Integrative Network Fusion: A Multi-Omics Approach in Molecular Profiling

Chierici, Marco; Bussola, Nicole; Marcolini, Alessia; Francescatto, Margherita; Zandonà, Alessandro; Trastulla, Lucia; Agostinelli, Claudio; Jurman, Giuseppe; Furlanello, Cesare

doi:10.3389/fonc.2020.01065

Cited by 38 publications

(22 citation statements)

References 110 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One advantage of such methods is that the network doesn’t get more complex with additional omics as their overall size is based on the number of samples, not the number of features. The resulting integrated graph can then be used as input for ML models [99] , [101] , [102] for clustering, subtype discovery or survival prediction.…”

Section: Main Integration Strategiesmentioning

confidence: 99%

Integration strategies of multi-omics data for machine learning analysis

Picard

Scott‐Boyer

Bodein

et al. 2021

Computational and Structural Biotechnology Journal

269

185

View full text Add to dashboard Cite

Graphical abstract Schematic representation of the main strategies for multi-omics datasets integration. A) Early integration concatenates all omics datasets into a single matrix on which machine learning model can be applied. B) Mixed integration first independently transforms or maps each omics block into a new representation before combining them for downstream analysis. C) Intermediate integration simultaneously transforms the original datasets into common and omics-specific representations. D) Late integration analyses each omics separately and combines their final predictions. E) Hierarchical integration bases the integration of datasets on prior regulatory relationships between omics layers.

show abstract

Section: Main Integration Strategiesmentioning

confidence: 99%

Integration strategies of multi-omics data for machine learning analysis

Picard

Scott‐Boyer

Bodein

et al. 2021

Computational and Structural Biotechnology Journal

269

185

View full text Add to dashboard Cite

show abstract

“…Estrogen receptor (ER) status is used in classifying breast cancer (Heng et al 2017;Søkilde et al 2019) as well as for prognosis and treatment eg (Gu et al 2020;López-Sánchez et al 2020;Reis-Filho and Pusztai 2011). The availability of the National Cancer Institute Cancer Genome Atlas has facilitated these investigations (Chierici et al 2020;Kan et al 2018;Li et al 2020) and has been used to assess the contribution of individual chaperones on the basis of their normalized expression levels and then identify potential gene networks important in breast cancer (Buttacavoli et al 2021;Klimczak et al 2019;Zoppino et al 2018).…”

Section: Introductionmentioning

confidence: 99%

Cluster analyses of the TCGA and a TMA dataset using the coexpression of HSP27 and CRYAB improves alignment with clinical-pathological parameters of breast cancer and suggests different epichaperome influences for each sHSP

Quinlan

Figeuredo

Mongan

et al. 2022

Cell Stress and Chaperones

View full text Add to dashboard Cite

Our cluster analysis of the Cancer Genome Atlas for co-expression of HSP27 and CRYAB in breast cancer patients identified three patient groups based on their expression level combination (high HSP27 + low CRYAB; low HSP27 + high CRYAB; similar HSP27 + CRYAB). Our analyses also suggest that there is a statistically significant inverse relationship between HSP27 and CRYAB and known clinicopathological markers in breast cancer. Screening an unbiased 248 breast cancer patient tissue microarray (TMA) for the protein expression of HSP27 and phosphorylated HSP27 (HSP27-82pS) with CRYAB also identified three patient groups based on HSP27 and CRYAB expression levels. TMA24 also had recorded clinical-pathological parameters, such as ER and PR receptor status, patient survival, and TP53 mutation status. High HSP27 protein levels were significant with ER and PR expression. HSP27-82pS associated with the best patient survival (Log Rank test). High CRYAB expression in combination with wild-type TP53 was significant for patient survival, but a different patient outcome was observed when mutant TP53 was combined with high CRYAB expression. Our data suggest that HSP27 and CRYAB have different epichaperome influences in breast cancer, but more importantly evidence the value of a cluster analysis that considers their coexpression. Our approach can deliver convergence for archival datasets as well as those from recent treatment and patient cohorts and can align HSP27 and CRYAB expression to important clinical-pathological features of breast cancer.

show abstract

“…A recent study by Chierici et al proposed a network-based framework, Integrative Network Fusion (INF), to identify multi-omics predictive biomarkers. It is based on machine learning models and was tested on three different datasets originated from The Cancer Genome Atlas [ 21 ].…”

Section: Introductionmentioning

confidence: 99%

Patient-Specific Network for Personalized Breast Cancer Therapy with Multi-Omics Data

Cava

Sabetian

Castiglioni

2021

Entropy

View full text Add to dashboard Cite

The development of new computational approaches that are able to design the correct personalized drugs is the crucial therapeutic issue in cancer research. However, tumor heterogeneity is the main obstacle to developing patient-specific single drugs or combinations of drugs that already exist in clinics. In this study, we developed a computational approach that integrates copy number alteration, gene expression, and a protein interaction network of 73 basal breast cancer samples. 2509 prognostic genes harboring a copy number alteration were identified using survival analysis, and a protein–protein interaction network considering the direct interactions was created. Each patient was described by a specific combination of seven altered hub proteins that fully characterize the 73 basal breast cancer patients. We suggested the optimal combination therapy for each patient considering drug–protein interactions. Our approach is able to confirm well-known cancer related genes and suggest novel potential drug target genes. In conclusion, we presented a new computational approach in breast cancer to deal with the intra-tumor heterogeneity towards personalized cancer therapy.

show abstract

Integrative Network Fusion: A Multi-Omics Approach in Molecular Profiling

Cited by 38 publications

References 110 publications

Integration strategies of multi-omics data for machine learning analysis

Integration strategies of multi-omics data for machine learning analysis

Cluster analyses of the TCGA and a TMA dataset using the coexpression of HSP27 and CRYAB improves alignment with clinical-pathological parameters of breast cancer and suggests different epichaperome influences for each sHSP

Patient-Specific Network for Personalized Breast Cancer Therapy with Multi-Omics Data

Contact Info

Product

Resources

About