1
|
Bohannan ZS, Coffman F, Mitrofanova A. Random survival forest model identifies novel biomarkers of event-free survival in high-risk pediatric acute lymphoblastic leukemia. Comput Struct Biotechnol J 2022; 20:583-597. [PMID: 35116134 PMCID: PMC8777142 DOI: 10.1016/j.csbj.2022.01.003] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2021] [Revised: 12/30/2021] [Accepted: 01/01/2022] [Indexed: 12/16/2022] Open
Abstract
High-risk pediatric B-ALL patients experience 5-year negative event rates up to 25%. Although some biomarkers of relapse are utilized in the clinic, their ability to predict outcomes in high-risk patients is limited. Here, we propose a random survival forest (RSF) machine learning model utilizing interpretable genomic inputs to predict relapse/death in high-risk pediatric B-ALL patients. We utilized whole exome sequencing profiles from 156 patients in the TARGET-ALL study (with samples collected at presentation) further stratified into training and test cohorts (109 and 47 patients, respectively). To avoid overfitting and facilitate the interpretation of machine learning results, input genomic variables were engineered using a stepwise approach involving univariable Cox models to select variables directly associated with outcomes, genomic coordinate-based analysis to select mutational hotspots, and correlation analysis to eliminate feature co-linearity. Model training identified 7 genomic regions most predictive of relapse/death-free survival. The test cohort error rate was 12.47%, and a polygenic score based on the sum of the top 7 variables effectively stratified patients into two groups, with significant differences in time to relapse/death (log-rank P = 0.001, hazard ratio = 5.41). Our model outperformed other EFS modeling approaches including an RSF using gold-standard prognostic variables (error rate = 24.35%). Validation in 174 standard-risk patients and 3 patients who failed to respond to induction therapy confirmed that our RSF model and polygenic score were specific to high-risk disease. We propose that our feature selection/engineering approach can increase the clinical interpretability of RSF, and our polygenic score could be utilized for enhance clinical decision-making in high-risk B-ALL.
Collapse
Affiliation(s)
- Zachary S. Bohannan
- Rutgers, The State University of New Jersey, School of Health Professions, Department of Health Informatics, 65 Bergen Street, Suite 120, Newark, NJ 07107-1709, United States
| | - Frederick Coffman
- Rutgers, The State University of New Jersey, School of Health Professions, Department of Health Informatics, 65 Bergen Street, Suite 120, Newark, NJ 07107-1709, United States
| | - Antonina Mitrofanova
- Rutgers, The State University of New Jersey, School of Health Professions, Department of Health Informatics, 65 Bergen Street, Suite 120, Newark, NJ 07107-1709, United States
| |
Collapse
|
2
|
Chamseddine AN, Cabrero M, Wei Y, Ganan-Gomez I, Colla S, Takahashi K, Yang H, Bohannan ZS, Garcia-Manero G. PDE4 Differential Expression Is a Potential Prognostic Factor and Therapeutic Target in Patients With Myelodysplastic Syndrome and Chronic Myelomonocytic Leukemia. Clin Lymphoma Myeloma Leuk 2017; 16 Suppl:S67-73. [PMID: 27521329 DOI: 10.1016/j.clml.2016.02.026] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/09/2016] [Accepted: 02/09/2016] [Indexed: 11/29/2022]
Abstract
BACKGROUND (OR PURPOSE) Inflammation has an essential role in the pathogenesis of myelodysplastic syndromes (MDS). Its expression is controlled by phosphodiesterase 4 (PDE4). Thus, PDE4 inhibitors might be useful therapeutic targets for MDS. PATIENTS (OR MATERIALS) AND METHODS We evaluated the expression of each isoform of PDE4 (A, B, C, and D) using transcriptomic profiling and examined the potential impact on the outcome of patients with MDS in terms of survival and response to hypomethylating agents. Total RNA was extracted from CD34(+) bone marrow hematopoietic cells from healthy individuals (n = 10) and patients with MDS (n = 24) or chronic myelomonocytic leukemia (n = 19). RESULTS The study cohort had a median follow-up period of 21.2 months (range, 0.2-68 months) and a median overall survival of 17.6 months (95% confidence interval, 9.6-25.6). The main finding of the present study was that PDE4 mean expression was generally higher in patients with MDS than in healthy individuals. Also, upregulated PDE4 expression seemed to have a possible negative effect on survival (P > .05). Moreover, lower, compared with higher, mean PDE4A and PDE4C expression is indicative of a response to a hypomethylating agent (0.09 and 0.03 vs. 0.54 and 0.49, respectively; P > .05). CONCLUSION These results should be confirmed in a larger patient cohort. PDE4 expression could be an effective potential prognostic factor and therapeutic target for patients with MDS and chronic myelomonocytic leukemia. The role of PDE4 inhibitors should be explored in vitro against MDS cell lines and in preclinical mouse models of MDS.
Collapse
Affiliation(s)
- Ali N Chamseddine
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX.
| | - Monica Cabrero
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Yue Wei
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Irene Ganan-Gomez
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Simona Colla
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Koichi Takahashi
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Hui Yang
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX
| | - Zachary S Bohannan
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX
| | | |
Collapse
|
3
|
Yang H, Fang Z, Wei Y, Bohannan ZS, Gañán-Gómez I, Pierola AA, Paradiso LJ, Iwamura H, Garcia-Manero G. Preclinical activity of FF-10501-01, a novel inosine-5'-monophosphate dehydrogenase inhibitor, in acute myeloid leukemia. Leuk Res 2017; 59:85-92. [PMID: 28599189 DOI: 10.1016/j.leukres.2017.05.016] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2017] [Revised: 05/22/2017] [Accepted: 05/23/2017] [Indexed: 01/20/2023]
Abstract
BACKGROUND FF-10501-01 is a selective inosine monophosphate dehydrogenase (IMPDH) inhibitor that has shown activity in cancer cell lines. We studied whether FF-10501-01 is effective in targeting a variety of hypomethylating agent (HMA)-sensitive and -resistant acute myelogenous leukemia (AML) cell lines. METHODS We treated multiple cell lines (including HMA-resistant cells) with FF-10501-01 and analyzed proliferation, apoptosis, and cell cycle status. We also assessed HMA-FF-10501-01 combinations and the ability of extracellular guanosine to rescue cell proliferation in FF-10501-01-treated cells. We performed high-performance liquid chromatography (HPLC) to study guanine nucleotide levels in treated and untreated cells. Finally, we studied the effects of FF-10501-01 in fresh peripheral blood cells taken from AML patients. RESULTS FF-10501-01 showed a strong dose-dependent effect on proliferation and induced apoptosis at approximately 30μM. The effects of FF-10501-01 treatment on cell cycle status were variable, with no statistically significant trends. Guanosine rescued proliferation in FF-10501-01-treated cells, and HPLC results showed significant decreases in phosphorylated guanosine levels in MOLM13 cells. FF-10501-01 effectively reduced proliferation at concentrations of 300μM and above in 3 primary AML samples. CONCLUSIONS FF-10501-01 effectively induces AML cell death and reduces AML peripheral blood cell proliferation by targeting guanine nucleotide biosynthesis regardless of HMA resistance status.
Collapse
Affiliation(s)
- Hui Yang
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Zhihong Fang
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Yue Wei
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Zachary S Bohannan
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Irene Gañán-Gómez
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | - Ana Alfonso Pierola
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX, United States
| | | | | | - Guillermo Garcia-Manero
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX, United States.
| |
Collapse
|
4
|
Chamseddine AN, Jabbour E, Kantarjian HM, Bohannan ZS, Garcia-Manero G. Unraveling Myelodysplastic Syndromes: Current Knowledge and Future Directions. Curr Oncol Rep 2016; 18:4. [PMID: 26700507 DOI: 10.1007/s11912-015-0489-2] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/16/2022]
Abstract
Myelodysplastic syndromes (MDS) affect more than 30,000 patients in the USA per year, most of whom are elderly, and these diseases are associated with dismal prognoses. The main features of MDS are ineffective hematopoiesis and aberrant myeloid differentiation. Furthermore, MDS are heterogeneous, both clinically and molecularly. This heterogeneity and the frequent occurrence of age-related comorbidities make the management of these diseases challenging. In fact, there have been no new drug approvals for MDS in the USA in the last 9 years, and few currently available investigational drugs are likely to be approved in the near future. Novel targeted treatment based on better understanding of the pathogenesis of MDS is needed to maximize patient outcomes. Here, we discuss new insights into diagnostic accuracy, prognostic assessment, pathogenic mechanisms, and effective treatments for MDS.
Collapse
Affiliation(s)
- Ali N Chamseddine
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, 1515 Holcombe Blvd, Houston, TX, 77015, USA
| | - Elias Jabbour
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, 1515 Holcombe Blvd, Houston, TX, 77015, USA
| | - Hagop M Kantarjian
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, 1515 Holcombe Blvd, Houston, TX, 77015, USA
| | - Zachary S Bohannan
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, 1515 Holcombe Blvd, Houston, TX, 77015, USA
| | - Guillermo Garcia-Manero
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, 1515 Holcombe Blvd, Houston, TX, 77015, USA.
| |
Collapse
|
5
|
Affiliation(s)
- Irene Gañán-Gómez
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Zachary S Bohannan
- Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | | |
Collapse
|