Applying interpretable machine learning in computational biology—pitfalls, recommendations and opportunities for new developments

V Chen, M Yang, W Cui, JS Kim, A Talwalkar, J Ma - Nature methods, 2024 - nature.com
Recent advances in machine learning have enabled the development of next-generation
predictive models for complex computational biology problems, thereby spurring the use of …

High-throughput methods in the discovery and study of biomaterials and materiobiology

L Yang, S Pijuan-Galito, HS Rho, AS Vasilevich… - Chemical …, 2021 - ACS Publications
The complex interaction of cells with biomaterials (ie, materiobiology) plays an increasingly
pivotal role in the development of novel implants, biomedical devices, and tissue …

Image-based cell phenotyping with deep learning

A Pratapa, M Doron, JC Caicedo - Current opinion in chemical biology, 2021 - Elsevier
A cell's phenotype is the culmination of several cellular processes through a complex
network of molecular interactions that ultimately result in a unique morphological signature …

Enhancing scientific discoveries in molecular biology with deep generative models

R Lopez, A Gayoso, N Yosef - Molecular systems biology, 2020 - embopress.org
Generative models provide a well‐established statistical framework for evaluating
uncertainty and deriving conclusions from large data sets especially in the presence of …

Visualizing population structure with variational autoencoders

CJ Battey, GC Coffing, AD Kern - G3, 2021 - academic.oup.com
Dimensionality reduction is a common tool for visualization and inference of population
structure from genotypes, but popular methods either return too many dimensions for easy …

Three million images and morphological profiles of cells treated with matched chemical and genetic perturbations

SN Chandrasekaran, BA Cimini, A Goodale, L Miller… - Nature …, 2024 - nature.com
The identification of genetic and chemical perturbations with similar impacts on cell
morphology can elucidate compounds' mechanisms of action or novel regulators of genetic …

From pixels to phenotypes: Integrating image-based profiling with cell health data as BioMorph features improves interpretability

S Seal, J Carreras-Puigvert, S Singh… - Molecular Biology of …, 2024 - Am Soc Cell Biol
Cell Painting assays generate morphological profiles that are versatile descriptors of
biological systems and have been used to predict in vitro and in vivo drug effects. However …

Contrastive learning of single-cell phenotypic representations for treatment classification

A Perakis, A Gorji, S Jain, K Chaitanya, S Rizza… - Machine Learning in …, 2021 - Springer
Learning robust representations to discriminate cell phenotypes based on microscopy
images is important for drug discovery. Drug development efforts typically analyse …

Machine learning in microscopy–insights, opportunities and challenges

I Cunha, E Latron, S Bauer, D Sage… - Journal of cell …, 2024 - journals.biologists.com
Machine learning (ML) is transforming the field of image processing and analysis, from
automation of laborious tasks to open-ended exploration of visual patterns. This has striking …

Self-supervised learning of phenotypic representations from cell images with weak labels

JO Cross-Zamirski, G Williams, E Mouchet… - arXiv preprint arXiv …, 2022 - arxiv.org
We propose WS-DINO as a novel framework to use weak label information in learning
phenotypic representations from high-content fluorescent images of cells. Our model is …