Patrick C. N. Martin

Cross-domain confidence reliability and remappability of frozen single-cell representations

The paper evaluates the reliability of confidence measures from single-cell models on new data and shows that raw confidence scores are unreliable, requiring recalibration with target-specific labels.

PersonaAI: An Interactive Agentic-AI Framework for Autonomous Hypothesis Generation and Validation in Aging

PersonaAI generates and validates aging-related hypotheses using literature and single-cell RNA-seq data, identifying novel aging mechanisms.

Multi-scale and multi-context mapping of cell states across heterogenous spatial samples.

This paper introduces an interpretable cell mapping strategy to align and compare heterogeneous spatial data across different scales and contexts, showing spatiotemporal decoupling during development and identifying subpopulations in cancer patient data.

CellNeighborEX: Deciphering Neighbor-Dependent Gene Expression from Spatial Transcriptomics Data

CellNeighborEX identifies gene expression influenced by neighboring cells in spatial transcriptomics data, revealing new insights into cell-cell interactions in mouse embryos, brain, and liver cancer.

Identification of mammalian transcription factors that bind to inaccessible chromatin

The paper develops a statistical model to predict TF binding to chromatin and finds that about one third of TFs bind independently of chromatin accessibility.

Vesalius: high-resolution in silico anatomization of Spatial Transcriptomic data using Image Analysis

Vesalius identifies tissue structures and cell-type-specific gene expression in spatial transcriptomics data by applying image analysis techniques.

Dissecting the binding mechanisms of transcription factors to DNA using a statistical thermodynamics framework.

The paper introduces ChIPanalyser, a statistical thermodynamics model for predicting TF-DNA binding, showing differences in binding mechanisms across TFs and cell lines.