Integrated analysis of numerous heterogeneous gene expression profiles for detecting robust disease-specific biomarkers and proposing drug targets

Amar, David; Hait, Tom Aharon; Izraeli, Shai; Shamir, Ron

doi:10.1093/nar/gkv810

Cited by 26 publications

(20 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…27 Error correcting belief propagation has been used to predict normal and disease cell states in a comprehensive compilation of gene expression signatures. 27–30 These approaches use standard machine-learning classifiers as inputs to the inference strategy. To our knowledge, little investigation of the optimal approaches has been done to determine the best base-level classifiers.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

One-Class Detection of Cell States in Tumor Subtypes

2015

View full text Add to dashboard Cite

The cellular composition of a tumor greatly influences the growth, spread, immune activity, drug response, and other aspects of the disease. Tumor cells are usually comprised of a heterogeneous mixture of subclones, each of which could contain their own distinct character. The presence of minor subclones poses a serious health risk for patients as any one of them could harbor a fitness advantage with respect to the current treatment regimen, fueling resistance. It is therefore vital to accurately assess the make-up of cell states within a tumor biopsy. Transcriptome-wide assays from RNA sequencing provide key data from which cell state signatures can be detected. However, the challenge is to find them within samples containing mixtures of cell types of unknown proportions. We propose a novel one-class method based on logistic regression and show that its performance is competitive to two established SVM-based methods for this detection task. We demonstrate that one-class models are able to identify specific cell types in heterogeneous cell populations better than their binary predictor counterparts. We derive one-class predictors for the major breast and bladder subtypes and reaffirm the connection between these two tissues. In addition, we use a one-class predictor to quantitatively associate an embryonic stem cell signature with an aggressive breast cancer subtype that reveals shared stemness pathways potentially important for treatment.

show abstract

Section: Resultsmentioning

confidence: 99%

“…standardized differential vectors as in 27,28 ) or a popular standard (e.g. SVMs 29,30 ). Thus, an open question remains about how best to build signature dictionaries.…”

Section: Resultsmentioning

confidence: 99%

One-Class Detection of Cell States in Tumor Subtypes

2015

View full text Add to dashboard Cite

show abstract

“…To joint analysis of expression profiles from GEO and TCGA, we used the Rank-based scores (Amar et al, 2015) to normalize the expression profiles of engineered organoids and CRC samples. 18,071 common genes were detected by both GEO and TCGA.…”

Section: Integrating the Gene Expression Profiles From Geo And Tcga Umentioning

confidence: 99%

Prioritizing Gene Cascading Paths to Model Colorectal Cancer Through Engineered Organoids

Ping

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Engineered organoids by sequential introduction of key mutations could help modeling the dynamic cancer progression. However, it remains difficult to determine gene paths which were sufficient to capture cancer behaviors and to broadly explain cancer mechanisms. Here, as a case study of colorectal cancer (CRC), functional and dynamic characterizations of five types of engineered organoids with different mutation combinations of five driver genes (APC, SMAD4, KRAS, TP53, and PIK3CA) showed that sequential introductions of all five driver mutations could induce enhanced activation of more hallmark signatures, tending to cancer. Comparative analysis of engineered organoids and corresponding CRC tissues revealed sequential introduction of key mutations could continually shorten the biological distance from engineered organoids to CRC tissues. Nevertheless, there still existed substantial biological gaps between the engineered organoid even with five key mutations and CRC samples. Thus, we proposed an integrative strategy to prioritize gene cascading paths for shrinking biological gaps between engineered organoids and CRC tissues. Our results not only recapitulated the well-known adenoma-carcinoma sequence model (e.g., AKST-organoid with driver mutations in APC, KRAS, SMAD4, and TP53), but also provided potential paths for delineating alternative pathogenesis underlying CRC populations (e.g., A-organoid with APC mutation). Our strategy also can be applied to both organoids with more mutations and other cancers, which can improve and innovate mechanism across cancer patients for drug design and cancer therapy.

show abstract

“…This network has 78 genes consisting of 96 PPI pairs. The 502 cancer-specific network (Amar, Hait, Izraeli & Shamir, 2015) consists of 78 genes, which are 503 of importance in DNA replication and cancer pathways. The interaction pairs in the 504 cancer-specific network are derived from the IntAct database (Kerrien, et al, 2007).…”

Section: Ppis Network Prediction 497mentioning

confidence: 99%

Prediction of protein-protein interactions based on elastic net and deep forest

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

Prediction of protein-protein interactions (PPIs) helps to grasp molecular roots of 14 disease. However, web-lab experiments to predict PPIs are limited and costly. Using 15 machine-learning-based frameworks can not only automatically identify PPIs, but also 16 provide new ideas for drug research and development from a promising alternative. We 17 present a novel deep-forest-based method for PPIs prediction. First, pseudo amino acid 18 composition (PAAC), autocorrelation descriptor (Auto), multivariate mutual information 19 (MMI), composition-transition-distribution (CTD), and amino acid composition PSSM 20 (AAC-PSSM), and dipeptide composition PSSM (DPC-PSSM) are adopted to extract and 21 construct the pattern of PPIs. Secondly, elastic net is utilized to optimize the initial feature 22 vectors and boost the predictive performance. Finally, GcForest-PPI model based on deep 23 forest is built up. Benchmark experiments reveal that the accuracy values of Saccharomyces 24 cerevisiae and Helicobacter pylori are 95.44% and 89.26%. We also apply GcForest-PPI on 25 independent test sets and CD9-core network, crossover network, and cancer-specific network. 26The evaluation shows that GcForest-PPI can boost the prediction accuracy, complement 27 experiments and improve drug discovery. The datasets and code of GcForest-PPI could be 28 downloaded at https://github.com/QUST-AIBBDRC/GcForest-PPI/. 29

show abstract

Integrated analysis of numerous heterogeneous gene expression profiles for detecting robust disease-specific biomarkers and proposing drug targets

Cited by 26 publications

References 60 publications

One-Class Detection of Cell States in Tumor Subtypes

One-Class Detection of Cell States in Tumor Subtypes

Prioritizing Gene Cascading Paths to Model Colorectal Cancer Through Engineered Organoids

Prediction of protein-protein interactions based on elastic net and deep forest

Contact Info

Product

Resources

About