Complementary feature selection from alternative splicing events and gene expression for phenotype prediction

Labuzzetta, Charles; Antonio, Margaret L.; Watson, Patricia M.; Wilson, Robert; Laboissonniere, Lauren A.; Trimarchi, Jeffrey M.; Genç, Barış; Özdinler, P. Hande; Watson, Dennis K.; Anderson, Paul E.

doi:10.1093/bioinformatics/btw430

Cited by 12 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these studies utilized RNA-seq data by leveraging only gene-level expression data rather than more detailed transcript-level data available for the alternative splicing transcripts (Chen and Manley 2009). Most recently, a study analyzed the utility of RNA-seq transcriptlevel data for the disease/nondisease phenotype classification of the samples, showing the advantage of the transcript expression data for the disease phenotype prediction task (Labuzzetta et al 2016). However, the question of whether or not the utility of transcript-level expression presents a general trend across all main biological and biomedical classification tasks remains open.…”

Section: Introductionmentioning

confidence: 99%

Biological classification with RNA-seq data: Can alternatively spliced transcript expression enhance machine learning classifiers?

Johnson

Dhroso

Hughes

et al. 2018

RNA

View full text Add to dashboard Cite

RNA sequencing (RNA-seq) is becoming a prevalent approach to quantify gene expression and is expected to gain better insights into a number of biological and biomedical questions compared to DNA microarrays. Most importantly, RNA-seq allows us to quantify expression at the gene or transcript levels. However, leveraging the RNA-seq data requires development of new data mining and analytics methods. Supervised learning methods are commonly used approaches for biological data analysis that have recently gained attention for their applications to RNA-seq data. Here, we assess the utility of supervised learning methods trained on RNA-seq data for a diverse range of biological classification tasks. We hypothesize that the transcript-level expression data are more informative for biological classification tasks than the gene-level expression data. Our large-scale assessment utilizes multiple data sets, organisms, lab groups, and RNA-seq analysis pipelines. Overall, we performed and assessed 61 biological classification problems that leverage three independent RNA-seq data sets and include over 2000 samples that come from multiple organisms, lab groups, and RNA-seq analyses. These 61 problems include predictions of the tissue type, sex, or age of the sample, healthy or cancerous phenotypes, and pathological tumor stages for the samples from the cancerous tissue. For each problem, the performance of three normalization techniques and six machine learning classifiers was explored. We find that for every single classification problem, the transcript-based classifiers outperform or are comparable with gene expression-based methods. The top-performing techniques reached a near perfect classification accuracy, demonstrating the utility of supervised learning for RNA-seq based data analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

Biological classification with RNA-seq data: Can alternatively spliced transcript expression enhance machine learning classifiers?

Johnson

Dhroso

Hughes

et al. 2018

RNA

View full text Add to dashboard Cite

show abstract

“…These methods include various network topology analyses, dimensionality reduction methods, anomaly detection, supervised and unsupervised machine learning algorithms, as well as summarization and visualization techniques for complex high-dimensional data [439]. These methods have been used for feature selection on big data sets directly [440,441].…”

Section: Current and Emerging Technologymentioning

confidence: 99%

The Translational Status of Cancer Liquid Biopsies

Bratulić

Gatto

Nielsen

2019

Regen. Eng. Transl. Med.

View full text Add to dashboard Cite

Precision oncology aims to tailor clinical decisions specifically to patients with the objective of improving treatment outcomes. This can be achieved by leveraging omics information for accurate molecular characterization of tumors. Tumor tissue biopsies are currently the main source of information for molecular profiling. However, biopsies are invasive and limited in resolving spatiotemporal heterogeneity in tumor tissues. Alternative non-invasive liquid biopsies can exploit patient's body fluids to access multiple layers of tumor-specific biological information (genomes, epigenomes, transcriptomes, proteomes, metabolomes, circulating tumor cells, and exosomes). Analysis and integration of these large and diverse datasets using statistical and machine learning approaches can yield important insights into tumor biology and lead to discovery of new diagnostic, predictive, and prognostic biomarkers. Translation of these new diagnostic tools into standard clinical practice could transform oncology, as demonstrated by a number of liquid biopsy assays already entering clinical use. In this review, we highlight successes and challenges facing the rapidly evolving field of cancer biomarker research. Lay SummaryPrecision oncology aims to tailor clinical decisions specifically to patients with the objective of improving treatment outcomes. The discovery of biomarkers for precision oncology has been accelerated by high-throughput experimental and computational methods, which can inform fine-grained characterization of tumors for clinical decision-making. Moreover, advances in the liquid biopsy field allow non-invasive sampling of patient's body fluids with the aim of analyzing circulating biomarkers, obviating the need for invasive tumor tissue biopsies. In this review, we highlight successes and challenges facing the rapidly evolving field of liquid biopsy cancer biomarker research.

show abstract

“…Several methods have been developed to automatically predict or generate genotype-phenotype associations. To predict phenotype associations, these methods use different sources such as literature [15][16][17], functional annotations [15,18,19], protein-protein interactions (PPIs) [15,[20][21][22], expression profiles [23,24], genetic variations [15,25], or their combinations [15]. The general idea behind most of these methods is to find genetic similarities, or interactions, and transfer phenotypes between genes based on the assumption that similar or interacting genes are involved in similar or related phenotypes [26].…”

Section: Introductionmentioning

confidence: 99%

DeepPheno: Predicting single gene loss-of-function phenotypes using an ontology-aware hierarchical classifier

Kulmanov

Hoehndorf

2020

PLoS Comput Biol

View full text Add to dashboard Cite

Predicting the phenotypes resulting from molecular perturbations is one of the key challenges in genetics. Both forward and reverse genetic screen are employed to identify the molecular mechanisms underlying phenotypes and disease, and these resulted in a large number of genotype–phenotype association being available for humans and model organisms. Combined with recent advances in machine learning, it may now be possible to predict human phenotypes resulting from particular molecular aberrations. We developed DeepPheno, a neural network based hierarchical multi-class multi-label classification method for predicting the phenotypes resulting from loss-of-function in single genes. DeepPheno uses the functional annotations with gene products to predict the phenotypes resulting from a loss-of-function; additionally, we employ a two-step procedure in which we predict these functions first and then predict phenotypes. Prediction of phenotypes is ontology-based and we propose a novel ontology-based classifier suitable for very large hierarchical classification tasks. These methods allow us to predict phenotypes associated with any known protein-coding gene. We evaluate our approach using evaluation metrics established by the CAFA challenge and compare with top performing CAFA2 methods as well as several state of the art phenotype prediction approaches, demonstrating the improvement of DeepPheno over established methods. Furthermore, we show that predictions generated by DeepPheno are applicable to predicting gene–disease associations based on comparing phenotypes, and that a large number of new predictions made by DeepPheno have recently been added as phenotype databases.

show abstract

Complementary feature selection from alternative splicing events and gene expression for phenotype prediction

Cited by 12 publications

References 20 publications

Biological classification with RNA-seq data: Can alternatively spliced transcript expression enhance machine learning classifiers?

Biological classification with RNA-seq data: Can alternatively spliced transcript expression enhance machine learning classifiers?

The Translational Status of Cancer Liquid Biopsies

DeepPheno: Predicting single gene loss-of-function phenotypes using an ontology-aware hierarchical classifier

Contact Info

Product

Resources

About