Biology subjects

Sandve, G. K.

Publications and source records attributed to Sandve, G. K..

35 records · Page 2Linked to original sources

bioRxiv2021

In silico proof of principle of machine learning-based antibody design at unconstrained scale

Generative machine learning (ML) has been postulated to be a major driver in the computational design of antigen-specific monoclonal antibodies (mAb). However, efforts to confirm this hypothesis have been hindered by the infeasibility of testing arbitrarily large numbers of antibody sequences for their most critical design parameters: paratope, epitope, affinity, and developability. To address this challenge, we leveraged a lattice-based antibody-antigen binding simulation framework, which incorporates a wide range of physiological antibody binding parameters. The simulation framework enables both the computation of antibody-antigen 3D-structures as well as functions as an oracle for unrestricted prospective evaluation of the antigen specificity of ML-generated antibody sequences. We found that a deep generative model, trained exclusively on antibody sequence (1D) data can be used to design native-like conformational (3D) epitope-specific antibodies, matching or exceeding the training dataset in affinity and developability variety. Furthermore, we show that transfer learning enables the generation of high-affinity antibody sequences from low-N training data. Finally, we validated that the antibody design insight gained from simulated antibody-antigen binding data is applicable to experimental real-world data. Our work establishes a priori feasibility and the theoretical foundation of high-throughput ML-based mAb design. HighlightsO_LIA large-scale dataset of 70M [3 orders of magnitude larger than the current state of the art] synthetic antibody-antigen complexes, that reflect biological complexity, allows the prospective evaluation of antibody generative deep learning C_LIO_LICombination of generative learning, synthetic antibody-antigen binding data, and prospective evaluation shows that deep learning driven antibody design and discovery at an unconstrained level is feasible C_LIO_LITransfer learning (low-N learning) coupled to generative learning shows that antibody-binding rules may be transferred across unrelated antibody-antigen complexes C_LIO_LIExperimental validation of antibody-design conclusions drawn from deep learning on synthetic antibody-antigen binding data C_LI Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=200 SRC="FIGDIR/small/451480v1_ufig1.gif" ALT="Figure 1"> View larger version (64K): org.highwire.dtl.DTLVardef@1d947bcorg.highwire.dtl.DTLVardef@1f4c51corg.highwire.dtl.DTLVardef@b8df67org.highwire.dtl.DTLVardef@1530ea5_HPS_FORMAT_FIGEXP M_FIG We leverage large synthetic ground-truth data to demonstrate the (A,B) unconstrained deep generative learning-based generation of native-like antibody sequences, (C) the prospective evaluation of conformational (3D) affinity, paratope-epitope pairs, and developability. (D) Finally, we show increased generation quality of low-N-based machine learning models via transfer learning. C_FIG

immunology↗

bioRxiv2021

A billion synthetic 3D-antibody-antigen complexes enable unconstrained machine-learning formalized investigation of antibody specificity prediction

Machine learning (ML) is a key technology for accurate prediction of antibody-antigen binding. Two orthogonal problems hinder the application of ML to antibody-specificity prediction and the benchmarking thereof: The lack of a unified ML formalization of immunological antibody specificity prediction problems and the unavailability of large-scale synthetic benchmarking datasets of real-world relevance. Here, we developed the Absolut! software suite that enables parameter-based unconstrained generation of synthetic lattice-based 3D-antibody-antigen binding structures with ground-truth access to conformational paratope, epitope, and affinity. We formalized common immunological antibody specificity prediction problems as ML tasks and confirmed that for both sequence and structure-based tasks, accuracy-based rankings of ML methods trained on experimental data hold for ML methods trained on Absolut!-generated data. The Absolut! framework thus enables real-world relevant development and benchmarking of ML strategies for biotherapeutics design. Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=195 SRC="FIGDIR/small/451258v3_ufig1.gif" ALT="Figure 1"> View larger version (86K): org.highwire.dtl.DTLVardef@4c3a6aorg.highwire.dtl.DTLVardef@8f1deborg.highwire.dtl.DTLVardef@1f55ec6org.highwire.dtl.DTLVardef@2135dd_HPS_FORMAT_FIGEXP M_FIG The software framework Absolut! enables (A,B) the generation of virtually arbitrarily large numbers of synthetic 3D-antibody-antigen structures, (C,D) the formalization of antibody specificity as machine learning (ML) tasks as well as the exploration of ML strategies for real-world antibody-antigen binding or paratope-epitope prediction. C_FIG HighlightsO_LISoftware framework Absolut! to generate an arbitrarily large number of synthetic 3D-antibody-antigen structures that contain biological layers of antibody-antigen binding complexity that render ML predictions challenging C_LIO_LIImmunological antibody specificity prediction problems formalized as machine learning tasks for which the in silico complexes are immediately usable as benchmark datasets C_LIO_LIExploration of machine learning prediction accuracy as a function of architecture, dataset size, choice of negatives, and sequence-structure encoding C_LIO_LIRelative ML performance learnt on Absolut! datasets transfers to experimental datasets C_LI

immunology↗

bioRxiv2021

Profiling the baseline performance and limits of machine learning models for adaptive immune receptor repertoire classification

BackgroundMachine learning (ML) methodology development for classification of immune states in adaptive immune receptor repertoires (AIRR) has seen a recent surge of interest. However, so far, there does not exist a systematic evaluation of scenarios where classical ML methods (such as penalized logistic regression) already perform adequately for AIRR classification. This hinders investigative reorientation to those scenarios where further method development of more sophisticated ML approaches may be required. ResultsTo identify those scenarios where a baseline method is able to perform well for AIRR classification, we generated a collection of synthetic benchmark datasets encompassing a wide range of dataset architecture-associated and immune state-associated sequence pattern (signal) complexity. We trained {approx}1300 ML models with varying assumptions regarding immune signal on{approx}850 datasets with a total of {approx}210000 repertoires containing {approx}42 billion TCR{beta} CDR3 amino acid sequences, thereby surpassing the sample sizes of current state-of-the-art AIRR ML setups by two orders of magnitude. We found that L1-penalized logistic regression achieved high prediction accuracy even when the immune signal occurs only in 1 out of 50000 AIR sequences. ConclusionsWe provide a reference benchmark to guide new AIRR ML classification methodology by: (i) identifying those scenarios characterised by immune signal and dataset complexity, where baseline methods already achieve high prediction accuracy and (ii) facilitating realistic expectations of the performance of AIRR ML models given training dataset properties and assumptions. Our study serves as a template for defining specialized AIRR benchmark datasets for comprehensive benchmarking of AIRR ML methods.

bioinformatics↗

bioRxiv2021

Individualized VDJ recombination predisposes the available Ig sequence space

The process of recombination between variable (V), diversity (D), and joining (J) immunoglobulin (Ig) gene segments determines an individuals naive Ig repertoire, and consequently (auto)antigen recognition. VDJ recombination follows probabilistic rules that can be modeled statistically. So far, it remains unknown whether VDJ recombination rules differ between individuals. If these rules differed, identical (auto)antigen-specific Ig sequences would be generated with individual-specific probabilities, signifying that the available Ig sequence space is individual-specific. We devised a sensitivity-tested distance measure that enables inter-individual comparison of VDJ recombination models. We discovered, accounting for several sources of noise as well as allelic variation in Ig sequencing data, that not only unrelated individuals but also human monozygotic twins and even inbred mice possess statistically distinguishable immunoglobulin recombination models. This suggests that, in addition to genetic, there is also non-genetic modulation of VDJ recombination. We demonstrate that population-wide individualized VDJ recombination can result in orders of magnitude of difference in the probability to generate (auto)antigen-specific Ig sequences. Our findings have implications for immune receptor-based individualized medicine approaches relevant to vaccination, infection, and autoimmunity.

immunology↗

bioRxiv2021

Adjustment of spurious correlations in co-expression measurements from RNA-Sequencing data

1Gene co-expression measurements are widely used in computational biology to identify coordinated expression patterns across a group of samples, which may indicate that these genes are controlled by the same transcriptional regulatory program, or involved in common biological processes. Gene co-expression is generally estimated from RNA-Sequencing data, which are commonly normalized to remove technical variability. Here, we demonstrate that certain normalization methods, in particular quantile-based methods, can introduce false-positive associations between genes, and that this can consequently hamper downstream co-expression network analysis. Quantile-based normalization can, however, be extremely powerful. In particular when preprocessing large-scale heterogeneous data, quantile-based normalization methods such as smooth quantile normalization can be applied to remove technical variability while maintaining global differences in expression for samples with different biological attributes. We therefore developed SNAIL, a normalization method based on smooth quantile normalization specifically designed for modeling of co-expression measurements. We show that SNAIL avoids formation of false-positive associations in co-expression as well as in downstream network analyses. Using SNAIL, one can avoid arbitrary gene filtering and retain associations to genes that only express in small subgroups of samples. This highlights the methods potential future impact on network modeling and other association-based approaches in large-scale heterogeneous data.

bioinformatics↗

bioRxiv2021

immuneML: an ecosystem for machine learning analysis of adaptive immune receptor repertoires

Adaptive immune receptor repertoires (AIRR) are key targets for biomedical research as they record past and ongoing adaptive immune responses. The capacity of machine learning (ML) to identify complex discriminative sequence patterns renders it an ideal approach for AIRR-based diagnostic and therapeutic discovery. To date, widespread adoption of AIRR ML has been inhibited by a lack of reproducibility, transparency, and interoperability. immuneML (immuneml.uio.no) addresses these concerns by implementing each step of the AIRR ML process in an extensible, open-source software ecosystem that is based on fully specified and shareable workflows. To facilitate widespread user adoption, immuneML is available as a command-line tool and through an intuitive Galaxy web interface, and extensive documentation of workflows is provided. We demonstrate the broad applicability of immuneML by (i) reproducing a large-scale study on immune state prediction, (ii) developing, integrating, and applying a novel method for antigen specificity prediction, and (iii) showcasing streamlined interpretability-focused benchmarking of AIRR ML.

bioinformatics↗

bioRxiv2020

DeepRC: Immune repertoire classification with attention-based deep massive multiple instance learning

A central mechanism in machine learning is to identify, store, and recognize patterns. How to learn, access, and retrieve such patterns is crucial in Hopfield networks and the more recent transformer architectures. We show that the attention mechanism of transformer architectures is actually the update rule of modern Hop-field networks that can store exponentially many patterns. We exploit this high storage capacity of modern Hopfield networks to solve a challenging multiple instance learning (MIL) problem in computational biology: immune repertoire classification. Accurate and interpretable machine learning methods solving this problem could pave the way towards new vaccines and therapies, which is currently a very relevant research topic intensified by the COVID-19 crisis. Immune repertoire classification based on the vast number of immunosequences of an individual is a MIL problem with an unprecedentedly massive number of instances, two orders of magnitude larger than currently considered problems, and with an extremely low witness rate. In this work, we present our novel method DeepRC that integrates transformer-like attention, or equivalently modern Hopfield networks, into deep learning architectures for massive MIL such as immune repertoire classification. We demonstrate that DeepRC outperforms all other methods with respect to predictive performance on large-scale experiments, including simulated and real-world virus infection data, and enables the extraction of sequence motifs that are connected to a given disease class. Source code and datasets: https://github.com/ml-jku/DeepRC

bioinformatics↗

bioRxiv2019

A finite vocabulary of antibody-antigen interaction enables predictability of paratope-epitope binding

Antibody-antigen binding relies on the specific interaction of amino acids at the paratope-epitope interface. The predictability of antibody-antigen binding is a prerequisite for de novo antibody and (neo-)epitope design. A fundamental premise for the predictability of antibody-antigen binding is the existence of paratope-epitope interaction motifs that are universally shared among antibody-antigen structures. In the largest set of non-redundant antibody-antigen structures, we identified structural interaction motifs, which together compose a commonly shared structure-based vocabulary of paratope-epitope interactions. We show that this vocabulary enables the machine learnability of antibody-antigen binding on the paratope-epitope level using generative machine learning. The vocabulary (i) is compact, less than 104 motifs, (ii) distinct from non-immune protein-protein interactions, and (iii) mediates specific oligo- and polyreactive interactions between paratope-epitope pairs. Our work successfully leveraged combined structure- and sequence-based learning showing that machine-learning-driven predictive paratope and epitope engineering is feasible.

immunology↗

bioRxiv2019

immuneSIM: tunable multi-feature simulation of B- and T-cell receptor repertoires for immunoinformatics benchmarking

SummaryB- and T-cell receptor repertoires of the adaptive immune system have become a key target for diagnostics and therapeutics research. Consequently, there is a rapidly growing number of bioinformatics tools for immune repertoire analysis. Benchmarking of such tools is crucial for ensuring reproducible and generalizable computational analyses. Currently, however, it remains challenging to create standardized ground truth immune receptor repertoires for immunoinformatics tool benchmarking. Therefore, we developed immuneSIM, an R package that allows the simulation of native-like and aberrant synthetic full length variable region immune receptor sequences. ImmuneSIM enables the tuning of the immune receptor features: (i) species and chain type (BCR, TCR, single, paired), (ii) germline gene usage, (iii) occurrence of insertions and deletions, (iv) clonal abundance, (v) somatic hypermutation, and (vi) sequence motifs. Each simulated sequence is annotated by the complete set of simulation events that contributed to its in silico generation. immuneSIM permits the benchmarking of key computational tools for immune receptor analysis such as germline gene annotation, diversity and overlap estimation, sequence similarity, network architecture, clustering analysis, and machine learning methods for motif detection.\n\nAvailabilityThe package is available via https://github.com/GreiffLab/immuneSIM and will also be available at CRAN (submitted). The documentation is hosted at https://immuneSIM.readthedocs.io.\n\nContactvictor.greiff@medisin.uio.no, sai.reddy@ethz.ch

bioinformatics↗

bioRxiv2019

Assessing graph-based read mappers against a novel baseline approach highlights strengths and weaknesses of the current generation of methods

Graph-based reference genomes have become popular as they allow read mapping and follow-up analyses in settings where the exact haplotypes underlying a high-throughput sequencing experiment are not precisely known. Two recent papers show that mapping to graph-based reference genomes can improve accuracy as compared to methods using linear references. Both of these methods index the sequences for most paths up to a certain length in the graph in order to enable direct mapping of reads containing common variants. However, the combinatorial explosion of possible paths through nearby variants also leads to a huge search space and an increased chance of false positive alignments to highly variable regions. We here assess two prominent graph-based read mappers against a novel hybrid baseline approach that combines an initial path determination with a tuned linear read mapping method. We show, using a previously proposed benchmark, that this simple approach is able to improve accuracy of read-mapping to graph-based reference genomes. Our method is implemented in a tool, Two-step Graph Mapper, which is available at https://github.com/uio-bmi/two_step_graph_mapper along with data and scripts for reproducing the experiments.

bioinformatics↗

bioRxiv2018

NucMerge: Genome assembly quality improvement assisted by alternative assemblies and paired-end Illumina reads

BackgroundIn spite of the major breakthroughs in the second-generation sequencing technologies and the developments of a plethora of assemblers over the last ten years, the resulting genome assemblies may still be fragmented and contain errors. It is typical in genome projects with second-generation reads involved to run multiple assemblers with different parameters and choose the best assembly. However, such an approach is always a trade-off between the strengths and weaknesses of the assemblies. To exploit the advantages of different assemblers, an alternative approach that combines the best parts of several assemblies into one may be applied. The existing tools based on such an approach assist in elongation of assembly fragments and/or improvement of assembly accuracy. Though there has been progress with such a strategy, there is still room for improvement of the existing tools.\n\nResultsWe present NucMerge, a tool for improving genome assembly accuracy by incorporating information derived from an alternative assembly and paired-end Illumina reads from the same genome. The tool corrects insertion, deletion, substitution, and inversion errors and locates different inter- and intra-chromosomal rearrangement errors. NucMerge was compared to two existing alternatives, namely Metassembler and GAM-NGS.\n\nConclusionsThe benchmarking results show that NucMerge has generally better performance than the other tools tested, providing accuracy improvement of more assemblies. NucMerge is freely available at https://github.com/uio-bmi/NucMerge under the MPL license.

bioinformatics↗

bioRxiv2018

Beware the Jaccard: the choice of metric is important and non-trivial in genomic colocalisation analysis.

BackgroundThe generation and systematic collection of genome-wide data is ever-increasing. This vast amount of data has enabled researchers to study relations between a variety of genomic and epigenomic features, including genetic variation, gene regulation, and phenotypic traits. Such relations are typically investigated by comparatively assessing genomic co-occurrence. Technically, this corresponds to assessing the similarity of pairs of genome-wide binary vectors. A variety of metrics have been proposed for this problem in other fields like ecology. However, while several of these metrics have been employed for assessing genomic co-occurrence, their appropriateness for the genomic setting has never been investigated.\n\nResultsWe show that the choice of metric may strongly influence results and propose two alternative modelling assumptions that can be used to guide this choice. On both simulated and real genomic data, the Jaccard index is strongly affected by dataset size and should be used with caution. The Forbes coefficient (fold change) and tetrachoric correlation are less affected by dataset size, but one should be aware of increased variance for small datasets.\n\nAvailabilityAll results on simulated and real data can be inspected and reproduced at: https://hyperbrowser.uio.no/sim-measure

bioinformatics↗

bioRxiv2018

A map of direct TF-DNA interactions in the human genome

Chromatin immunoprecipitation followed by sequencing (ChIP-seq) is the most popular assay to identify genomic regions, called ChIP-seq peaks, that are bound in vivo by transcription factors (TFs). These regions are derived from direct TF-DNA interactions, indirect binding of the TF to the DNA (through a co-binding partner), nonspecific binding to the DNA, and noise/bias/artifacts. Delineating the bona fide direct TF-DNA interactions within the ChIP-seq peaks remains challenging. We developed a dedicated software, ChIP-eat, that combines computational TF binding models and ChIP-seq peaks to automatically predict direct TF-DNA interactions. Our work culminated with predicted interactions covering >4% of the human genome, obtained by uniformly processing 1,983 ChIP-seq peak data sets from the ReMap database for 232 unique TFs. The predictions were a posteriori assessed using protein binding microarray and ChIP-exo data, and were predominantly found in high quality ChIP-seq peaks. The set of predicted direct TF-DNA interactions suggested that high-occupancy target regions are likely not derived from direct binding of the TFs to the DNA. Our predictions derived co-binding TFs supported by protein-protein interaction data and defined cis-regulatory modules enriched for disease- and trait-associated SNPs. Finally, we provide this collection of direct TF-DNA interactions and cis-regulatory modules in the human genome through the UniBind web-interface (http://unibind.uio.no).

bioinformatics↗

bioRxiv2018

NucBreak: Location of structural errors in a genome assembly by using paired-end Illumina reads

BackgroundAdvances in whole genome sequencing strategies have provided the opportunity for genomic and comparative genomic analysis of a vast variety of organisms. The analysis results are highly dependent on the quality of the genome assemblies used. Assessment of the assembly accuracy may significantly increase the reliability of the analysis results and is therefore of great importance.\n\nResultsHere, we present a new tool called NucBreak aimed at detecting structural errors in assemblies, including insertions, deletions, duplications, inversions, and different inter-and intra-chromosomal rearrangements. NucBreak analyses the alignments of reads properly mapped to an assembly and exploits information about the alternative read alignments. We have compared NucBreak with other existing assembly accuracy assessment tools, namely Pilon, REAPR, and FRCbam as well as with several structural variant detection tools, including BreakDancer, Lumpy, and Wham, by using both simulated and real datasets.\n\nConclusionsThe benchmarking results have shown that NucBreak in general predicts assembly errors of different types and sizes with relatively high sensitivity and with higher precision than the other tools. Such a balance between sensitivity and precision makes NucBreak a good alternative to the existing assembly accuracy assessment tools and SV detection tools. NucBreak is freely available at https://github.com/uio-bmi/NucBreak under the MPL license.

bioinformatics↗

bioRxiv2018

Graph Peak Caller: calling ChIP-Seq Peaks on Graph-based Reference Genomes

Graph-based representations are considered to be the future for reference genomes, as they allow integrated representation of the steadily increasing data on individual variation. Currently available tools allow de novo assembly of graph-based reference genomes, alignment of new read sets to the graph representation as well as certain analyses like variant calling and haplotyping. We here present a first method for calling ChIP-Seq peaks on read data aligned to a graph-based reference genome. The method is a graph generalization of the peak caller MACS2, and is implemented in an open source tool, Graph Peak Caller. By using the existing tool vg to build a pan-genome of Arabidopsis thaliana, we validate our approach by showing that Graph Peak Caller with a pan-genome reference graph can trace variants within peaks that are not part of the linear reference genome, and find peaks that in general are more motif-enriched than those found by MACS2.

bioinformatics↗

bioRxiv2018

Mind your gaps: Overlooking assembly gaps confounds statistical testing in genome analysis

BackgroundThe difficulties associated with sequencing and assembling some regions of the DNA sequence result in gaps in the reference genomes that are typically represented as stretches of Ns. Although the presence of assembly gaps causes a slight reduction in the mapping rate in many experimental settings, that does not invalidate the typical statistical testing comparing read count distributions across experimental conditions. However, we hypothesize that not handling assembly gaps in the null model may confound statistical testing of co-localization of genomic features.\n\nResultsFirst, we performed a series of explorative analyses to understand whether and how the public genomic tracks intersect the assembly gaps track (hg19). The findings rightly confirm that the genomic regions in public genomic tracks intersect very little with assembly gaps and the intersection was observed only at the beginning and end regions of the assembly gaps rather than covering the whole gap sizes. Further, we simulated a set of query and reference genomic tracks in a way that nullified any dependence between them to test our hypothesis that not avoiding assembly gaps in the null model would result in spurious inflation of statistical significance. We then contrasted the distributions of test statistics and p-values of Monte Carlo simulation-based permutation tests that either avoided or not avoided assembly gaps in the null model when testing for significant co-localization between a pair of query and reference tracks. We observed that the statistical tests that did not account for the assembly gaps in the null model resulted in a distribution of the test statistic that is shifted to the right and a distribu tion of p-values that is shifted to the left (leading to inflated significance).\n\nConclusionOur results shows that not accounting for assembly gaps in statistical testing of co-localization analysis may lead to false positives and over-optimistic findings.

bioinformatics↗

bioRxiv2017

Genome Build Information Is An Essential Part Of Genomic Track Files

Genomic locations are represented as coordinates on a specific genome build version, but the build information is frequently missing when coordinates are provided. It is essential to correctly interpret and analyse the genomic intervals contained in genomic track files. Here, we demonstrate that this crucial metadatum (or rather datum) is often isolated from the genomic track files in public repositories and journal articles, which could be a major time thief. We propose best practices to ensure that genome build version is always carried along with genomic track files. Although not a substitute to the best practices, we also provide a tool to predict the genome build version of genomic track files.

bioinformatics↗