Biology subjects

Gagneur, J.

Publications and source records attributed to Gagneur, J..

9 recordsLinked to original sources

bioRxiv2018

Modular modeling improves the predictions of genetic variant effects on splicing

Predicting the effects of genetic variants on splicing is highly relevant for human genetics. We describe the framework MMSplice (modular modeling of splicing) with which we built the winning model of the CAGI 2018 exon skipping prediction challenge. The MMSplice modules are neural networks scoring exon, intron, and splice sites, trained on distinct large-scale genomics datasets. These modules are combined to predict effects of variants on exon skipping, alternative donor and acceptor sites, splicing efficiency, and pathogenicity, with matched or higher performance than state-of-the-art. Our models, available in the repository Kipoi, apply to variants including indels directly from VCF files.

genomics↗

bioRxiv2018

Kipoi: accelerating the community exchange and reuse of predictive models for genomics

Advanced machine learning models applied to large-scale genomics datasets hold the promise to be major drivers for genome science. Once trained, such models can serve as a tool to probe the relationships between data modalities, including the effect of genetic variants on phenotype. However, lack of standardization and limited accessibility of trained models have hampered their impact in practice. To address this, we present Kipoi, a collaborative initiative to define standards and to foster reuse of trained models in genomics. Already, the Kipoi repository contains over 2,000 trained models that cover canonical prediction tasks in transcriptional and post-transcriptional gene regulation. The Kipoi model standard grants automated software installation and provides unified interfaces to apply and interpret models. We illustrate Kipoi through canonical use cases, including model benchmarking, transfer learning, variant effect prediction, and building new models from existing ones. By providing a unified framework to archive, share, access, use, and build on models developed by the community, Kipoi will foster the dissemination and use of machine learning models in genomics.

bioinformatics↗

bioRxiv2018

Quantification and discovery of sequence determinants of protein per mRNA amount in 29 human tissues

Despite their importance in determining protein abundance, a comprehensive catalogue of sequence features controlling protein-to-mRNA (PTR) ratios and a quantification of their effects is still lacking. Here we quantified PTR ratios for 11,575 proteins across 29 human tissues using matched transcriptomes and proteomes. We analyzed the contribution of known sequence determinants of protein synthesis and degradation and 15 novel mRNA and protein sequence motifs that we found by association testing. While the dynamic range of PTR ratios spans more than 2 orders of magnitude, our integrative model predicts PTR ratios at a median precision of 3.2-fold. A reporter assay provided significant functional support for two novel UTR motifs and a proteome-wide competition-binding assay identified motif-specific bound proteins for one motif. Moreover, our direct comparison of protein to RNA levels led to a new metrics of codon optimality. Altogether, this study shows that a large fraction of PTR ratio variance across genes can be predicted from sequence and identified many new candidate post-transcriptional regulatory elements in the human genome.

systems biology↗

bioRxiv2018

A deep proteome and transcriptome abundance atlas of 29 healthy human tissues

Genome-, transcriptome- and proteome-wide measurements provide valuable insights into how biological systems are regulated. However, even fundamental aspects relating to which human proteins exist, where they are expressed and in which quantities are not fully understood. Therefore, we have generated a systematic, quantitative and deep proteome and transcriptome abundance atlas from 29 paired healthy human tissues from the Human Protein Atlas Project and representing human genes by 17,615 transcripts and 13,664 proteins. The analysis revealed that few proteins show truly tissue-specific expression, that vast differences between mRNA and protein quantities within and across tissues exist and that the expression levels of proteins are often more stable across tissues than those of transcripts. In addition, only ~2% of all exome and ~7% of all mRNA variants could be confidently detected at the protein level showing that proteogenomics remains challenging, requires rigorous validation using synthetic peptides and needs more sophisticated computational methods. Many uses of this resource can be envisaged ranging from the study of gene/protein expression regulation to protein biomarker specificity evaluation to name a few.

systems biology↗

bioRxiv2018

OUTRIDER: A statistical method for detecting aberrantly expressed genes in RNA sequencing data

RNA sequencing (RNA-seq) is gaining popularity as a complementary assay to genome sequencing for precisely identifying the molecular causes of rare disorders. A powerful approach is to identify aberrant gene expression levels as potential pathogenic events. However, existing methods for detecting aberrant read counts in RNA-seq data either lack assessments of statistical significance, so that establishing cutoffs is arbitrary, or rely on subjective manual corrections for confounders. Here, we describe OUTRIDER (OUTlier in RNA-seq fInDER), an algorithm developed to address these issues. The algorithm uses an autoencoder to model read count expectations according to the co-variation among genes resulting from technical, environmental, or common genetic variations. Given these expectations, the RNA-seq read counts are assumed to follow a negative binomial distribution with a gene-specific dispersion. Outliers are then identified as read counts that significantly deviate from this distribution. The model is automatically fitted to achieve the best correction of artificially corrupted data. Precision-recall analyses using simulated outlier read counts demonstrated the importance of combining correction for co-variation and significance-based thresholds. OUTRIDER is open source and includes functions for filtering out genes not expressed in a data set, for identifying outlier samples with too many aberrantly expressed genes, and for the P-value-based detection of aberrant gene expression, with false discovery rate adjustment. Overall, OUTRIDER provides a computationally fast and scalable end-to-end solution for identifying aberrantly expressed genes, suitable for use by rare disease diagnostic platforms.

bioinformatics↗

bioRxiv2018

GenoGAM 2.0: Scalable and efficient implementation of genome-wide generalized additive models for gigabase-scale genomes

GenoGAM (Genome-wide generalized additive models) is a powerful statistical modeling tool for the analysis of ChIP-Seq data with flexible factorial design experiments. However large runtime and memory requirements of its current implementation prohibit its application to gigabase-scale genomes such as mammalian genomes.\n\nHere we present GenoGAM 2.0 a scalable and efficient implementation that is 2-3 orders of magnitude faster than the previous version. This is achieved by exploiting the sparsity of the model using the SuperLU direct solver for parameter fitting, and sparse Cholesky factorization together with the sparse inverse subset algorithm for computing standard errors. Furthermore the HDF5 library is employed to store data efficiently on hard drive, reducing memory footprint while keeping I/O low. Whole-genome fits for human ChIP-seq datasets (ca. 300 million parameters) could be obtained in less than 9 hours on a standard 60-core server. GenoGAM 2.0 is implemented as an open source R package and currently available on GitHub. A Bioconductor release of the new version is in preparation.\n\nWe have vastly improved the performance of the GenoGAM framework, opening up its application to all types of organisms. Moreover, our algorithmic improvements for fitting large GAMs could be of interest to the statistical community beyond the genomics field.

bioinformatics↗

bioRxiv2017

OCR-Stats: Robust estimation and statistical testing of mitochondrial respiration activities using Seahorse XF Analyzer

Accurate quantification of cellular and mitochondrial bioenergetic activity is of great interest in medicine and biology. Mitochondrial stress tests performed with Seahorse Bioscience XF Analyzers allow estimating different bioenergetic measures by monitoring oxygen consumption rates (OCR) of living cells in multi-well plates. However, studies of statistical best practices for determining OCR measurements and comparisons have been lacking so far. Therefore, we performed mitochondrial stress tests in 126 96-well plates involving 203 fibroblast cell lines to understand how OCR behaves across different biosamples, wells, and plates. We show that the noise of OCR is multiplicative, that outlier data points can concern individual measurements or all measurements of a well, and that the inter-plate variation is greater than intra-plate variation. Based on these insights, we developed a novel statistical method, OCR-Stats, that: i) robustly estimates OCR levels modeling multiplicative noise and automatically identifying outlier data points and outlier wells; and ii) performs statistical testing between samples, taking into account the different magnitudes of the between- and within-plates variations. This led to a significant reduction of the coefficient of variation across plates of basal respiration by 36% and of maximal respiration by 32%. Moreover, using positive and negative controls, we show that our statistical test outperforms existing methods, which either suffer from an excess of false positives (within-plates methods), or of false negatives (between-plates methods). Altogether, the aim of this study is to propose statistical good practices to support experimentalists in designing, analyzing, testing and reporting results of mitochondrial stress tests using this high throughput platform.

bioinformatics↗

bioRxiv2017

Modeling positional effects of regulatory sequences with spline transformations increases prediction accuracy of deep neural networks

MotivationRegulatory sequences are not solely defined by their nucleic acid sequence but also by their relative distances to genomic landmarks such as transcription start site, exon boundaries, or polyadenylation site. Deep learning has become the approach of choice for modeling regulatory sequences because of its strength to learn complex sequence features. However, modeling relative distances to genomic landmarks in deep neural networks has not been addressed.\n\nResultsHere we developed spline transformation, a neural network module based on splines to flexibly and robustly model distances. Modeling distances to various genomic landmarks with spline transformations significantly increased state-of-the-art prediction accuracy of in vivo RNA-binding protein binding sites for 114 out of 123 proteins. We also developed a deep neural network for human splice branchpoint based on spline transformations that outperformed the current best, already distance-based, machine learning model. Compared to piecewise linear transformation, as obtained by composition of rectified linear units, spline transformation yields higher prediction accuracy as well as faster and more robust training. As spline transformation can be applied to further quantities beyond distances, such as methylation or conservation, we foresee it as a versatile component in the genomics deep learning toolbox.\n\nAvailabilitySpline transformation is implemented as a Keras layer in the CONCISE python package: https://github.com/gagneurlab/concise. Analysis code is available at goo.gl/3yMY5w.\n\nContactavsec@in.tum.de; gagneur@in.tum.de

bioinformatics↗

bioRxiv2016

Sequence features explain most of the mRNA stability variation across genes

The stability of mRNA is one of the major determinants of gene expression. Although a wealth of sequence elements regulating mRNA stability has been described, their quantitative contributions to half-life are unknown. Here, we built a quantitative model for Saccharomyces cerevisiae based on functional mRNA sequence features that explains 60% of the half-life variation between genes and predicts half-life at a median relative error of 30%. The model revealed a new destabilizing 3UTR motif, ATATTC, which we functionally validated. Codon usage proves to be the major determinant of mRNA stability. Nonetheless, single-nucleotide variations have the largest effect when occurring on 3UTR motifs or upstream AUGs. Analyzing mRNA half-life data of 34 knockout strains showed that the effect of codon usage not only requires functional decapping and deadenylation, but also the 5-to-3 exonuclease Xrn1, the non-sense mediated decay genes, but not no-go decay. Altogether, this study quantitatively delineates the contributions of mRNA sequence features on stability in yeast, reveals their functional dependencies on degradation pathways, and allows accurate prediction of half-life from mRNA sequence.

genomics↗