Publications

Machine learning model finds genetic factors for heart disease

By analyzing electrocardiograms and magnetic resonance images of the heart, the model can predict heart-related traits and drive genetic discovery.

Allison Whitten

4/28/2023

LINK TO ARTICLE

A more effective experimental design for engineering a cell into a new state

By focusing on causal relationships in genome regulation, a new AI method could help scientists identify new immunotherapy techniques or regenerative therapies.

Publications.

Machine learning model finds genetic factors for heart disease

LINK TO ARTICLE

A more effective experimental design for engineering a cell into a new state

LINK TO ARTICLE

Researchers identify new regulators of cellular aging

LINK TO ARTICLE

2023

Adhesome receptor clustering is accompanied by the co-localization of the associated genes in the cell nucleus

Systematically characterizing the roles of E3-ligase family members in inflammatory responses with massively parallel Perturb-seq

Unsupervised representation learning of chromatin images identifies changes in cell state and tissue organization during DCIS progression

Image2Reg: Linking chromatin images to gene regulation using genetic perturbation screens

Maximum likelihood estimation for Brownian motion tree models based on one sample

Efficient permutation discovery in causal DAGs

Linear convergence and implicit regularization of generalized mirror descent with time-dependent mirrors

Transcriptional changes are tightly coupled to chromatin reorganization during cellular aging

Meek separators and their applications in targeted causal discovery

Identifiability guarantees for causal disentanglement from soft interventions

Unpaired multi-domain causal representation learning

Unsupervised protein-ligand binding energy prediction via neural Euler’s rotation equation

Active learning for optimal intervention design in causal models

The DeCAMFounder: Non-linear causal discovery in the presence of hidden variables

Transfer Learning with Kernel Methods

Linear causal disentanglement via interventions

Cross-modal autoencoder framework learns holistic representations of cardiovascular state

Wide and deep neural networks achieve optimality for classification

2022

Causal structure learning: a combinatorial perspective

Graph-based autoencoder integrates spatial transcriptomics with chromatin images and identifies joint biomarkers for Alzheimer’s disease

Lateral confined growth of cells activates Lef1 dependent pathways to regulate cell-state transitions

Simple, fast, and flexible framework for matrix completion with infinite width neural networks

Machine learning approaches to single-cell data integration and translation

Joint inference of multiple graphs from matrix polynomials

Causal structure discovery between clusters of nodes induced by latent factors

Causal imputation via synthetic interventions

Identifying 3D genome organization in diploid organisms via Euclidean distance geometry

Multiscale simulations of complex systems by learning their effective dynamics

2021

Improved conditional flow models for molecule to image synthesis

DCI: Learning causal differences between gene regulatory networks

Total positivity in exponential families with application to binary variables

Causal network models of SARS-CoV-2 expression and aging to identify candidates for drug repurposing

Matching a desired causal state via shift interventions

Near-optimal multi-perturbation experimental design for causal structure learning

Causality in digital medicine

Maximum likelihood estimation for totally positive log-concave densities

Do deeper convolutional networks perform better?

On alignment in deep linear neural networks

Local quadratic convergence of stochastic gradient descent with adaptive step size

Consistency guarantees for greedy permutation-based causal inference algorithms

Multidomain translation between single-cell imaging and sequencing data using autoencoders

Mechanogenomic coupling of lung tissue stiffness, EMT and coronavirus pathogenicity

2020

Ordering-based causal structure learning in the presence of latent variables

Permutation-based causal structure learning with unknown intervention targets

Causal structure discovery from distributions arising from mixtures of DAGs

Optimal transport using GANs for lineage tracing

Overparameterized neural networks can implement associative memory

Covariance matrix estimation under total positivity for portfolio selection

Learning high-dimensional Gaussian graphical models under total positivity without tuning parameters

Anchored causal inference in the presence of measurement error

Brownian motion tree models are toric

Predicting cell lineages using autoencoders and optimal transport

Mechano-genomic regulation of coronaviruses and its interplay with ageing

High-dimensional joint estimation of multiple directed Gaussian graphical models

Algebraic statistics in practice: Applications to networks

2019

Maximum likelihood estimation in Gaussian models under total positivity

Multi-domain translation by learning uncoupled autoencoders

Memorization in overparameterized autoencoders

ABCD-Strategy: Budgeted experimental design for targeted causal structure discovery

Size of interventional Markov equivalence classes in random DAG models

Scalable unbalanced optimal transport using generative adversarial networks

Geometry of discrete copulas

Loading monotonicity of weighted premiums, and total positivity properties of weight functions

Generalized Fréchet bounds for cell entries in multidimensional contingency tables

Geometry of log-concave density estimation

2018

Direct estimation of differences in causal graphs

PatchNet: Interpretable neural networks for image classification