contrastive learning

GeneEmbedLLM: Harnessing Large Language Models for Gene Functional Embedding and Association Prediction

This paper introduces GeneEmbedLLM, a framework using large language models to generate gene embeddings from multi-source textual annotations, achieving competitive performance in various downstream tasks.

Contrastive Learning Improves Generalization on M2OR Olfactory Binding Dataset

The paper evaluates contrastive learning on VOC-OR binding datasets, showing improved generalization and reduced performance inflation from identity leakage.

Perturbation-induced gene programs map the hidden regulatory architecture of complex diseases

This paper introduces Perturbscape, a framework that uses perturbation-induced gene programs to identify disease-relevant genes and pathways, showing higher heritability informativeness than steady-state approaches.

MaxCAT-Net: Hybrid Transformer-Based Skin Lesion Classification and Lightweight Segmentation with Calibration and Cross-Dataset Validation

MaxCAT-Net improves skin lesion classification and segmentation with hybrid architecture and calibration, showing performance on benchmark datasets but with preliminary results.

A single-cell multimodal foundation model enables cross modality analysis between transcriptome and chromatin

MUTUAL enables cross-modality analysis between transcriptome and chromatin by learning a shared RNA-ATAC space from multiome data without refitting.

Ground-truth evaluation of sparse autoencoder features on spatial, single-cell and language-model embeddings

The paper evaluates sparse autoencoder features on various embeddings, finding that reproducibility does not guarantee meaningfulness, and proposes reporting features with concept coverage and purity.

Regularized logistic regression-based gene selection for functional analysis of heterogeneous scRNA-seq macrophage populations in muscle aging and regeneration.

The paper introduces DisTwiner, a method for subgroup-aware gene selection in scRNA-seq data, showing it captures biologically relevant aging pathways in macrophages.

Prediction transfer does not imply reliability transfer in single-cell foundation models

The paper investigates reliability transfer in single-cell foundation models across biological contexts and finds it varies independently from prediction transfer.

DNA-LLM2Vec: Architecture-Aware Task-Conditioned Adaptation of Decoder DNA Foundation Models

DNA-LLM2Vec adapts decoder DNA models to bidirectional context for genomic tasks, improving performance on extended-context tasks but varying by task and backbone.

Revealing pan-cancer clonal niches of T cells from single-cell RNA sequencing using contrastive learning

CloneTrast uses contrastive learning to infer T-cell clonal niches from single-cell RNA-seq, identifying NK-like niches linked to poor immunotherapy response across cancers.

An integrated multi-omic atlas of the choroid plexus highlights conserved molecular programs of epithelial function

This study integrates multi-omic data from mouse and human choroid plexus to identify conserved molecular programs of epithelial function across species.

Auditing Protein-Protein Interaction Signals with Sparse Autoencoder Fingerprints

AuditPPI evaluates PPI predictors by transforming language model features into auditable fingerprints, revealing that predictive success does not necessarily reflect biological signal capture.

Branch-Wise Regularization for Heterogeneous GNN-Based MALDI-TOF AMR Prediction with Biomarker-Consensus Edges

This paper evaluates a heterogeneous GNN for AMR prediction from MALDI-TOF spectra, showing it performs better than MLP only at high spectral similarity.

FAMUS: A Few-Shot Learning Framework for Large-Scale Protein Annotation

FAMUS improves protein annotation by using contrastive learning to compare query sequences against multiple profiles, outperforming existing tools in KEGG and PANTHER annotations.

Multi-Model Machine Learning Consensus Identifies a Dual-Interferon Gene Signature in Ischemic Stroke: An Integrative Single-Cell Transcriptomic Analysis

This paper uses a multi-model consensus framework to identify a dual-interferon gene signature in ischemic stroke using single-cell RNA sequencing data from a mouse model.

Spatially resolved contrastive analysis of perturbation-driven microenvironmental heterogeneity across tissues and conditions

Haruka identifies condition-specific and shared spatial domains across tissues and conditions using contrastive learning, demonstrating improved detection of spatially heterogeneous perturbation responses.

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.

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.

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.

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.

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.

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.

scDisent: regulatory-aware disentangled representation learning for multi-omic single-cell analysis

scDisent separates regulatory and expression variables in multi-omic single-cell data, improving integration and interpretability.

Time-resolved operator archetypes characterize dynamical sensitivity during cell-state transitions

This paper introduces scJDO, a framework for analyzing dynamical sensitivity during cell-state transitions, and applies it to iPSC reprogramming to distinguish productive from diverted fates.

Mapping disease traits onto spatiotemporal domain landscapes through scalable multi-sample integration of spatial transcriptomics

STUltra integrates spatial transcriptomics data to map disease traits onto spatiotemporal tissue landscapes, outperforming existing methods in scalability and speed.

Unlocking biological insight from single-cell data with an interpretable dual-stream foundation model

This paper introduces scDMC, a dual-stream foundation model for single-cell data that improves representation learning and achieves state-of-the-art results in cell annotation, clustering, and integration.

Contrastive Regulatory Embeddings Attention Model for Differential Expression Prediction with Personalized Genomes: Insights and Challenges

This paper introduces CREAM, a deep learning model for differential expression prediction using personalized genomes, showing improved performance on training genes but challenges in generalizing to unseen genes.

CENO: A Genome-Scale World Model for Evolutionary Sequence Interpretation and Programmable Regulatory Design

CENO is a long-context generative model for genomic sequence understanding and design, showing improved variant prediction and regulatory sequence generation across species.

SpatialJEPA: JEPA-inspired graph-context distillation for spatially aware multiomics integration

SpatialJEPA transfers spatial context from spatial multiomics data to dissociated non-spatial data through graph-context distillation, improving alignment and recovery of spatially organized programs in mouse brain multiomics.

SST-MAE: Learning Spectral-Spatio-Temporal Representations from Plant Hyperspectral Time Series to Discover Complex Genotype-Phenotype Relations