Explainable Artificial Intelligence Reveals Novel Insight into Tumor Microenvironment Conditions Linked with Better Prognosis in Patients with Breast Cancer.
Explainable Artificial Intelligence Reveals Novel Insight into Tumor Microenvironment Conditions Linked with Better Prognosis in Patients with Breast Cancer.
复制标题
可解释的人工智能揭示了对与乳腺癌患者更好的预后相关的肿瘤微环境条件的新见解。
DOI：
10.3390/cancers13143450
复制
发表时间：
2021-07-09
期刊：
影响因子：
5.2
通讯作者：
Lopez-Berestein G
中科院分区：
文献类型：
--
作者：
Chakraborty D;Ivan C;Amero P;Khan M;Rodriguez-Aguayo C;Başağaoğlu H;Lopez-Berestein G
在过去的十年中，组学数据集的数量显著增加，为系统地表征癌症进化的潜在生物学机制以及了解肿瘤微环境如何促进这种进化提供了前所未有的机会。人工智能（AI）的新技术可以帮助确定治疗需求领域，加强临床试验解释，确定新的靶点，并产生传统统计技术无法实现的准确预测。然而，将高度精确和非线性的人工智能模型纳入医疗领域的一个主要批评是，人工智能本质上是一个“黑盒子”。我们利用可解释的人工智能（XAI）解决了这一首要问题，以确定乳腺癌患者的预后，并揭示与预后和患者生存增强相关的肿瘤微环境条件的有价值信息。在开发新的靶向疗法中使用XAI的好处将是显著的。我们使用可解释的人工智能（XAI）模型研究了肿瘤微环境（TME）中免疫细胞组成与乳腺癌患者≥5年生存率之间的数据驱动关系。我们从cbioPortal获得TCGA乳腺浸润性癌数据，并基于EPIC、CIBERSORT、TIMER和xCell计算方法从TIMER2.0的大量RNA测序数据中检索免疫细胞组成估计。从我们的XAI模型中获得的新见解表明，B细胞、CD8+ T细胞、M0巨噬细胞和NK T细胞是乳腺癌患者预后改善的最关键的TME特征。我们的XAI模型还揭示了这些关键TME特征的拐点，高于或低于≥5年生存率提高的拐点。随后，我们确定了从拐点推断的特定条件下≥5年生存的条件概率。特别是，XAI模型显示，TME中B细胞分数（相对于样本中所有细胞）超过0.025，M0巨噬细胞分数（相对于总免疫细胞含量）低于0.05，NK T细胞和CD8+ T细胞分数（基于癌症类型特异性任意单位）分别高于0.075和0.25，可提高乳腺癌患者≥5年的生存率。这些发现可能会导致准确的临床预测和增强免疫治疗，并设计创新的策略来重新编程乳房TME。
Over the past decade, there has been a significant increase in the number of omics datasets that provide unprecedented opportunities to systematically characterize the underlying biological mechanisms involved in cancer evolution and to understand how the tumor microenvironment contributes to this evolution. Novel techniques in artificial intelligence (AI) can help determine areas of therapeutic need, enhance clinical trial interpretation, identify novel targets, and generate accurate predictions that are impossible with traditional statistical techniques. However, a major criticism of incorporating the highly accurate and nonlinear AI models into medical fields is the notion that AI is essentially a “black box”. We resolved this overarching problem with explainable artificial intelligence (XAI) to determine prognoses in patients with breast cancer and reveal valuable information about conditions in the tumor microenvironment that are associated with enhanced prognosis and patient survival. The benefits of using XAI in the development of new targeted therapies would be significant. We investigated the data-driven relationship between immune cell composition in the tumor microenvironment (TME) and the ≥5-year survival rates of breast cancer patients using explainable artificial intelligence (XAI) models. We acquired TCGA breast invasive carcinoma data from the cbioPortal and retrieved immune cell composition estimates from bulk RNA sequencing data from TIMER2.0 based on EPIC, CIBERSORT, TIMER, and xCell computational methods. Novel insights derived from our XAI model showed that B cells, CD8+ T cells, M0 macrophages, and NK T cells are the most critical TME features for enhanced prognosis of breast cancer patients. Our XAI model also revealed the inflection points of these critical TME features, above or below which ≥5-year survival rates improve. Subsequently, we ascertained the conditional probabilities of ≥5-year survival under specific conditions inferred from the inflection points. In particular, the XAI models revealed that the B cell fraction (relative to all cells in a sample) exceeding 0.025, M0 macrophage fraction (relative to the total immune cell content) below 0.05, and NK T cell and CD8+ T cell fractions (based on cancer type-specific arbitrary units) above 0.075 and 0.25, respectively, in the TME could enhance the ≥5-year survival in breast cancer patients. The findings could lead to accurate clinical predictions and enhanced immunotherapies, and to the design of innovative strategies to reprogram the breast TME.
登录
查看更多内容
影响因子：
7.3
作者：
Gao J;Aksoy BA;Dogrusoz U;Dresdner G;Gross B;Sumer SO;Sun Y;Jacobsen A;Sinha R;Larsson E;Cerami E;Sander C;Schultz N
通讯作者：
Schultz N
基于案例的集成学习系统，用于可解释的乳腺癌复发预测
影响因子：
7.5
作者：
Gu, Dongxiao;Su, Kaixiang;Zhao, Huimin
通讯作者：
Zhao, Huimin
影响因子：
3.3
作者：
Dilorenzo, Giuseppe;Telegrafo, Michele;Moschetta, Marco
通讯作者：
Moschetta, Marco
影响因子：
10.3
作者：
Bareche, Yacine;Buisseret, Laurence;Sotiriou, Christos
通讯作者：
Sotiriou, Christos
影响因子：
50.3
作者：
Allinen, M;Beroukhim, R;Polyak, K
通讯作者：
Polyak, K