MOTIVATION: Accurately predicting how DNA sequence drives gene regulation and how genetic variants alter gene expression is a central challenge in genomics. Borzoi, which models over ten thousand genomic assays including RNA-seq coverage from over half a megabase of sequence context alone promises to become an important foundation model in regulatory genomics, both for massively annotating variants and for further model development. However, the currently used relative positional encodings limit Borzoi's computational efficiency. RESULTS: We present Flashzoi, an enhanced Borzoi model that leverages rotary positional encodings and FlashAttention-2. This achieves over 3-fold faster training and inference and up to 2.4-fold reduced memory usage, while maintaining or improving accuracy in modeling various genomic assays including RNA-seq coverage, predicting variant effects, and enhancer-promoter linking. Flashzoi's improved efficiency facilitates large-scale genomic analyses and opens avenues for exploring more complex regulatory mechanisms and modeling. AVAILABILITY AND IMPLEMENTATION: The Flashzoi model architecture is part of the MIT-licensed borzoi-pytorch package, can be found at https://github.com/johahi/borzoi-pytorch and installed via pip. Model weights for all four Flashzoi and Borzoi replicates are available at https://huggingface.co/johahi under the MIT license. The code has been archived at https://zenodo.org/records/15669913.

MOTIVATION: Detection of gene regulatory aberrations enhances our ability to interpret the impact of inherited and acquired genetic variation for rare disease diagnostics and tumor characterization. While numerous methods for calling RNA expression outliers from RNA-sequencing data have been proposed, the establishment of protein expression outliers from mass spectrometry data is lacking. RESULTS: Here, we propose and assess various modeling approaches to call protein expression outliers across three datasets from rare disease diagnostics and oncology. We use as independent evidence the enrichment for outlier calls in matched RNA-seq samples and the enrichment for rare variants likely disrupting protein expression. We show that controlling for hidden confounders and technical covariates, while simultaneously modeling the occurrence of missing values, is largely beneficial and can be achieved using conditional autoencoders. Moreover, we find that the differences between experimental and fitted log-transformed intensities by such models exhibit heavy tails that are poorly captured with the Gaussian distribution and report stronger statistical calibration when instead using the Student's t-distribution. Our resulting method, PROTRIDER, outperformed baseline approaches based on raw log-intensities Z-scores, PCA, and isolation-based anomaly detection with Isolation forests. The application of PROTRIDER reveals significant enrichments of AlphaMissense pathogenic variants in protein expression outliers. Overall, PROTRIDER provides a method to confidently identify aberrantly expressed proteins applicable to rare disease diagnostics and cancer proteomics. AVAILABILITY AND IMPLEMENTATION: PROTRIDER is freely available at github.com/gagneurlab/PROTRIDER and also available on Zenodo under the DOI zenodo.15569781.

MOTIVATION: Spatially resolved chromatin accessibility profiling offers the potential to investigate gene regulatory processes within the spatial context of tissues. However, current methods typically work at spot resolution, aggregating measurements from multiple cells, thereby obscuring cell-type-specific spatial patterns of accessibility. Spot deconvolution methods have been developed and extensively benchmarked for spatial transcriptomics, yet no dedicated methods exist for spatial chromatin accessibility, and it is unclear if RNA-based approaches are applicable to that modality. RESULTS: Here, we demonstrate that these RNA-based approaches can be applied to spot-based chromatin accessibility data by a systematic evaluation of five top-performing spatial transcriptomics deconvolution methods. To assess performance, we developed a simulation framework that generates both transcriptomic and accessibility spot data from dissociated single-cell and targeted multiomic datasets, enabling direct comparisons across both data modalities. Our results show that Cell2location and RCTD, in contrast to other methods, exhibit robust performance on spatial chromatin accessibility data, achieving accuracy comparable to RNA-based deconvolution. Generally, we observed that RNA-based deconvolution exhibited slightly better performance compared to chromatin accessibility-based deconvolution, especially for resolving rare cell types, indicating room for future development of specialized methods. In conclusion, our findings demonstrate that existing deconvolution methods can be readily applied to chromatin accessibility-based spatial data. Our work provides a simulation framework and establishes a performance baseline to guide the development and evaluation of methods optimized for spatial epigenomics. AVAILABILITY AND IMPLEMENTATION: All methods, simulation frameworks, peak selection strategies, analysis notebooks and scripts are available at https://github.com/theislab/deconvATAC.

MOTIVATION: Identifying regulatory regions in the genome is of great interest for understanding the epigenomic landscape in cells. One fundamental challenge in this context is to find the target genes whose expression is affected by the regulatory regions. A recent successful method is the Activity-By-Contact (ABC) model which scores enhancer-gene interactions based on enhancer activity and the contact frequency of an enhancer to its target gene. However, it describes regulatory interactions entirely from a gene's perspective, and does not account for all the candidate target genes of an enhancer. In addition, the ABC model requires two types of assays to measure enhancer activity, which limits the applicability. Moreover, there is neither implementation available that could allow for an integration with transcription factor (TF) binding information nor an efficient analysis of single-cell data. RESULTS: We demonstrate that the ABC score can yield a higher accuracy by adapting the enhancer activity according to the number of contacts the enhancer has to its candidate target genes and also by considering all annotated transcription start sites of a gene. Further, we show that the model is comparably accurate with only one assay to measure enhancer activity. We combined our generalized ABC model with TF binding information and illustrated an analysis of a single-cell ATAC-seq dataset of the human heart, where we were able to characterize cell type-specific regulatory interactions and predict gene expression based on TF affinities. All executed processing steps are incorporated into our new computational pipeline STARE. AVAILABILITY AND IMPLEMENTATION: The software is available at https://github.com/schulzlab/STARE. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The 5' untranslated region plays a key role in regulating mRNA translation and consequently protein abundance. Therefore, accurate modeling of 5'UTR regulatory sequences shall provide insights into translational control mechanisms and help interpret genetic variants. Recently, a model was trained on a massively parallel reporter assay to predict mean ribosome load (MRL)-a proxy for translation rate-directly from 5'UTR sequence with a high degree of accuracy. However, this model is restricted to sequence lengths investigated in the reporter assay and therefore cannot be applied to the majority of human sequences without a substantial loss of information. Here, we introduced frame pooling, a novel neural network operation that enabled the development of an MRL prediction model for 5'UTRs of any length. Our model shows state-of-the-art performance on fixed length randomized sequences, while offering better generalization performance on longer sequences and on a variety of translation-related genome-wide datasets. Variant interpretation is demonstrated on a 5'UTR variant of the gene HBB associated with beta-thalassemia. Frame pooling could find applications in other bioinformatics predictive tasks. Moreover, our model, released open source, could help pinpoint pathogenic genetic variants.

Motivation: Regulatory 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. Results: Here 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 120 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. Availability and implementation: Spline transformation is implemented as a Keras layer in the CONCISE python package: https://github.com/gagneurlab/concise. Analysis code is available at https://github.com/gagneurlab/Manuscript_Avsec_Bioinformatics_2017. Contact: [email protected] or [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

BACKGROUND: 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. RESULTS: Here we present GenoGAM 2.0, a scalable and efficient implementation that is 2 to 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. CONCLUSIONS: We 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.

MOTIVATION: Chromatin immunoprecipitation followed by deep sequencing (ChIP-Seq) is a widely used approach to study protein-DNA interactions. Often, the quantities of interest are the differential occupancies relative to controls, between genetic backgrounds, treatments, or combinations thereof. Current methods for differential occupancy of ChIP-Seq data rely however on binning or sliding window techniques, for which the choice of the window and bin sizes are subjective. RESULTS: Here, we present GenoGAM (Genome-wide Generalized Additive Model), which brings the well-established and flexible generalized additive models framework to genomic applications using a data parallelism strategy. We model ChIP-Seq read count frequencies as products of smooth functions along chromosomes. Smoothing parameters are objectively estimated from the data by cross-validation, eliminating ad hoc binning and windowing needed by current approaches. GenoGAM provides base-level and region-level significance testing for full factorial designs. Application to a ChIP-Seq dataset in yeast showed increased sensitivity over existing differential occupancy methods while controlling for type I error rate. By analyzing a set of DNA methylation data and illustrating an extension to a peak caller, we further demonstrate the potential of GenoGAM as a generic statistical modeling tool for genome-wide assays. AVAILABILITY AND IMPLEMENTATION: Software is available from Bioconductor: https://www.bioconductor.org/packages/release/bioc/html/GenoGAM.html . CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary information is available at Bioinformatics online.

UNLABELLED: Gene Ontology and other forms of gene-category analysis play a major role in the evaluation of high-throughput experiments in molecular biology. Single-category enrichment analysis procedures such as Fisher's exact test tend to flag large numbers of redundant categories as significant, which can complicate interpretation. We have recently developed an approach called model-based gene set analysis (MGSA), that substantially reduces the number of redundant categories returned by the gene-category analysis. In this work, we present the Bioconductor package mgsa, which makes the MGSA algorithm available to users of the R language. Our package provides a simple and flexible application programming interface for applying the approach. AVAILABILITY: The mgsa package has been made available as part of Bioconductor 2.8. It is released under the conditions of the Artistic license 2.0. CONTACT: [email protected]; [email protected].

BACKGROUND: With the advance of genome sequencing technologies, phenotyping, rather than genotyping, is becoming the most expensive task when mapping genetic traits. The need for efficient selective phenotyping strategies, i.e. methods to select a subset of genotyped individuals for phenotyping, therefore increases. Current methods have focused either on improving the detection of causative genetic variants or their precise genomic location separately. RESULTS: Here we recognize selective phenotyping as a Bayesian model discrimination problem and introduce SPARE (Selective Phenotyping Approach by Reduction of Entropy). Unlike previous methods, SPARE can integrate the information of previously phenotyped individuals, thereby enabling an efficient incremental strategy. The effective performance of SPARE is demonstrated on simulated data as well as on an experimental yeast dataset. CONCLUSIONS: Using entropy reduction as an objective criterion gives a natural way to tackle both issues of detection and localization simultaneously and to integrate intermediate phenotypic data. We foresee entropy-based strategies as a fruitful research direction for selective phenotyping.

BACKGROUND: Metabolic pathway analysis has been recognized as a central approach to the structural analysis of metabolic networks. The concept of elementary (flux) modes provides a rigorous formalism to describe and assess pathways and has proven to be valuable for many applications. However, computing elementary modes is a hard computational task. In recent years we assisted in a multiplication of algorithms dedicated to it. We require a summarizing point of view and a continued improvement of the current methods. RESULTS: We show that computing the set of elementary modes is equivalent to computing the set of extreme rays of a convex cone. This standard mathematical representation provides a unified framework that encompasses the most prominent algorithmic methods that compute elementary modes and allows a clear comparison between them. Taking lessons from this benchmark, we here introduce a new method, the binary approach, which computes the elementary modes as binary patterns of participating reactions from which the respective stoichiometric coefficients can be computed in a post-processing step. We implemented the binary approach in FluxAnalyzer 5.1, a software that is free for academics. The binary approach decreases the memory demand up to 96% without loss of speed giving the most efficient method available for computing elementary modes to date. CONCLUSIONS: The equivalence between elementary modes and extreme ray computations offers opportunities for employing tools from polyhedral computation for metabolic pathway analysis. The new binary approach introduced herein was derived from this general theoretical framework and facilitates the computation of elementary modes in considerably larger networks.

MOTIVATION: Elucidation of metabolic networks for an increasing number of organisms reveals that even small networks can contain thousands of reactions and chemical species. The intimate connectivity between components complicates their decomposition into biologically meaningful sub-networks. Moreover, traditional higher-order representations of metabolic networks as metabolic pathways, suffers from the lack of rigorous definition, yielding pathways of disparate content and size. RESULTS: We introduce a hierarchical representation that emphasizes the gross organization of metabolic networks in largely independent pathways and sub-systems at several levels of independence. The approach highlights the coupling of different pathways and the shared compounds responsible for those couplings. By assessing our results on Escherichia coli (E.coli metabolic reactions, Genetic Circuits Research Group, University of California, San Diego, http://gcrg.ucsd.edu/organisms/ecoli.html, 'model v 1.01. reactions') against accepted biochemical annotations, we provide the first systematic synopsis of an organism's metabolism. Comparison with operons of E.coli shows that low-level clusters are reflected in genome organization and gene regulation. AVAILABILITY: Source code, data sets and supplementary information are available at http://www.mas.ecp.fr/labo/equipe/gagneur/hierarchy/hierarchy.html