Md. Abul Hassan Samee

The paper introduces a reference-free scRNA-seq analysis method using k-mers, identifies elevated rRNA and mtRNA transcription during axolotl neurogenesis, and detects other RNA features in disease datasets.

SPARC improves trajectory inference by jointly modeling state progression and transitions between conditions, revealing osteoclastogenesis-associated malignant states in osteosarcoma metastasis.

K-PoPS improves gene prioritization for complex traits by providing explainable insights into GWAS results, identifying plausible effector genes with supporting evidence.

This paper models tissue-specific biological age using machine learning on GTEx data, finding that extreme aging in specific tissues correlates with increased mortality risk.

This paper introduces scPSS, a method to quantify pathological shifts in single-cell data by comparing diseased cells to healthy references, showing it can predict individual health conditions.

The paper introduces a framework to model feature interactions and temporal dynamics in Alzheimer's disease progression using ADNI data, identifying key clinical and molecular markers.

This paper demonstrates the use of 19F-Eu-based contrast agents for real-time hypoxia imaging in tumors, showing reliable delivery and integration with spatial biology for biomarker identification.

This paper introduces a supervised NMF framework to link spatial transcriptomics data with molecular events, identifying genes associated with disease progression in Alzheimer's and myocardial infarction.

GAGER identifies key transcription factors to restore gene expression from a source to target state across multiple datasets, improving similarity between healthy and diseased states.

This paper introduces scGIST, a deep learning method for designing spatial transcriptomics panels that prioritizes genes of interest while maintaining accuracy in cell type detection.

The paper introduces CRISPR-DIPOFF, a deep learning model for CRISPR-Cas9 off-target prediction that improves performance and provides interpretability through integrated gradients and genetic algorithm optimization.

The paper evaluates imputation methods and quality standards for predicting epigenetic age from single-cell DNA methylation data in humans.

This paper introduces a probabilistic clustering method for scRNA-seq data that handles dropouts and does not require prior marker gene information, outperforming existing methods on six datasets.

CC-Tempo improves prediction of cell fate by integrating cell-cell communication scores into a temporal model of cellular differentiation.

This study shows that Hippo-deficient cardiac fibroblasts differentiate into osteochondroprogenitors and interact with macrophages, promoting fibrosis through CSF1 signaling.

The paper models human genome mutation rates using DNA shape features, achieving higher accuracy than sequence-based models and identifying structural properties linked to mutation rates.

DeepBend is a convolutional neural network that identifies DNA bendability motifs and their spatial patterns, revealing known and novel motifs and their role in chromatin structure.

This paper introduces NoVaTeST, a framework to detect genes with location-dependent noise variance in spatial transcriptomics data, showing it provides complementary insights to existing tools.

The paper analyzes how EBNA2 and EBNA3 vTFs bind the human genome across cell-types, showing they use both cell-type specific and independent cofactors and reveal novel sequence motifs.

The paper develops STANN, a neural network model to integrate spatial transcriptomics and scRNA-seq data, revealing spatial organization and intercellular communication principles in mouse olfactory bulb.

The paper introduces MuSeAM, a convolutional neural network that models sequence-specific motifs and enhancer activities from MPRAs, achieving high accuracy and generalizing to related tasks.

The paper shows that transcription factors recognize DNA shape rather than sequence, using ShapeMF to identify shape-motifs that drive binding independent of sequence motifs.