1
|
Cernea A, Fernández-Martínez JL, deAndrés-Galiana EJ, Fernández-Ovies FJ, Alvarez-Machancoses O, Fernández-Muñiz Z, Saligan LN, Sonis ST. Robust pathway sampling in phenotype prediction. Application to triple negative breast cancer. BMC Bioinformatics 2020; 21:89. [PMID: 32164540 PMCID: PMC7068866 DOI: 10.1186/s12859-020-3356-6] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/23/2023] Open
Abstract
Background Phenotype prediction problems are usually considered ill-posed, as the amount of samples is very limited with respect to the scrutinized genetic probes. This fact complicates the sampling of the defective genetic pathways due to the high number of possible discriminatory genetic networks involved. In this research, we outline three novel sampling algorithms utilized to identify, classify and characterize the defective pathways in phenotype prediction problems, such as the Fisher’s ratio sampler, the Holdout sampler and the Random sampler, and apply each one to the analysis of genetic pathways involved in tumor behavior and outcomes of triple negative breast cancers (TNBC). Altered biological pathways are identified using the most frequently sampled genes and are compared to those obtained via Bayesian Networks (BNs). Results Random, Fisher’s ratio and Holdout samplers were more accurate and robust than BNs, while providing comparable insights about disease genomics. Conclusions The three samplers tested are good alternatives to Bayesian Networks since they are less computationally demanding algorithms. Importantly, this analysis confirms the concept of “biological invariance” since the altered pathways should be independent of the sampling methodology and the classifier used for their inference. Nevertheless, still some modifications are needed in the Bayesian networks to be able to sample correctly the uncertainty space in phenotype prediction problems, since the probabilistic parameterization of the uncertainty space is not unique and the use of the optimum network might falsify the pathways analysis.
Collapse
Affiliation(s)
- Ana Cernea
- Group of Inverse Problems, Optimization and Machine Learning, Department of Mathematics, University of Oviedo, C/ Federico García-Lorca, 18, 33007, Oviedo, Spain
| | - Juan Luis Fernández-Martínez
- Group of Inverse Problems, Optimization and Machine Learning, Department of Mathematics, University of Oviedo, C/ Federico García-Lorca, 18, 33007, Oviedo, Spain.
| | - Enrique J deAndrés-Galiana
- Group of Inverse Problems, Optimization and Machine Learning, Department of Mathematics, University of Oviedo, C/ Federico García-Lorca, 18, 33007, Oviedo, Spain.,Department of Informatics and Computer Science, University of Oviedo, C/ Federico García-Lorca, 18, 33007, Oviedo, Spain
| | - Francisco Javier Fernández-Ovies
- Group of Inverse Problems, Optimization and Machine Learning, Department of Mathematics, University of Oviedo, C/ Federico García-Lorca, 18, 33007, Oviedo, Spain
| | - Oscar Alvarez-Machancoses
- Group of Inverse Problems, Optimization and Machine Learning, Department of Mathematics, University of Oviedo, C/ Federico García-Lorca, 18, 33007, Oviedo, Spain
| | - Zulima Fernández-Muñiz
- Group of Inverse Problems, Optimization and Machine Learning, Department of Mathematics, University of Oviedo, C/ Federico García-Lorca, 18, 33007, Oviedo, Spain
| | - Leorey N Saligan
- National Institutes of Health, National Institute of Nursing Research, Bethesda, MD, USA
| | - Stephen T Sonis
- Primary Endpoint Solutions, Watertown, MA, USA.,Brigham and Women's Hospital and the Dana-Farber Cancer Institute, Boston, MA, USA
| |
Collapse
|
2
|
Fernández-Martínez JL, de Andrés-Galiana EJ, Fernández-Ovies FJ, Cernea A, Kloczkowski A. Robust Sampling of Defective Pathways in Multiple Myeloma. Int J Mol Sci 2019; 20:ijms20194681. [PMID: 31546608 PMCID: PMC6801400 DOI: 10.3390/ijms20194681] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2019] [Revised: 09/12/2019] [Accepted: 09/19/2019] [Indexed: 11/16/2022] Open
Abstract
We present the analysis of defective pathways in multiple myeloma (MM) using two recently developed sampling algorithms of the biological pathways: The Fisher's ratio sampler, and the holdout sampler. We performed the retrospective analyses of different gene expression datasets concerning different aspects of the disease, such as the existing difference between bone marrow stromal cells in MM and healthy controls (HC), the gene expression profiling of CD34+ cells in MM and HC, the difference between hyperdiploid and non-hyperdiploid myelomas, and the prediction of the chromosome 13 deletion, to provide a deeper insight into the molecular mechanisms involved in the disease. Our analysis has shown the importance of different altered pathways related to glycosylation, infectious disease, immune system response, different aspects of metabolism, DNA repair, protein recycling and regulation of the transcription of genes involved in the differentiation of myeloid cells. The main difference in genetic pathways between hyperdiploid and non-hyperdiploid myelomas are related to infectious disease, immune system response and protein recycling. Our work provides new insights on the genetic pathways involved in this complex disease and proposes novel targets for future therapies.
Collapse
Affiliation(s)
- Juan Luis Fernández-Martínez
- Group of Inverse Problems, Optimization and Machine Learning, Department of Mathematics, University of Oviedo, Oviedo 33007, Asturias, Spain.
| | - Enrique J de Andrés-Galiana
- Group of Inverse Problems, Optimization and Machine Learning, Department of Mathematics, University of Oviedo, Oviedo 33007, Asturias, Spain.
- Department of Computer Science, University of Oviedo, Oviedo 33007, Asturias, Spain.
| | - Francisco Javier Fernández-Ovies
- Group of Inverse Problems, Optimization and Machine Learning, Department of Mathematics, University of Oviedo, Oviedo 33007, Asturias, Spain.
| | - Ana Cernea
- Group of Inverse Problems, Optimization and Machine Learning, Department of Mathematics, University of Oviedo, Oviedo 33007, Asturias, Spain.
| | - Andrzej Kloczkowski
- Battelle Center for Mathematical Medicine, Nationwide Children's Hospital, Columbus, OH 43205, USA.
- Department of Pediatrics, The Ohio State University, Columbus, OH 43205, USA.
- Future Value Creation Research Center, Graduate School of Informatics, Nagoya University, Nagoya 464-8601, Japan.
| |
Collapse
|