Latest bioRxiv papers

Category: bioinformatics — Showing 50 items

• Tensor-based machine learning for multi-omics integrative clustering and feature discovery

  Zhang, Y.; Liu, L.; Liu, Z.; Liu, Q.; Ma, L.; Zhang, Z.

  Abstract

  Multi-omics integrative analysis is pivotal for elucidating complex molecular mechanisms and biological processes, yet remains challenging due to the high dimensionality and heterogeneity of multi-omics data. Here we present MIA, a machine learning framework for accurate sample clustering and feature discovery from multi-omics data. Unlike existing algorithms that primarily rely on two-dimensional representations, MIA models multi-omics data as a three-dimensional tensor and integrates tensor decomposition, fuzzy c-means, and an enhanced random forest model within a unified framework. Benchmarking on simulated and empirical datasets demonstrates that MIA consistently outperforms representative state-of-the-art algorithms in both clustering and feature identification. Application to multiple TCGA cancer types further shows its ability to stratify samples and identify molecular features associated with clinically relevant outcomes. Specifically, in glioblastoma, MIA reveals three previously uncharacterized subtypes with distinct prognostic profiles and uncovers feature genes strongly associated with subtype identity. These genes are further linked to therapeutic response and retain discriminative power across major glioblastoma cellular populations at single-cell resolution. Collectively, our results establish MIA as a generalizable computational framework for multi-omics integrative analysis, enabling systematic molecular stratification and interpretable feature discovery across diverse biological systems.

  bioinformatics2026-07-11v3

• DNA-MGC+: A versatile codec for reliable and resource-efficient data storage on synthetic DNA

  Khabbaz, R.; Mateos, J.; Antonini, M.; Kas Hanna, S.

  Abstract

  The biochemical processes underlying DNA data storage, including synthesis, amplification, and sequencing, are inherently noisy. Consequently, base-level insertion, deletion, and substitution (IDS) errors, as well as sequence-level dropouts, occur and pose major challenges for reliable data retrieval. Here we introduce DNA-MGC+, a DNA storage codec designed to enable reliable and resource-efficient data retrieval under diverse operating conditions. We evaluate DNA-MGC+ across a wide range of in silico and in vitro settings, including experiments with both Illumina and Nanopore sequencing, and show that it consistently outperforms several representative codecs from the literature. In particular, DNA-MGC+ achieves simultaneous gains in sequencing depth requirements, read cost, decoding time, storage density, and error-correction capability under explicit reliability constraints. These gains persist and become more pronounced for larger files, with DNA-MGC+ remaining reliable and efficient well beyond the practical scalability limits of the benchmarked codecs. Notable performance results include reliable decoding under IDS error rates of up to 24% in synthetic scenarios, and reliable retrieval at sequencing depths below 3x with read costs below 3.5 nts/bit under electrochemical synthesis for both Illumina and Nanopore sequencing.

  bioinformatics2026-07-11v2

• Differential T cell receptor clonotype abundance analysis with similarity-based counts weighting

  Buytenhuijs, F.; Smits, T. C.; Ankan, A.; Textor, J.

  Abstract

  To better understand immune responses, comparing the abundance of T cell receptors (TCRs) between conditions can provide insights into which T cells have proliferated or were involved in immune activation. This requires methods that can accurately identify significant differences in TCR sequencing (TCR-seq). For conventional RNA-seq data, well-established differential gene expression (DGE) analysis tools such as DESeq2 and edgeR have been developed. However, applying these methods to data presents additional challenges. TCR-seq data is highly sparse, overdispersed, and contains many artificial zeros, which can lead to inflated false-positive rates when using traditional approaches. While non-parametric methods like the Wilcoxon test better control false positives, they may suffer from lower statistical power. To address these issues, we propose a novel pre-processing step for TCR-seq data using network-based local weighting based on TCR sequence similarity. This pre-processing step improves the sensitivity and reduces the false-positive rates of methods like DESeq2 and edgeR while enhancing the power of the Wilcoxon test. Through empirical analysis of both simulated and real datasets, we show that combining our pre-processing step with the Wilcoxon test achieves robust performance, outperforming traditional RNA-seq methods. This simple but powerful approach to TCR-seq analysis could help advance our understanding of adaptive immune responses.

  bioinformatics2026-07-11v2

• Tokenizing single-cell transcriptomes as a native language for large language models

  Xiao, C.; Ding, Y.; Bian, H.; Chen, Y.; Wei, L.; Zhang, X.

  Abstract

  Large language models (LLMs) can process diverse forms of information once they are represented as tokens in a shared sequence space. However, single-cell transcriptomes remain a foreign modality to LLMs because they are continuous, high-dimensional molecular profiles rather than discrete linguistic units. Here, we propose CellTok, a tokenized single-cell language modeling approach that converts transcriptomic profiles into compact cellular token sequences and incorporates them into the vocabulary of a pretrained LLM. By representing cells as native tokens, CellTok enables cellular measurements, textual instructions, biological context, and multi-cell populations to be jointly processed within the same autoregressive modeling framework. Across diverse tasks, CellTok enable LLMs to recognize individual cells, interpret homogeneous and heterogeneous cell populations, infer disease-associated cellular states, predict cell-cell communication, model developmental trajectories, and generate cellular states. Moreover, prompt-based experiments show that providing appropriate biological context improves performance, indicating that CellTok can leverage LLM knowledge and contextual reasoning to support cellular data interpretation. These results demonstrate that single-cell transcriptomes can be transformed from a foreign molecular modality into a native language for LLMs, establishing a unified interface for modeling cells, populations, and biological knowledge in a shared token space.

  bioinformatics2026-07-11v2

• scDiagnostics: systematic assessment of cell type annotation in single-cell transcriptomics data

  Christidis, A.; Ghazi, A. R.; Chawla, S.; Turaga, N.; Gentleman, R.; Geistlinger, L.

  Abstract

  Although cell type annotation has become an integral part of single-cell analysis workflows, the assessment of computational annotations remains challenging. Many annotation tools transfer labels from an annotated reference dataset to a new query dataset of interest, but blindly transferring labels from one dataset to another has its own set of challenges. Often enough there is no perfect alignment between datasets, especially when transferring annotations from a healthy reference atlas for the discovery of disease states. We present scDiagnostics, a new open-source software package that facilitates the detection of complex or ambiguous annotation cases that may otherwise go unnoticed, thus addressing a critical unmet need in current single-cell analysis workflows. scDiagnostics is equipped with novel diagnostic methods that are compatible with all major cell type annotation tools. We demonstrate that scDiagnostics reliably detects complex or conflicting annotations using both carefully designed simulated datasets and diverse real-world single-cell datasets. Our evaluation demonstrates that scDiagnostics reliably identifies misleading annotations that systematically distort downstream analysis and interpretation and that would otherwise remain undetected. The scDiagnostics R package is available from Bioconductor (https://bioconductor.org/packages/scDiagnostics).

  bioinformatics2026-07-11v2

• Somatic mutation inference from single-cell transcriptomics: A survey in the esophagus

  Mendez-Alejandre, A.; Gonzalez-Menendez, D.; Vidal-Notari, S.; Skrupskelyte, G.; Rodriguez-Rodriguez, M.; Ajith, H.; Torralba, A. S.; Alcolea, M. P.; Piedrafita, G.

  Abstract

  Human somatic tissues accumulate mutations during normal aging. Some of these affect cancer-associated driver genes and confer mutant progenitor cells a competitive advantage that leads to clonal expansions. The human esophageal epithelium exemplifies this phenomenon, becoming a dense mosaic of competing mutant clones by adulthood. However, the phenotypic consequence of those mutations and their possible role in carcinogenesis remains unknown. Novel bioinformatic tools for de novo mutant detection from single-cell transcriptomics (scRNA-seq) could potentially leverage on the wealth of publicly available data to help draw mutant cell phenotypes in vivo. In this study we test SComatic algorithm's ability to identify somatic mutations in the normal, polyclonal esophageal epithelium. We analyze a public scRNA-seq dataset from a human cohort with multiple esophageal samples per donor, and an independent study in mice subjected to experimental mutagenesis where samples have been re-sequenced for validation. These unconventional experimental designs allow us to control unspecificity. We observe scRNA-seq variant calling output is heavily affected by undesired technical artifacts and germline variants, which we are able to reduce following a customized series of rational filters that enrich in somatic mutations. Final candidate mutations are then used to reconstitute clonal lineages and map them to differentiation trajectories in the UMAP embeddings. We find low read depth and sparse cellular sampling favor detection of passenger mutations and hinder driver mutant phenotypic inferences. Altogether, we showcase current limitations of scRNA-seq-derived mutation calling, while we offer methodological indications that should be considered for future studies aimed at investigating mutant clone behavior in normal polyclonal tissues from single-cell transcriptomics.

  bioinformatics2026-07-11v1

• Spatial mitochondrial lineage tracing uncovers a premetastatic niche and microenvironment programmed fate switching in osteosarcoma

  Xue, Y.; Su, Z.; Su, J.; Chu, A. S.; Wan, L.; Chen, M.; Cheung, J. P. Y.; Cheung, K. S. C.; Ho, J. W. K.

  Abstract

  Osteosarcoma progression involves complex spatiotemporal dynamics, yet the lineage relationships underlying tumor cell fate decisions remain poorly understood. Here we integrate single cell and spatial transcriptomics and mitochondrial variants-based lineage tracing to map the evolution of a late-stage, non-metastatic osteosarcoma. Single cell pseudotemporal reconstruction of malignant cells reveals a stepwise cascade of transcriptional programs that instructs bifurcation of COL3A1 progenitors into ALPL osteoblastic and THY1 mesenchymal lineages. Critically, we demonstrate that the metastatic THY1 mesenchymal cell fate is not governed by cell-autonomous transcriptional programs alone; this pro-tumorigenic state requires strict spatial licensing via direct co-localization with PLVAP dysfunctional endothelia to form a pro-metastatic niche (THY1-Endo) enriched for PTN/NOTCH signaling. To distinguish clonal ancestry from microenvironmental plasticity, we leveraged spatially resolved somatic mitochondrial variants as endogenous lineage tracers. A spatial autocorrelation filter confirmed significant clonal spatial coherence (Z = 10.07, p = 4 x10 -24). Phylogenetic reconstruction using a Wright-Fisher drift model coupled with a hidden Markov tree (WF-HMT) revealed a striking directional transition rate from COL3A1 to THY1 tumor cells (724.08) versus the reverse (4.09), a ~177-fold asymmetry, whereas the COL3A1 to ALPL transition rate was lower (0.47). Notably, drift--agnostic coarse VAF clustering failed to resolve ALPL versus THY1 bifurcation, underscoring that explicit modeling of stochastic mitochondrial drift is essential for uncovering directional fate locking. We propose a "time--space--lineage" relay model where sequential microenvironmental signals program tumor cell fate and pre-metastatic niche assembly through irreversible clonal commitment. This multi dimensional framework bridges single cell states, spatial organization, temporal dynamics, and clonal ancestry -underscoring the power of somatic mitochondrial variants to resolve clonal history and intercept cancer evolution.

  bioinformatics2026-07-11v1

• AGPI: An AI-Powered Genomic Pathogen Intelligence Platform for Integrated Classification, Visualization, and Therapeutic Targeting

  Goel, A.; Mishra, P.

  Abstract

  Rapid and accurate pathogen detection remains a major challenge in modern bioinformatics, as existing tools are often fragmented and require multiple specialized workflows. We present AGPI (AI-powered Genomic Pathogen Intelligence), an integrated platform that combines genomic sequence classification, biological enrichment, three-dimensional structural visualization, and AI-guided therapeutic prioritization within a single interpretable pipeline. AGPI employs a hybrid convolutional Bidirectional Gated Recurrent Unit (BiGRU) architecture trained on DNA sequences from 40 pathogen classes spanning viruses, bacteria, fungi, and protozoan pathogens. The model achieved 99.61% validation accuracy and 94.90% accuracy on an independent held-out evaluation of 600 pathogen sequences following iterative refinement. As a proof of concept, AGPI correctly classified a Zika virus genome with 96.14% confidence, retrieved curated biological context from 245 peer-reviewed studies, and identified Ribavirin as a leading therapeutic candidate against the Zika NS5 polymerase through AI-guided molecular docking. Multi-metric ligand similarity analysis further differentiated candidate compounds according to their structural and pharmacological properties. These results demonstrate that integrated AI-driven genomic pipelines can accelerate pathogen characterization and therapeutic hypothesis generation while providing an accessible and interpretable framework for infectious disease surveillance and computational drug repurposing.

  bioinformatics2026-07-11v1

• Metagenomic contextualization of proteins with state space models

  Azbijari, N.; Wynne, J. H.; David, M.; Thurber, A. R.

  Abstract

  Since the early adoption of metagenomics (the culture-free sequencing of microbial community genomes) in 2011, sequence data has increased over 500-fold across ecosystems. This surge in data has outpaced reliable taxonomic and functional annotation, with over half of sequences lacking confident functional assignment. These unknown sequences limit our understanding of microbial processes central to planetary health and human health. Recent advances in genomic language modeling have made progress in the interpretation of metagenomics datasets. Most state-of-the-art models rely on transformer architectures, which limit the maximum sequence length and therefore capture only a fraction of assembled metagenomic sequences due to the quadratic scaling of attention. This prevents training and inference on sequences with broad context, including multiple coding and non-coding regions. To overcome this limitation, we propose leveraging new model architectures that scale linearly with sequence length, making them more suitable for modeling longer metagenomic sequences. Here, we introduce Nammu, a mixed-modality Mamba-based foundation model with 167M parameters trained on the OpenMetaGenomic (OMG) corpus. Nammu is a bidirectional encoder trained with a 20K context length using a curriculum strategy, first on 64M protein sequences and then on 32M mixed-modality metagenomic contigs. We compared Nammu to gLM2, a mixed-modality transformer also trained on OMG using 37% more tokens, using taxonomy inference on a marine dataset from the Critical Assessment of Metagenome Interpretation (CAMI). Nammu outperforms gLM2 at every taxonomic level. We further assessed function via KEGG Orthology prediction in deep-sea metagenome-assembled genomes, where Nammu outperforms gLM2 (150M). These results demonstrate improved performance.

  bioinformatics2026-07-11v1

• Structure-guided computational design and mechanistic understanding of the p95HER2-targeting NAZ-mAb antibody and its variants

  Rawat, P.; Kyte, J. A.; Greiff, V.; Dorraji, E.

  Abstract

  Human epidermal growth factor receptor 2 (HER2) is an oncogenic receptor tyrosine kinase in breast cancer and other malignancies. A subset of HER2-positive tumours expresses 611-CTF-p95HER2, a tumour-specific, hyperactive truncated isoform associated with metastasis and treatment resistance that lacks most of the extracellular domain targeted by conventional HER2-directed antibodies. We previously developed NAZ-mAb (formerly known as Oslo-2), a monoclonal antibody against 611-CTF-p95HER2. Here, we describe a computational antibody-engineering workflow for designing variants of NAZ-mAb. Starting from the sequence alone, we modeled the NAZ-mAb-611-CTF-p95HER2 complex, generated a combinatorial mutational landscape using FoldX 5.0, and prioritized candidate variants using predicted interaction energy and developability criteria. Two variants representing distinct design strategies were selected for validation: an aromatic double mutant, NAZ-mAb v1 (L:S31W/L:H107W), and a conservative single mutant, NAZ-mAb v2 (L:S31M). Both variants were successfully expressed as recombinant IgGs; NAZ-mAb v2 achieved a five-fold higher recombinant expression yield than parental NAZ-mAb, while both variants retained antigen binding with a higher apparent signal than the parental antibody in indirect ELISA. However, Biacore two-state kinetic analysis revealed weaker affinities than the parental antibody (KD NAZ-mAb v1: 32.6 nM, NAZ-mAb v2: 9.45 nM vs. parental NAZ-mAb: 5.33 nM). These findings show that the computational workflow can generate experimentally tractable, antigen-engaging NAZ-mAb variants, while also highlighting the limitations of fixed-backbone interaction-energy ranking as a predictor of binding affinity and yield. This study provides a practical framework for computationally driven, developability-aware antibody optimization in the absence of experimental structural data.

  bioinformatics2026-07-11v1

• Combining transcriptomic resolutions and machine learning strategies uncovers new OXPHOS genes in Caenorhabditis elegans

  Zeballos - Goron, S.; Salinas, G.; Pazos Obregon, F.

  Abstract

  Assigning functions to genes remains a major challenge in biology, as many genes remain uncharacterized despite the availability of complete genome sequences. Oxidative phosphorylation (OXPHOS), the primary source of ATP in eukaryotes, exemplifies this gap. Although extensively studied in mammals, OXPHOS in other lineages has largely been inferred through sequence homology, an approach that may overlook lineage-specific components and propagate incorrect annotations. Here, we hypothesized that OXPHOS genes share characteristic transcriptional signatures that can be exploited for functional prediction. Using a curated set of 64 well-established OXPHOS genes, we combined supervised and unsupervised machine learning approaches to identify novel OXPHOS-associated genes in Caenorhabditis elegans. An ensemble of support vector machine, random forest, and k-nearest neighbors classifiers was trained on time-resolved bulk RNA-seq data using a novel informed bagging strategy and a two-round training scheme that incorporated weakly annotated genes after an initial prediction round. In parallel, embryonic and adult single-cell RNA-seq datasets were used to infer co-expression networks and identify clusters enriched in known OXPHOS genes. Integrating both approaches yielded a high-confidence set of candidate genes supported by strong predictive performance on an independent test set. Several candidates lacked prior functional annotation. Functional validation of one top-ranked candidate, ril-1, revealed significantly reduced oxygen consumption in mutant animals, supporting its involvement in mitochondrial respiration. Our results demonstrate that integrating complementary machine learning strategies with transcriptomic data across multiple biological resolutions enables systematic discovery of genes associated with complex cellular processes.

  bioinformatics2026-07-10v2

• synpact: accurate, memory-light PacBio HiFi read mapping via a hierarchy of locally-consistent syncmer blocks

  Aydin, M. S.; Sahlin, K.

  Abstract

  Motivation: Mapping PacBio HiFi reads is a routine task and serves as a central step in many bioinformatics analyses. However, the most accurate long-read mappers have a high memory consumption and are slow. Some light-weight mappers have been proposed for faster runtime, but their accuracy is not comparable to state-of-the-art mappers. With the increasing number of available reference sequences, memory-efficient and fast methods for read mapping without the large accuracy drop are desired. A general trade-off with seed-chain-extend mappers is selecting a single, fixed seed size, which forces a compromise between sensitivity and specificity. Results: We present synpact, a long-read mapper that uses several seed sizes (a hierarchy) constructed with Locally Consistent Parsing (LCP) over syncmers. A read is mapped by querying for matches at different levels, followed by sliding window voting. By storing only the coarse upper levels rather than the full hierarchy, the index holds several times fewer entries, while still handling errors by falling back from coarser to finer stored levels at query time. We benchmark synpact against popular long-read mappers on four genomes and different read lengths. For simulated PacBio HiFi data, synpact matches or approaches minimap2 accuracy with higher precision in most cases, while using roughly 5-13 times less peak memory (e.g., about 0.8GB vs. 10.7GB on human) and mapping faster on large or repetitive genomes (e.g., about 10 to 13 times faster than minimap2 on rye). On real HiFi reads synpact has high concordance with minimap2 across the four genomes, as opposed to the other lightweight long-read mappers. Availability and Implementation: synpact is written in Rust and is available at https://github.com/mahmudsami/synpact

  bioinformatics2026-07-10v2

• GenCore: Genomic distance estimation using Locally Consistent Parsing

  Ashyralyyev, A.; Sirvan, E.; Malikic, S.; Batu, T.; Sahinalp, C.; Alkan, C.

  Abstract

  In the era of exponential data generation, a fast, consistent, and efficient string processing technique is necessary to represent extensive genomic data. One of the earliest string processing techniques, predating MinHash and minimizer-based sketching, is Locally Consistent Parsing (LCP). This technique partitions an input string and identifies short, exactly occurring substrings called cores, which collectively cover the input string while maintaining Partition and Labeling Consistency. The iterative application of LCP yields progressively longer cores in a compressed format, thereby substantially enhancing the efficiency of genomic sequence representation and subsequent downstream analysis. We have previously developed LCPtools as the first iterative implementation of LCP for the DNA alphabet and demonstrated its effectiveness in identifying cores with minimal collisions. Here, we introduce GenCore, a computational method that leverages LCP cores for the first time to sketch and estimate genomic distances for closely related large genomes, and successfully reconstruct simulated progression trees. GenCore also successfully recapitulates primate phylogeny using both telomere-to-telomere (T2T) assemblies and the PacBio HiFi reads for assembly-free comparisons. Availability: GenCore is available at https://github.com/BilkentCompGen/gencore

  bioinformatics2026-07-10v2

• Classpose drives the discovery of colorectal cancer phenotypes in clinical grade whole slide images

  Mandal, S.; de Almeida, J. G.; Bräutigam, K.; Papanikolaou, N.; Graham, T. A.

  Abstract

  Cell phenotyping in histopathology samples is essential for diagnostic and research workflows. However, human expert annotation requires significant time and expertise while being affected by inter-observer variability. Here, we present Classpose, an easily trainable framework for cell segmenting and phenotyping built on top of Cellpose-SAM with state-of-the-art performance across 6 distinct datasets, outperforming competing methods. We show that this requires fine-tuning the entire network, highlighting how instance segmentation is a poor objective for downstream cellular classification. We apply it to a large whole slide image (WSI) colorectal cancer (CRC) cohort (SurGen) and show that Classpose-derived cellular organisation and morphology features can be used to determine novel spatial morphological phenotypes for clinically relevant molecular conditions (MMR deficiency, BRAF mutations, KRAS mutations) and to predict these same molecular conditions. We make Classpose models available and provide a user-friendly QuPath extension for widespread use by the digital pathology community.

  bioinformatics2026-07-10v2

• LeafRank: A phylodynamic framework for inferring relative fitness from single-cell phylogenies in chromosomally unstable tumors

  Wu, C.; Leder, K.; Wang, Z.; Sun, R.

  Abstract

  Tumors contain cancer cells with diverse growth potentials that shape evolutionary trajectories, yet this fitness diversity remains difficult to quantify in cases of whole-genome duplication (WGD) and chromosomal instability. We present LeafRank, a mathematical framework that leverages single-cell DNA-seq phylogenies to infer the relative fitness of individual cells. Using a multi-type branching process model, LeafRank integrates full tree topology, including branch lengths and bifurcation patterns, to estimate marginal fitness probabilities under punctuated evolutionary regimes driven by rare driver events. To account for elevated aberration rates following WGD, we introduce a tree-rescaling strategy that adjusts for lineage-specific genomic instability. Unlike methods focused on predefined subclones, LeafRank ranks all sampled cells, enabling flexible assessment of growth heterogeneity. Simulations demonstrate high accuracy across spatial and non-spatial virtual tumors. Applied to ovarian cancer, LeafRank reveals directional and parallel selection in WGD tumors and identifies recurrent copy number events enriched in high-fitness lineages. WGD lineages do not show immediate growth advantages but acquire fitness through subsequent alterations.

  bioinformatics2026-07-10v2

• The role of space in explaining macroecological patterns of microbial abundance

  Gutierrez-Arroyo, A.; Lampo, A.; Cuesta, J. A.

  Abstract

  Understanding the origin of universal macroecological patterns in microbial communities remains a central open question in ecology. A key observation is that species abundance fluctuations across diverse biomes are well described by a gamma distribution, yet the mechanism responsible for this regularity is debated. Prevailing explanations invoke exogenous stochastic forcing, while endogenous interaction-based approaches -grounded in generalized Lotka-Volterra (gLV) dynamics- have so far failed to reproduce this pattern. Here we show that incorporating spatial structure resolves this discrepancy. In a gLV model with constant migration, local abundance dynamics remain inconsistent with a gamma distribution. However, when the community is embedded in a fragmented landscape as a metacommunity -with species dispersing among patches- aggregating abundances across patches yields distributions that closely match the empirically observed gamma form. We further demonstrate that this result can be reproduced by aggregating independent realizations of the constant-migration gLV model, entailing statistical aggregation rather than a specific biological mechanism as the origin of this pattern. Our findings highlight the fundamental role of spatial structure in shaping microbial macroecology, and suggest that observed abundance distributions may largely reflect the spatial coarse-graining inherent in metagenomic sampling.

  bioinformatics2026-07-10v2

• Generative continuous time model reveals epistatic signatures in protein evolution

  Pagnani, A.; Barrat-Charlaix, P.

  Abstract

  Protein evolution is fundamentally shaped by epistasis, where the effect of a mutation depends on the sequence context. As standard phylogenetic methods assume independently evolving sites, there is a need for more complex models based on accurate estimations of the fitness landscape. Good candidates are modern generative models -- such as the Potts model -- which successfully capture epistatic effects. However, recent work on generative evolutionary models usually use discrete time, making them difficult to integrate with the standard frameworks in evolutionary biology. We introduce a continuous-time sequence evolution model using the Gillespie algorithm and parameterized by a generative Potts model. This approach enables us to simulate realistic, family-specific evolutionary trajectories and allows for direct comparison with independent-site models. Surprisingly, we find that while epistasis significantly slows down evolution, it does not change the average evolutionary rates at individual sites. This is explained by the rate heterogeneity caused by context-dependence: we show that the rate at some positions varies between null to high values depending on the context, while other positions are essentially independent from the context. Finally, we show that epistasis leads to a systematic underestimation bias in the inference of evolutionary distance between sequences. Overall, our work provides a new tool for simulating realistic protein evolution and offers novel insights into the complex interplay between epistasis and evolutionary dynamics.

  bioinformatics2026-07-10v2

• Reference-Based Library Construction Improves Performance in low-input Workflows

  Charkow, J.; Ghaznavi, M.; Seale, B.; Peng, J.; Gingras, A.-C.; Rost, H.

  Abstract

  In low input mass spectrometry-based proteomics, Data Independent Acquisition (DIA), is quickly becoming the method of choice for label free quantification. Whether using empirical or in silico spectral libraries, performance is dependent on the library; however, the optimal library construction strategy for low input proteomics remains an open question. To address this, we examine and develop library construction approaches that are compatible with both spectrum-centric and peptide-centric analysis workflows. These approaches leverage a closely related, high-quality sample to improve library quality. First, we validated our approach in bulk sample amounts where we observed that the effects of gas-phase fractionation based library construction is dependent on the software framework, with improvements more pronounced in OpenSWATH compared to DIA-NN. In OpenSWATH, our peptide-centric library reconstruction workflow consistently outperforms a transfer learning strategy, an emerging alternative approach. In DIA-NN, trends are dependent on library source highlighting OpenSWATH's stronger dependence on the search space. In low-input applications, such as single-cell-equivalent injection amounts (100 pg) of HeLa cell digest on a timsTOF SCP, our library construction approach provided more pronounced improvements across both software tools compared to bulk samples. Using a peptide-centric reconstruction approach with the OpenSWATH analysis framework, we detected over 15,000 peptide precursors (2480 protein groups), a 90% improvement over the original library. Furthermore, using a spectrum-centric construction approach, peptide precursor identification rates improved over 6-fold ( ~1000 to ~6000). Our strategy provides a practical solution for generating high-quality libraries in low-input applications.

  bioinformatics2026-07-10v2

• Enhanced proteome relative quantification using refined quantotypic spectral libraries

  Barnes, B. A.; Alharbi, H.; Unwin, R.

  Abstract

  Plasma proteomics is used for a variety of applications including biomarker discovery, disease monitoring, and drug development. Data-independent acquisition (DIA) has vastly improved the breadth of proteins that are identified from samples; however, given challenges in reproducibility and translation, it is critical that the quantitative performance of these methods is reliable. Analysis of global proteomics data typically incorporates information from all detected peptides. However, some peptides do not reflect their parent protein amount, due to irreproducible digestion, modification, analytical interferences or instability. We hypothesise that including these peptides impacts protein relative quantification, and thus, a refined spectral library containing only quantitatively representative peptides provides superior protein quantification. By analysing a defined multi-species spike-in model, we show that refining a plasma spectral library by removing precursors that fail to meet quality control metrics (25.4% of all identified precursors) reduces noise and variability, improving precision, accuracy and differential abundance analysis by up to ~11%, with minimal identification losses and substantial reduction in computational demand. This demonstrates proof-of-concept that refining spectral libraries produces results that prioritize quantification quality over quantity. This approach could enable development of universal tissue-specific refined spectral libraries able to improve quantification quality with easy implementation and minimal processing time.

  bioinformatics2026-07-10v1

• Coordinate- and Sequence-Based Features for a new Combined Annotation-Dependent Depletion Framework of Structural Variants (CADD-SV v2.0)

  Catona, O.; Kircher, M.

  Abstract

  Structural variants are a major source of genomic variation and contribute to human disease and evolution through diverse mechanisms, yet their functional interpretation remains challenging. We present CADD-SV v2.0, an improved machine learning framework for scoring SV deleteriousness that expands on the original CADD-SV implementation. This version introduces a unified Random Forest model trained on an expanded set of proxy-neutral and proxy-deleterious variants drawn from human and non-human primate genomes. The model integrates updated genomic annotations, including constraint metrics, regulatory elements, and chromatin architecture features. It scores Deletions, Insertions, Duplications and Inversions based on a single scoring framework that uses both the variant and its flanking regions. To complement this framework, we also explore sequence-based annotations derived from SegmentNT, a deep learning model that provides functional predictions from DNA sequence at nucleotide resolution. Our analysis evaluated whether sequence-derived functional signals can provide additional information for SV prioritization and whether additional models with these features alone or in combination with previous coordinate-based annotations can be used. CADD-SV v2.0 outperforms its previous version and other tools in prioritizing deleterious variants across major SV types, including some previously unsupported, and substantially improves the computational workflow, increasing predictive power for genome-wide SV interpretation.

  bioinformatics2026-07-10v1

• Adaptive 2.5D base-pairing subgraph search detects RNA small-molecule binding sites

  Nitchi, D.; Waldispuhl, J.; Oliver, C.

  Abstract

  Ribo-LENS is a geometric deep-learning framework for detecting small-molecule binding sites in RNA structures. It is designed to exploit two properties of RNA base-pairing networks: their robustness to conformational fluctuation and the functional signatures they encode. By reasoning directly in the space of base-pairing subgraphs, Ribo-LENS assembles coherent binding sites, in contrast to methods that score residues independently. In extensive experiments, Ribo-LENS is competitive with, and often outperforms, large all-atom co-folding models (AlphaFold3, Chai-1), fine-tuned language models (GerNA-Bind), and structure-based tools (RNAsite), raising mean MCC to 0.380 (versus 0.321 for the state-of-the-art GerNA-Bind). It is strongly robust to apo/holo rearrangement, with its accuracy tracking the base-pairing graph (Spearman rho = 0.82 with binding-site graph edit distance) rather than backbone displacement (rho = -0.15 with RMSD), and depends far less on sequence homology than competing predictors. In an end-to-end, sequence-based virtual screen of the ROBIN assay (approximately 25,000 compounds), Ribo-LENS guides docking to a small predicted pocket, matching a blind all-atom cavity search (enrichment factors up to 6.1) at a fraction of the search cost; on two SARS-CoV-2 targets its predicted sites align with NMR chemical-shift perturbations. Ribo-LENS turns coarse base-pairing structure into a practical entry point for screening the vast, largely unexplored RNA target space.

  bioinformatics2026-07-10v1

• Deconvolving the spatiotemporal chromatin landscape through the cell cycle

  Tran, T. Q.; Li, Y.; MacAlpine, D. M.; Hartemink, A. J.

  Abstract

  Profiling genomic processes during the cell cycle is challenging because synchronized populations gradually lose synchrony as individual cells progress through the cycle at different rates and divide asymmetrically. Researchers have addressed this challenge by modeling the loss of synchrony and applying sophisticated branching process deconvolution methods to mitigate the effects of imperfect synchrony. Such methods have been used to deconvolve cell cycle transcription, but despite the central role of the chromatin landscape in orchestrating eukaryotic transcription and replication, comparable approaches to deconvolving cell cycle chromatin occupancy have not been developed, because the data are orders of magnitude larger and because DNA replication introduces non-uniform copy number effects across the genome during S phase. We present CyCLOPS, a computational framework that overcomes these technical challenges, enabling deconvolution of the genome-wide chromatin landscape throughout the cell cycle at high spatiotemporal resolution. We apply CyCLOPS to MNase-seq data collected from synchronized yeast populations at 10-minute intervals to produce the first dynamic atlas of genome-wide chromatin occupancy through the cell cycle, profiled at sub-minute resolution. We identify functional groups of cell cycle genes through chromatin-based clustering and uncover chromatin regulatory dynamics, including at non-genic loci. Our atlas reveals that chromatin occupancy and transcription fluctuate largely independently.

  bioinformatics2026-07-10v1

• Extended t-cores for the de novo identification of transposable elements and other inexact repeats from short read RNAseq data

  Darmon, S.; Mary, A.; Lacroix, V.

  Abstract

  Transcribed repeats represent a major challenge in the de novo assembly of transcriptomes from short RNA-seq reads. Young transposable elements (TEs) and other inexact repeats create dense and ambiguous regions in the assembly graph, preventing the correct assembly of transcripts. In this paper, we introduce a fully de novo method based on the discovery of dense regions in the compacted De Bruijn graph (DBG) to identify such repeats directly from short reads RNA-seq data, without requiring a reference genome or repeat database. Our approach defines the extended t-cores, subgraphs of the DBG that capture the complex topology induced by highly expressed inexact repeats appearing in RNA-seq reads. Independently of its interest for transcriptome assembly, the proposed method appears to be effective for the de novo identification of repeats in transcriptomes. After classifying cores using sequence-based motifs to distinguish simple repeats from potential TEs, we demonstrate its potential for the de novo discovery of transposable elements. We validate the approach on a Mus musculus dataset using expressed TE consensus sequences, showing that extended t-cores correspond to known expressed TE families. We also illustrate its de novo discovery potential on a non-model species, Canis lupus familiaris, where the method was also able to recover known transposable elements.

  bioinformatics2026-07-10v1

• pylimma: a faithful, AnnData-native Python port of R limma for differential expression analysis

  Mulvey, J.

  Abstract

  pylimma is a faithful Python port of limma, intended to bring one of the most widely used tools for differential expression analysis to the developing Python ecosystem for transcriptomics and proteomics. We validated pylimma against the existing R implementation through 227 function-level comparisons and across six real world datasets spanning microarray, RNAseq, proteomics and single-cell transcriptomics. pylimma reproduces limma's numerical output to a median agreement of 13 significant figures and calls identical sets of differentially expressed features and gene sets. This supports its use as a drop-in replacement for the R implementation.

  bioinformatics2026-07-10v1

• Spatial Autocorrelation Aware Resampling Improves Cell-Cell Interaction Inference in Spatial Transcriptomics Data

  Khatri, P. H.; Newton, M. A.; Kendziorski, C. A.; Dinh, H. Q.

  Abstract

  Spatial transcriptomics has enabled finer-grained analyses of cell-cell interactions through the co-expression of ligands and their cognate receptors, thereby accounting for the spatial constraints of signaling. However, existing methods employ random permutations or analytic calculations to assess statistical significance, neither of which accounts for spatial autocorrelation, a common property of spatially resolved data. Here, we introduce SOAAR (Spatial Omics Autocorrelation-Aware Resampling), a statistical method for testing gene-gene correlations in spatial data that maintains spatial gene-level autocorrelation in resampled datasets used to generate null distributions. SOAAR uses spatial map patterns to decompose autocorrelation. The associations between gene expression and autocorrelation patterns are then randomized to construct resampled datasets used for evaluating significance testing. We showed that SOAAR maintains gene-level spatial autocorrelation and yields a lower false-positive rate than random permutations across varying degrees of gene-level spatial autocorrelation in simulation studies. In a 10X Visium dataset from 10 HNSCC patients treated with immunotherapy, SOAAR filters out low-confidence interactions that were present in only individual samples or in fewer than 3 samples. That led to the identification of a consistent signature of T-cell recruitment in Responder patients and a resistance signature driven by angiogenesis and tumor cell proliferation in Non-Responders. Similar trends were observed in a larger cohort of 23 patients profiled with single-cell spatial CosMX SMI data, revealing immune cell interactions in response to immunotherapy. Overall, SOAAR provides a more calibrated framework for testing spatial correlation, grounded in spatial statistics. Future developments will seek to link localized correlation patterns to downstream changes in biological pathways, thereby informing biomarker and therapeutic target discovery.

  bioinformatics2026-07-10v1

• CellPilot: an agentic framework that pilots small language models through autonomous single-cell annotation

  Jiang, S.; Qi, C.; Chen, Y.; Song, X.; Wei, Z.

  Abstract

  Large language models can annotate cell types from marker gene lists, but they typically operate after preprocessing and clustering are complete, treating annotation as a terminal labeling step rather than controlling the analytical decisions that produce the evidence for cell identity. We present CellPilot, an agentic framework that guides a locally deployable small language model through the full single-cell analysis workflow, from raw count matrices to cluster-level annotation. CellPilot combines standard single-cell analysis tools with structured workflow control and observation-guided reasoning, allowing the model to plan analyses, execute tools, inspect intermediate results and revise decisions within a traceable session. On GTEx, structured workflow orchestration raised the same 8B model from 0.39 in a prompt-only setting to 0.89, closing most of the gap to GPT-4o (0.92) within the same framework; the framework gain was substantially larger for the smaller backbone across datasets (+0.35 versus +0.19). Across GTEx, Tabula Sapi- ens, and Mouse Cell Atlas, CellPilot achieves cluster-level annotation accuracies of 0.891, 0.750, and 0.773, outperforming representative reference-based, marker-based, and LLM-based methods. CellPilot confidence scores were associated with annotation correctness and supported post hoc filtering, while complete execution traces were retained for each analysis. These results suggest that structured workflow orchestration can be a critical determinant of performance in multi-step single-cell analysis, enabling locally deployable small language models to approach larger proprietary models while preserving transparency and practical usability.

  bioinformatics2026-07-10v1

• MKMC enables reference-free transcriptomic analysis using k-mer representations

  Mboning, L.; Dlugosz, M.; Kokot, M.; Chen, J.; Costa, E. K.; Wu, M.-R.; Wang, S.; Bouchard, L.-S.; Deorowicz, S.; Pellegrini, M.

  Abstract

  Traditional RNA-seq analysis depends heavily on genome alignment and gene annotation, limiting its utility in non-model organisms and introducing biases that can obscure regulatory complexity. We present MKMC (Multi-sample Kmer Counter), a scalable, reference-free toolkit for RNA-seq analysis that leverages k-mer-based statistics to detect biological variation without requiring alignment. MKMC integrates fast k-mer counting, abundance matrix generation, normalization, dimensionality reduction, and differential analysis into a unified workflow. Across diverse datasets, MKMC recapitulates key biological signals, including sex differences in killifish liver, and matches alignment-based pipelines in differential expression analysis and transcriptomic age prediction. Notably, MKMC detects isoform-specific events missed by traditional methods, one of which we validated using in situ hybridization. These results reveal previously hidden isoform-level regulatory events that contribute to sex- and age-associated transcriptional programs. MKMC offers a robust, extensible alternative to alignment-based approaches, enabling transcriptomic discovery across both model and non-model systems. While we focus here on RNA-seq as a primary application, MKMC is broadly applicable to any k-mer-based analysis of next-generation sequencing data.

  bioinformatics2026-07-10v1

• Modelling the impacts of imports and non-native subspecies hybridisation in honeybees

  de Carlos, I.; Strachan, L.; McCormack, G. P.; Gorjanc, G.; Obsteter, J.

  Abstract

  Human-mediated movement of organisms for agriculture and ecosystem services often results in hybridisation and introgression between populations of native and non-native species. While introgression may increase genetic diversity, it can erode unique adaptations and reduce fitness, threatening the survival of native lineages. Honeybees offer a good model with extensive records, queen trade and migratory beekeeping facilitating genetic exchange among subspecies. To explore these dynamics, we used SIMplyBee to simulate hybridisation between populations of native Apis mellifera mellifera and non-native A. m. carnica. We adopted the parameters from the Irish honeybee population that maintains relatively low levels of import, but is threatened by commercial imports. The model included colony honey yield and fitness as complex polygenic traits. We simulated varying import rates, genetic correlations between fitness in native and non-native environments, and spatial distributions of introgression over 20 years, measuring levels and rate of introgression and genetic means for both traits. Increased imports accelerated introgression and induced a trade-off between higher honey yield and lower fitness, and decreasing genetic correlations between environments amplified fitness decline. Spatial simulations showed the spread of introgression across the entire simulated area. Halting imports reversed the trend, but purging of introgressed material was slow and varied among replicates. These findings highlight the trade-off between short-term production gains and long-term losses in fitness and adaptation. Our modelling framework provides a reference for exploring introgression in other systems, emphasising that sustainable management of introgression requires restricting imports and breeding locally adapted populations rather than relying on non-native imports.

  bioinformatics2026-07-09v3

• Emergence of Biological Structural Discovery in General-Purpose Language Models

  Wang, L.

  Abstract

  Large language models (LLMs) are evolving into engines for scientific discovery, yet the assumption that biological understanding requires domain-specific pre-training remains largely unchallenged. Here we report that general-purpose LLMs possess an emergent capability for biological structural discovery. Under strict, shortcut-controlled evaluation, a small-scale GPT-2 (124M) fine-tuned solely on English paraphrase discrimination detects protein homology zero-shot at ROC-AUC 0.79 on a shortcut-controlled benchmark. Controls establish that the ability is conferred by pre-training, not architecture: a randomly initialized GPT-2 is at chance (0.52). To exclude the possibility that public checkpoints were contaminated with biological data, we train our own GPT-2 from scratch on an English-only web corpus; it reproduces the transfer (0.76), proving the effect arises from linguistic pre-training alone. Network-based interpretability reveals a deep structural isomorphism: the discriminative signal localizes to deep layers (0.97 at layer 9), and attention analysis surfaces modality-agnostic "difference" operators. Scaling to massive instruction-tuned models further improves performance, including in the remote-homology "twilight zone", which we report as an exploratory upper bound because those models' training corpora are undisclosed. We formalize these tasks through the BioPAWS benchmark. Our controlled results, obtained entirely on models with known training data, establish that abstract logical structures distilled from human language constitute a genuine, if bounded, cognitive prior for decoding the syntax of biology.

  bioinformatics2026-07-09v2

• VicMAG, an open-source tool for visualizing circular metagenome-assembled genomes highlighting bacterial virulence and antimicrobial resistance

  Tsuda, Y.; Tanizawa, Y.; Vu, T. M. H.; Nishimura, Y.; Shintani, M.; Abe, H.; Hasebe, F.; Kasuga, I.; Nagao, M.; Suzuki, M.

  Abstract

  Bacterial pathogens spread in clinical and environmental settings, and mobile genetic elements (MGEs), such as plasmids and phages, mediate the transfer of virulence factor genes (VFGs) and antimicrobial resistance genes (ARGs) among bacterial communities. Metagenomic analysis of environmental and wastewater samples using highly accurate long-read sequencing technologies, such as PacBio HiFi sequencing, provides valuable insights into monitoring the regional spread of VFGs and ARGs, including dissemination mediated by MGEs. No visualization tool is currently available for the comprehensive display of numerous resulting circular metagenome-assembled genomes (cMAGs) with functional gene annotations. Here, we developed VicMAG, a visualization tool for highly complex cMAGs derived from long-read metagenome assemblies annotated using updated databases of VFGs, ARGs, and MGEs. Using 353 cMAGs from PacBio HiFi sequencing of a wastewater sample, we demonstrated the utility of VicMAG for metagenome visualization. VicMAG provides comprehensive, size-aware visualization of cMAGs representing bacterial chromosomes and plasmids, annotated with VFGs, ARGs, and phages. By simultaneously visualizing all cMAGs in a framework, VicMAG facilitates a holistic understanding of the distribution and genomic context of VFGs and ARGs across complex microbial communities. This tool supports integrated surveillance of bacteria associated with virulence and antimicrobial resistance across clinical, environmental, and One Health contexts.

  bioinformatics2026-07-09v2

• Expanding the Landscape of Disordered Flexible Linkers: A Structural and Computational Framework for DLD dataset assembly

  meng, d.; Glavina, J.; Garcia Alvarez, H. M.; Leonetti, C. O.; Pollastri, G.; Chemes, L. B.

  Abstract

  Disordered flexible linkers (DFLs) are functional elements found within intrinsically disordered regions that carry out key functions by connecting domains and/or short linear motifs. Understanding the features of DFLs is limited by the lack of comprehensive datasets and accurate predictive models. In this study, we propose a classification for DFLs that includes linkers joining two domains (DLD), a domain and a motif or two short linear motifs. We developed a workflow that allows the systematic identification of DLD-type linkers from protein structures and created a comprehensive dataset known as the DLD dataset. The DLD dataset includes 1640 independent domain linkers (IDLs) which expands currently available linker datasets and annotates related regions such as dependent-domain linkers, intra-domain loops, and termini. Our data collection process integrates missing residue completion and smoothing of short secondary structure stretches enabling to capture a higher number of longer IDLs. We assessed the features of IDLs using t-SNE analysis and protein language model embedding with a CNN-based classifier as well as PCA analysis. IDLs can be distinguished from other disordered and folded protein regions, and their features highly overlap with DisProt Linkers, considered the gold standard for linker annotation. The DLD dataset offers a valuable resource for researchers seeking to investigate the features of disordered flexible linkers and to improve the accuracy and generalizability of DFL predictive models. The DLD dataset is available via an interactive web server at https://dld.chemeslab.org/ where linkers are annotated with sequence and structural features and can be visualized using a structure viewer.

  bioinformatics2026-07-09v2

• CircDiscoverer: A multispecies comprehensive resource for circRNA-protein interactions and RNA modification landscapes

  Srinivasan, S.; Kumar, S.; Chatterjee, S.; Chande, A.

  Abstract

  Circular RNAs (circRNAs) regulate various cellular processes by interacting with miRNAs, proteins, and by encoding peptides. Compared to circRNA-miRNA interactions, circRNA-protein interactions (CPIs) and circRNA modifications have been relatively less explored. Here, we developed a comprehensive user-friendly web resource, CircDiscoverer, to explore CPIs and modification landscapes across multiple species, including Homo sapiens, Mus musculus, Drosophila melanogaster, and Arabidopsis thaliana. CircDiscoverer integrates manually curated literature-supported CPIs with computationally predicted interactions. Furthermore, it offers comprehensive insights into protein-binding profiles and detailed information on interacting circRNAs, including qRT-PCR primer sequences, guide RNAs for experimental validation and potential RNA modifications, thereby providing an integrated platform for further research. CircDiscoverer is available at https://aclab.iiserb.ac.in.

  bioinformatics2026-07-09v2

• LeafRank: A phylodynamic framework for inferring relative fitness from single-cell phylogenies in chromosomally unstable tumors

  Wu, C.; Leder, K.; Wang, Z.; Sun, R.

  Abstract

  Tumors contain cancer cells with diverse growth potentials that shape evolutionary trajectories, yet this fitness diversity remains difficult to quantify in cases of whole-genome duplication (WGD) and chromosomal instability. We present LeafRank, a mathematical framework that leverages single-cell DNA-seq phylogenies to infer the relative fitness of individual cells. Using a multi-type branching process model, LeafRank integrates full tree topology, including branch lengths and bifurcation patterns, to estimate marginal fitness probabilities under punctuated evolutionary regimes driven by rare driver events. To account for elevated aberration rates following WGD, we introduce a tree-rescaling strategy that adjusts for lineage-specific genomic instability. Unlike methods focused on predefined subclones, LeafRank ranks all sampled cells, enabling flexible assessment of growth heterogeneity. Simulations demonstrate high accuracy across spatial and non-spatial virtual tumors. Applied to ovarian cancer, LeafRank reveals directional and parallel selection in WGD tumors and identifies recurrent copy number events enriched in high-fitness lineages. WGD lineages do not show immediate growth advantages but acquire fitness through subsequent alterations.

  bioinformatics2026-07-09v1

• Coding agents author interpretable single-cell embedding models from the literature

  Brunn, N.; Krissmer, S. M.; Frosch, M.; Frick, M.; Prinz, M.; Binder, H.

  Abstract

  The single-cell literature catalogs cell states as validated marker-gene programs - a sparse, compositional prior. Conventional embedding methods do not leverage this prior and learn cell-state structure de novo from the expression matrix, producing dense dimensions needing post-hoc interpretation and batch correction. Here we show coding agents can author single-cell embedding models directly from the literature. Given a scenario that focuses this literature lens on a chosen biological subdomain, the agent edits a structured Python template, curating named, literature-cited gene programs and composing them into axes, without a gene-set database, training, or sight of the data. Across mouse and human tissues these zero-shot embeddings are competitive in biological quality with conventional, foundation-model, and program-informed baselines, batch-robust by construction and reproducible across runs, complementing data-driven embeddings. Because each dimension is a named, cited gene program, the embedding is interpretable and auditable, and its composable axes can be steered into a developmental tree.

  bioinformatics2026-07-09v1

• Mind the Alignment Gap: A Spatial Transcriptomics Benchmark for Scientific Coding Agents

  Chen, Y. T.; Hicks, S. C.

  Abstract

  Scientific coding agents are difficult to benchmark because many research tasks require executable work yet produce ambiguous or hard-to-verify outputs. Because benchmark construction requires substantial time and resources, automation offers a path to accelerating methods evaluation. We introduce an interactive framework for constructing scientific-agent benchmarks from peer-reviewed papers and diagnosing agent behavior through trace inspection. We apply it as a case study in spatial transcriptomics alignment, constructing 40 tasks from SABench in which agents submit coordinate tables aligning pairs of two-dimensional tissue slices. Across 120 runs and three configurations, we compare a basic prompt, a package-aware prompt, and a full prompt with a prebuilt virtual environment. In this setting, richer package and environment context increased tool exploration but reduced the mean alignment score relative to the basic prompt (0.36 vs. 0.43; 95% CI, [-0.11,-0.03]). Trace inspection showed that added scaffolding often induced unnecessary transformations, fragile package-first workflows, and infrastructure failures. These results illustrate how specialized tooling can alter agent behavior and why scientific-agent benchmarks should evaluate agent traces and the workflows that produce them in addition to the final outputs.

  bioinformatics2026-07-09v1

• Rectangle: robust and scalable multiscale deconvolution informed by single-cell RNA sequencing data

  Eder, B.; Rigato, I.; Dietrich, A.; Merotto, L.; Sturm, G.; Treis, T.; List, M.; Theis, F.; Finotello, F.

  Abstract

  Bulk RNA-seq enables effective profiling of large cohorts and complex experimental designs, but current single-cell-informed deconvolution methods incompletely resolve closely related cell phenotypes, do not scale efficiently to large single-cell datasets, or fail to account for cellular content not represented in the reference. Here, we present Rectangle, an scverse Python framework for single-cell-informed deconvolution of bulk RNA-seq data. Rectangle combines multiscale deconvolution, capturing cellular composition across multiple resolution levels, with explicit modeling of unknown cellular content. In a diverse, cross-method benchmark, Rectangle achieved consistently strong performance across all evaluated metrics, demonstrating high accuracy, high resolution, low spillover, strong scalability and efficiency, and robustness to unknown cellular content. By bridging the resolution of single-cell transcriptomics with the scale and cost-efficiency of bulk RNA-seq, Rectangle enables cell-type and cell-state profiling at scale, supporting population-scale cellular biomarker discovery and tracking of cellular dynamics in settings impractical for comprehensive single-cell sequencing.

  bioinformatics2026-07-09v1

• Gene Program Negotiation Defines Cellular Identity in Single-Cell Transcriptomes

  Sung, J.-Y.; Cheong, J.-H.

  Abstract

  Single-cell transcriptomics has transformed the characterization of cellular heterogeneity by enabling systematic analysis of biological gene programs. However, existing computational approaches primarily quantify the activity of individual programs independently and therefore provide limited insight into how multiple simultaneously active programs collectively determine cellular identity. Here we present Gene Program Negotiation (GPN), a graph-based computational framework that models regulatory decision-making among concurrently active biological programs. GPN reconstructs cell-specific program interaction networks from local transcriptional neighborhoods and quantifies regulatory organization using the Gene Program Coherence Index (GPCI) together with measures of local regulatory conflict, program diversity, and dominance. These graph-derived properties enable the classification of individual cells into five regulatory decision states: Consensus, Competition, Negotiation, Dominance, and Low activity. Applying GPN to gastric cancer single-cell transcriptomes revealed that cells sharing the same dominant biological program frequently occupied distinct regulatory decision states, demonstrating that dominant program identity alone does not uniquely define cellular regulatory organization. Competition states consistently exhibited elevated local regulatory conflict and were preferentially enriched among transition-like cells, indicating that regulatory competition is closely associated with transcriptional plasticity. Independent validation using glioblastoma single-cell transcriptomes reproduced these regulatory patterns without modification of the computational framework, supporting the robustness and generalizability of the approach across biologically distinct malignancies. These findings establish regulatory negotiation as an additional layer of cellular organization beyond conventional gene-program activity analysis. By explicitly modeling interactions among simultaneously active biological programs, GPN provides a general computational framework for investigating regulatory coordination, cellular plasticity, and dynamic cell-state organization in single-cell transcriptomic data.

  bioinformatics2026-07-09v1

• IgGM2: An All-Atom Foundation Model for Adaptive Immune Receptor Design

  Ma, J.; Wu, F.; Yao, L.; Gao, J.; Wang, R.; Li, Q.; Yang, N.; Jiang, S.; Huang, D.; Pan, X.; Zhu, Y.; Hou, T.; Yao, J.; Yan, J.

  Abstract

  Accurate immune receptor design requires modeling the coupled variation of amino-acid sequence, full-atom conformation, and target-binding geometry across antibodies, nanobodies, and T-cell receptors (TCRs). Existing methods often address only part of this problem, either by separating structure generation from sequence design, relying on fixed-backbone inverse folding, or focusing on a single receptor class. We introduce IgGM2, a unified all-atom generative framework for immune receptor structure prediction and CDR sequence-structure co-design. IgGM2 follows a structure-to-design strategy: it first learns how immune receptors are positioned around fixed target structures, and then transfers this target-conditioned structural prior to CDR design. Unlike modular design pipelines, IgGM2 jointly generates CDR residue identities and full-atom receptor structures, allowing framework geometry to adapt to designed CDRs without separate inverse folding or external sidechain packing. Unlike continuous residue encodings based on virtual-atom geometry, IgGM2 keeps sequence prediction explicit while using atom14 placeholders only for full-atom representation. On structure prediction benchmarks, IgGM2 better captures receptor-target spatial relationships than AlphaFold3 on FoldBench and achieves strong performance on TCR-pMHC modeling. On sequence design benchmarks, IgGM2 improves amino-acid recovery and Rosetta-based interface preference metrics, suggesting more favorable generated binding interfaces. These results support IgGM2 as a unified all-atom framework for adaptive immune receptor structure prediction and design.

  bioinformatics2026-07-09v1

• Gene-specific exponent-corrected normalization for library size in bulk RNA-seq

  Yin, R.; Li, D.; Zong, W.; Ketchesin, K. D.; Seney, M. L.; McClung, C. A.; Baldoni, P. L.; Tseng, G. C.

  Abstract

  Correcting for library size is an essential step in bulk RNA-seq analyses, as differences in sequencing depth across samples can obscure biological signal with technical noise. While numerous normalization methods and model-based strategies have been proposed, we demonstrate here that library size-normalized counts and differential expression results obtained from such widely adopted approaches often remain strongly correlated with library size in large-scale RNA-seq experiments. Through a systematic analysis of over 100 publicly available GEO and TCGA RNA-seq datasets with raw count data, we show that library size association is observed for a substantial proportion of genes even after state-of-the-art library size correction approaches recommended by leading normalization tools. To address this issue, we propose gecco, a gene-specific exponent-corrected normalization method for RNA-seq counts that incorporates library size directly into the statistical framework via a gene-specific correction term, rather than applying a uniform adjustment factor across all genes. This formulation generalizes existing normalization approaches and yields normalized counts that are free of residual library size effects. Using both simulation studies and real large-scale RNA-seq datasets, we show that our method mitigates library size bias while preserving biological signal across a range of parameter settings. We further demonstrate that our approach leads to higher detection accuracy and more biologically meaningful pathway enrichment results in downstream differential expression and rhythmicity analyses without compromising false discovery rate control. Our method is implemented in R and is fully compatible with the widely used differential expression analysis methods DESeq2 and edgeR.

  bioinformatics2026-07-09v1

• A five-dimensional functional state space for fingerprinting disease transcriptomes

  Nie, F.; Zhuang, Y.; Chen, K.; Lin, J.; Sun, J.

  Abstract

  High-throughput transcriptomics has transformed disease biology, but its outputs often remain fragmented into gene and pathway lists that are difficult to compare across conditions or use for human-AI interpretation. We developed a five-dimensional (5-D) functional state space that represents disease transcriptomes as coordinated activity patterns across major biological systems. The framework maps transcriptomic signals onto five functional systems, 14 subcategories, and a distinct infrastructure layer, and was implemented as a reproducible pipeline for functional scoring, cross-condition profiling, benchmarking, and large language model (LLM)-assisted interpretation. Applied to wound healing, sepsis, colorectal cancer-related datasets, an extended GEO atlas of 38 complete case-control disease fingerprints spanning diverse disease contexts, and a TCGA-COAD/READ stage benchmark, the approach recovered interpretable disease-state patterns and retained progression-related information under strong compression. It also improved the quantitative grounding of LLM-generated summaries. This framework provides a compact and auditable representation for comparing disease transcriptomes and supporting human-AI biological interpretation.

  bioinformatics2026-07-09v1

• Generative AI Models Reveal Dynamic Views of Aging (DyViA) Phenotypes in Healthy Individuals

  Ray, D.; Ray, M.; Pyne, S.

  Abstract

  Background and objectives: In recent years, the need to develop analytical strategies for healthy aging has assumed great importance. In this study, we introduce DyViA, a generative artificial intelligence (genAI) platform that can construct personalized trajectories capable of predicting the plausible progression of selected phenotypes with advancing age. Research design and methods: DyViA presents a suite of deep learning models covering two major GenAI approaches: DyViA-Diff, a new diffusion model; and DyViA-mGAN, an improved version of a recent Generative Adversarial Network model. It demonstrated the dynamic progression of femoral neck bone mineral density (BMD) using data from a longitudinal cohort study of women in the U.S. of age 65 years or above. Results: Using very few initial measurements, DyViA generated individual-specific continuous trajectories of BMD, with a corresponding region of acceptable predictions, from 66 to 89 years. The results were subjected to rigorous quality-control and comparative analysis across multiple methods. While DyViA-Diff is the superior model with more coherent and accurate predictions, DyViA-mGAN allows for encoding population- and individual-level effects with a better control. Discussion and implications: Given the prevalence of osteoporosis in the aging population, the main impact of DyViAs genAI-driven contribution in the form of personalized, plausible models of BMD progression with age lies in the systematic yet rigorous transition from otherwise static models of inference about a clearly dynamic phenomenon to a continuous one. The foresight offered by DyViAs outputs empowers an individual by conferring a certain degree of strategic preparedness in the course of aging.

  bioinformatics2026-07-09v1

• Assessing tensor decomposition quality of immune profiling data from a dictionary learning perspective

  Konstorum, A.; Xing, J.; Aeron, S.; Kilmer, M.; Kleinstein, S.

  Abstract

  Systems-level immune profiling data arising from longitudinal studies of vaccination or infection has an inherent multi-index array structure. While tensor decomposition of such datasets has gained popularity, choosing a rank and trial for a decomposition is not straightforward. We show that taking into account the experimental data model can inspire the development of new metrics to assess the quality of a Non-negative CANDECOMP/PARAFAC (NCPD) decomposition, and can thus be used to choose a rank and trial for the decomposition. Moreover, we show how framing the results via a dictionary learning framework can better enable interpretation of the components of the decomposition.

  bioinformatics2026-07-09v1

• Learning the spatial cell-cell communication network to decode multi-channel signaling and predict network-hub vulnerabilities with MOSANIC

  Das, D.; Mitra, P.

  Abstract

  Intercellular signaling governs the central decisions of tissue biology, from proliferation and immune recruitment to metabolic adaptation and cell death, and its dysregulation is a hallmark of disease. What matters most are properties of the signaling network as a whole rather than of individual interactions: the hubs that hold the network together and mark rational points of intervention, the relays through which a signal propagates across intermediate cells to reach partners it does not directly contact, the response of tissue-wide communication to the loss of a single node, and the metabolite-mediated axis that operates alongside secreted-protein signalling. Scoring known ligand-receptor pairs yields a ranked interaction list that captures none of these and excludes metabolite signalling. We present MOSANIC (Multi-mOdal Self-Attention Network for Intercellular Communication), which learns a tissue's communication network directly from spatial transcriptomics. MOSANIC represents each tissue as a single heterogeneous graph of cells, genes and metabolites, initialises every node with a frozen foundation-model representation (scVI, ESM-2 and ChemBERTa), and propagates these representations through a self-attention network over biologically typed edges. Supervision is restricted to spatial gene-expression prediction and excludes ligand-receptor annotation, rendering the inferred communication statistically independent of the reference databases used for evaluation. Across five spatial datasets spanning three platforms and two species, MOSANIC attains the highest accuracy on all eight independent ligand-receptor benchmarks (mean AUROC 0.756) against nine established methods, resolves a metabolite-receptor channel statistically orthogonal to the peptide channel, and reconstructs multi-step signal relays that concentrate within a compact rich-core of load-bearing hub genes and cells whose removal fragments the network far beyond a degree-preserving null. In-silico knockout of these hubs recovers experimentally reported phenotypes, and, given no prior oncological input, MOSANIC nominates SCARF1 as a previously unrecognised communication hub in breast cancer whose elevated expression predicts significantly worse survival in an independent cohort after adjustment for tumour stage and age (hazard ratio 1.17, P = 0.043). MOSANIC is released as an open-source Python package (mosanic-ccc).

  bioinformatics2026-07-09v1

• Metabolic Rewiring in Triple-Negative Breast Cancer: Systems Analysis of TCGA-BRCA Transcriptome Reveals Prognostic Hub Genes

  Chandrasekar, S.

  Abstract

  Triple Negative Breast Cancer (TNBC) is the deadliest and most aggressive subtype of breast cancer, with poor prognosis and high rates of metastasis. Despite knowledge of metabolic rewiring in TNBC, the systems-level coordination of these adaptive pathways remains unmapped. This integrative systems-level analysis reveals key metabolic hub genes and identifies ATP1A2 as a significant prognostic marker. Analysis identified 764 differentially expressed genes, with 89 enriched biological processes predominantly involving metabolic pathways. Co-expression network analysis of 261 genes identified metabolic hub genes including LEP, ADIPOQ, and ATP1A2. To evaluate the prognostic framework, survival analysis of the top 10 hubs was performed on synthetic survival data, revealing ATP1A2 as a significant marker (p = 0.03) under Cox regression, with elevated expression associating with altered survival outcomes. By systematically mapping metabolic rewiring in TNBC, this work identifies ATP1A2 as an actionable therapeutic target and establishes a systems-level framework for rational drug discovery and patient stratification in this aggressive malignancy.

  bioinformatics2026-07-09v1

• qg: Configuration-Driven, Multi-Vendor Acquisition Queue Generation with Reproducible Run-Order and QC Control for Mass Spectrometry

  Wolski, W. E.; Schwarz, L.; Trachsel, C.; Zanella, M.; Riedi, C.; Schlapbach, R.; Othman, A.; Tuerker, C.; Nanni, P.; Panse, C.

  Abstract

  Mass spectrometry laboratories must turn lists of submitted samples into acquisition queues. The run order and the placement of quality-control (QC) injections determine whether a design controls batch effects and signal drift, and whether those effects stay correctable afterward. Yet operators usually set them by hand in vendor worklist editors that neither randomize run order nor offer configurable, pattern-driven QC. We present *qg*, an open-source tool that builds acquisition queues with systematic run-order handling: four run-order modes (none, simple, blocked/randomized-complete-block, and group-uniform blocked), pattern-driven QC and standard injections, and sampler- and plate-aware positioning. Unlike plate-design tools that stop at a generic sample sheet, *qg* writes the native vendor acquisition file directly, for three instrument ecosystems (Thermo Fisher XCalibur, Axel Semrau Chronos, Bruker HyStar) across proteomics, metabolomics, and lipidomics. It separates a small, stateless generation pipeline from a declarative configuration layer, so a laboratory adapts instruments, QC patterns, layouts, and naming by editing version-controlled configuration through a validating editor rather than changing code. *qg* runs from a reactive web interface or a scripted command-line interface, integrated with a LIMS (B-Fabric) or standalone from uploaded tables; randomized runs record their seed and reproduce from exported parameters. On an unbalanced design, group-uniform blocked randomization spreads biological groups evenly across acquisition time, whereas textbook block randomization leaves a tail of the largest group and can track acquisition time worse than a plain shuffle. *qg* is released under the Apache-2.0 license.

  bioinformatics2026-07-09v1

• Thematic Shifts in Early-High-Impact Cancer Genomics and Diagnostics Research: A Bibliometric and Semantic Analysis

  Su, Z.; Li, T.

  Abstract

  Cancer genomics and diagnostics is a rapidly evolving field in which identifying which topics attract early citation prominence can inform laboratory investment, clinical translation, and research strategy. We developed a bibliometric framework to identify and characterize the most influential recent publications in this domain across two consecutive annual cohorts. Using a mathematically exact threshold-expansion algorithm, we ranked over 10,000 OpenAlex-indexed research articles per cohort by 18-month post-publication citation count. Large language model (LLM)-based topical relevance filtering yielded 50 substantively on-topic papers per cohort (100 total). LLM-based concept extraction and a two-stage, embedding-guided normalization pipeline produced 1,853 canonical concepts organized into 103 parent themes, enabling structured cross-cohort comparison of paper-level concept prevalence. The most cited papers in both cohorts were large-scale genomic infrastructure resources rather than single-disease mechanistic studies. Between consecutive cohorts, normalized frequencies increased most for whole-genome sequencing, tumor microenvironment biology, molecular biomarkers, and cancer pharmacotherapy, while liquid biopsy-related themes showed the largest declines. These findings indicate that early citation impact in cancer genomics is shifting toward integrative, population-scale, and microenvironment-aware research, and demonstrate that LLM-augmented citation ranking provides a replicable, semantically enriched lens for monitoring thematic evolution in precision oncology. A web interface for exploring the results is available at https://pri.pepkio.com/.

  bioinformatics2026-07-09v1

• BertST: BERT-based Spatial Domain Identification in Patient Data

  Nnadi, G. O.

  Abstract

  Spatial transcriptomics enables the study of gene expression within its native tissue context, providing critical insights into cellular organization and microenvironment-driven biological processes. A key challenge in this field is spatial domain identification, which aims to partition tissue into coherent regions by jointly leveraging gene expression and spatial information. Existing approaches are predominantly based on Graph Neural Networks (GNNs), and approach based on Transformers particularly, Bidirectional Encoder Reppresentation Transformer (BERT) model for modelling both local and long-range dependencies remains largely unexplored. In this work, we propose BERT for Spatial Transcriptomics (BertST), a transformer-based framework that reformulates spatial transcriptomics as a graph-to-text representation learning problem. Building upon the BERTwalk paradigm, we construct a task-specific multi-graph representation integrating spatial adjacency, pruned gene-expression similarity, and a fully connected gene-expression graph. This design enables the modelling of both local spatial structure and global molecular relationships. Random walks over these graphs are treated as sequences, allowing a BERT model to learn contextualised node embeddings. To further enhance representation quality, we introduce a hierarchical multi-graph propagation strategy, where embedding refinement is performed sequentially: first on the fully connected graph to capture global structure, followed by the pruned graph to refine molecular relationships, and finally on the spatial graph to enforce local smoothness. This ordering ensures that global information is effectively distributed and progressively constrained by biologically meaningful neighbourhoods. We also improve computational efficiency by leveraging \textit{PecanPy}, a fast and scalable implementation of node2vec, enabling efficient random walk generation on dense graphs. Experimental results on multiple 10x Visium datasets, including DLPFC and Human Breast Cancer, demonstrate that BertST consistently outperforms or matches GNN-based methods such as ConST, CCST, and SpaceFlow in terms of Adjusted Rand Index (ARI) and Adjusted Mutual Information (AMI). Overall, BertST highlights the potential of transformer-based architectures for spatial omics analysis by effectively capturing both local and long-range spatial-molecular dependencies, offering a promising alternative to traditional graph-based methods.

  bioinformatics2026-07-09v1

• EZSolver: Template-free prediction of polar enzymatic mechanisms via bidirectional flow matching and search

  Kuo, L.-H.; Yang, J.; Arnold, F.

  Abstract

  Predicting enzymatic reaction mechanisms is critical for understanding enzyme function and for designing and dis-covering new enzymes. Current computational predictors rely on deterministic, rule-based dictionaries, which per-form well on in-distribution tasks but fail to generalize to out-of-distribution (OOD) chemistry. To address this limita-tion, we present EZSolver, a template-free, generative framework for polar enzymatic mechanism prediction. Powered by a flow matching predictor (EZFlow) and navigated by an evaluator-guided bidirectional beam search, EZSolver learns the chemistry of electron redistribution instead of memorizing rigid templates. Evaluated across diverse en-zyme classes, EZSolver achieves a 60.0% accuracy and an 84.6% chemical plausibility rate for full mechanism predic-tion of unseen polar enzymatic reactions. While rule-based models collapse without predefined templates, EZSolver successfully extrapolates chemical knowledge to infer uncatalogued pathways, as demonstrated during rigorous OOD benchmarking. By illuminating enzymatic chemical mechanisms, EZSolver helps pave the way for automated predic-tion of enzyme function and discovery and design of novel biocatalysts for sustainable chemistry.

  bioinformatics2026-07-09v1

• Design of a Multi-epitope Vaccine Against Human Glanders Targeting Outer Membrane β-barrel Proteins of Burkholderia mallei

  Kapoor, J.; Panda, A.; Kumar, S.; Bandyopadhyay, A.

  Abstract

  Burkholderia mallei, a facultative intracellular Gram-negative pathogen, is the causative agent of glanders that primarily affects solipeds and sporadically transmitted to humans. Current interventions mainly rely on antibiotics; however, increasing resistance and the lack of a licensed vaccine further complicate disease management. In the present study, a consensus-based computational framework was employed on the B. mallei turkey2 proteome. Total 59 proteins - including porins, TonB receptors, autotransporters, and efflux components - were identified as surface exposed outer membrane {beta}-barrel (OMBB) proteins that were used to design a multi-epitope vaccine (MEV) construct. B- and T-cell epitopes were predicted from 59 proteins, and ten epitopes each of cytotoxic T-lymphocyte (CTL), helper T-lymphocyte (HTL), and B-cell were chosen based on their antigenicity, non-allergenicity, non-toxicity, surface accessibility, and conservation across 32 B. mallei strains. The MEV was included with suitable adjuvants at the N-terminus to enhance its immunogenicity. The 780 amino acid MEV construct was predicted to be antigenic, and soluble upon overexpression with 62.69% random coils, while the rest formed -helices and {beta}-strands. The tertiary structure of the MEV was generated and subsequently validated, indicating good structural quality. Molecular docking of the MEV with toll-like receptor 4 (TLR4) demonstrated strong affinity, and molecular dynamics simulation confirmed the structural stability of the MEV-TLR4 complex. In-silico immune simulation showed the capability of MEV to induce a strong immune response. Codon optimization and in-silico cloning were performed for efficient protein expression in the E. coli host. The study proposes an MEV construct by utilizing surface exposed OMBB proteins which directly interact with the host and serve as effective immunogenic targets against B. mallei infection.

  bioinformatics2026-07-08v2

• Modeling patient tissues at molecular resolution with Eva

  Liu, Y.; Sharma, R.; Bieniosek, M.; Kang, A.; Wu, E.; Chou, P.; Li, I.; Rahim, M.; Bauer, E.; Ji, R.; Duan, W.; Qian, L.; Luo, R.; Sharma, P.; Dhanasekaran, R.; Schürch, C. M.; Charville, G.; Mayer, A.; Zou, J.; Trevino, A. E.; Wu, Z.

  Abstract

  Tissue structure is essential to function and homeostasis in all organs, and disruptions to structure usually indicate disease. Modeling relationships between structural, molecular, and clinical aspects of tissues could advance new diagnostics and treatment strategies. Although profiling techniques like spatial proteomics can capture these relationships, the data remain challenging to extract insight from. Here, we present Eva, a foundation model for tissue imaging data that learns multi-scale spatial representations of tissues at the molecular, cellular, and sample level. Eva uses a novel vision transformer architecture and is pre-trained on masked reconstruction of matched spatial proteomics and histopathology images. We show that Eva excels at a variety of tasks, including cross-modal inference, quality control, data annotation, zero-shot retrieval, survival modeling, and patient stratification. Extensive evaluations on held-out validation data demonstrate the versatility and generalizability of the learned embeddings. We anticipate that Eva will accelerate translational science by bridging basic research and clinical practice.

  bioinformatics2026-07-08v2