Dataset Information

Network-guided modeling allows tumor-type independent prediction of sensitivity to all-trans-retinoic acid.

ABSTRACT:

Background

All-trans-retinoic acid (ATRA) is a differentiating agent used in the treatment of acute-promyelocytic-leukemia (APL) and it is under-exploited in other malignancies despite its low systemic toxicity. A rational/personalized use of ATRA requires the development of predictive tools allowing identification of sensitive cancer types and responsive individuals.

Materials and methods

RNA-sequencing data for 10 080 patients and 33 different tumor types were derived from the TCGA and Leucegene datasets and completely re-processed. The study was carried out using machine learning methods and network analysis.

Results

We profiled a large panel of breast-cancer cell-lines for in vitro sensitivity to ATRA and exploited the associated basal gene-expression data to initially generate a model predicting ATRA-sensitivity in this disease. Starting from these results and using a network-guided approach, we developed a generalized model (ATRA-21) whose validity extends to tumor types other than breast cancer. ATRA-21 predictions correlate with experimentally determined sensitivity in a large panel of cell-lines representative of numerous tumor types. In patients, ATRA-21 correctly identifies APL as the most sensitive acute-myelogenous-leukemia subtype and indicates that uveal-melanoma and low-grade glioma are top-ranking diseases as for average predicted responsiveness to ATRA. There is a consistent number of tumor types for which higher ATRA-21 predictions are associated with better outcomes.

Conclusions

In summary, we generated a tumor-type independent ATRA-sensitivity predictor which consists of a restricted number of genes and has the potential to be applied in the clinics. Identification of the tumor types that are likely to be generally sensitive to the action of ATRA paves the way to the design of clinical studies in the context of these diseases. In addition, ATRA-21 may represent an important diagnostic tool for the selection of individual patients who may benefit from ATRA-based therapeutic strategies also in tumors characterized by lower average sensitivity.

SUBMITTER: Bolis M

PROVIDER: S-EPMC5834014 | biostudies-literature | 2017 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Network-guided modeling allows tumor-type independent prediction of sensitivity to all-trans-retinoic acid.

Bolis M M Garattini E E Paroni G G Zanetti A A Kurosaki M M Castrignanò T T Garattini S K SK Biancardi F F Barzago M M MM Gianni' M M Terao M M Pattini L L Fratelli M M

Annals of oncology : official journal of the European Society for Medical Oncology 20170301 3

<h4>Background</h4>All-trans-retinoic acid (ATRA) is a differentiating agent used in the treatment of acute-promyelocytic-leukemia (APL) and it is under-exploited in other malignancies despite its low systemic toxicity. A rational/personalized use of ATRA requires the development of predictive tools allowing identification of sensitive cancer types and responsive individuals.<h4>Materials and methods</h4>RNA-sequencing data for 10 080 patients and 33 different tumor types were derived from the T ...[more]

PMID: 27993792

Similar Datasets

Project description:BackgroundDrug sensitivity prediction and drug responsive biomarker selection on high-throughput genomic data is a critical step in drug discovery. Many computational methods have been developed to serve this purpose including several deep neural network models. However, the modular relations among genomic features have been largely ignored in these methods. To overcome this limitation, the role of the gene co-expression network on drug sensitivity prediction is investigated in this study.MethodsIn this paper, we first introduce a network-based method to identify representative features for drug response prediction by using the gene co-expression network. Then, two graph-based neural network models are proposed and both models integrate gene network information directly into neural network for outcome prediction. Next, we present a large-scale comparative study among the proposed network-based methods, canonical prediction algorithms (i.e., Elastic Net, Random Forest, Partial Least Squares Regression, and Support Vector Regression), and deep neural network models for drug sensitivity prediction. All the source code and processed datasets in this study are available at https://github.com/compbiolabucf/drug-sensitivity-prediction .ResultsIn the comparison of different feature selection methods and prediction methods on a non-small cell lung cancer (NSCLC) cell line RNA-seq gene expression dataset with 50 different drug treatments, we found that (1) the network-based feature selection method improves the prediction performance compared to Pearson correlation coefficients; (2) Random Forest outperforms all the other canonical prediction algorithms and deep neural network models; (3) the proposed graph-based neural network models show better prediction performance compared to deep neural network model; (4) the prediction performance is drug dependent and it may relate to the drug's mechanism of action.ConclusionsNetwork-based feature selection method and prediction models improve the performance of the drug response prediction. The relations between the genomic features are more robust and stable compared to the correlation between each individual genomic feature and the drug response in high dimension and low sample size genomic datasets.

Project description:BACKGROUND:The understanding of the importance of RNA has dramatically changed over recent years. As in the case of proteins, the function of an RNA molecule is encoded in its tertiary structure, which in turn is determined by the molecule's sequence. The prediction of tertiary structures of complex RNAs is still a challenging task. RESULTS:Using the observation that RNA sequences from the same RNA family fold into conserved structure, we test herein whether parallel modeling of RNA homologs can improve ab initio RNA structure prediction. EvoClustRNA is a multi-step modeling process, in which homologous sequences for the target sequence are selected using the Rfam database. Subsequently, independent folding simulations using Rosetta FARFAR and SimRNA are carried out. The model of the target sequence is selected based on the most common structural arrangement of the common helical fragments. As a test, on two blind RNA-Puzzles challenges, EvoClustRNA predictions ranked as the first of all submissions for the L-glutamine riboswitch and as the second for the ZMP riboswitch. Moreover, through a benchmark of known structures, we discovered several cases in which particular homologs were unusually amenable to structure recovery in folding simulations compared to the single original target sequence. CONCLUSION:This work, for the first time to our knowledge, demonstrates the importance of the selection of the target sequence from an alignment of an RNA family for the success of RNA 3D structure prediction. These observations prompt investigations into a new direction of research for checking 3D structure "foldability" or "predictability" of related RNA sequences to obtain accurate predictions. To support new research in this area, we provide all relevant scripts in a documented and ready-to-use form. By exploring new ideas and identifying limitations of the current RNA 3D structure prediction methods, this work is bringing us closer to the near-native computational RNA 3D models.

Project description:Forty-two cell lines recapitulating mammary carcinoma heterogeneity were profiled for all-trans retinoic acid (ATRA) sensitivity. Luminal and ER(+) (estrogen-receptor-positive) cell lines are generally sensitive to ATRA, while refractoriness/low sensitivity is associated with a Basal phenotype and HER2 positivity. Indeed, only 2 Basal cell lines (MDA-MB157 and HCC-1599) are highly sensitive to the retinoid. Sensitivity of HCC-1599 cells is confirmed in xenotransplanted mice. Short-term tissue-slice cultures of surgical samples validate the cell-line results and support the concept that a high proportion of Luminal/ER(+) carcinomas are ATRA sensitive, while triple-negative (Basal) and HER2-positive tumors tend to be retinoid resistant. Pathway-oriented analysis of the constitutive gene-expression profiles in the cell lines identifies RAR? as the member of the retinoid pathway directly associated with a Luminal phenotype, estrogen positivity and ATRA sensitivity. RAR?3 is the major transcript in ATRA-sensitive cells and tumors. Studies in selected cell lines with agonists/antagonists confirm that RAR? is the principal mediator of ATRA responsiveness. RAR? over-expression sensitizes retinoid-resistant MDA-MB453 cells to ATRA anti-proliferative action. Conversely, silencing of RAR? in retinoid-sensitive SKBR3 cells abrogates ATRA responsiveness. All this is paralleled by similar effects on ATRA-dependent inhibition of cell motility, indicating that RAR? may mediate also ATRA anti-metastatic effects. We define gene sets of predictive potential which are associated with ATRA sensitivity in breast cancer cell lines and validate them in short-term tissue cultures of Luminal/ER(+) and triple-negative tumors. In these last models, we determine the perturbations in the transcriptomic profiles afforded by ATRA. The study provides fundamental information for the development of retinoid-based therapeutic strategies aimed at the stratified treatment of breast cancer subtypes.

Dataset Information

Network-guided modeling allows tumor-type independent prediction of sensitivity to all-trans-retinoic acid.

Background

Materials and methods

Results

Conclusions

Publications

Network-guided modeling allows tumor-type independent prediction of sensitivity to all-trans-retinoic acid.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets