A5062928181- Machine Learning in Healthcare
- Genomics and Chromatin Dynamics
- Marine Invertebrate Physiology and Ecology
- Chromosomal and Genetic Variations
- CRISPR and Genetic Engineering
- Epigenetics and DNA Methylation
- Epilepsy research and treatment
- Topic Modeling
- Genetic Associations and Epidemiology
- Molecular Biology Techniques and Applications
- Protist diversity and phylogeny
- Chronic Disease Management Strategies
- Computational Drug Discovery Methods
- RNA and protein synthesis mechanisms
- RNA Interference and Gene Delivery
- Advanced biosensing and bioanalysis techniques
- Biomedical Text Mining and Ontologies
- MicroRNA in disease regulation
- Cancer-related gene regulation
- Marine Ecology and Invasive Species
- Cancer therapeutics and mechanisms
- Machine Learning in Materials Science
- Artificial Intelligence in Healthcare
- Gene Regulatory Network Analysis
- Hepatitis B Virus Studies
Boehringer Ingelheim (Germany)
2024-2025
Boehringer Ingelheim (Australia)
2023-2024
Digital Science (United States)
2023-2024
UCB Pharma (Germany)
2019-2023
The Netherlands Cancer Institute
2013-2019
Oncode Institute
2019
Centre for Medical Systems Biology
2014
Genesis Foundation
2013
Wellcome Sanger Institute
2011
University of Amsterdam
2010-2011
Highlights•A method for parallel monitoring of thousands reporters integrated in the genome•Genome-wide landscape chromatin position effects mouse embryonic stem cells•Attenuation transcriptional activity lamina-associated domains•• Enhancers and transcription units influence gene expression generally over ∼20 kbSummaryReporter genes into genome are a powerful tool to reveal regulatory elements local context on expression. However, so far such reporter assays have been low throughput. Here,...
Accurate and individualized prediction of response to therapies is central precision medicine. However, because the generally complex multifaceted nature clinical drug response, realizing this vision highly challenging, requiring integrating different data types from same individual into one model. We used anti-epileptic brivaracetam as a case study combine hybrid data/knowledge-driven feature extraction with machine learning systematically integrate genetic discovery dataset (n = 235...
The ability of retroviruses and transposons to insert their genetic material into host DNA makes them widely used tools in molecular biology, cancer research gene therapy. However, these systems have biases that may strongly affect outcomes. To address this issue, we generated very large datasets consisting unselected integrations the mouse genome for Sleeping Beauty (SB) piggyBac (PB) transposons, Mouse Mammary Tumor Virus (MMTV). We analyzed (epi)genomic features generate bias maps at both...
EZH2 is frequently overexpressed in glioblastoma (GBM), suggesting an oncogenic function that could be a target for therapeutic intervention. However, reduced activity can also promote tumorigenesis, leading to concerns about the use of inhibitors. Here, we provide further insight effects prolonged Ezh2 inhibition using preclinical mouse models and primary tumor-derived human GBM cell lines. Using doxycycline-inducible shRNAs mimic selective inhibitor, demonstrate depletion causes robust...
Abstract Understanding the impact of guide RNA (gRNA) and genomic locus on CRISPR-Cas9 activity is crucial to design effective gene editing assays. However, it challenging profile Cas9 in endogenous cellular environment. Here we leverage our TRIP technology integrate ~ 1k barcoded reporter genes genomes mouse embryonic stem cells. We target integrated reporters (IRs) using RNA-guided characterize induced mutations by sequencing. report that gRNA-sequence IR explain most variation mutation...
Precision medicine requires a stratification of patients by disease presentation that is sufficiently informative to allow for selecting treatments on per-patient basis. For many diseases, such as neurological disorders, this problem translates into complex clustering multivariate and relatively short time series because (i) these diseases are multifactorial not well described single clinical outcome variables (ii) progression needs be monitored over time. Additionally, data often...
Genomically distal mutations can contribute to the deregulation of cancer genes by engaging in chromatin interactions. To study this, we overlay viral cancer-causing insertions obtained a murine retroviral insertional mutagenesis screen with genome-wide conformation capture data. Here find that tend cluster 3D hotspots within nucleus. The identified are significantly enriched for known genes, and bear expected characteristics bona fide regulatory interactions, such as enrichment...
The evaluation and management of first-time seizure-like events in children can be difficult because these episodes are not always directly observed might epileptic seizures or other conditions (seizure mimics). We aimed to evaluate whether machine learning models using real-world data could predict seizure recurrence after an initial event. This retrospective cohort study compared trained evaluated on two separate datasets between Jan 1, 2010, 2020: electronic medical records (EMRs) at...
Insertional mutagenesis is a potent forward genetic screening technique used to identify candidate cancer genes in mouse model systems. An important, yet unresolved issue the analysis of these screens, identification affected by insertions. To address this, we developed Kernel Convolved Rule Based Mapping (KC-RBM). KC-RBM exploits distance, orientation and insertion density across tumors automatically map integration sites target genes. We perform first genome-wide evaluation association...
Abstract Dementia probably due to Alzheimer’s disease is a progressive condition that manifests in cognitive decline and impairs patients’ daily life. Affected patients show great heterogeneity their symptomatic progression, which hampers the identification of efficacious treatments clinical trials. Using artificial intelligence approaches enable enrichment trials serves promising avenue identify treatments. In this work, we used deep learning method cluster multivariate trajectories 283...
The forkhead transcription factor FOXP1 is generally regarded as an oncogene in activated B cell-like diffuse large B-cell lymphoma. Previous studies have suggested that a small isoform of rather than full-length FOXP1, may possess this oncogenic activity. Corroborating those studies, we herein show lymphoma cell lines and primary cells predominantly express isoform, the 5′-end Foxp1 gene common insertion site murine lymphomas leukemia virus- transposon-mediated insertional mutagenesis...
Epilepsy is a complex brain disorder characterized by repetitive seizure events. patients often suffer from various and severe physical psychological comorbidities (e.g., anxiety, migraine, stroke). While general comorbidity prevalences incidences can be estimated epidemiological data, such an approach does not take into account that actual patient-specific risks depend on individual factors, including medication. This motivates to develop machine learning for predicting of future epilepsy...
Background The starlet sea anemone Nematostella vectensis is a diploblastic cnidarian that expresses set of conserved genes for gut formation during its early development. During the last decade, spatial distribution many these has been visualized with RNA hybridization or protein immunolocalization techniques. However, due to N. vectensis' curved and changing morphology, quantification data problematic. A method developed two-dimensional gene expression quantification, which enables...
Abstract Background Machine learning and deep are powerful tools for analyzing electronic health records (EHRs) in healthcare research. Although family history has been recognized as a major predictor wide spectrum of diseases, research so far adopted limited view relations, essentially treating patients independent samples the analysis. Methods To address this gap, we present ALIGATEHR, which models inferred relations graph attention network augmented with an attention-based medical...
Abstract Dementia probably due to Alzheimer’s disease (AD) is a progressive condition that manifests in cognitive decline and impairs patients’ daily life. Affected patients show great heterogeneity their symptomatic progression, which hampers the identification of efficacious treatments clinical trials. Using artificial intelligence approaches enable enrichment trials serves promising avenue identify treatments. In this work, we used deep learning method cluster multivariate trajectories...
The spatial distribution of many genes has been visualized during the embryonic development in starlet sea anemone Nematostella vectensis last decade. In situ hybridization images are available Kahi Kai gene expression database, and a method developed to quantify patterns N. vectensis. this paper, quantification is performed on wide range from database descriptions observed domains stored separate for further analysis. Spatial suitable quantified with GenExp program. A correlation analysis...
Abstract Precision medicine requires accurate identification of clinically relevant patient subgroups. Electronic health records provide major opportunities for leveraging machine learning approaches to uncover novel However, many existing fail adequately capture complex interactions between diagnosis trajectories and disease-relevant risk events, leading subgroups that can still display great heterogeneity in event underlying molecular mechanisms. To address this challenge, we implemented...
Abstract Artificial intelligence and machine learning are powerful tools in analyzing electronic health records (EHRs) for healthcare research. Despite the recognized importance of family history, research individual patients often treated as independent samples, overlooking relations. To address this gap, we present ALIGATEHR, which models predicted relations a graph attention network integrates information with medical ontology representation. Taking disease risk prediction use case,...