Michael M. Danziger
YOU?
Author Swipe
View article: Multimodal BEHRT: transformers for multimodal electronic health records to predict breast cancer prognosis
Multimodal BEHRT: transformers for multimodal electronic health records to predict breast cancer prognosis Open
Background Electronic Health Records (EHRs) contain a wealth of information about patients that could be useful toward improving treatment outcomes for breast cancer patients, but remain mostly unexploited. Recent methodological developmen…
View article: Multivariate Recovery Dependency in Networks with Time Delays: Effects on Resilience and Scaling Laws
Multivariate Recovery Dependency in Networks with Time Delays: Effects on Resilience and Scaling Laws Open
The recovery process in real-world systems needs to consider the combined effects of internal and external failures and is rarely instantaneous, typically involving inherent time delays.Here, we investigate the impact of a time delay, τ, o…
View article: BMFM-DNA: A SNP-aware DNA foundation model to capture variant effects
BMFM-DNA: A SNP-aware DNA foundation model to capture variant effects Open
Large language models (LLMs) trained on text demonstrated remarkable results on natural language processing (NLP) tasks. These models have been adapted to decipher the language of DNA, where sequences of nucleotides act as "words" that enc…
View article: BMFM-RNA: An Open Framework for Building and Evaluating Transcriptomic Foundation Models
BMFM-RNA: An Open Framework for Building and Evaluating Transcriptomic Foundation Models Open
Transcriptomic foundation models (TFMs) have recently emerged as powerful tools for analyzing gene expression in cells and tissues, supporting key tasks such as cell-type annotation, batch correction, and perturbation prediction. However, …
View article: Immune checkpoint Inhibitor-Induced Autoimmune hemolytic anemia in endometrial cancer
Immune checkpoint Inhibitor-Induced Autoimmune hemolytic anemia in endometrial cancer Open
View article: Combining genetics with real-world patient data enables ancestry-specific target identification and drug discovery in Alzheimer’s disease
Combining genetics with real-world patient data enables ancestry-specific target identification and drug discovery in Alzheimer’s disease Open
Although high-throughput DNA/RNA sequencing technologies have generated massive genetic and genomic data in human disease, these findings have not been translated into new patient treatments. To address this problem, we utilized Mendelian …
View article: Critical Evaluation of Real-World Evidence for Repurposable Medicines in the Alzheimer's Disease Drug Development Pipeline Using a Target Trial Emulation
Critical Evaluation of Real-World Evidence for Repurposable Medicines in the Alzheimer's Disease Drug Development Pipeline Using a Target Trial Emulation Open
View article: Single‐microglia transcriptomic transition network‐based prediction and real‐world patient data validation identifies ketorolac as a repurposable drug for Alzheimer's disease
Single‐microglia transcriptomic transition network‐based prediction and real‐world patient data validation identifies ketorolac as a repurposable drug for Alzheimer's disease Open
INTRODUCTION High microglial heterogeneities hinder the development of microglia‐targeted treatment for Alzheimer's disease (AD). METHODS We integrated 0.7 million single‐nuclei RNA‐sequencing transcriptomes from human brains using a varia…
View article: Does your model understand genes? A benchmark of gene properties for biological and text models
Does your model understand genes? A benchmark of gene properties for biological and text models Open
The application of deep learning methods, particularly foundation models, in biological research has surged in recent years. These models can be text-based or trained on underlying biological data, especially omics data of various types. H…
View article: Single‐Microglia Transcriptomic Transition Network‐based Prediction and Real‐world Patient Data Validation Identifies Ketorolac as a Repurposable Drug for Alzheimer’s Disease
Single‐Microglia Transcriptomic Transition Network‐based Prediction and Real‐world Patient Data Validation Identifies Ketorolac as a Repurposable Drug for Alzheimer’s Disease Open
Background Microglia have been implicated as a key aspect of the pathology of Alzheimer’s disease (AD). However, high microglial heterogeneities, including disease‐associated microglia (DAM), tau microglia (tau‐pathology related), and neur…
View article: Network‐based prediction and real‐world patient data observation identifies Doxycycline and Irbesartan as candidate medicines for Alzheimer’s disease and Traumatic Brain Injury
Network‐based prediction and real‐world patient data observation identifies Doxycycline and Irbesartan as candidate medicines for Alzheimer’s disease and Traumatic Brain Injury Open
Background Traumatic Brain Injury (TBI) is one of the most common nonheritable causes of Alzheimer’s disease (AD). However, there is lack of effective treatment for both AD and TBI. We posit that network‐based integration of multi‐omics an…
View article: Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models
Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models Open
While language models have exceptional capabilities at text generation, they lack a natural inductive bias for emitting numbers and thus struggle in tasks involving quantitative reasoning, especially arithmetic. One fundamental limitation …
View article: MAMMAL -- Molecular Aligned Multi-Modal Architecture and Language
MAMMAL -- Molecular Aligned Multi-Modal Architecture and Language Open
Large language models applied to vast biological datasets have the potential to transform biology by uncovering disease mechanisms and accelerating drug development. However, current models are often siloed, trained separately on small-mol…
View article: Mastering percolation-like games with deep learning
Mastering percolation-like games with deep learning Open
Though robustness of networks to random attacks has been widely studied, intentional destruction by an intelligent agent is not tractable with previous methods. Here we devise a single-player game on a lattice that mimics the logic of an a…
View article: Mastering Percolation-like Games with Deep Learning
Mastering Percolation-like Games with Deep Learning Open
Though robustness of networks to random attacks has been widely studied, intentional destruction by an intelligent agent is not tractable with previous methods. Here we devise a single-player game on a lattice that mimics the logic of an a…
View article: Single-Microglia Transcriptomic Transition Network-Based Prediction and Real-World Patient Data Validation Identifies Ketorolac as a Repurposable Drug for Alzheimer's Disease
Single-Microglia Transcriptomic Transition Network-Based Prediction and Real-World Patient Data Validation Identifies Ketorolac as a Repurposable Drug for Alzheimer's Disease Open
View article: Fragmentation of outage clusters during the recovery of power distribution grids
Fragmentation of outage clusters during the recovery of power distribution grids Open
View article: Recovery coupling in multilayer networks
Recovery coupling in multilayer networks Open
View article: High-resolution human mobility data reveal race and wealth disparities in disaster evacuation patterns
High-resolution human mobility data reveal race and wealth disparities in disaster evacuation patterns Open
Major disasters such as extreme weather events can magnify and exacerbate pre-existing social disparities, with disadvantaged populations bearing disproportionate costs. Despite the implications for equity and emergency planning, we lack a…
View article: Optimal resilience of modular interacting networks
Optimal resilience of modular interacting networks Open
Significance In real-world scenarios, many subnetworks interact with other subnetworks to form a modular interacting network system. In previous models, it was assumed that all subnetworks may be linked pairwise; however, in real systems, …
View article: High-resolution human mobility data reveal race and wealth disparities in disaster evacuation patterns
High-resolution human mobility data reveal race and wealth disparities in disaster evacuation patterns Open
Major disasters such as extreme weather events can magnify and exacerbate pre-existing social disparities, with disadvantaged populations bearing disproportionate costs. Despite the implications for equity and emergency planning, we lack a…
View article: Faster calculation of the percolation correlation length on spatial networks
Faster calculation of the percolation correlation length on spatial networks Open
The divergence of the correlation length ξ at criticality is an important phenomenon of percolation in two-dimensional systems. Substantial speed-ups to the calculation of the percolation threshold and component distribution have been achi…
View article: Critical Stretching of Mean-Field Regimes in Spatial Networks
Critical Stretching of Mean-Field Regimes in Spatial Networks Open
We study a spatial network model with exponentially distributed link lengths on an underlying grid of points, undergoing a structural crossover from a random, Erdős-Rényi graph, to a d-dimensional lattice at the characteristic interaction …
View article: Dynamic interdependence and competition in multilayer networks
Dynamic interdependence and competition in multilayer networks Open
View article: Rifamycin congeners kanglemycins are active against rifampicin-resistant bacteria via a distinct mechanism
Rifamycin congeners kanglemycins are active against rifampicin-resistant bacteria via a distinct mechanism Open
View article: Critical field-exponents for secure message-passing in modular networks
Critical field-exponents for secure message-passing in modular networks Open
We study secure message-passing in the presence of multiple adversaries in\nmodular networks. We assume a dominant fraction of nodes in each module have\nthe same vulnerability, i.e., the same entity spying on them. We find both\nanalytica…
View article: Robustness of spatial networks and networks of networks
Robustness of spatial networks and networks of networks Open
Many complex networks have recently been recognized to involve significant interdependence between different systems. Motivation comes primarily from infrastructures like power grids and communications networks, but also includes areas suc…
View article: Color-avoiding percolation
Color-avoiding percolation Open
Many real world networks have groups of similar nodes which are vulnerable to the same failure or adversary. Nodes can be colored in such a way that colors encode the shared vulnerabilities. Using multiple paths to avoid these vulnerabilit…
View article: Bi-universality characterizes a realistic spatial network model
Bi-universality characterizes a realistic spatial network model Open
One of the most powerful findings of statistical physics is the discovery of universality classes which can be used to categorize and predict the behavior of seemingly different systems. However, many real--world complex networks have not …
View article: Hidden Connectivity in Networks with Vulnerable Classes of Nodes
Hidden Connectivity in Networks with Vulnerable Classes of Nodes Open
In many complex systems representable as networks, nodes can be separated into different classes. Often these classes can be linked to a mutually shared vulnerability. Shared vulnerabilities may be due to a shared eavesdropper or correlate…