scholarly journals Predicting Deep Learning Based Multi-Omics Parallel Integration Survival Subtypes in Lung Cancer Using Reverse Phase Protein Array Data

Biomolecules ◽  
2020 ◽  
Vol 10 (10) ◽  
pp. 1460 ◽  
Author(s):  
Satoshi Takahashi ◽  
Ken Asada ◽  
Ken Takasawa ◽  
Ryo Shimoyama ◽  
Akira Sakai ◽  
...  

Mortality attributed to lung cancer accounts for a large fraction of cancer deaths worldwide. With increasing mortality figures, the accurate prediction of prognosis has become essential. In recent years, multi-omics analysis has emerged as a useful survival prediction tool. However, the methodology relevant to multi-omics analysis has not yet been fully established and further improvements are required for clinical applications. In this study, we developed a novel method to accurately predict the survival of patients with lung cancer using multi-omics data. With unsupervised learning techniques, survival-associated subtypes in non-small cell lung cancer were first detected using the multi-omics datasets from six categories in The Cancer Genome Atlas (TCGA). The new subtypes, referred to as integration survival subtypes, clearly divided patients into longer and shorter-surviving groups (log-rank test: p = 0.003) and we confirmed that this is independent of histopathological classification (Chi-square test of independence: p = 0.94). Next, an attempt was made to detect the integration survival subtypes using only one categorical dataset. Our machine learning model that was only trained on the reverse phase protein array (RPPA) could accurately predict the integration survival subtypes (AUC = 0.99). The predicted subtypes could also distinguish between high and low risk patients (log-rank test: p = 0.012). Overall, this study explores novel potentials of multi-omics analysis to accurately predict the prognosis of patients with lung cancer.

2021 ◽  
Author(s):  
Nan Wang ◽  
Li Zhang ◽  
Qi Ying ◽  
Zhentao Song ◽  
Aiping Lu ◽  
...  

Abstract Background: Systematic quantification of phosphoprotein within cell signaling networks in solid tissues remains challenging and precise quantification in large scale samples has great potential for biomarker identification and validation. Methods:We developed a reverse phase protein array (RPPA) based phosphor-antibody characterization workflow by taking advantage of the lysis buffer compatible with alkaline phosphatase (AP) treatment and here termed it as a bottom-up antibody screening that differs from the conventional RPPA antibody validation procedure and applied it onto fresh frozen and formalin-fixed and paraffin-embedded tissue (FFPE) to test its applicability.Results:We tested the feasibility of this method by screening 106 phospho-antibodies with RPPA first followed by western blots on a panel of cell lines and demonstrated that AP treatment could serve as an independent factor that can be adopted for rapid RPPA phospho-antibody selection. We also performed studies on different clinical materials. For fresh frozen (FF) samples, pre-selected highly-specific antibodies showed a desirable data reproducibility and antibody specificity based on AP treatment indicating a potential for fresh tissue-based phospho-protein RPPA profiling. Of further clinical significance, using the same approach, based on two sets of FFPE samples from 63 melanoma and 40 lung cancer patients, we showed great interexperimental reproducibility and significant correlation with pathological markers MelanA for melanoma as well as a panel of lung cancer biomarkers for subtyping (EGFR, Napsin A, p63/p40, TTF1 and CK7) generating meaningful data that match clinical features. Conclusions:Our findings establish a highly efficient approach for phospho-antibody characterization by taking advantage of RPPA whereby the same methodology can be applied for tissue-based proteomics and phosphoproteomics in clinical assay development and application.


Author(s):  
Silvia von der Heyde ◽  
Johanna Sonntag ◽  
Frank Kramer ◽  
Christian Bender ◽  
Ulrike Korf ◽  
...  

PLoS ONE ◽  
2012 ◽  
Vol 7 (6) ◽  
pp. e38686 ◽  
Author(s):  
Sylvie Troncale ◽  
Aurélie Barbet ◽  
Lamine Coulibaly ◽  
Emilie Henry ◽  
Beilei He ◽  
...  

Microarrays ◽  
2015 ◽  
Vol 4 (4) ◽  
pp. 520-539 ◽  
Author(s):  
Astrid Wachter ◽  
Stephan Bernhardt ◽  
Tim Beissbarth ◽  
Ulrike Korf

2012 ◽  
Vol 48 ◽  
pp. S150 ◽  
Author(s):  
L. De Koning ◽  
S. Troncale ◽  
A. Barbet ◽  
L. Coulibaly ◽  
E. Henry ◽  
...  

2021 ◽  
pp. jbt.2021-3202-001
Author(s):  
Cristian Coarfa ◽  
Sandra L. Grimm ◽  
Kimal Rajapakshe ◽  
Dimuthu Perera ◽  
Hsin-Yi Lu ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document