Peter Karl Sorger

This paper introduces CyLinter, a quality control tool that removes imaging artefacts from high-plex spatial profiling data, improving single-cell analysis of archival tumor specimens.

The paper identifies a subset of mismatch repair proficient colorectal cancers with high immune infiltration that may benefit from immune checkpoint inhibitors, using spatial profiling and genomics.

This study identifies ASCT2 as the primary serine transporter in cancer cells and shows its role in purine biosynthesis and therapeutic targeting.

This study shows PRAME expression in melanoma is negatively regulated by TET2-mediated DNA hydroxymethylation, with reduced 5hmC levels correlating with PRAME upregulation.

The paper identifies TYK2 as a potential therapeutic target for neurodegenerative diseases by linking cdsRNA-induced inflammation to interferon signaling and demonstrating protective effects of TYK2 inhibitors.

psudo is an interactive system that optimizes pseudocolor palettes for multichannel biomedical images to enhance perceptual distinction and reduce color confusion in overlapping channels.

This paper introduces a MALDI MSI method to spatially profile metals in tissues, applying it to study embryogenesis, genetic disorders, and chemotherapy delivery.

The paper trains a new version of AlphaFold2, OpenFold, and evaluates its generalization ability and learning mechanisms.

SpatialCells automates the analysis of spatially resolved multiplexed single-cell data to characterize tumor microenvironments, enabling efficient feature extraction and downstream machine learning applications.

Cell Spotter (CSPOT) uses supervised machine learning to automate cell spotting and quantification in highly multiplexed tissue images, improving speed, accuracy, and reproducibility.

The paper shows nuclear rupture is common in cancer, especially glioblastoma, and links it to lamin proteins and immune signaling.

The paper proposes deep learning methods to reconstruct 3D CyCIF images and select optimal ROIs from histology and MTI data for tumor representation.

This study creates a multimodal tumor atlas to analyze how metastatic HR+ breast cancers adapt to CDK4/6 inhibitors, revealing mechanisms like mTORC1 activation and immune microenvironment changes.

This study compares CyCIF and IHC for immune profiling in ICI-induced dAEs, finding CyCIF provides more detailed single-cell characterization of immune infiltrates.

This paper introduces INDRA, a system that uses NLP and probability models to assemble high-quality molecular mechanisms from text and databases, improving accuracy over machine reading alone.

The paper constructs a database of receptor-ligand pairs and uses single-cell transcriptomics to identify injury-specific neuroimmune interactomes in inflammatory pain.

The paper models MAPK signaling in BRAFV600E melanoma cells to show how allostery and rewiring lead to drug resistance.

The paper introduces two methods to improve tissue segmentation in highly multiplexed images using real augmentations and nuclear envelope imaging, resulting in more accurate models.

The paper introduces a method called Dye Drop for high-throughput single-cell assays in 384-well plates, enabling detailed dose-response analysis of small molecules in breast cancer cell lines.

The paper develops ProtMapper to normalize phosphosite positions from databases and text mining, creating a comprehensive corpus of regulatory annotations.

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.

The paper investigates how varying ERK activity levels influence proliferation in cells undergoing oncogene-induced senescence, finding intermediate ERK activity promotes maximal proliferation.

This paper introduces RGN2, a deep learning model that predicts protein structure from single sequences without MSAs, outperforming AlphaFold2 and RoseTTAFold on orphan proteins and achieving faster computation.

This study introduces paired evaluation to improve performance estimation of machine learning models in drug response and disease severity prediction, showing up to 30% variation in performance estimates based on test data choice.

Galaxy-ME is a web-based software hub for analyzing and visualizing multiplex tissue imaging datasets, demonstrating its utility on normal and cancerous tissue data.

ASHLAR is a Python tool that stitches and registers highly multiplexed whole slide images to generate accurate mosaics, outperforming existing software.

The paper introduces fides, a Python framework for ODE model calibration using trust-region optimization, showing improved reliability and efficiency over existing methods.

The paper shows JNK and Erk signaling pathways have distinct roles in initiating and maintaining cell senescence after DNA damage through AP-1 and the senescence-associated secretory phenotype.

This study quantifies cell proliferation in tumors using multiplexed imaging and identifies spatial and temporal patterns of cell cycle regulation.

This study uses spatial transcriptomics to analyze cell type dynamics in rheumatoid arthritis synovium, revealing chemokine-driven interactions in inflamed tissue.