A survey on deep matrix factorizations

P De Handschutter, N Gillis, X Siebert - Computer Science Review, 2021 - Elsevier
Constrained low-rank matrix approximations have been known for decades as powerful
linear dimensionality reduction techniques able to extract the information contained in large …

The evolution, evolvability and engineering of gene regulatory DNA

ED Vaishnav, CG de Boer, J Molinet, M Yassour, L Fan… - Nature, 2022 - nature.com
Mutations in non-coding regulatory DNA sequences can alter gene expression, organismal
phenotype and fitness,–. Constructing complete fitness landscapes, in which DNA …

Map** phenotypic plasticity upon the cancer cell state landscape using manifold learning

DB Burkhardt, BP San Juan, JG Lock, S Krishnaswamy… - Cancer discovery, 2022 - AACR
Phenotypic plasticity describes the ability of cancer cells to undergo dynamic, nongenetic
cell state changes that amplify cancer heterogeneity to promote metastasis and therapy …

Non-linear archetypal analysis of single-cell RNA-seq data by deep autoencoders

Y Wang, H Zhao - PLoS computational biology, 2022 - journals.plos.org
Advances in single-cell RNA sequencing (scRNA-seq) have led to successes in discovering
novel cell types and understanding cellular heterogeneity among complex cell populations …

K-Deep Simplex: Manifold Learning via Local Dictionaries

A Tasissa, P Tankala, JM Murphy… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
We propose-Deep Simplex (KDS) which, given a set of data points, learns a dictionary
comprising synthetic landmarks, along with representation coefficients supported on a …

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

CK Chan, A Hadjitheodorou, TYC Tsai, JA Theriot - bioRxiv, 2020 - biorxiv.org
Cell motility is a crucial biological function for many cell types, including the immune cells in
our body that act as first responders to foreign agents. In this work we consider the …

Biarchetype analysis: simultaneous learning of observations and features based on extremes

A Alcacer, I Epifanio… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
We introduce a novel exploratory technique, termed biarchetype analysis, which extends
archetype analysis to simultaneously identify archetypes of both observations and features …

Map** the gene space at single-cell resolution with gene signal pattern analysis

A Venkat, S Leone, SE Youlten, E Fagerberg… - Nature Computational …, 2024 - nature.com
In single-cell sequencing analysis, several computational methods have been developed to
map the cellular state space, but little has been done to map or create embeddings of the …

K-deep simplex: Deep manifold learning via local dictionaries

P Tankala, A Tasissa, JM Murphy, D Ba - arxiv preprint arxiv:2012.02134, 2020 - arxiv.org
We propose K-Deep Simplex (KDS) which, given a set of data points, learns a dictionary
comprising synthetic landmarks, along with representation coefficients supported on a …

A comprehensive fitness landscape model reveals the evolutionary history and future evolvability of eukaryotic cis-regulatory DNA sequences

ED Vaishnav, CG de Boer, M Yassour, J Molinet, L Fan… - BioRxiv, 2021 - biorxiv.org
Mutations in non-coding cis-regulatory DNA sequences can alter gene expression,
organismal phenotype, and fitness. Fitness landscapes, which map DNA sequence to …