Ola Spjuth

Single-cell morphological profiling reveals insights into programmed cell death

The paper compares single-cell and aggregated morphological profiling to identify programmed cell death mechanisms, finding aggregated data performs better in supervised models.

Human-supervised Agentic AI for Hypothesis Generation and Experimental Assistance in Drug Repurposing

A human-supervised multi-agent LLM system covered drug repurposing from knowledge graph building to assay analysis in three case studies; retrospective COVID-19 screen AUC-ROC 0.986 without predefined thresholds.

The time dimension matters: Improving mode of action classification with live-cell imaging

This paper introduces LCTP, a workflow for analyzing live-cell time series data to improve mode of action classification by capturing temporal phenotypes across compounds and cell lines.

Morphological cell profiling for drug repurposing against SARS-CoV-2 infection

The paper identifies host-targeting antivirals against SARS-CoV-2 using morphological profiling, finding compounds that reverse infected cell phenotypes and validate host processes hijacked by viruses.

Integrating Cell Painting and Thermal Proteome Profiling for Inference of Targets and Mechanism of Action

The paper integrates Cell Painting and Thermal Proteome Profiling to infer targets and mechanisms of action for compounds, accurately identifying known MoAs for four out of five tested compounds.

Small molecule bioactivity benchmarks are often well-predicted by counting cells

The paper shows that cell counting can predict compound bioactivity as well as Cell Painting or gene expression, but Cell Painting adds unique value in protein-target-specific benchmarks.

High-content morphological profiling by Cell Painting in 3D spheroids.

This paper introduces a method to apply Cell Painting to 3D spheroids for morphological profiling, detecting phenotypic changes in colorectal cancer cells under compound treatments.

Comparing Lipinskis Rule of 5 and Machine Learning Based Prediction of Fraction Absorbed for Assessing Oral Absorption in Humans

This paper compares Lipinski's Rule of 5 and machine learning predictions of fraction absorbed to assess oral absorption in humans, finding machine learning models more accurate.

CPSign - Conformal Prediction for Cheminformatics Modeling

CPSign provides a conformal prediction framework for cheminformatics, offering robust predictive performance with efficient runtime and lower hardware requirements compared to neural networks.

Federated Learning for Predicting Compound Mechanism of Action Based on Image-data from Cell Painting

This work uses federated learning to predict compound mechanism of action from cell painting image data, showing its effectiveness in handling data heterogeneity across institutions.

A Decade in a Systematic Review: The Evolution and Impact of Cell Painting

This paper reviews methodological advancements in Cell Painting over a decade, highlighting improvements in protocols, feature extraction, and machine learning applications for biological insights.

PKSmart: An Open-Source Computational Model to Predict in vivo Pharmacokinetics of Small Molecules

This paper develops PKSmart, a computational model to predict human pharmacokinetic parameters using molecular features and animal PK data, achieving performance comparable to industry models.

Improved Detection of Drug-Induced Liver Injury by Integrating Predicted in vivo and in vitro Data

This paper develops a machine learning model to predict drug-induced liver injury by integrating in vitro and in vivo data with chemical features, achieving improved detection and human-specific sensitivity.

Insights into Drug Cardiotoxicity from Biological and Chemical Data: The First Public Classifiers for FDA DICTrank

This study develops public classifiers for predicting drug-induced cardiotoxicity using FDA DICTrank data, identifying key chemical and biological features that distinguish toxic from non-toxic compounds.

Merging Bioactivity Predictions from Cell Morphology and Chemical Fingerprint Models Using Similarity to Training Data

The paper develops similarity-based merger models that combine chemical structure and cell morphology predictions to improve assay hit calls across multiple biological assays.

Designing microplate layouts using artificial intelligence

This paper introduces a constraint programming method for designing microplate layouts to reduce bias and batch effects, improving accuracy in dose-response experiments and drug screening.

Combining molecular and cell painting image data for mechanism of action prediction

The paper combines molecular and cell painting image data to predict drug mechanisms of action, showing improved performance with integrated data.

Is brightfield all you need for mechanism of action prediction?

This study compares the predictive performance of models trained on fluorescence and brightfield images for drug mechanism of action prediction, finding comparable results.

Integrating Cell Morphology with Gene Expression and Chemical Structure to Aid Mitochondrial Toxicity Detection

The paper combines chemical structure, gene expression, and cell morphology data to improve mitochondrial toxicity prediction in drug discovery.

Rapid development of cloud-native intelligent data pipelines for scientific data streams using the HASTE Toolkit

The paper introduces the HASTE Toolkit, a cloud-native toolkit for intelligent data pipelines that prioritize resource usage based on data content, demonstrating it in microscopy imaging case studies.

Evaluation of gene expression and phenotypic profiling data as quantitative descriptors for predicting drug targets and mechanisms of action

This study evaluates machine learning models using gene expression and phenotypic profiling data to predict drug mechanisms of action and targets, showing varying accuracy across endpoints and the potential benefit of combining methods.

SciPipe - A workflow library for agile development of complex and dynamic bioinformatics pipelines

SciPipe is a workflow library for managing complex and dynamic pipelines in bioinformatics, supporting machine learning tasks with features like branching and dynamic scheduling.

Interoperable and scalable data analysis with microservices: Applications in Metabolomics

The paper introduces a microservices-based framework for scalable data analysis, validated in metabolomics, enabling dynamic scaling and integration of software tools.

Galaxy-Kubernetes integration: scaling bioinformatics workflows in the cloud

This paper integrates Galaxy with Kubernetes to enable scalable, cloud-agnostic bioinformatics workflows.

Transfer learning with deep convolutional neural networks for classifying cellular morphological changes

This study uses transfer learning with pre-trained deep convolutional neural networks to classify cellular morphological changes from drug-treated cells, achieving 95-97% accuracy.

PhenoMeNal: Processing and analysis of Metabolomics data in the Cloud

PhenoMeNal provides a cloud-based platform for metabolomics data analysis, integrating tools and workflows to enable reproducible and scalable research.

Container-based bioinformatics with Pachyderm

The paper demonstrates the use of Pachyderm for efficient and reproducible metabolomics workflows in bioinformatics.