点在于 AI 是否能从高维组学数据中提取可解释、可复现的生物学信号,并在独立数据集上保持稳定。
AI单细胞/空间组学
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 方法/模型AISK / 83

Prompt Injection in Clinical Artificial Intelligence Systems: The Emerging Security Challenge of Large Language Models and Agentic AI.

Europe PMC · 论文发布 2026-09-15

Clinical discussion of artificial intelligence safety has concentrated on accuracy, bias, and hallucination, each of which describes a model failing at its assigned task. Prompt injection describes the opposite condition: a model performing…

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
AI 药物发现· 方法/模型AISK / 82

An AI-Driven Chemogenomics Knowledgebase for Human-Transmissible Pathogens: A Platform for Antimicrobial Drug Discovery.

Europe PMC · 论文发布 2026-09-15

Emerging infectious diseases (EIDs) pose a critical threat to global biosecurity. Integrating bio/chemical information and artificial intelligence would bring new strategies for antimicrobial drug discovery. Herein, the Human Pathogenic Mic…

为什么值得关注关注点在于 AI 是否真正提升靶点发现、分子筛选或研发决策效率,以及关键结果是否得到数据或实验验证。
AI蛋白/结构药物发现
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
AI 药物发现· 综述AISK / 81

Microwell platform for single-cell applications and future integration with artificial intelligence (AI).

Europe PMC · 论文发布 2026-09-14

Single-cell analysis has become an essential approach for understanding cellular heterogeneity and its implications in biological function, disease progression and therapeutic response. Microwell platforms provide a versatile approach for s…

为什么值得关注关注点在于 AI 是否真正提升靶点发现、分子筛选或研发决策效率,以及关键结果是否得到数据或实验验证。
AI单细胞/空间组学药物发现
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 方法/模型AISK / 77

How Well Do AI Chatbots Understand Abnormal Anatomy: A Comparative Study Using Congenital Anomalies and Tumor Cases.

Europe PMC · 论文发布 2026-09-09

Artificial Intelligence (AI) chatbots are becoming an efficient option to understand medical data and also help with clinical reasoning. There has been a recent progression in research of large language models and their ability to be used i…

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
AI 药物发现· 综述AISK / 76

Artificial Intelligence and Complementary Digital Health Technologies Across the Travel Medicine Continuum: A Narrative Review.

Europe PMC · 论文发布 2026-09-09

Background Artificial intelligence (AI) and complementary digital health technologies are increasingly being applied to improve prevention, diagnosis and surveillance in travel medicine. This narrative review evaluates current applications …

为什么值得关注关注点在于 AI 是否真正提升靶点发现、分子筛选或研发决策效率,以及关键结果是否得到数据或实验验证。
AI蛋白/结构药物发现
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
精准医疗· 方法/模型AISK / 83

Human Judgment and the Limits of Artificial Intelligence for Automated Rank Order Lists in Diagnostic Radiology Residency Selection.

Europe PMC · 论文发布 2026-09-11

To evaluate whether large language models (LLMs) can reliably reproduce a residency program's rank order list (ROL) from pre-interview application data alone versus with human interviews included, and to determine whether automated ranking …

为什么值得关注关注点在于 AI 与计算方法能否改善临床决策、患者分层或医疗流程,并通过独立验证证明其可推广性。
AI
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
基因组与单细胞· 方法/模型AISK / 78

Research priorities in Spine Deformity: a machine learning-based topic analysis of the journal's first decade (2013-2026).

Europe PMC · 论文发布 2026-09-08

Purpose Spine Deformity is the official journal of the Scoliosis Research Society (SRS) and the leading publication dedicated to scoliosis, deformity, and surgical correction. We applied BERTopic, a transformer-based machine learning topic-…

为什么值得关注关注点在于 AI 是否能从高维组学数据中提取可解释、可复现的生物学信号,并在独立数据集上保持稳定。
AI单细胞/空间组学
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
AI 药物发现· 方法/模型AISK / 82

AI adoption among French oncology pharmacists: A national survey.

Europe PMC · 论文发布 2026-09-10

BackgroundLarge language model (LLM)-based generative artificial intelligence (AI) tools have rapidly entered clinical practice. In oncology pharmacy, a specialty marked by high technical complexity, strict regulatory constraints, and an ex…

为什么值得关注关注点在于 AI 是否真正提升靶点发现、分子筛选或研发决策效率,以及关键结果是否得到数据或实验验证。
AI药物发现
查看原始来源 ↗
Europe PMCdoi.org
Europe PMC 来源页面预览
doi.org
Europe PMCSOURCE SNAPSHOT
蛋白质与结构生物学· 方法/模型AISK / 82

Real Science Is Harder Than Benchmarks: Evaluating Advanced AI Frameworks on Published Studies. II. Antibody Properties, Lipid-RNA Interactions

Europe PMC · 论文发布 2026-09-07

Artificial Intelligence (AI) frameworks for automating scientific research have shown strong performance on benchmarks, but their utility for real-world industrial research remains insufficiently characterized. Extending the analysis presen…

为什么值得关注关注点在于 AI 是否提升结构解析、功能预测或蛋白设计能力,以及预测结果能否经实验验证。
AI蛋白/结构
查看原始来源 ↗
Allen Institutealleninstitute.org
Allen Institute 来源页面预览
alleninstitute.org
Allen InstituteSOURCE SNAPSHOT
AI for Science· 机构发布AISK / 94

AI BioDesign 启动:把 AI 与实验生物学闭环用于设计自然界不存在的新型生物分子

Allen Institute · 论文发布 2026-09-03

Allen Institute、Fred Hutch Cancer Center 与华盛顿大学启动 AI BioDesign 项目,计划把生成式 AI、合成生物学与湿实验验证连接起来,设计新的蛋白、基因与生物系统,并通过实验反馈持续改进模型。

为什么值得关注它代表 AI for Science 正从“预测已有生物学”走向“主动设计新的生物学”。对蛋白设计、精准治疗和合成生物学而言,真正重要的是计算设计与实验验证形成闭环。
AI BioDesign蛋白设计合成生物学湿实验闭环
查看原始来源 ↗
Owkin / Reutersowkin.com
Owkin / Reuters 来源页面预览
owkin.com
Owkin / ReutersSOURCE SNAPSHOT
AI 药物发现· 产业动态AISK / 91

Owkin 向勃林格殷格翰授权 K Pro AI Scientist 与多模态患者数据

Owkin / Reuters · 论文发布 2026-09-02

Owkin 与勃林格殷格翰达成许可合作,后者将使用 K Pro AI Scientist 及肿瘤和免疫领域的多模态患者数据,用于靶点研究和药物发现。合作建立在双方 2025 年试点项目基础上。

为什么值得关注AI 药物发现的竞争正在从单纯的分子生成模型,转向“模型 + 高质量患者数据 + 可复现分析环境”的组合。真实临床多模态数据正在成为药企采用 AI 平台的重要壁垒。
药物发现多模态数据AI Scientist肿瘤
查看原始来源 ↗
Cell Death & Diseasenature.com
Cell Death & Disease 来源页面预览
nature.com
Cell Death & DiseaseSOURCE SNAPSHOT
肿瘤生物学· 同行评议论文AISK / 86

紫杉醇诱导凋亡后的存活癌细胞呈现 ZEB1 相关的铁死亡敏感性

Cell Death & Disease · 论文发布 2026-09-02

研究关注紫杉醇处理后逃逸凋亡的癌细胞状态,并将 ZEB1 与这些存活细胞的铁死亡敏感性联系起来,为理解化疗后的残存细胞状态提供了新的机制线索。

为什么值得关注化疗后残存细胞往往决定复发和耐药。若这些细胞同时获得可利用的铁死亡脆弱性,就可能为序贯治疗或联合治疗提供新的机制依据。
ZEB1铁死亡紫杉醇耐药
查看原始来源 ↗
Nature Medicinenature.com
Nature Medicine 来源页面预览
nature.com
Nature MedicineSOURCE SNAPSHOT
精准医疗· III 期临床试验AISK / 93

早期三阴性乳腺癌 III 期试验:阿替利珠单抗总体未显著改善 EFS,但分子分层提示潜在获益亚群

Nature Medicine · 论文发布 2026-09-01

在超过 1,500 名 II–III 期三阴性乳腺癌患者中,阿替利珠单抗联合新辅助化疗未达到事件无生存期主要终点。预设和探索性分析提示,淋巴结受累以及 basal-like immune-activated 等免疫相关亚型可能存在差异化获益。

为什么值得关注这类阴性总结果仍然对精准治疗非常重要:它提示免疫治疗不能只按肿瘤名称使用,分子亚型和肿瘤免疫微环境可能决定真正的获益人群。
TNBC免疫治疗生物标志物临床分层
查看原始来源 ↗
Nature Medicinenature.com
Nature Medicine 来源页面预览
nature.com
Nature MedicineSOURCE SNAPSHOT
基因组与单细胞· 同行评议论文AISK / 92

COMPASS:用泛癌转录组基础模型预测跨癌种免疫治疗反应

Nature Medicine · 论文发布 2026-08-01

COMPASS 以 10,184 个肿瘤样本进行泛癌预训练,将 15,672 个蛋白编码基因映射到 44 个具有生物学意义的免疫概念,并在多个独立临床队列中预测免疫检查点抑制剂疗效。

为什么值得关注它展示了一个更适合精准肿瘤学的方向:不只追求预测准确率,而是把大模型中间表示约束到可解释的免疫和微环境概念,同时考察跨癌种、跨药物泛化能力。
转录组基础模型免疫治疗泛癌
查看原始来源 ↗
Nature Biotechnologynature.com
Nature Biotechnology 来源页面预览
nature.com
Nature BiotechnologySOURCE SNAPSHOT
蛋白质与结构生物学· 产业动态AISK / 88

Isomorphic Labs 获 21 亿美元融资,继续扩展 AI 驱动的药物设计平台

Nature Biotechnology · 论文发布 2026-06-16

Isomorphic Labs 完成 21 亿美元 B 轮融资,计划扩大其 AI 药物设计引擎。Nature Biotechnology 报道称,其新一代 Drug Design Engine 在结构预测、结合亲和力与配体口袋识别等任务上强调相较 AlphaFold 3 的进一步提升。

为什么值得关注结构预测正在快速变成药物设计系统中的一个模块,而不是终点。行业竞争正转向从结构、结合、生成到实验验证的一体化设计引擎。
结构预测蛋白-配体AI 药物设计Isomorphic Labs
查看原始来源 ↗
当前筛选条件下没有快讯。