Hardwiring Mechanism into Predicting Cancer Phenotypes by Computational Learning

通过计算学习预测癌症表型的硬连线机制

• 批准号: 10328651
• 负责人: Luigi Marchionni
• 金额: $ 23.49万
• 依托单位: WEILL MEDICAL COLL OF CORNELL UNIV
• 依托单位国家: 美国
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-04-05 至 2023-03-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10328651
• 关键词: Hardwiring; Mechanism; into; Predicting; Cancer

DESCRIPTION (provided by applicant): Few biomarkers derived from genome scale data have translated into improved clinical classification of cancer subtypes, in spite of the wealth of available genome-wide studies and of the corresponding application of numerous statistical algorithms. This widespread shortcoming derives from the pervasive use of "off the shelf" algorithms and machine learning techniques developed for image classification and language processing, which are naïve of the underlying biology of the system. Furthermore, for genome-wide data, the number of samples is often small relative to the number of potential candidate biomarkers, resulting in variable accuracy on independent test data despite high accuracy in the samples used for discovery, which contributes to the failure of clinical biomarkers. This problem - so called "curse of dimensionality" - is further exacerbated by the prohibitive cost of dramatically increasing sample size and by patient stratification into smaller subgroups for personalized and precision medicine. Disease phenotypes arise from distinct and specific perturbations in selected networks and pathways defined by the interactions of their molecular constituents. In cancer, these perturbations may reside in gene regulatory networks topology and state, in cell signaling activity, or in metabolic conditions. We hypothesize that by leveragin such prior biological information on cancer biology we will be able to reduce model complexity and build mechanistically justified predictive models. To pursue this hypothesis, we will develop an analytical framework to embed mechanistic constraints derived from network biology into the statistical learning process itself. Hence, this application will develop a novel suite of statistial learning algorithms that embed (Aim 1) gene expression regulatory networks, (Aim 2) cell signaling activity, and (Aim 3) metabolism to classify breast and prostate cancer. Throughout the study we will work closely with clinical collaborators to ensure that our method improve over and above current predictive and prognostic models. Finally, since in our study we will also generate mechanistic classifiers based on gene expression measurements obtained from clinical assays that are already commercially available (i.e., MammaPrint®, and Decipher®), our innovative models and predictors will be also readily available for clinical translation. Our mechanism-driven classifiers will simultaneously have greater accuracy and interpretability than classifiers developed without regard for the underlying biology of the disease. Furthermore, embedding biological mechanisms in the classifiers will also facilitate the identification of alternative therapeutic targets specific to each cancer subtype, potentially improving patient prognosis and health outcomes. Finally, the substantial curation of molecular pathways and biological networks we will carry on in the project will also provide a powerful resource for futur studies, and the methodologies we will develop will be also applicable to other cancer and other human diseases, like neurodegenerative disorders, hearth disease, and diabetes.

描述（由申请人提供）：尽管有大量可用的全基因组研究以及大量统计算法的相应应用，但很少有源自基因组规模数据的生物标志物能够转化为改进的癌症亚型临床分类。这种普遍存在的缺陷源于普遍使用为图像分类和语言处理而开发的“现成”算法和机器学习技术，而这些技术对系统的底层生物学来说是幼稚的。此外，对于全基因组数据，相对于潜在候选生物标志物的数量，样本数量通常较小，尽管用于发现的样本具有较高的准确性，但导致独立测试数据的准确性存在差异，这导致了临床生物标志物的失败。这个问题——所谓的“维数灾难”——因大幅增加样本量的高昂成本以及将患者分层为更小的亚组以进行个性化和精准医疗而进一步加剧。疾病表型源自于由其分子成分的相互作用定义的选定网络和途径中的独特且特定的扰动。在癌症中，这些扰动可能存在于基因调控网络拓扑和状态、细胞信号传导活动或代谢条件中。我们假设，通过利用癌症生物学的此类先前生物学信息，我们将能够降低模型复杂性并建立机械上合理的预测模型。为了实现这一假设，我们将开发一个分析框架，将源自网络生物学的机械约束嵌入到统计学习过程本身中。因此，该应用程序将开发一套新颖的统计学习算法，嵌入（目标 1）基因表达调控网络、（目标 2）细胞信号传导活动和（目标 3）代谢来对乳腺癌和前列腺癌进行分类。在整个研究过程中，我们将与临床合作者密切合作，以确保我们的方法优于当前的预测和预后模型。最后，由于在我们的研究中，我们还将根据从已经商业化的临床检测（即 MammaPrint® 和 Decipher®）获得的基因表达测量结果生成机械分类器，因此我们的创新模型和预测器也将随时可用于临床转化。我们的机制驱动的分类器将同时比不考虑疾病的基础生物学而开发的分类器具有更高的准确性和可解释性。此外，在分类器中嵌入生物机制还将有助于识别每种癌症亚型特有的替代治疗靶点，从而有可能改善患者的预后和健康结果。最后，我们将在该项目中进行的分子途径和生物网络的实质性管理也将为未来的研究提供强大的资源，我们将开发的方法也将适用于其他癌症和其他人类疾病，如神经退行性疾病、心脏病和糖尿病。

项目成果

Synthesizer: Expediting synthesis studies from context-free data with information retrieval techniques.

合成器：利用信息检索技术加速上下文无关数据的合成研究。

• DOI: 10.1371/journal.pone.0175860
• 发表时间: 2017
• 期刊: PloS one
• 影响因子: 3.7
• 作者: Gandy,LisaM;Gumm,Jordan;Fertig,Benjamin;Thessen,Anne;Kennish,MichaelJ;Chavan,Sameer;Marchionni,Luigi;Xia,Xiaoxin;Shankrit,Shambhavi;Fertig,ElanaJ
• 通讯作者: Fertig,ElanaJ

Donor-derived acute myeloid leukemia in solid organ transplantation.

• DOI: 10.1111/ajt.17174
• 发表时间: 2022-12
• 期刊: American journal of transplantation : official journal of the American Society of Transplantation and the American Society of Transplant Surgeons

RNA-sequencing highlights differential regulated pathways involved in cell cycle and inflammation in orbitofacial neurofibromas.

• DOI: 10.1111/bpa.13007
• 发表时间: 2022-01
• 期刊: Brain pathology (Zurich, Switzerland)
• 作者: Imada EL;Strianese D;Edward DP;alThaqib R;Price A;Arnold A;Al-Hussain H;Marchionni L;Rodriguez FJ
• 通讯作者: Rodriguez FJ

Using biological constraints to improve prediction in precision oncology.

• DOI: 10.1016/j.isci.2023.106108
• 发表时间: 2023-03-17
• 期刊: ISCIENCE
• 影响因子: 5.8
• 作者: Omar, Mohamed;Dinalankara, Wikum;Mulder, Lotte;Coady, Tendai;Zanettini, Claudio;Imada, Eddie Luidy;Younes, Laurent;Geman, Donald;Marchionni, Luigi
• 通讯作者: Marchionni, Luigi

MicroRNA expression profiling of Xp11 renal cell carcinoma.

• DOI: 10.1016/j.humpath.2017.03.011
• 发表时间: 2017-09
• 期刊: Human pathology
• 影响因子: 3.3
• 作者: Marchionni L;Hayashi M;Guida E;Ooki A;Munari E;Jabboure FJ;Dinalankara W;Raza A;Netto GJ;Hoque MO;Argani P
• 通讯作者: Argani P