Michael Krauthammer

ORCID: 0000-0002-4808-1845
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Melanoma and MAPK Pathways
  • Biomedical Text Mining and Ontologies
  • Computational Drug Discovery Methods
  • Semantic Web and Ontologies
  • Cancer Genomics and Diagnostics
  • Natural Language Processing Techniques
  • Bioinformatics and Genomic Networks
  • Immunotherapy and Immune Responses
  • Topic Modeling
  • Genomics and Phylogenetic Studies
  • RNA regulation and disease
  • CRISPR and Genetic Engineering
  • Ferroptosis and cancer prognosis
  • Cancer Research and Treatments
  • Machine Learning in Healthcare
  • Cancer, Hypoxia, and Metabolism
  • Scientific Computing and Data Management
  • Image Retrieval and Classification Techniques
  • Genetics, Bioinformatics, and Biomedical Research
  • Cutaneous Melanoma Detection and Management
  • CAR-T cell therapy research
  • Prostate Cancer Treatment and Research
  • RNA Interference and Gene Delivery
  • Distributed and Parallel Computing Systems
  • Service-Oriented Architecture and Web Services

University of Zurich
2018-2025

University Hospital of Zurich
2019-2025

ETH Zurich
2023

Kyoto University
2023

Quantitative BioSciences
2023

Dalle Molle Institute for Artificial Intelligence Research
2023

Yale University
2013-2022

Wake Forest University
2020

Yale Cancer Center
2016

National Institutes of Health
2015

Abstract Systems that extract structured information from natural language passages have been highly successful in specialized domains. The time is opportune for developing analogous applications molecular biology and genomics. We present a system, GENIES, extracts structures about cellular pathways the biological literature accordance with knowledge model we developed earlier. implemented GENIES by modifying an existing medical processing MedLEE, performed preliminary evaluation study. Our...

10.1093/bioinformatics/17.suppl_1.s74 article EN Bioinformatics 2001-06-01

The goal of the gene normalization task is to link genes or products mentioned in literature biological databases. This a key step an accurate search literature. It challenging task, even for human expert; are often described rather than referred by symbol and, confusingly, one name may refer different (often from organisms). For BioCreative II, was list Entrez Gene identifiers PubMed/MEDLINE abstracts. We selected abstracts associated with articles previously curated genes. provided 281...

10.1186/gb-2008-9-s2-s3 article EN cc-by Genome biology 2008-01-01

BRAF(V600E/K) is a frequent mutationally active tumor-specific kinase in melanomas that currently targeted for therapy by the specific inhibitor PLX4032. Our studies with melanoma tumor cells are and BRAF(WT) showed that, paradoxically, while PLX4032 inhibited ERK1/2 highly sensitive BRAF(V600E/K), it activated pathway resistant cells, via RAF1 activation, regardless of status mutations NRAS or PTEN. The persistently triggered downstream effectors induced changes expression wide-spectrum...

10.1111/j.1755-148x.2010.00685.x article EN Pigment Cell & Melanoma Research 2010-02-10

The sixth “Melanoma Bridge Meeting” took place in Naples, Italy, December 1st–4th, 2015. four sessions at this meeting were focused on: (1) molecular and immune advances; (2) combination therapies; (3) news immunotherapy; 4) tumor microenvironment biomarkers. Recent advances biology immunology has led to the development of new targeted immunotherapeutic agents that prolong progression-free survival (PFS) overall (OS) cancer patients. Immunotherapies particular have emerged as highly...

10.1186/s12967-016-1070-y article EN cc-by Journal of Translational Medicine 2016-11-15

10.1016/j.jbi.2004.08.004 article EN Journal of Biomedical Informatics 2004-10-12

DNA methylation is an important component of epigenetic modifications, which influences the transcriptional machinery aberrant in many human diseases. In this study we present first genome-wide integrative analysis promoter and gene expression for identification markers melanoma. Genome-wide eight early-passage melanoma cell strains were compared with newborn adult melanocytes. We used linear mixed effect models (LME) combination a series filters based on localization relative to...

10.1101/gr.091447.109 article EN cc-by-nc Genome Research 2009-06-02

Heterogeneity of tumor cells and their microenvironment can affect outcome in cancer. Blockade immune checkpoints (ICPs) expressed only on a subset leads to durable responses advanced melanoma. Tissue-resident memory T (TRM) have recently emerged as distinct nonlymphoid tissues. Here, we show that functional properties expression ICPs within tumor-infiltrating lymphocytes (TILs) differ from those blood cells. TILs secrete less IL-2, IFN-γ, TNF-α compared with circulating counterparts, VEGF...

10.1172/jci.insight.88955 article EN JCI Insight 2016-12-21

Abstract The major genetic determinants of cutaneous melanoma risk in the general population are disruptive variants ( R alleles) melanocortin 1 receptor MC1R ) gene. These alleles also linked to red hair, freckling, and sun sensitivity, all which known phenotypic factors. Here we report that melanomas for somatic C>T mutations, a signature exposure, expected single-nucleotide variant count associated with presence an allele is estimated be 42% (95% CI, 15–76%) higher than among persons...

10.1038/ncomms12064 article EN cc-by Nature Communications 2016-07-12

The Melanoma Research Foundation (MRF) has charted a comprehensive assessment of the current state melanoma research and care. Intensive discussions among members MRF Scientific Advisory Council Breakthrough Consortium, group that included clinicians scientists, focused on four thematic areas - diagnosis/early detection, prevention, tumor cell dormancy (including metastasis), therapy (response resistance). These extended over course 2015 culminated at Society International Congress in...

10.1111/pcmr.12475 article EN Pigment Cell & Melanoma Research 2016-04-17

Inspired by Curriculum Learning, we propose a consecutive (i.e., image-to-text-to-text) generation framework where divide the problem of radiology report into two steps. Contrary to generating full from image at once, model generates global concepts in first step and then reforms them finer coherent texts using transformer-based architecture. We follow sequence-to-sequence paradigm each step. improve upon state-of-the-art on benchmark datasets.

10.18653/v1/2021.findings-emnlp.241 preprint EN cc-by 2021-01-01

Base editors are chimeric ribonucleoprotein complexes consisting of a DNA-targeting CRISPR-Cas module and single-stranded DNA deaminase. They enable transition C•G into T•A base pairs vice versa on genomic DNA. While have great potential as genome editing tools for basic research gene therapy, their application has been hampered by broad variation in efficiencies different loci. Here we perform an extensive analysis adenine- cytosine library 28,294 lentivirally integrated genetic sequences...

10.1038/s41467-021-25375-z article EN cc-by Nature Communications 2021-08-25

Contrastive learning methods have shown an impressive ability to learn meaningful representations for image or time series classification. However, these are less effective forecasting, as optimization of instance discrimination is not directly applicable predicting the future state from historical context. To address limitations, we propose SimTS, a simple representation approach improving forecasting by predict past in latent space. SimTS exclusively uses positive pairs and does depend on...

10.1109/icassp48485.2024.10446875 article EN ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024-03-18

The widespread use of chest X-rays (CXRs), coupled with a shortage radiologists, has driven growing interest in automated CXR analysis and AI-assisted reporting. While existing vision-language models (VLMs) show promise specific tasks such as report generation or abnormality detection, they often lack support for interactive diagnostic capabilities. In this work we present RadVLM, compact, multitask conversational foundation model designed interpretation. To end, curate large-scale...

10.48550/arxiv.2502.03333 preprint EN arXiv (Cornell University) 2025-02-05

A major challenge in human genetics is identifying the molecular basis of common heritable disorders. In contrast to rare single-gene diseases, multifactorial disorders are thought arise from combined effect multiple gene variants, such that any single variant may have only a modest on disease susceptibility. We present method identify genes harbor significant proportion genetic variation predisposes individuals given disorder. First, we perform an automated literature analysis predicts...

10.1073/pnas.0404315101 article EN Proceedings of the National Academy of Sciences 2004-10-07

DNA methylation is an important component of epigenetic modifications that influences the transcriptional machinery and aberrant in many human diseases. Several methods have been developed to map for either limited regions or genome-wide. In particular, antibodies specific methylated CpG successfully applied genome-wide studies. However, despite relevance obtained results, interpretation antibody enrichment not trivial. Of greatest importance, coupling antibody-enriched fragments with...

10.1101/gr.080721.108 article EN cc-by-nc Genome Research 2008-09-02

Melanoma is an aggressive cancer that highly resistance to therapies once metastasized. We studied microRNA (miRNA) expression in clinical melanoma subtypes and evaluated different miRNA signatures the background of gain function somatic inherited mutations associated with melanoma. Total RNA from 42 patient derived primary cell lines three independent normal melanocyte cultures was by array. MiRNA then analyzed comparing additional clinicopathologic criteria including mutations. The...

10.4161/cc.10.11.15777 article EN Cell Cycle 2011-06-01
Coming Soon ...