Dataset Information

Comparative study of computational methods for reconstructing genetic networks of cancer-related pathways.

ABSTRACT: Network reconstruction is an important yet challenging task in systems biology. While many methods have been recently proposed for reconstructing biological networks from diverse data types, properties of estimated networks and differences between reconstruction methods are not well understood. In this paper, we conduct a comprehensive empirical evaluation of seven existing network reconstruction methods, by comparing the estimated networks with different sparsity levels for both normal and tumor samples. The results suggest substantial heterogeneity in networks reconstructed using different reconstruction methods. Our findings also provide evidence for significant differences between networks of normal and tumor samples, even after accounting for the considerable variability in structures of networks estimated using different reconstruction methods. These differences can offer new insight into changes in mechanisms of genetic interaction associated with cancer initiation and progression.

SUBMITTER: Sedaghat N

PROVIDER: S-EPMC4179645 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparative study of computational methods for reconstructing genetic networks of cancer-related pathways.

Sedaghat Nafiseh N Saegusa Takumi T Randolph Timothy T Shojaie Ali A

Cancer informatics 20140921 Suppl 2

Network reconstruction is an important yet challenging task in systems biology. While many methods have been recently proposed for reconstructing biological networks from diverse data types, properties of estimated networks and differences between reconstruction methods are not well understood. In this paper, we conduct a comprehensive empirical evaluation of seven existing network reconstruction methods, by comparing the estimated networks with different sparsity levels for both normal and tumo ...[more]

PMID: 25288880

Similar Datasets

Project description:Esophageal cancer (EC) is a multifaceted disease. Our understanding of the involvement of esophageal microbiota in its pathogenesis and progression is limited, which is due to the lack of proper endoscopic sampling methods. Hereby, we conducted a comparative analysis of paired samples obtained through endoscopic brushing and cytosponge, aiming at assessing the feasibility of using cytosponge as a minimally invasive sampling way for studying esophageal microbiota. Our findings suggest that cytosponge sampling yielded significantly superior community richness and diversity compared to endoscopic brushing in both controls (non-cancerous) and EC individuals. The analysis of beta-diversity revealed distinct microbial community pattern in the genus diversity between the two sampling methods, underscoring the importance of selecting appropriate sampling methods to effectively characterize the esophageal microbiota. Specifically, Lactococcus and Serratia showed higher abundance in the samples collected by endoscopic brushing, while Alloprevotella and Leptotrichia were more enriched in the samples collected by cytosponge. These differences in dominant microbes were associated with metabolic pathways that particularly were related to host inflammation, such as pyruvate and glucose metabolisms. Notably, the phylogenetic levels of the microbiota indicated varied explanatory power for different detection purposes. This study underscores the substantial impact of sampling method selection on the acquisition of esophageal microbiota associated with the EC development, encompassing considerations of both abundance and diversity. This highlights the significance of selecting an appropriate sampling method for investigating the esophageal microbial status and studying the micro-environment in EC-related individuals.ImportanceThis study addresses a critical issue in esophageal cancer study by comparing two different sampling methods, endoscopic brushing and cytosponge, for investigating the esophageal microbiota. Our work highlights the suitability of the cytosponge technique as a minimally invasive sampling method for studying the esophageal microbiota and emphasizes the importance of selecting an appropriate sampling method to characterize the microbial community. Our findings have significant implications for advancing the understanding of the role of the esophageal microbiota in cancer development and will inform future research and clinical approaches in this field.

Project description:Anti-cancer peptides (ACPs) are known as potential therapeutics for cancer. Due to their unique ability to target cancer cells without affecting healthy cells directly, they have been extensively studied. Many peptide-based drugs are currently evaluated in the preclinical and clinical trials. Accurate identification of ACPs has received considerable attention in recent years; as such, a number of machine learning-based methods for in silico identification of ACPs have been developed. These methods promote the research on the mechanism of ACPs therapeutics against cancer to some extent. There is a vast difference in these methods in terms of their training/testing datasets, machine learning algorithms, feature encoding schemes, feature selection methods and evaluation strategies used. Therefore, it is desirable to summarize the advantages and disadvantages of the existing methods, provide useful insights and suggestions for the development and improvement of novel computational tools to characterize and identify ACPs. With this in mind, we firstly comprehensively investigate 16 state-of-the-art predictors for ACPs in terms of their core algorithms, feature encoding schemes, performance evaluation metrics and webserver/software usability. Then, comprehensive performance assessment is conducted to evaluate the robustness and scalability of the existing predictors using a well-prepared benchmark dataset. We provide potential strategies for the model performance improvement. Moreover, we propose a novel ensemble learning framework, termed ACPredStackL, for the accurate identification of ACPs. ACPredStackL is developed based on the stacking ensemble strategy combined with SVM, Naïve Bayesian, lightGBM and KNN. Empirical benchmarking experiments against the state-of-the-art methods demonstrate that ACPredStackL achieves a comparative performance for predicting ACPs. The webserver and source code of ACPredStackL is freely available at http://bigdata.biocie.cn/ACPredStackL/ and https://github.com/liangxiaoq/ACPredStackL, respectively.

Dataset Information

Comparative study of computational methods for reconstructing genetic networks of cancer-related pathways.

Publications

Comparative study of computational methods for reconstructing genetic networks of cancer-related pathways.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets