Biology subjects

Sandve, G. K.

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

At least 19 recordsLinked to original sources

bioRxiv2026

Single-cell immune repertoire atlas maps coordinated circulating adaptive immune states in inflammatory bowel disease

Single-cell studies have defined immune states in inflammatory bowel disease (IBD), but how adaptive receptor histories organize circulating immunity remains unclear. We generated a single-cell transcriptomic atlas of peripheral blood from 249 participants with Crohn's disease, ulcerative colitis, or non-IBD control status, including 182 with productive TCR and BCR recovery. Expanded TCR clonotypes marked inflammatory-memory and cytotoxic states, while distinct but similar paired TCRs shared inflammatory programs across participants. BCR lineage maturation linked IgA-associated mucosal and plasma B cell programs to somatic mutation and class switching, distinguishing maturation-associated biology from clonal expansion. Helper, regulatory, and cytotoxic T-cell programs covaried with B-cell states, and inferred interactions nominated reciprocal antigen-presentation and helper pathways. Repertoire-based machine learning distinguished diagnosis, inflammation, and contemporaneous six-month treatment-response status. Together, this atlas connects receptor architecture to coordinated systemic immune remodeling, establishes a foundation for repertoire-informed patient stratification, and prioritizes candidate mechanisms of IBD pathogenesis.

immunology↗

bioRxiv2026

What Do Generative Models Learn About Adaptive Immune Receptor Repertoires? A Benchmark Study

Generative models are increasingly used to model adaptive immune receptor repertoire (AIRR) sequence distributions, promising to decode the sequence diversity shaping immune responses and accelerate the design of therapeutic antibodies and T-cell receptors. Yet it remains unclear whether these models produce biologically meaningful outputs or merely capture surface-level sequence statistics while missing features driven by receptor generation and selection. Rigorous evaluation is needed, but the field lacks established standards, as existing machine learning metrics do not all translate directly to the AIRR domain, given the complex structure of the data and the lack of biological ground truth. Consequently, researchers face difficulties in evaluating the models and selecting appropriate ones, which can critically affect downstream clinical applications. Here, we apply a suite of evaluation metrics tailored to AIRR sequence data and present a systematic comparison of popular generative model families proposed for the AIRR field, including variational autoencoders, long short-term memory networks, antibody language models, selection models, and simple statistical baselines. We focus specifically on the task of learning individual-specific immune receptor repertoires, a clinically relevant challenge with direct implications for personalized immunotherapy, disease monitoring, and vaccine response studies. By analyzing the sequences generated by each model, we identify memorization risks, innovation capabilities, and sensitivity to hyperparameter tuning. Taken together, these results advance the understanding of how current generative models reproduce the biology of individual immune repertoires and lay the groundwork for more principled model development and evaluation.

immunology↗

bioRxiv2026

Unsupervised Machine Learning for Adaptive Immune Receptors with immuneML

Machine learning (ML) enables adaptive immune receptor repertoires (AIRRs) analyses for biomarker identification and therapeutic development. With the majority of AIRR data partially or imperfectly labeled, unsupervised ML is essential for motif discovery, biologically meaningful clustering, and generation of novel receptor sequences. However, no unified framework for unsupervised ML exists in the AIRR field, hindering the assessment of model robustness and generalizability. Here, we present an immuneML release advancing unsupervised ML in the AIRR field through unified clustering workflows, interpretable generative modeling, integration with protein language model embeddings, dimensionality reduction, and visualization. We demonstrate immuneMLs utility in three use cases: (i) benchmarking generative models for epitope-specific sequence generation, assessing specificity and novelty, (ii) systematic evaluation of clustering approaches on experimental receptor sequences against biological properties, such as epitope specificity and MHC, and (iii) unsupervised analysis of an experimental AIRR dataset to examine potential confounding, a practice widespread in related fields but unexplored in AIRR analyses.

bioinformatics↗

bioRxiv2025

Quantitative mapping of antigen specificity in adaptive immune repertoire embedding spaces

The adaptive immune receptor repertoire (AIRR) encompasses an immense diversity of antibody and T-cell receptor sequences, whose collective organization - how receptors are distributed, clustered, and interrelated across sequence and functional (e.g., antigen-binding) dimensions - remains poorly characterized. Representing AIRRs in continuous representation spaces that capture sequence, biochemical, and structural similarity between receptors may enable comparisons beyond discrete sequence features. Using both one-hot encodings and protein language model (PLM) embeddings, we developed a quantitative framework to map immune receptor organization at global (sequence-set-level) and local (single-sequence-level) scales. Applying the geometry-aware Wasserstein-2 distance, we show that the global structure of the AIRR space can be recovered from as few as [~]105 sequence embeddings, at least 10 orders of magnitude smaller than the theoretical immune receptor diversity. We found that immune receptor sequences annotated with different antigen specificities occupy distinct regions of representation space. To resolve local relationships, we introduce a spatial homogeneity metric that quantifies the extent of functional clustering. We found higher spatial homogeneity in embedding spaces than in sequence space for diverse antigen-specific datasets. Our framework establishes a foundation for quantitative mapping of adaptive immune repertoire organization.

immunology↗

bioRxiv2025

PEPE: Scalable extraction of multi-modal protein language model representations

MotivationProtein language models (PLMs) capture intricate amino-acid dependencies, producing embeddings that encode rich structural, functional, and evolutionary information. Despite their potential, current extraction workflows rely on arbitrary choices, with respect to embedding layer, pooling, and padding, that frequently yield suboptimal representations for feature extraction and downstream analyses. Large-scale embedding generation is further limited by inefficiencies in computation and memory: (i) accumulating all model outputs in memory before writing to disk causes severe bottlenecks, and (ii) repeatedly embedding identical sequences to extract different modes introduces redundant computation and drastically reduces throughput and scalability. ResultsWe introduce PEPE (Parallel Extraction for Protein Embeddings), a command-line tool and Python library that enables efficient, high-throughput, and multimodal extraction from protein language models. PEPEs parallelized and streaming-based architecture achieves runtimes several orders of magnitude faster than sequential approaches. Unlike conventional methods--whose peak memory usage scales linearly with output size and fails when memory capacity is exceeded--PEPE maintains stable, low memory consumption, enabling multimodal embedding extraction even beyond available RAM. PEPE supports a wide range of state-of-the-art and custom PLMs through a simple, flexible interface. By combining scalability, robustness, and ease of use, PEPE allows researchers to generate massive, information-rich embedding datasets efficiently, and facilitate the discovery of optimal representations for structural, functional, and evolutionary downstream tasks. By streamlining the generation of diverse embedding configurations, PEPE provides researchers with the necessary data to identify high-performing latent states for specific biological contexts without requiring additional computational resources. Availability and ImplementationPEPE is a command-line tool written in Python and published under MIT license. The source code and documentation are available at https://github.com/csi-greifflab/pepe-cli. PEPE is also available for installation from PyPI under https://pypi.org/project/pepe-cli and deposited on Zenodo at https://zenodo.org/records/15912054.

bioinformatics↗

bioRxiv2025

Active learning for improving out-of-distribution lab-in-the-loop experimental design

The accurate prediction of antibody-antigen binding is crucial for developing antibody-based therapeutics and advancing immunological research. Library-on-library approaches, where many antigens are probed against many antibodies, can identify specific interacting pairs. Machine learning models can predict target binding by analyzing many-to-many relationships between antibodies and antigens. However, these models face challenges when predicting interactions when test antibodies and antigens are not represented in the training data, a scenario known as out-of-distribution prediction. Generating experimental binding data is costly, limiting the availability of comprehensive datasets. Active learning can reduce costs by starting with a small labeled subset of data and iteratively expanding the labeled dataset. Few active learning approaches are available to handle data with many-to-many relationships as, for example, obtained from library-on-library screening approaches. In this study, we developed and evaluated fourteen novel active learning strategies for antibody-antigen binding prediction in a library-on-library setting and evaluated their out-of-distribution performance using the Absolut! simulation framework. We found that three of the fourteen algorithms tested significantly outperformed the baseline where random data are iteratively labeled. The best algorithm reduced the number of required antigen mutant variants by up to 35%, and sped up the learning process by 28 steps compared to the random baseline. These findings demonstrate that active learning can improve experimental efficiency in a library-on-library setting and advance antibody-antigen binding prediction.

bioinformatics↗

bioRxiv2024

Systematic benchmarking of mass spectrometry-based antibody sequencing reveals methodological biases

The circulating antibody repertoire is crucial for immune protection, holding significant immunological and biotechnological value. While bottom-up mass spectrometry (MS) is the most widely used proteomics technique for profiling the sequence diversity of circulating antibodies (Ab-seq), it has not been thoroughly benchmarked. We quantified the replicability and robustness of Ab-seq using six monoclonal antibodies with known protein sequences in 70 different combinations of concentration and oligoclonality, both with and without polyclonal serum IgG background. Each combination underwent four protease treatments and was analyzed across four experimental and three technical replicates, totaling 3,360 LC-MS/MS runs. We quantified the dependence of MS-based Ab-seq identification on antibody sequence, concentration, protease, background signal diversity, and bioinformatics setups. Integrating the data from experimental replicates, proteases, and bioinformatics tools enhanced antibody identification. De novo peptide sequencing showed similar performance to database-dependent methods for higher antibody concentrations, but de novo antibody reconstruction remains challenging. Our work provides a foundational resource for the field of MS-based antibody profiling.

immunology↗

bioRxiv2024

Training data composition determines machine learning generalization and biological rule discovery

Supervised machine learning models depend on training datasets with positive and negative examples. Therefore, dataset composition directly impacts model performance and bias. Given the importance of machine learning for immunotherapeutic design, we examined how different negative class definitions affect model generalization and rule discovery for antibody-antigen binding. Using synthetic structure-based binding data, we evaluated models trained with various definitions of negative sets. Our findings reveal that high out-of-distribution performance can be achieved when the negative dataset contains more similar samples to the positive dataset despite a lower within-distribution performance. Furthermore, leveraging ground truth information, we show that binding rules discovered as associated with positive data change based on the negative data used. Validation on experimental data supported simulation-based observations. This work underscores the role of dataset composition, including negative data selection, in creating robust, generalizable, and biology-aware sequence-based ML models.

bioinformatics↗

bioRxiv2023

KAGE 2: Fast and accurate genotyping of structural variation using pangenomes

Structural variation is known to play an important and often overlooked role in regulating disease and traits, but accurately detecting structural variants from sequencing data has traditionally been difficult. However, recent improvements in high-quality genome assembly along with methodological advancements in pangenome creation have opened up the landscape for methods that use such pangenomes for structural variant calling and genotyping. We here present KAGE2, which accurately and efficiently genotypes structural variation by exploiting the availability of pangenomes that represent known variation in a population. Through comprehensive benchmarking, we highlight limitations of existing methodology and show that KAGE2 is more accurate and considerably faster than existing methods.

bioinformatics↗

bioRxiv2023

Cartography of the developability landscapes of native and human-engineered antibodies

Designing effective monoclonal antibody (mAb) therapeutics faces a multi-parameter optimization challenge known as "developability", which reflects an antibodys ability to progress through development stages based on its physicochemical properties. While natural antibodies may provide valuable guidance for mAb selection, we lack a comprehensive understanding of natural developability parameter (DP) plasticity (redundancy, predictability, sensitivity) and how the DP landscapes of human-engineered and natural antibodies relate to one another. These gaps hinder fundamental developability profile cartography. To chart natural and engineered DP landscapes, we computed 40 sequence- and 46 structure-based DPs of over two million native and human-engineered single-chain antibody sequences. We found lower redundancy among structure-based compared to sequence-based DPs. Sequence DP sensitivity to single amino acid substitutions varied by antibody region and DP, and structure DP values varied across the conformational ensemble of antibody structures. Sequence DPs were more predictable than structure-based ones across different machine-learning tasks and embeddings, indicating a constrained sequence-based design space. Human-engineered antibodies were localized within the developability and sequence landscapes of natural antibodies, suggesting that human-engineered antibodies explore mere subspaces of the natural one. Our work quantifies the plasticity of antibody developability, providing a fundamental resource for multi-parameter therapeutic mAb design.

bioinformatics↗

bioRxiv2023

Simulation of adaptive immune receptors and repertoires with complex immune information to guide the development and benchmarking of AIRR machine learning

Machine learning (ML) has shown great potential in the adaptive immune receptor repertoire (AIRR) field. However, there is a lack of large-scale ground-truth experimental AIRR data suitable for AIRR-ML-based disease diagnostics and therapeutics discovery. Simulated ground-truth AIRR data are required to complement the development and benchmarking of robust and interpretable AIRR-ML methods where experimental data is currently inaccessible or insufficient. The challenge for simulated data to be useful is incorporating key features observed in experimental repertoires. These features, such as antigen or disease-associated immune information, cause AIRR-ML problems to be challenging. Here, we introduce LIgO, a software suite, which simulates AIRR data for the development and benchmarking of AIRR-ML methods. LIgO incorporates different types of immune information both on the receptor and the repertoire level and preserves native-like generation probability distribution. Additionally, LIgO assists users in determining the computational feasibility of their simulations. We show two examples where LIgO supports the development and validation of AIRR-ML methods: (1) how individuals carrying out-of-distribution immune information impacts receptor-level prediction performance and (2) how immune information co-occurring in the same AIRs impacts the performance of conventional receptor-level encoding and repertoire-level classification approaches. LIgO guides the advancement and assessment of interpretable AIRR-ML methods.

bioinformatics↗

bioRxiv2023

Weakly supervised identification and generation of adaptive immune receptor sequences associated with immune disease status

Adaptive immune receptor (AIR) repertoires carry immune signals as sequence motif imprints of past and present encounters with antigen (immune status). Machine learning (ML)-based identification and generation of antigen-specific immune receptors is potentially immense value for public health. The ideal training data for such ML tasks would be AIR datasets, where each sequence is labeled with its cognate antigen. However, given current technological constraints, sequence-labeled datasets are scarce, contrasted by an abundance of repertoire-labeled ones - AIR repertoire datasets where only the repertoire dataset, but not the individual AIRs, are labeled. Therefore, an unmet need exists for an ML approach that enables predictive identification and generation of disease-specific novel AIR sequences using exclusively repertoire-level immune status information. To address this need, we developed AIRRTM, an end-to-end generative model using an encoder-decoder architecture and Topic Modeling (TM) that requires exclusively repertoire-labeled AIR sequencing data as input. We validated AIRRTMs capacity to identify and generate novel disease-associated receptors on several ground truth synthetic datasets of increasingly complex immune signals and experimental data. AIRRTM broadens the discovery space for immunotherapeutics by enabling the exploitation of large-scale and broadly available immune repertoire data previously deemed largely unsuitable for this task.

immunology↗

bioRxiv2023

ANDA: An open-source tool for automated image analysis of neuronal differentiation

BackgroundImaging of in vitro neuronal differentiation and measurements of cell morphologies has led to novel insights into neuronal development. Live-cell imaging techniques and large datasets of images has increased the demand for automated pipelines for quantitative analysis of neuronal morphological metrics. ResultsWe present ANDA, an analysis workflow for quantification of various aspects of neuronal morphology from high-throughput live-cell imaging screens. This tool automates the analysis of neuronal cell numbers, neurite lengths and neurite attachment points. We used rat, chicken and human in vitro models for neuronal differentiation and have demonstrated the accuracy, versatility, and efficiency of the tool. ConclusionsANDA is an open-source tool that is easy to use and capable of automated processing from time-course measurements of neuronal cells. The strength of this pipeline is the capability to analyse high-throughput imaging screens.

cell biology↗

bioRxiv2023

Ultra-fast genotyping of SNPs and short indels using GPU acceleration

As decreasing DNA sequencing costs leads to a steadily increasing rate of generated data, the development of efficient algorithms for processing of the sequence data is increasingly important to reduce costs and energy consumption. Recent work have shown that genotyping can be done efficiently and accurately using alignment-free methods that are based on analyzing kmers from sequenced reads. In particular, we have recently presented the KAGE genotyper, which uses an efficient pangenome representation of known individuals in a population to further increase accuracy and efficiency. While existing genotypers like KAGE use the Central Processing Unit (CPU) to count and analyze kmers, the Graphical Processing Unit (GPU) has shown promising for reducing runtime for similar problems. We here present GKAGE, a new and improved version of KAGE that utilizes the GPU to further increase the computational efficiency. This is done by counting and analyzing large amounts of kmers in the many parallel cores of a GPU. We show that GKAGE is, on hardware of comparable cost, able to genotype an individual up to an order of magnitude faster than KAGE while producing the same output, which makes it by far the fastest genotyper available today. GKAGE can run on consumer-grade GPUs, and enables genotyping of a human sample in only a matter of minutes without the need for expensive high-performance computers. GKAGE is open source and available at https://github.com/kage-genotyper/kage.

bioinformatics↗

bioRxiv2022

BioNumPy: Fast and easy analysis of biological data with Python

Python is a popular and widespread programming language for scientific computing, in large part due to the powerful array programming library NumPy, which makes it easy to write clean, vectorized and efficient code for handling large datasets. A challenge with using array programming for biological data is that the data is often non-numeric and variable-length (such as DNA sequences), inhibiting out-of-the-box use of standard array programming techniques. Thus, a tradition in bioinformatics has been to use low-level languages like C and C++ to write efficient code. This makes the tools less transparent to the average computational biologist - making them harder to understand, modify and contribute to. We here present a new Python package BioNumPy, which adds a layer on top of NumPy in order to enable intuitive array programming on biological datasets. BioNumPy is able to efficiently load biological datasets (e.g. FASTQ-files, BED-files and BAM-files) into NumPy-like data structures, so that NumPy operations like indexing, vectorized functions and reductions can be applied to the data. We show that BioNumPy is considerably faster than vanilla Python and other Python packages for common bioinformatics tasks, and in many cases as fast as tools written in C/C++. BioNumPy thus bridges a long-lasting gap in bioinformatics, allowing the same programming language (Python) to be used across the full spectrum from quick and simple scripts to computationally efficient processing of large-scale data.

bioinformatics↗

bioRxiv2022

Reference-based comparison of adaptive immune receptor repertoires

B- and T-cell receptor (immune) repertoires can represent an individuals immune history. While current repertoire analysis methods aim to discriminate between health and disease states, they are typically based on only a limited number of parameters (e.g., clonal diversity, germline usage). Here, we introduce immuneREF: a quantitative multi-dimensional measure of adaptive immune repertoire (and transcriptome) similarity that allows interpretation of immune repertoire variation by relying on both repertoire features and cross-referencing of simulated and experimental datasets. immuneREF is implemented in an R package and was validated based on detection sensitivity of immune repertoires with known similarities and dissimilarities. To quantify immune repertoire similarity landscapes across health and disease, we applied immuneREF to >2400 datasets from individuals with varying immune states (healthy, [autoimmune] disease and infection [Covid-19], immune cell population). Importantly we discovered, in contrast to the current paradigm, that blood-derived immune repertoires of healthy and diseased individuals are highly similar for certain immune states, suggesting that repertoire changes to immune perturbations are less pronounced than previously thought. In conclusion, immuneREF implements population-wide analysis of immune repertoire similarity and thus enables the study of the adaptive immune response across health and disease states.

systems biology↗

bioRxiv2021

KAGE: Fast alignment-free graph-based genotyping of SNPs and short indels

Genotyping is a core application of high-throughput sequencing. We present KAGE, a genotyper for SNPs and short indels that is inspired by recent developments within graph-based genome representations and alignment-free methods. KAGE uses a pan-genome representation of the population to efficiently and accurately predict genotypes. Two novel ideas improve both the speed and accuracy: a Bayesian model incorporates genotypes from thousands of individuals to improve prediction accuracy, and a computationally efficient method leverages correlation between variants. We show that the accuracy of KAGE is at par with the best existing alignment-free genotypers, while being an order of magnitude faster.

bioinformatics↗

bioRxiv2021

CompAIRR: ultra-fast comparison of adaptive immune receptor repertoires by exact and approximate sequence matching

Adaptive immune receptor (AIR) repertoires (AIRRs) record past immune encounters with exquisite specificity. Therefore, identifying identical or similar AIR sequences across individuals is a key step in AIRR analysis for revealing convergent immune response patterns that may be exploited for diagnostics and therapy. Existing methods for quantifying AIRR overlap do not scale with increasing dataset numbers and sizes. To address this limitation, we developed CompAIRR, which enables ultra-fast computation of AIRR overlap, based on either exact or approximate sequence matching. CompAIRR improves computational speed 1000-fold relative to the state of the art and uses only one-third of the memory: on the same machine, the exact pairwise AIRR overlap of 104 AIRRs with 105 sequences is found in [~]17 minutes, while the fastest alternative tool requires 10 days. CompAIRR has been integrated with the machine learning ecosystem immuneML to speed up various commonly used AIRR-based machine learning applications. Availability and implementationCompAIRR code and documentation are available at https://github.com/uio-bmi/compairr. Docker images are available at https://hub.docker.com/r/torognes/compairr. The scripts used for benchmarking and creating figures, and all raw data, may be found at https://github.com/uio-bmi/compairr-benchmarking.

bioinformatics↗