Scholarlink

<p>Contemporary risk models in chronic myelomonocytic leukemia (CMML) focus on the prognostic relevance of individual rather than concurrent mutations. In the current study of 605 Mayo Clinic patients with CMML, we applied machine-learning algorithms in order to examine the influence of cooperative mutational interactions on blast transformation (BT). A hierarchical clustering algorithm was developed and tailored for patient stratification using survival outcomes and co-occurrence of genomic alterations. Five molecular clusters were identified with 3-year blast BT rates ranging from 0% to 100% (AUC at 3 years 0.78). A subsequent Cox regression analysis confirmed independent detrimental impact of specific mutations or their combinations including <i>NPM1</i> (HR 26.7; <i>p</i> &lt; 0.01), “<i>NRAS</i> + <i>SETBP1</i>” (HR 12.6; <i>p</i> &lt; 0.01), “<i>ASXL1</i> + <i>BCOR”</i> (HR 8.4; <i>p</i> &lt; 0.01), “<i>ASXL1</i> + <i>RUNX1</i>” (HR 2.2, <i>p</i> &lt; 0.01), <i>JAK2</i> (HR 2.1; <i>p</i> &lt; 0.01), and “<i>ASXL1</i> + <i>TET2</i>” (HR 1.7; <i>p</i> = 0.02) while “<i>PHF6</i>+wild-type <i>ASXL1”</i> (HR 5.61e−10; <i>p</i> &lt; 0.01) had a favorable impact. Furthermore, compared to <i>NPM1</i> wild-type cases<i>, NPM1</i>-mutated patients were less likely to have co-occurring mutations involving <i>ASXL1</i> (0% vs. 43%, <i>p</i> &lt; 0.01), <i>RUNX1</i> (0% vs. 17%, <i>p</i> = 0.02), and <i>SRSF2</i> (7% vs. 39%, <i>p</i> &lt; 0.01) and were more likely <i>DNMT3A</i> (71% vs. 7%, <i>p</i> &lt; 0.01). The prognostic relevance of “<i>NRAS</i> + <i>SETBP1</i>”, “<i>ASXL1</i> + <i>RUNX1</i>”, <i>NPM1</i> and <i>BCOR</i> was validated in an external cohort from Italy (<i>N</i> = 501). Taken together, these observations highlight i) the possibility of prognostic interaction of mutations in CMML that should be considered in the development of future risk models and ii) the distinct genotypic and prognostic characteristics of <i>NPM1</i>-mutated CMML.</p><p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CMML2AML: machine-learning discovery of co-mutations and specific single mutations predictive of blast transformation in chronic myelomonocytic leukemia

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月12日

查看全文
  • Saubia Fathima,
  • Lior Rokach,
  • Muhammad Yousuf,
  • Priyansh Faldu,
  • Ali Alsugair,
  • Clifford Csizmar,
  • Merry Nakhleh,
  • Abhishek A. Mangaonkar,
  • Animesh Pardanani,
  • Luca Lanino,
  • Alessia Campagna,
  • Giulia Maggioni,
  • Noushin Farnoud,
  • Raajit Rampal,
  • Kaaren K. Reichard,
  • Rong He,
  • Naseema Gangat,
  • Mrinal M. Patnaik,
  • Matteo G. Della Porta,
  • Ayalew Tefferi

摘要

Contemporary risk models in chronic myelomonocytic leukemia (CMML) focus on the prognostic relevance of individual rather than concurrent mutations. In the current study of 605 Mayo Clinic patients with CMML, we applied machine-learning algorithms in order to examine the influence of cooperative mutational interactions on blast transformation (BT). A hierarchical clustering algorithm was developed and tailored for patient stratification using survival outcomes and co-occurrence of genomic alterations. Five molecular clusters were identified with 3-year blast BT rates ranging from 0% to 100% (AUC at 3 years 0.78). A subsequent Cox regression analysis confirmed independent detrimental impact of specific mutations or their combinations including NPM1 (HR 26.7; p < 0.01), “NRAS + SETBP1” (HR 12.6; p < 0.01), “ASXL1 + BCOR” (HR 8.4; p < 0.01), “ASXL1 + RUNX1” (HR 2.2, p < 0.01), JAK2 (HR 2.1; p < 0.01), and “ASXL1 + TET2” (HR 1.7; p = 0.02) while “PHF6+wild-type ASXL1” (HR 5.61e−10; p < 0.01) had a favorable impact. Furthermore, compared to NPM1 wild-type cases, NPM1-mutated patients were less likely to have co-occurring mutations involving ASXL1 (0% vs. 43%, p < 0.01), RUNX1 (0% vs. 17%, p = 0.02), and SRSF2 (7% vs. 39%, p < 0.01) and were more likely DNMT3A (71% vs. 7%, p < 0.01). The prognostic relevance of “NRAS + SETBP1”, “ASXL1 + RUNX1”, NPM1 and BCOR was validated in an external cohort from Italy (N = 501). Taken together, these observations highlight i) the possibility of prognostic interaction of mutations in CMML that should be considered in the development of future risk models and ii) the distinct genotypic and prognostic characteristics of NPM1-mutated CMML.