variational autoencoder

uniPort: a unified computational framework for single-cell data integration with optimal transport

uniPort integrates single-cell multi-omics datasets using a coupled-VAE and Minibatch-UOT, enabling shared latent space embedding and reference atlas construction.

DeepVelo: Data-driven Single-cell Transcriptomic Deep Velocity Field Learning with Neural Ordinary Differential Equations

DeepVelo models single-cell transcriptome dynamics using neural ODEs, improving velocity field accuracy and identifying developmental driver genes.

Digitally Predicting Protein Localization and Manipulating Protein Activity in Fluorescence Images Using Four-dimensional Reslicing GAN

The paper introduces a GAN-based method to predict protein localization in fluorescence images and manipulate protein activity to study localization-based functions.

Ibex: Variational autoencoder for single-cell BCR sequencing.

Ibex vectorizes BCR sequences for dimensional reduction and integrates into single-cell analysis workflows.

Vaeda computationally annotates doublets in single-cell RNA sequencing data

Vaeda annotates doublets in scRNA-seq data using a variational auto-encoder and Positive-Unlabeled learning, performing competitively and outperforming Python-based methods.

An Artificial Intelligence Framework for Optimal Drug Design

This paper introduces an AI framework for optimal drug design that enhances brain exposure by integrating molecular design, QSAR, and PBPK modeling, showing significant improvements over existing drugs and random molecules.

Deep generative modeling and clustering of single cell Hi-C data

This paper introduces scDEC-Hi-C, a deep generative framework for analyzing single cell Hi-C data, showing improved clustering and imputation over existing methods.

Gating interactions steer loop conformational changes in the active site of the L1 metallo-β-lactamase

The paper investigates how gating interactions between loops in the L1 metallo-β-lactamase affect active site conformational changes and identifies key residues critical for enzyme activity.

Joint Variational Autoencoders for Multi-Modal Imputation and Embedding

JAMIE imputes and embeds multimodal single-cell data with partial modality matches, outperforming existing methods and providing mechanistic insights.

Deformability Cytometry Clustering with Variational Autoencoders

This paper uses a variational autoencoder with a clustering loss to perform unsupervised classification of cells based on their mechanical properties.

Rapid, Reference-Free Human Genotype Imputation with Denoising Autoencoders

This paper introduces a denoising autoencoder for rapid, reference-free human genotype imputation, achieving higher accuracy and faster runtime than standard methods.

This population does not exist: learning the distribution of evolutionary histories with generative adversarial networks

This paper trains a GAN to generate artificial population genetic alignments that mimic key features of real data across diverse evolutionary models.

A Variational Inference Approach to Single-Cell Gene Regulatory Network Inference using Probabilistic Matrix Factorization

This paper introduces PMF-GRN, a variational inference method for single-cell GRN inference, showing improved accuracy and uncertainty estimates compared to existing methods.

Multi-block RNN Autoencoders Enable Broadband ECoG Signal Reconstruction

This paper introduces RAE and MRAE models for broadband ECoG signal reconstruction, showing MRAE improves accuracy over RAE by overcoming time-bandwidth limitations.

Disentangled multi-subject and social behavioral representations through a constrained subspace variational autoencoder (CS-VAE)

This paper introduces a constrained subspace variational autoencoder (CS-VAE) to disentangle individual and social behavioral features in multi-subject settings, enabling analysis of latent variables for downstream tasks.

Goal-specific brain MRI harmonization

This paper introduces a goal-specific MRI harmonization framework that improves downstream prediction performance by integrating application-specific constraints during harmonization.

BindVAE: Dirichlet variational autoencoders for de novo motif discovery from accessible chromatin

BindVAE is a deep learning method for discovering TF motifs from open chromatin data, achieving higher precision than existing methods but with lower recall.

End-to-End deep structure generative model for protein design

This paper introduces a VAE-based generative model for protein design that generates high-quality 3D structures and outperforms existing methods in sequence design.

Bayesian Inference of RNA Velocity from Multi-Lineage Single-Cell Data

This paper introduces VeloVAE, a Bayesian model for RNA velocity inference that improves accuracy and captures complex dynamics in multi-lineage single-cell data.

Designing Single-Cell RNA-Sequencing Experiments for Learning Latent Representations

This paper introduces scVIDE, a method to determine statistical power for cell group detection in scRNA-seq data by generating synthetic datasets and using permutation tests.

Deep attention based variational autoencoder for antimicrobial peptide discovery

This study uses a variational autoencoder with attention mechanisms to generate novel antimicrobial peptides with physicochemical properties similar to real ones.

Differential geometry methods for constructing manifold-targeted recurrent neural networks.

This paper introduces a method using differential geometry to construct recurrent neural networks with dynamics targeted to a specific manifold, improving the design of task-solving neural dynamics.

Hi-C-LSTM: Learning representations of chromatin contacts using a recurrent neural network identifies genomic drivers of conformation

Hi-C-LSTM uses a recurrent neural network to learn low-dimensional representations of Hi-C data, enabling the identification of genomic elements that define chromatin conformation.

Ig-VAE: Generative Modeling of Immunoglobulin Proteins by Direct 3D Coordinate Generation

The paper introduces Ig-VAE, a variational auto-encoder that generates 3D coordinates of immunoglobulin proteins, demonstrating its use in creating a SARS-CoV2-RBD binder and guiding protein design.

Linearization Autoencoder: an autoencoder-based regression model with latent space linearization

The paper introduces a linearization autoencoder for regression analysis with high-dimensional data, achieving prediction and feature selection by aligning data points to linear relations of labels.

scDeepC3: scRNA-seq Deep Clustering by A Skip AutoEncoder Network with Clustering Consistency

scDeepC3 improves scRNA-seq clustering by using a skip AutoEncoder with clustering consistency loss and adaptive shortcut connections, achieving better performance than existing methods.

inClust: a general framework for clustering that integrates data from multiple sources

inClust is a clustering framework that integrates multi-source data using variational autoencoder and vector arithmetic, performing well in various clustering tasks.

Cross-Modal Autoencoder Framework Learns Holistic Representations of Cardiovascular State

This paper develops a cross-modal autoencoder framework to integrate cardiac MRI and ECG data, improving phenotype prediction and enabling MRI imputation from ECGs.

A method for morphological feature extraction based on variational auto-encoder : an application to mandible shape

The paper introduces Morpho-VAE, a landmark-free method for shape analysis using variational autoencoders, applied to primate mandible images to extract morphological features for classification.

A graph-embedded topic model enables characterization of diverse pain phenotypes among UK Biobank individuals

The paper introduces a graph-embedded topic model to analyze UK Biobank data, identifying pain phenotypes and revealing cardiovascular-related medication and condition patterns.