variational autoencoder

Efficient approximations for stationary single-channel Ca2+ nanodomains across length scales

The paper develops efficient approximations for stationary Ca2+ nanodomains near a single channel, improving accuracy across parameter space using novel interpolation and variational methods.

Improving protein function prediction with synthetic feature samples created by generative adversarial networks

This work introduces FFPred-GAN, a GAN-based method to generate synthetic protein feature samples, improving function prediction accuracy across all three Gene Ontology domains.

Synthetic observations from deep generative models and binary omics data with limited sample size

The paper evaluates generative models for binary omics data with small sample sizes, finding DBMs and VAEs perform better than GANs for recovering pairwise relationships.

Variational Inference Using Approximate Likelihood Under the Coalescent With Recombination

This paper introduces a variational inference method for coalHMMs that learns evolutionary parameters and infers local genealogies with comparable accuracy to existing methods, using simulated data.

VAE-SNE: a deep generative model for simultaneous dimensionality reduction and clustering

VAE-SNE is a deep generative model that simultaneously reduces dimensionality and clusters data, performing well on real-world datasets and applicable to various life science data types.

Style transfer with variational autoencoders is a promising approach to RNA-Seq data harmonization and analysis

This paper applies style transfer methods to RNA-Seq data harmonization and treatment outcome prediction, showing improved style and semantics prediction accuracy compared to existing approaches.

DiffNets: Self-supervised deep learning to identify the mechanistic basis for biochemical differences between protein variants

DiffNets identifies structural features predicting biochemical differences between protein variants using self-supervised learning.

VAE-Sim: a novel molecular similarity measure based on a variational autoencoder

VAE-Sim introduces a variational autoencoder to compute molecular similarity, offering a novel metric that outperforms traditional fingerprint-based methods.

Protein Contact Map Denoising Using Generative Adversarial Networks

This paper introduces ContactGAN, a GAN-based method to denoise protein contact maps, improving accuracy over existing methods on CASP13 datasets.

Quantitative comparison of principal component analysis and unsupervised deep learning using variational autoencoders for shape analysis of motile cells

This paper compares PCA and VAE-GAN for analyzing cell shape in neutrophils, finding that VAE-GAN more efficiently captures shape variation while maintaining interpretability.

Unsupervised generative and graph representation learning for modelling cell differentiation

This paper develops a computational framework using variational autoencoders and graph autoencoders to model cell differentiation from single-cell RNA-seq data across species.

Bio-informed Protein Sequence Generation for Multi-class Virus Mutation Prediction

This paper introduces a GAN-based model to generate protein sequences for predicting virus mutations across multiple classes.

A Framework for Integrating Directed and Undirected Annotations to Build Explanatory Models of cis-eQTL Data.

This paper introduces BAGEA, a Bayesian framework for analyzing cis-eQTL data using genomic annotations, showing it can predict up to 5% of expression variance for top-effect genes.

Adaptive Efficient Coding: A Variational Auto-encoder Approach

This paper introduces a variational auto-encoder model of neural coding that adapts to environmental statistics and explains perceptual discrimination and neural tuning curves.

Variational Autoencoder Modular Bayesian Networks (VAMBN) for Simulation of Heterogeneous Clinical Study Data

This paper introduces VAMBN, a variational autoencoder modular Bayesian network for simulating realistic clinical study data while ensuring privacy and enabling counterfactual scenarios.

scVAE: Variational auto-encoders for single-cell gene expression data

scVAE is a variational auto-encoder for scRNA-seq data that avoids preprocessing and improves clustering by using raw counts and latent space clustering.

Latent periodic process inference from single-cell RNA-seq data

Cyclum improves cell-cycle characterization in scRNA-seq data, enhancing subpopulation delineation and cell atlas construction.

Interpretable factor models of single-cell RNA-seq via variational autoencoders

The paper introduces an interpretable variational autoencoder for single-cell RNA-seq to identify gene programs in large datasets.

Disentangling latent representations of single cell RNA-seq experiments

This paper explores using modified VAE objectives to improve interpretability of latent representations in scRNA-seq data, finding better alignment with generative factors but reduced clustering performance.

Deriving Disease Modules from the Compressed Transcriptional Space Embedded in a Deep Auto-encoder

The paper uses a deep auto-encoder to discover disease-related gene modules from transcriptional data without relying on prior biological networks, finding significant enrichment of GWAS genes in the third layer.

Model reconstruction from Small angle X-ray Scattering data using deep learning methods

The paper presents a deep learning algorithm using an auto-encoder to reconstruct 3D protein models from SAXS data, demonstrating accuracy without prior size information.

Imputation of single-cell gene expression with an autoencoder neural network

The paper introduces LATE and TRANSLATE autoencoder-based methods for imputing single-cell RNA-seq data, showing improved performance over existing methods.

A generative modeling approach for interpreting population-level variability in brain structure

This paper uses a deep generative model to analyze brain structure variability across mouse brains and validates the model through structured perturbations.

Evaluating probabilistic programming and fast variational Bayesian inference in phylogenetics

This study compares variational inference and MCMC methods for phylogenetic inference using Stan, finding variational methods faster but less accurate.

Variational Autoencoders for Cancer Data Integration: Design Principles and Computational Practice

This paper explores autoencoder architectures for integrating cancer patient data and demonstrates their effectiveness in analyzing heterogeneous breast cancer data for accurate diagnosis.

Estimating Rates of Progression and Predicting Future Visual Fields in Glaucoma Using a Deep Variational Autoencoder

This paper develops a deep variational autoencoder to estimate glaucoma progression rates and predict future visual field loss, showing improved performance compared to traditional methods.

Unsupervised Machine Learning for Data Encoding appliedto Ovarian Cancer Transcriptomes

This paper trains a variational autoencoder on ovarian cancer transcriptomes to predict cisplatin resistance and identifies biological processes associated with platinum resistance.

scGAIN: Single Cell RNA-seq Data Imputation using Generative Adversarial Networks

scGAIN imputes missing gene expressions in scRNA-seq data using GANs, improving clustering and matching with bulk RNA-seq.

Reverse engineering neural networks to characterise their cost functions

This paper shows that biologically plausible cost functions in neural networks correspond to variational free energy under specific prior beliefs, enabling optimization of network parameters.

Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference

This paper introduces a Bayesian model using variational autoencoder for localizing spike sources in extracellular recordings, showing improved accuracy over heuristic methods.