Skip to main content
Search

Utrecht University

5 related articles

Subscribe to updates
  1. bioRxiv

    DNA-LLM2Vec turns causal DNA decoders into bidirectional encoders, with frozen-probe gains that shift by task and backbone

    DNA-LLM2Vec converts pretrained causal DNA decoders into frozen bidirectional encoders in stages: it opens bidirectional context, repairs the resulting mismatch with masked next-token prediction, then adds contrastive views encoding strand and positional invariance. Across two backbones, DNAGPT and HyenaDNA, and seven biological task families, the benefit is not uniform but depends on task structure and backbone; crop contrastive learning helps most for extended-context families such as enhancer–promoter interaction and Virus-COVID, reaching frozen Avg-EPI MCC of 27.5% and 26.7%.

  2. Sleep staging stops picking electrodes: any EEG-EOG mix scores a night, and resolution drops to seconds

    Sleep staging has long depended on fixed electrode sets and 30-second expert-scored epochs, which makes multi-center studies hard to harmonize. AnySleep fuses any number of EEG and EOG channels through channel attention, trained and validated on 20,589 overnight recordings from 28 datasets, matching or slightly exceeding U-Sleep at 30-second epochs and staying strong with no EOG or a single derivation. At sub-30-second resolution, the share of expert-annotated arousal time overlapping predicted Wake rises from 7.7% at 30 seconds to 57.7% near 2 seconds.

  3. arXiv

    Flow matching for sparse-view CT reconstruction: reusing velocity fields cuts network evaluations to 7 while matching diffusion-model quality

    The authors propose FMCT, the first flow-matching-based CT reconstruction framework, and an efficient variant EFMCT that reuses previously predicted velocity fields over consecutive steps to cut neural network function evaluations (NFEs), motivated by the deterministic ODE sampling of flow matching being naturally compatible with repeated data consistency corrections and by the strong correlation of predicted velocities across adjacent steps; they provide a theoretical analysis showing the reuse error is of the same order as Euler discretization and bounded for a bounded number of consecutive reuse steps, and on the AAPM and Medical Segmentation Decathlon CT datasets with 20-view and 40-view parallel-beam sparse sampling, FMCT/EFMCT achieve PSNR/SSIM competitive with diffusion-based method

  4. medRxiv

    A Large Language Model for Risk-of-Bias Assessment in Systematic Reviews of Prognosis Studies in Clinical Neurology

    This study designed a zero-shot prompted LLM pipeline as a virtual mimic of a human reviewer for the QUIPS framework and applied it to 298 articles from previously published systematic reviews of prognosis studies in neurology across three domains (epilepsy, traumatic brain injury, stroke), finding limited LLM-human agreement (weighted kappa = 0.22, 95% CI 0.12-0.33) while tentatively suggesting, based on a small sample (n=5), that it may not be inferior to human-human agreement (weighted kappa = -0.25, 95% CI -1.04-0.54), with Wilcoxon signed-rank tests statistically significant (p < 0.05) across four bias domains and overall risk scores, and rank-biserial correlations demonstrating human raters' tendency to assign higher risk scores than LLM counterparts.

  5. Combining AI Structure Prediction and Integrative Modeling for Nanobody-Antigen Complexes

    This study evaluates state-of-the-art machine-learning-based methods for nanobody structure prediction and benchmarks various HADDOCK workflows for modeling nanobody-antigen interactions across different input nanobody ensembles and information scenarios, proposing an ensemble docking pipeline that starts from nanobody structural models predicted by AlphaFold2 and ImmuneBuilder and, provided some epitope information is available, achieves higher success rates than the AlphaFold baseline on all generated models.

You’re all caught up