A5028422521- Cancer Genomics and Diagnostics
- AI in cancer detection
- Cancer Immunotherapy and Biomarkers
- Radiomics and Machine Learning in Medical Imaging
- Reinforcement Learning in Robotics
- Evolution and Genetic Dynamics
- Bioinformatics and Genomic Networks
- Neural dynamics and brain function
- Lung Cancer Treatments and Mutations
- Advanced Memory and Neural Computing
- vaccines and immunoinformatics approaches
- Computational Drug Discovery Methods
- Colorectal Cancer Treatments and Studies
- Cancer, Stress, Anesthesia, and Immune Response
- Mental Health Research Topics
- 3D Printing in Biomedical Research
- Plant Virus Research Studies
- Modular Robots and Swarm Intelligence
- Evolutionary Game Theory and Cooperation
- Stress Responses and Cortisol
- Immune Cell Function and Interaction
- Cell Image Analysis Techniques
- Gene Regulatory Network Analysis
- Hepatocellular Carcinoma Treatment and Prognosis
- Genetics, Aging, and Longevity in Model Organisms
University of Iowa
2007
Stanford University
2005
Hebrew University of Jerusalem
2001-2003
Tel Aviv University
1999
Abstract The adaptive value of recombination remains something a puzzle. One the basic problems is that not only creates new and advantageous genetic combinations, but also breaks down existing good ones. A negative correlation between fitness an individual its rate would result in prolonged integrity fitter combinations while enabling less fit ones to produce combinations. Such could be mediated by various factors, including stress responses, age, or direct DNA damage. For haploid...
Precision oncology is gradually advancing into mainstream clinical practice, demonstrating significant survival benefits. However, eligibility and response rates remain limited in many cases, calling for better predictive biomarkers.We present ENLIGHT, a transcriptomics-based computational approach that identifies clinically relevant genetic interactions uses them to predict patient's variety of therapies multiple cancer types without training on previous treatment data. We study ENLIGHT two...
Introduction Immune checkpoint inhibitors (ICI) have improved outcomes in non-small cell lung cancer (NSCLC). Nevertheless, the clinical benefit of ICI as monotherapy or combination with chemotherapy remains widely varied and existing biomarkers limited predictive value. We present an analysis ENLIGHT-DP, a novel transcriptome-based biomarker directly from histopathology slides, patients adenocarcinoma (LUAD) treated platinum-based chemotherapy. Methods retrospectively scanned...
Abstract Background: A major aim in precision oncology is establishing predictive biomarkers to enable improved treatment matching for patients. mRNA expression one of the most available and explored modalities generation such models. Several works have demonstrated that supervised learning using transcriptomic data can generate biomarkers. However, scarcity datasets couple with drug response severely limit this approach. In contrast, unsupervised models offer a potential broadly applicable...
Abstract Background: Transcriptomics-based predictors show great promise in identifying responders to immune checkpoint inhibitors (ICI) who are rejected by standard biomarkers like PD-L1. However, the reliance on gene-expression data makes these less applicable clinic. On other hand, H&E-stained slides commonly available, so predicting response from slide scans could greatly improve accessibility. We have previously described DeepPT - a deep learning model infer gene expression H&E...
Many drugs show promising results in laboratory research but eventually fail to clinical benefit. One main reason for this translational gap is that the cancer models used are inadequate. Most lack complex tumor-stromal-immune cell interactions with their tumor microenvironment (TME) required progression. Conventional 2D models, where cells grow on rigid plastic plates mainly as mono-cultures, recapitulate these interactions. Hence, we developed two platforms of 3D better mimic TME: (i) a...
Fibrolamellar carcinoma (FLC) is a rare cancer of the liver that most commonly affects children and young adults. There no clear standard care for disease, whose response to treatment seems be very different from hepatocellular carcinoma. We present case FLC in patient her mid 30s recurred persisted despite resection multiple lines treatment. Following transcriptomic analysis, combination ipilimumab (anti-CTLA4) nivolumab (anti-PD-1) led complete remission, although common biomarkers immune...
Abstract A negative correlation between fitness and recombination rates seems to exist in various organisms. In this article we suggest that a of kind may play an important role the evolution complex traits. We study effects such fitness-associated (FAR) simple two-locus deterministic model, as well multi-loci NK rugged adaptive landscape. both models studied, FAR results faster adaptation higher average population fitness, compared with uniform-rate recombination.
Among the long-standing conundrums of evolutionary theory, obligatory sex is one hardest. Current theory suggests multiple factors that might explain benefits when compared with complete asexuality, but no satisfactory explanation for prevalence in face facultative sexual reproduction. We show selection present can evolve and be maintained even against sex, under common scenarios deleterious mutations environmental changes.
Using evolutionary simulations, we develop autonomous agents controlled by artificial neural networks (ANNs). In simple lifelike tasks of foraging and navigation, high performance levels are attained equipped with fully recurrent ANN controllers. a set experiments sharing the same behavioral task but differing in sensory input available to agents, find common structure command neuron switching dynamics network between radically different modes. When position information is available,...
The reaction of the body to prolonged stress has many harmful effects. Classical theory assumes that responses have evolved due their short-term selective advantages (‘flight or fight’), and despite adverse long-term In contrast, we demonstrate effects may a advantage. Using an analytical model show gene causes early death relatively unfit individual can increase in frequency structured population even if it no positive effect on individual. This result offers new perspective relations...
Advances in artificial intelligence have paved the way for leveraging hematoxylin and eosin (H&E)-stained tumor slides precision oncology. We present ENLIGHT-DeepPT, an approach predicting response to multiple targeted immunotherapies from H&E-slides. In difference existing approaches that aim predict treatment directly slides, ENLIGHT-DeepPT is indirect two-step consisting of (1) DeepPT, a new deep-learning framework predicts genome-wide mRNA expression (2) ENLIGHT, which based on DeepPT...
ABSTRACT Advances in artificial intelligence have paved the way for leveraging hematoxylin and eosin (H&E)-stained tumor slides precision oncology. We present ENLIGHT-DeepPT, an approach predicting response to multiple targeted immunotherapies from H&E-slides. In difference existing approaches that aim predict treatment directly slides, ENLIGHT-DeepPT is indirect two-step consisting of (1) DeepPT, a new deep-learning framework predicts genome-wide mRNA expression (2) ENLIGHT, which...
1551 Background: In recent years, the use of tumour molecular profiling within clinic has allowed for more accurate cancer diagnostics, as well delivery precision oncology. Rapid advances in digital histopathology have extraction clinically relevant information embedded tumor slides by applying machine learning methods, capitalizing on advancements image analysis via deep learning. However, many supervised approaches, predicting response to therapy using whole slide images (WSI) tissue...
Abstract Background Precision oncology is gradually advancing into mainstream clinical practice, demonstrating significant survival benefits. However, eligibility and response rates remain limited in many cases, calling for better predictive biomarkers. Methods We present ENLIGHT, a transcriptomics-based computational approach that identifies clinically relevant genetic interactions uses them to predict patient’s variety of therapies multiple cancer types, without training on previous...
e15170 Background: A key goal in precision oncology is to develop predictive biomarkers that can identify patients likely benefit from a given treatment. The main hurdle for generating such the availability of datasets match features each patient (clinical, omics etc.) with treatment and individual outcome data. Such are hard obtain approved drugs, nonexistent drugs development. In contrast, there ample data matching survival data, but methods use validate drug-specific lacking. Here, we...
2666 Background: Immune checkpoint blockers (ICB) are revolutionizing cancer treatment, and being approved for an increasingly wide range of types. The most common biomarkers currently in use to select patients ICB PD-L1 expression on tumor cells, as measured by IHC, mutational burden (TMB) microsatellite instability (MSI), both NGS. However, some that negative these markers still respond ICB. This calls complementary better identify responders ICB, especially current biomarkers. Here, we...
1553 Background: Precision oncology is gradually advancing into mainstream clinical practice, demonstrating significant survival benefits. However, eligibility and response rates remain limited in many cases, calling for better predictive biomarkers. Methods: We present ENLIGHT, a transcriptomics-based computational approach that identifies clinically relevant genetic interactions uses them to predict patient’s variety of therapies multiple cancer types, importantly, without training on...
<h3>Background</h3> Immune checkpoint blockers (ICB) are revolutionizing cancer treatment, approved for increasingly more types. The most common biomarkers currently used routinely to select patients ICB TMB, microsatellite stability and PDL1 presentation. However, some that do not meet the criteria of these markers still respond ICBs. This calls complementary could better identify responders ICBs importantly, discover where standard fail so. Here, we focus on predicting response anti-PD1 in...
3064 Background: In recent years, the use of tumor molecular profiling in clinical settings has enhanced cancer diagnostics, as well delivery precision oncology. Recently, several methods for predicting gene expression directly from Haematoxylin-and-Eosin-stained (H&E) histology images have offered a new way to leverage easily obtainable and cost-effective H&E multiple oncology applications. We previously introduced such method – DeepPT demonstrated how we can its imputed successful...
<h3>Background</h3> Immune checkpoint inhibitors (ICI) are in the forefront of contemporary clinical oncology and have become an integral part treatment many malignancies, including advanced or recurrent head-and-neck squamous cell carcinoma (HNSCC). Positive CPS score stratifies survival with programmed death (PD)-1 but has limited predictive value, which calls for development practical more accurate biomarkers.<sup>1</sup> We previously presented results a novel marker response to PD-1...
e13556 Background: Precision oncology is gradually advancing into mainstream clinical practice. Despite the significant recent growth in number of approved biomarkers for immune and targeted therapies, demonstrating survival benefits, eligibility response rates remain limited many cases, calling better predictive biomarkers. Methods: We developed ENLIGHT - a transcriptomics-based computational platform that identifies utilizes clinically relevant genetic interactions (GIs) to predict...