SEARCH · PubMed Health

Results for “algorithmic awareness”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

30 records · Page 2Linked to original sources

PubMed2026

EvoSNR-Prom: Predicting promoters at single-nucleotide resolution with label-aware transfer learning of the pretrained EVO model.

The precise identification of promoters is crucial for understanding gene regulation. Deep learning methods have achieved considerable success in promoter prediction, yet most operate at the sequence level with coarse-grained labels. This means they label an entire DNA segment as either a "promoter" or "non-promoter," which results in a lack of the nucleotide-level resolution in prediction. In this study, we propose EvoSNR-Prom, a model designed for promoter prediction at single-nucleotide resolution. EvoSNR-Prom is built on the Evo foundation model and formulates promoter identification as a token-level sequence labeling problem, analogous to named entity recognition in natural language processing. To address the limited contextual information available in single-nucleotide tokenization, we introduce a lexicon-enhanced embedding strategy that incorporates biologically meaningful DNA lexicons, enriching contextual representations and improving the model's ability to capture complex sequence motifs. Furthermore, to enhance predictive performance on small size datasets, we integrate a label-aware transfer learning framework to leverage knowledge from well-annotated source species to a target organism. The results across various prokaryotic datasets show that EvoSNR-Prom achieves excellent performance. This work provides a valuable computational framework for the high-precision analysis of gene regulatory elements, contributing to the advancement of promoter prediction at single-nucleotide resolution.

Promoter Regions, Genetic↗

PubMed2025

Locality-aware pooling enhances protein language model performance across varied applications.

MOTIVATION: Protein language models (PLMs) are amongst the most exciting recent advances for characterizing protein sequences, and have enabled a diverse set of applications, including structure determination, functional property prediction, and mutation impact assessment, all from single protein sequences alone. State-of-the-art PLMs leverage transformer architectures originally developed for natural language processing, and are pre-trained on large protein databases to generate contextualized representations of individual amino acids. To harness the power of these PLMs to predict protein-level properties, these per-residue embeddings are typically "pooled" to fixed-size vectors that are further utilized in downstream prediction networks. Common pooling strategies include Cls-Pooling and Avg-Pooling, but neither of these approaches can capture the local substructures and long-range interactions observed in proteins. RESULTS: We propose the use of attention pooling, which can naturally capture these important features of proteins. To make the expensive attention operator (quadratic in the length of the input protein) feasible in practice, we introduce bag-of-mer pooling, or BoM-Pooling, a locality-aware hierarchical pooling technique that combines windowed average pooling with attention pooling. We empirically demonstrate that both full attention pooling and BoM-Pooling outperform previous pooling strategies on three important, diverse tasks: (i) predicting the activities of two proteins as they are varied; (ii) detecting remote homologs; and (iii) predicting signaling protein interactions with peptides. Overall, our work highlights the advantages of biologically inspired pooling techniques in protein sequence modeling and is a step toward more effective adaptations of language models in biological settings. AVAILABILITY AND IMPLEMENTATION: https://github.com/Singh-Lab/bom-pooling.

Natural Language Processing↗

PubMed2025

CaLMPhosKAN: prediction of general phosphorylation sites in proteins via fusion of codon aware embeddings with amino acid aware embeddings and wavelet-based Kolmogorov-Arnold network.

MOTIVATION: The mapping from codon to amino acid is surjective due to codon degeneracy, suggesting that codon space might harbor higher information content. Embeddings from the codon language model have recently demonstrated success in various protein downstream tasks. However, predictive models for residue-level tasks such as phosphorylation sites, arguably the most studied Post-Translational Modification (PTM), and PTM sites prediction in general, have predominantly relied on representations in amino acid space. RESULTS: We introduce a novel approach for predicting phosphorylation sites by utilizing codon-level information through embeddings from the codon adaptation language model (CaLM), trained on protein-coding DNA sequences. Protein sequences are first reverse-translated into reliable coding sequences by mapping UniProt sequences to their corresponding NCBI reference sequences and extracting the exact coding sequences from their GenBank format using a dynamic programming-based global pairwise alignment. The resulting coding sequences are encoded using the CaLM encoder to generate codon-aware embeddings, which are subsequently integrated with amino acid-aware embeddings obtained from a protein language model, through an early fusion strategy. Next, a window-level representation of the site of interest, retaining the full sequence context, is constructed from the fused embeddings. A ConvBiGRU network extracts feature maps that capture spatiotemporal correlations between proximal residues within the window. This is followed by a prediction head based on a Kolmogorov-Arnold network (KAN) using the derivative of gaussian wavelet transform to generate the inference for the site. The overall model, dubbed CaLMPhosKAN, performs better than the existing approaches across multiple datasets. AVAILABILITY AND IMPLEMENTATION: CaLMPhosKAN is publicly available at https://github.com/KCLabMTU/CaLMPhosKAN.

Codon↗

PubMed2026

GT-Mamba: a Topology-Aware Graph-State space model for robust and interpretable epigenetic age prediction.

MOTIVATION: Current epigenetic clocks face a trade-off between predictive accuracy and biological interpretability, often relying on dataset-specific correction to generalize across cohorts. We propose GT-Mamba, a novel architecture that integrates a Structure-Aware Graph Transformer with the Mamba state space model. This design captures CpG topological correlations and genome-wide long-range dependencies. RESULTS: GT-Mamba demonstrates strong out-of-the-box robustness across heterogeneous independent validation cohorts, achieving a weighted average MAE of 4.43 years. Notably, it effectively generalizes to EPIC 850k arrays despite partial feature missingness, and maintains consistent performance across homologous age distribution shifts (MAE 2.94 years in a young cohort). Ablation studies confirm that graph topology contributes to improved robustness against noise. Mechanistic analysis suggests that the model captures methylation patterns associated with both developmental and functional processes. AVAILABILITY: Source code and pre-trained models are freely available at https://github.com/NENUBioCompute/GT-Mamba and archived on Zenodo (DOI: 10.5281/zenodo.19703155).

Epigenesis, Genetic↗

PubMed2026

CROP: a feature-independent context-aware method for CRISPR-Cas9 frameshift prediction.

MOTIVATION: The CRISPR-Cas9 complex has revolutionized genome-editing technologies. By designing a 20 nt-long guide RNA, a Cas9 nuclease can be guided to cleave almost any genomic target site (followed by NGG). The cleavage induces double-stranded DNA breaks, which are then repaired by cellular pathways. Accurate CRISPR-Cas9 repair-outcome prediction is essential for designing guide RNAs with desired genomic effects, such as gene knockout. A central challenge is quantifying the rate of frameshifts, i.e. repair-outcomes that lead to a change in the local length that is not a multiple of three. Previous methods for frameshift-rate prediction were trained on only a few experimental or cellular contexts, mostly relied on manually defined microhomology features, and were limited by sparse features and class labels. RESULTS: We developed CROP, a feature-independent context-aware repair-outcome prediction method. By aggregating specific repair outcomes as Δlength classes, CROP overcomes class sparsity. We designed CROP to work with variable input sequence lengths and output classes to utilize multiple datasets simultaneously. We benchmarked CROP against state-of-the-art repair-outcome prediction methods over 18 datasets, which we curated and standardized from various studies. Across all datasets, CROP outperformed all competing methods in frameshift-rate prediction. We performed cross-experiment and cross-cellular frameshift-rate predictions to investigate the generalizability of repair mechanisms. Finally, we show that CROP learned microhomology principles from raw sequences without explicit feature engineering, establishing an end-to-end architecture for CRISPR-Cas9 repair-outcome prediction that learns from multiple datasets. AVAILABILITY AND IMPLEMENTATION: CROP is available at https://github.com/OrensteinLab/CROP.

CRISPR-Cas Systems↗

PubMed2026

CAGNet: a structure-aware clustering-alternated graph network for cell-cell interaction inference in spatial transcriptomics.

MOTIVATION: Understanding cell-cell interactions (CCIs) in spatial transcriptomics is crucial for uncovering the spatial organization and functional heterogeneity of tissues. However, existing graph-based models typically rely on static clustering or fixed adjacency structures, which limits their ability to capture dynamic cellular relationships. RESULTS: We propose CAGNet, a two-stage framework for CCI inference from spatial transcriptomics data. In Stage 1, a Graph Attention Network encoder with joint feature and graph reconstruction learns structure-aware node embeddings from spatial gene expression profiles. In Stage 2, an alternating optimization mechanism iteratively updates cluster centers via KL-guided soft assignment and refines node embeddings through spatial graph reconstruction, establishing a closed-loop between representation learning and clustering. Experiments on three 10x Genomics Visium datasets demonstrate that CAGNet consistently outperforms six CCI inference baselines across ACC, AUC, AP, Precision, Recall, and F1. CAGNet also achieves the highest Adjusted Rand Index on all three datasets against six spatial domain identification methods, confirming that the learned embeddings capture biologically relevant spatial organization. Information-theoretic analysis further shows that CAGNet retains the highest mutual information between input features and learned embeddings among all compared methods. Ablation studies and 5-fold cross-validation confirm the contribution of each component and the reproducibility of the results. AVAILABILITY: The proposed method is implemented in the CAGNet package available at http://github.com/mahan1233333-maker/CAGNet .

Spatial Transcriptomics↗

PubMed2026

Beyond benchmarking: an expert-guided consensus approach to spatially aware clustering.

Spatial omics technologies have revolutionized the study of tissue architecture and cellular heterogeneity by integrating molecular profiles with spatial localization. In spatially resolved transcriptomics, delineating higher-order anatomical structures is critical for understanding how cellular organization affects function. However, the reliability of current benchmarks of spatially aware clustering (SAC) methods is undermined by their narrow focus on Visium and brain tissue datasets and the incorrect interpretation of manual annotation as ground truth. Here we present SACCELERATOR, a community-driven, extensible framework that standardizes data formatting, method integration and metric evaluation, enabling rapid inclusion of new methods and datasets. Our analysis revealed substantial limitations in the generalizability and reproducibility of SAC methods and shows that anatomical labels commonly used as ground truths are often biased, error prone and unsuitable for benchmarking. Rather than ranking methods, we propose a consensus-guided workflow where descriptive spatial metrics highlight high-entropy regions of method disagreement, enabling targeted feedback for tissue experts. Applied to brain and cancer datasets, this approach uncovered biologically meaningful patterns overlooked by individual SAC methods and manual annotations, highlighting the need for iterative, expert-in-the-loop evaluation.

Benchmarking↗

PubMed2025

Absolute copy number aware CNV calling of sub-megabase segments in ultra-low coverage single-cell DNA sequencing data.

Recent advances in ultra-low coverage whole-genome sequencing (WGS) of single cells have enabled detailed analysis of copy number variation at a throughput approaching that of single-cell RNA sequencing. However, downstream computational methods have not seen comparable advances and are largely adaptations of deep sequencing methodology with reduced precision. Here, we present ASCENT, a computational method built to take full advantage of modern direct tagmentation-based WGS at ultra-low depth. Using joint segmentation with high-resolution bins, we accurately detect small segments, achieving accurate copy number profiles even at 100 000 reads per cell. ASCENT implements true absolute copy state inference for single cells, based on statistical modeling of coverage rather than comparison to a reference, while taking variable segment copy state into account. Further, ASCENT implements per-segment copy-neutral loss of heterozygosity (LOH) calling without the need for non-tumor or bulk WGS reference. When applied to a pediatric B-ALL sample, ASCENT finds copy-neutral LOH in a small segment and a minor subclone defined by breakpoints missed in bulk WGS. Thus, by applying appropriate computational methods, single-cell WGS provides clear advantages over bulk, even at a relatively low cell number and sequencing depth.

DNA Copy Number Variations↗

PubMed2026

Leveraging ONT move table values for signal aware variant calling.

Oxford Nanopore Technologies (ONT) sequencing enables long-range haplotype phasing and contiguous genome assembly but still exhibits elevated error rates that challenge small variant calling, particularly for insertions and deletions (Indels). While raw electrical signals contain rich information, existing signal-aware methods require computationally intensive processing of large signal files. Here, we present Clair3 v2, a method that leverages the ONT move table-a lightweight byproduct of basecalling that maps signal events to nucleotide positions-to improve variant calling accuracy. Clair3 v2 builds upon Clair3 and integrates signal-level dwelling time to significantly enhance variant calling performance. We also propose a genome position based circular buffer to incorporate dwelling time with minimal computational overhead. Benchmarking across six Genome in a Bottle samples demonstrates substantial improvements in variant calling accuracy. With HAC basecalling, Clair3 v2 achieves a mean SNP F1-score of 97.69% at 10 × depth (compared to 96.45% for baseline Clair3), and Indel F1 scores improved from 64.27% to 76.70%, while gains persisted at higher depths. The benefits were most pronounced for longer Indels and in complex genomic regions, where Indel F1 scores in long homopolymer regions improved from 14.3% to 45.2%. Benchmark results across various basecalling modes, samples, and coverage settings outperformed Clair3 baselines and other methods, including DeepVariant and Dorado Variant, and demonstrate the significant benefits of Clair3 v2. Furthermore, Clair3 v2 incurs negligible runtime compared to standard Clair3, making it practical for routine use.

Sequence Analysis, DNA↗

PubMed2025

DNABERT-S: pioneering species differentiation with species-aware DNA embeddings.

SUMMARY: We introduce DNABERT-S, a tailored genome model that develops species-aware embeddings to naturally cluster and segregate DNA sequences of different species in the embedding space. Differentiating species from genomic sequences (i.e. DNA and RNA) is vital yet challenging, since many real-world species remain uncharacterized, lacking known genomes for reference. Embedding-based methods are therefore used to differentiate species in an unsupervised manner. DNABERT-S builds upon a pre-trained genome foundation model named DNABERT-2. To encourage effective embeddings to error-prone long-read DNA sequences, we introduce Manifold Instance Mixup (MI-Mix), a contrastive objective that mixes the hidden representations of DNA sequences at randomly selected layers and trains the model to recognize and differentiate these mixed proportions at the output layer. We further enhance it with the proposed Curriculum Contrastive Learning (C2LR) strategy. Empirical results on 28 diverse datasets show DNABERT-S's effectiveness, especially in realistic label-scarce scenarios. For example, it identifies twice more species from a mixture of unlabeled genomic sequences, doubles the Adjusted Rand Index (ARI) in species clustering, and outperforms the top baseline's performance in 10-shot species classification with just a 2-shot training. AVAILABILITY AND IMPLEMENTATION: Model, codes, and data are publically available at https://github.com/MAGICS-LAB/DNABERT_S.

Sequence Analysis, DNA↗

PubMed2026

DNA-aware evaluation and debiasing of sequence-to-function models.

MOTIVATION: Genome sequence-to-function (S2F) models are widely used to interpret base-resolution functional genomics assays. Most S2F models are trained and evaluated against observed counts and profile-shapes using statistical objectives and fidelity metrics. These choices are well motivated, but they are DNA-independent. At the same time, experimental measurements arise from DNA-dependent assays with distinct characteristics. This mismatch motivates a complementary DNA-aware evaluation of S2F-predicted and experimental functional genomic tracks. RESULTS: We study DNA-dependency of experimental and S2F-predicted tracks using track-conditional genome language models (cgLMs). cgLMs predict masked nucleotides from a conditioning track under controlled DNA visibility. Across ATAC-seq and TF ChIP-seq peaks from GM12878 and K562, cgLM-probing reveals a consistent masked DNA-decodability gap between many experimental and S2F-predicted tracks. In particular, single-task (e.g. BPNet) and multi-task (e.g. AlphaGenome) S2F-predicted tracks enabled cgLMs to recover masked nucleotides with significantly higher accuracy and confidence than matched experimental tracks. Analyses of nonpeak and dinucleotide-shuffled sequences show that this gap is not confined to peaks and is not captured by standard DNA-agnostic profile-shape fidelity metrics alone. ChromBPNet Tn5-denoised predictions were an exception and behaved closer to the experimental regime, suggesting that staged training may reduce the gap. We then convert this diagnostic into a critic-derived objective, DNA-dependency matching (DDM), using a frozen multi-headed cgLM critic. We introduce Critic-Guided Profile-Shape Editing (CGPSE), a preliminary post hoc debiasing framework for frozen S2F models. In GM12878 ATAC-seq, CGPSE partially reduces the masked DNA-decodability gap for AlphaGenome and BPNet predictions, while exposing a tradeoff with profile-shape fidelity. AVAILABILITY AND IMPLEMENTATION: https://github.com/li-lab-mcgill/dna-aware-s2f-eval.

DNA↗

PubMed2026

PMGen: from peptide-MHC structure prediction to peptide generation.

MOTIVATION: Accurate structural modeling of peptide-major histocompatibility complex (pMHC) complexes is essential for structure-driven immunotherapy design, yet current prediction tools suffer from narrow class coverage, restricted peptide lengths, insufficient accuracy, and a lack of built-in structure-aware peptide sampling. Consequently, most mimotope and altered peptide ligand designs rely solely on sequence substitution, leaving spatial and biophysical insights from pMHC structures largely unexploited. RESULTS: We introduce peptide-MHC generator (PMGen), an integrated framework for structure prediction and structure-guided design of variable-length peptides across MHC Class I and II. PMGen enforces anchor constraints within AlphaFold2 through two complementary strategies, initial guess and template engineering, achieving state-of-the-art structural fidelity without model fine-tuning. On a comprehensive benchmark, PMGen outperforms all existing methods, yielding median peptide-core Cα RMSDs of 0.62 Å for MHC-I and 0.33 Å for MHC-II. We show that PMGen can recover incorrectly predicted anchor positions and that AlphaFold pLDDT scores enable sequence-independent binding-core identification. Applied to a published neoantigen/wild-type pair, PMGen accurately captures mutation-induced conformational changes. Beyond structure prediction, we show that ProteinMPNN sampling on PMGen-predicted backbones yields higher affinity peptides while preserving the parental 3D conformation. Using PMGen to generate 63 817 high-confidence pMHC structures as training data, we further improve ProteinMPNN's peptide sequence recovery from 0.14 to 0.64 on a test set of 85 unseen MHC-I alleles, highlighting the value of accurate predicted structures for downstream machine learning tasks. AVAILABILITY AND IMPLEMENTATION: PMGen is freely available at https://github.com/soedinglab/PMGen, with an interactive Colab notebook at https://colab.research.google.com/github/soedinglab/PMGen/blob/master/colab.ipynb.

Peptides↗