The study introduces WTKO-CNN, a convolutional neural network with an attention mechanism, to classify DNA sequences as wild‑type (WT) or knockout (KO) based on ATAC‑seq data. By generating saliency maps, the authors pinpointed influential nucleotide positions, extracted high‑saliency k‑mers, and performed de novo motif discovery, producing sequence logos and consensus motifs that align with known transcription factor binding sites. Validation with MEME, TOMTOM, and HOMER confirmed that the identified motifs belong to transcription factor families that differentiate WT from KO sequences.
arXiv:2511. 09026v2 Announce Type: replace-cross Abstract: Whole-genome sequencing (WGS) has revealed numerous non-coding short variants whose functional impacts remain poorly understood.
arXiv:2606. 09558v1 Announce Type: cross Abstract: Motivation: Transformer-based models are increasingly applied to large-scale single-cell transcriptomics, showing strong performance through self-supervised learning on millions of cells.
arXiv:2603. 24025v2 Announce Type: replace Abstract: Unsupervised learning of high-dimensional data is challenging due to irrelevant or noisy features obscuring underlying structures.
arXiv:2506. 13196v5 Announce Type: replace Abstract: Accurate prediction of protein-ligand binding affinity is critical for drug discovery.
arXiv:2609.14882v1 Announce Type: cross Abstract: Nucleotide sequence analysis is central to problems spanning regulatory genomics, evolutionary biology, and phenotype prediction. Classical bioinform...
arXiv:2606. 00685v1 Announce Type: new Abstract: Gene regulatory networks (GRNs) capture transcription factor-target interactions and are central to understanding cell-state regulation and disease.
arXiv:2606. 13007v1 Announce Type: cross Abstract: Clustering is fundamental to scRNA-seq analysis, serving as a cornerstone for identifying cell populations and resolving tissue heterogeneity.
arXiv:2410. 00945v2 Announce Type: replace-cross Abstract: Gene-expression profiling is widely used in research and central to many areas of precision oncology, but remains costly and not universally accessible.
GATE-ST is a gene-aware text-image encoder that enhances spatial transcriptomics predictions by integrating gene descriptions into image-based models. The method encodes gene summaries with a text encoder and fuses these embeddings with image features via cross‑attention, aligning them with morphological cues. Benchmarks show GATE‑ST outperforms random gene embeddings and other image‑text fusion architectures, indicating its potential to improve accuracy while reducing time and cost in spatial gene expression analysis.
While recent advancements in anomaly detection have demonstrated the efficacy of CNN- and Transformer-based approaches, these architectures face inherent limitations: CNNs struggle to capture long-range dependencies, whereas Transformers suffer from quadratic computational complexity. Consequently, Mamba-based architectures have attracted considerable attention, as they successfully combine superior long-range dependency modeling with linear computational complexity.
The paper introduces a multimodal framework that learns subcellularly resolved cell embeddings by integrating RNA expression profiles, protein sequence representations, and protein structural information using a cross‑attention architecture. This approach models interactions within distinct subcellular compartments, producing fine‑grained embeddings that capture both molecular expression patterns and functional protein properties. It is presented as the first method to jointly incorporate transcriptomic data, sequence, and structural knowledge for subcellularly resolved cell representation.
The paper introduces Denoising Attention (DnA), a modification to the standard softmax activation used in multihead attention for visual perception tasks. DnA employs a positive query to highlight correct class features and a negative query to suppress irrelevant features, projecting these interactions into two distinct subspaces to enhance discriminability. Experiments with a ViT-B backbone show an absolute 0.8% improvement on ImageNet-1K and additional gains on video understanding and video LLM tasks.