Gordon Brent Mills

SCORPy: Lowering the computational barrier to reproducible multiplexed imaging spatial single cell proteomics analysis

SCORPy provides a code-free desktop application for analyzing spatial single-cell proteomic data, improving accessibility and standardization in multiplexed imaging analysis.

ACCREDIT: A Quality-Aware Agentic Engine for Cell-resolved Cross-modal Image Registration with Dynamic Iterative Tuning

ACCREDIT improves cross-modal image registration by detecting failures and automatically recovering alignments, outperforming existing methods in accuracy and robustness.

High-Density Wild-Type IL-2 Nanoparticles Preferentially Enhance CD8⁺ T-Cell Expansion and Reprogram the Tumor Microenvironment

This paper develops IL2-NP nanoparticles that enhance CD8 T-cell expansion and reprogram the tumor microenvironment, showing efficacy in multiple cancer models.

Tumor-immune trajectory context connects static tissue architecture to clinical outcomes

This paper introduces a trajectory-centric framework to model dynamic tumor-immune interactions, showing that treatment-phase TME states predict immunotherapy response better than pre-treatment states.

Global mRNA 3'UTR lengthening in small-cell neuroendocrine carcinoma

The paper identifies global 3'UTR lengthening in SCNC through APA and develops a neural network model to classify SCNC using APA signatures.

miniMTI: minimal multiplex tissue imaging enhances biomarker expression prediction from histology

miniMTI reduces the number of molecular markers needed for multiplex tissue imaging by combining H&E with a few measured markers, preserving biological and clinical information.

Neoplastic immune mimicry potentiates breast tumor progression

This study identifies immune mimicry in breast cancer cells, where neoplastic cells express leukocyte receptors, enhancing tumor aggressiveness and therapy resistance.

Tumor-intrinsic MHC-II activation in pancreatic ductal adenocarcinoma enhances immune response and treatment efficacy

This study shows that MHC-II expression in pancreatic cancer cells correlates with immune infiltration and improves immunotherapy response in mouse models.

Spatial organization of the tumor-immune microenvironment in ER-positive breast cancer: remodeling during treatment and associations with clinical response

This study examines how the spatial organization of the tumor-immune microenvironment changes during treatment in ER-positive breast cancer and links these changes to clinical response.

Language of Stains: Tokenization Enhances Multiplex Immunofluorescence and Histology Image Synthesis

The paper introduces a computational method to synthesize marker stains from H&E images, improving marker prediction and reducing reliance on experimental data.

UniFORM: Towards Universal Immunofluorescence Normalization for Multiplex Tissue Imaging

UniFORM normalizes multiplex tissue imaging data by aligning negative populations and preserving positive variation, outperforming existing methods in batch effect mitigation and downstream analysis.

COEXIST: Coordinated single-cell integration of serial multiplexed tissue images

COEXIST integrates serial multiplexed tissue images at the single-cell level by combining molecular profiles with spatial information to improve profiling and platform validation.

Automated Machine Learning Profiling with MAP-HR for Quantifying Homologous Recombination Foci in Patient Samples

The paper introduces MAP-HR, a machine learning platform for quantifying homologous recombination foci in patient samples to assess HR deficiency and guide therapy.

Sensitizing Immune-Refractory Ovarian Tumors via p53 Mutation-Tailored Immunotherapy

This study identifies a p53 mutation-specific immunotherapy strategy for ovarian cancer by targeting AREG and PD-L1, showing efficacy in mouse models and patient-derived organoids.

Deciphering single-cell heterogeneity and cellular ecosystem dynamics during prostate cancer progression

This study constructs the Prostate Cancer Cell Atlas by analyzing ~710,000 single cells from 197 human samples to characterize cell states and dynamics across prostate cancer progression stages.

A Comprehensive Proteogenomic and Spatial Analysis of Innate and Acquired Resistance of Metastatic Melanoma to Immune Checkpoint Blockade Therapies

This study identifies molecular mechanisms of resistance to immune checkpoint blockade in metastatic melanoma using proteogenomic and spatial analyses of tumor and immune microenvironment data.

Androgen receptor activity inversely correlates with immune cell infiltration and immunotherapy response across multiple cancer lineages

The paper examines the relationship between androgen receptor activity and immune cell infiltration, showing that lower AR activity correlates with increased immune activity and better immunotherapy response across multiple cancers.

MIM-CyCIF: Masked Imaging Modeling for Enhancing Cyclic Immunofluorescence (CyCIF) with Panel Reduction and Imputation

The paper introduces a computational method to reduce CyCIF panel size while preserving information content through masked imaging modeling and imputation.

Graph Structured Neural Networks for Perturbation Biology

This paper introduces Graph Structured Neural Networks (GSNN) for perturbation biology, showing they outperform baselines in predicting perturbed gene expression, drug combinations, and disease-specific drug prioritization.

Explainable Machine Learning Reveals the Role of the Breast Tumor Microenvironment in Neoadjuvant Chemotherapy Outcome

The paper uses scRNA-seq and explainable machine learning to analyze how tumor microenvironment cell types affect neoadjuvant chemotherapy outcomes in breast cancer.

Selective enrichment of plasma cell-free messenger RNA in cancer-associated extracellular vesicles

The paper analyzes cf-mRNA in EVs and non-vesicular carriers from cancer patients and healthy donors, finding EVs selectively enrich cf-mRNA associated with specific biological pathways.

Supervised learning of high-confidence phenotypic subpopulations from single-cell data

PENCIL identifies phenotype-relevant cell subpopulations from single-cell data using a supervised learning framework with feature selection and trajectory prediction capabilities.

Systematic Pan-cancer Functional Inference and Validation of Hyper, Hypo and Neomorphic Mutations

The paper functionally characterizes 577,866 non-recurrent mutations across TCGA cohorts by analyzing TF activity, identifying neomorphic and mimicry mutations, and validating them with knock-in assays.

A LINCS microenvironment perturbation resource for integrative assessment of ligand-mediated molecular and phenotypic responses

The paper presents a LINCS Microenvironment perturbation dataset cataloging transcriptional, proteomic, epigenomic, and phenotypic responses of MCF10A cells to six ligands, enabling integrative analysis of molecular and phenotypic changes.

Beyond BRCA: Discovery of novel causes and consequences of homologous recombination deficiencies

This study identifies RNA binding proteins as novel drivers of homologous recombination deficiency in tumors, expanding the known genetic causes beyond BRCA1/2 mutations.

ME-VAE: Multi-Encoder Variational AutoEncoder for Controlling Multiple Transformational Features in Single Cell Image Analysis

The paper introduces ME-VAE, a multi-encoder VAE for single-cell image analysis that extracts transform-invariant biologically meaningful features, improving cell population separation and phenotypic differences.

Spatially Interacting Phosphorylation Sites and Mutations in Cancer

The paper introduces HotPho, a tool that identifies 3D co-clustering of phosphosites and cancer mutations on protein structures, revealing 474 hybrid clusters with potential functional significance.

Targeting Adaptation to Cancer Treatment by Drug Combinations

This paper introduces TargetScore, a method to identify adaptive responses and predict drug-induced vulnerabilities in cancer cells, validated through experiments on breast cancer cells.

Large-scale Characterization of Drug Responses of Clinically Relevant Proteins in Cancer Cell Lines

The paper compiles protein response data from cancer cell lines to drug perturbations, showing improved drug sensitivity prediction and building a protein-drug connectivity map with an accessible data portal.