contrastive learning

OpenCRS: an open-source regulated human cardiorespiratory model with large-scale calibration and global sensitivity analysis at rest and during exercise

OpenCRS is a cardiorespiratory model calibrated with global sensitivity analysis to identify influential parameters and mechanisms during rest and exercise.

Exploring the potential role of the TETRATRICOPEPTIDE THIOREDOXIN-LIKE gene family in nitrogen-fixing and water-restricted soybean plants

This study characterizes the soybean TTL gene family, identifies co-expression modules related to abiotic stress, and links TTL proteins to nitrate reductase interactions in nitrogen-fixing plants under water deficit.

Interrogating contrastive learning embeddings for structure-based virtual screening: a case study on DrugCLIP

This paper evaluates DrugCLIP's contrastive learning embeddings for virtual screening, showing strong performance but limitations under realistic conditions.

Mechanistic Interpretability of Fine-Tuned Protein Language Models for Nanobody Thermostability Prediction

This paper fine-tunes a protein language model on nanobody thermostability data and uses sparse autoencoders to uncover biophysical rules governing stability, identifying both known and novel stabilizing features.

Extensive nuclear introgression accompanied ancient mitochondrial capture in the common ancestor of two sister hare species

The paper quantifies and localizes nuclear introgression in two hare species by combining demographic, phylogenomic, and polarisation-based methods, revealing extensive gene flow from mountain hare.

RamiGlyph Captures Microglial Morphological Diversity and Predicts Functional States in Ischemia Reperfusion and Amyloid Pathology

scACORN: Context-engineered agent orchestration of specialized small language models for single-cell transcriptomic interpretation

scACORN improves single-cell transcriptomic interpretation by combining specialized small language models with context-engineered agent orchestration, achieving higher accuracy and reducing unsupported gene citations.

ImmuneLens: linking transcriptional states and TCR clonotypes through disentangled multimodal learning

ImmuneLens links transcriptional states and TCR clonotypes using disentangled multimodal learning to improve antigen-specificity prediction and reveal T cell heterogeneity in immunotherapy.

How effective are contrastive learning-based approaches for activity-cliff prediction?

This study evaluates contrastive learning-based approaches for activity cliff prediction in drug discovery, finding they improve embedding separation but have dataset-dependent accuracy impacts.

SVD-SN2N: Self-Inspired Noise2Noise Learning for Denoising Log-Compressed SVD-Filtered Ultrasound Imaging

SVD-SN2N improves denoising of SVD-filtered ultrasound images by converting multiplicative speckle to additive noise, enhancing SNR and vessel resolution without requiring clean references or raw data.

DINOCT: robust skin surface localization for robotic noncontact dynamic optical coherence elastography

DINOCT improves skin surface localization in noncontact OCE by combining self-supervised pretraining with DINO and iBOT objectives, achieving high accuracy and robustness to artifacts.

DNT: Diploid Genomic Foundation Model

The paper introduces a diploid genomic foundation model to represent diploid genotypes in genomic language models, improving variant discrimination in compound-heterozygous cases.

Advancing long-read metagenomic binning via single-copy-gene guided contrastive learning

SCGBinner improves long-read metagenomic binning by using single-copy gene guided contrastive learning, outperforming existing methods on real-world datasets and recovering novel microbial species.

Overcoming artificial structures in resolution-enhanced Hi-C data by signal decomposition and multi-scale attention

This paper introduces SHARP, a method to enhance Hi-C data resolution while avoiding artificial structures by decomposing signals and using multi-scale attention.

Learning from tandem mass spectra at scale with a self-supervised foundation model for proteomics

This paper introduces InstaNovo-FM, a self-supervised foundation model for proteomics that learns from tandem mass spectra to enable transferable applications across datasets and instruments.

How do Co-Folding Models Organize Structural Information?

The paper analyzes how co-folding models organize structural information by examining the Boltz-1 trunk's internal representations and their role in predicting biomolecular complexes.

From Predicted Ki to Surrogate IC50: Similarity-Guided Empirical Calibration of Drug Target Affinity Predictions

The paper calibrates drug target affinity predictions to align with IC50 values using similarity-guided methods, reducing median fold error across kinase and non-kinase panels.

CORSICA: Reproducible Suppression of Cochlear Implant Artifacts in EEG evoked by Continuous Speech

CORSICA suppresses cochlear implant artifacts in speech-evoked EEG data using cross-correlation with speech stimuli, outperforming alternative methods with minimal manual intervention.

ContrasTED: contrastive domain embeddings for scalable remote homology classification

ContrasTED improves homology classification by using contrastive learning to assign domains to superfamilies with high accuracy, outperforming existing methods.

ReTIF: Granularity-Aware Multitask Interaction Routing for RNA-Compound Interaction Prediction and Binding-Site Localization

ReTIF improves RNA-compound interaction prediction and binding-site localization by using task-specific interaction representations, outperforming baselines in multiple evaluation scenarios.

Macrophage signature-based prediction of cancer treatment response using MIL-attention

The paper predicts cancer treatment response using a MIL-attention framework that analyzes macrophage states from single-cell RNA data, showing improved performance over existing methods.

Multimodal Protein Retrieval via Joint Representation Learning from Sequences and Cryo-EM Density Maps

This paper develops a multimodal framework to align protein sequences with cryo-EM density maps using joint representation learning, achieving strong retrieval performance across species and resolutions.

scRep: A Latent-Space Self-Distilled Foundation Model for Single-Cell Representation Learning

scRep is a foundation model for single-cell representation learning that uses self-distillation in latent space, achieving strong performance without task-specific fine-tuning.

Resolving Heterogeneous Mechanical Domains via Physics-Aware Deep Clustering of Single-Molecule Force Spectroscopy Data

This paper introduces a physics-aware deep clustering method to identify heterogeneous folding domains in single-molecule force spectroscopy data, revealing distinct mechanical properties in natural proteins.

GNMCADS: Sampling For Protein Conformation Diversity With Gaussian Network Model Guided Condition Annealed Diffusion Sampler

GNMCADS improves conformational sampling diversity by guiding diffusion models with Gaussian Network Model dynamics, outperforming existing methods on 92 proteins.

Audited vibe coding suggests partial fetal-like convergence of tumor proteomes

The paper reanalyzes a proteomic atlas using audited vibe coding to assess if tumors show fetal-like proteomic convergence, finding partial alignment with reverse fetal-to-adult maturation.

FuncSeek: Multi-PLM contrastive learning for protein functional similarity search

FuncSeek improves enzyme function prediction by using contrastive learning with multiple PLMs, outperforming existing methods on benchmark datasets.

RPDynaFlow: Generating RNA-Protein Conformational Ensembles by Atomic Conditional Flow Matching

RPDynaFlow generates RNA-protein conformational ensembles using flow-matching, expanding phase space sampling beyond MD simulations for studying interactions.

Decoupling Detection and Classification to Improve Morphological Phenotype Analysis of Sickle Red Blood Cells in Full-Scope Microscopy

This paper improves sickle cell disease morphology analysis by combining a YOLO detector with a DenseNet classifier for accurate detection and classification of red blood cell morphologies in full-scope microscopy images.

Quartet-based species tree methods enable fast and consistent tree of blobs reconstruction under network multispecies coalescent

The paper introduces TOB-QMC, a method for scalable and accurate tree of blobs reconstruction under network multispecies coalescent, improving upon TINNiK in both speed and accuracy.