Andreas Bender

Model Validation Protocols for Machine Learning in Small Molecule Drug Discovery

The paper presents a model validation framework for molecular property prediction models in drug discovery, revealing four failure modes and showing that common evaluation protocols overestimate performance.

A novel IL-1β reporter assay identifies tolcapone as a caspase-1 suppressor targeting pyroptosis in endotoxemia

The paper develops a CRISPR-based IL-1β reporter assay to identify tolcapone as a caspase-1 inhibitor that suppresses pyroptosis in endotoxemia.

Decoding Non-coding SNPs: Systems Genomics Modelling Dissects the Heterogeneity of IBD

The paper models the impact of non-coding SNPs on gene regulatory networks in IBD to stratify patients based on gene dysregulation and therapeutic response.

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.

SimMS: A GPU-Accelerated Cosine Similarity implementation for Tandem Mass Spectrometry

SimMS provides a GPU-accelerated cosine similarity method for tandem mass spectrometry with a 1000-fold speedup while maintaining high accuracy.

Transfer learning enables discovery of sub-micromolar antibacterials for ESKAPE pathogens from ultra-large chemical spaces

This paper uses transfer learning to identify potent antibacterials from large chemical libraries, finding 54% of tested compounds active against E. coli with sub-micromolar potency.

Step Forward Cross Validation for Bioactivity Prediction: Out of Distribution Validation in Drug Discovery

This study evaluates k-fold n-step forward cross-validation for improving out-of-distribution bioactivity predictions in drug discovery and recommends its use with specific metrics.

Calibrated prediction of scarce adverse drug reaction labels with conditional neural processes

This paper uses conditional neural processes to predict adverse drug reactions from sparse data and finds they are well-calibrated and effective across organ systems.

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.

MAVEN: Compound mechanism of action analysis and visualisation using transcriptomics and compound structure data in R/Shiny

MAVEN is an R/Shiny app that predicts drug targets and visualizes compound mechanisms of action using transcriptomics and chemical structure data, enabling hypothesis generation for wet-lab scientists.

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.

scRNA-Seq-based drug repurposing targeting idiopathic pulmonary fibrosis (IPF)

This study uses scRNA-Seq data to identify drug candidates for repurposing in IPF by matching cell transition signatures to drug perturbation signatures.

Identification of potential biomarker candidates of drug-induced vascular injury (DIVI) in rats using gene expression and histopathology data

This study identifies 33 gene biomarkers for drug-induced vascular injury in rats using gene expression and histopathology data from treated animals.

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.

Deriving time-concordant event cascades from gene expression data: A case study for Drug-Induced Liver Injury (DILI)

The paper develops a framework to identify time-concordant gene expression events in DILI using time-resolved transcriptomics and applies it to rat liver data from TG-GATEs to derive mechanistic hypotheses.

Cancer Cell Line Profiler (CCLP): a webserver for the prediction of compound activity across the NCI60 panel

CCLP predicts compound activity across the NCI60 panel using a multi-task Random Forest model and provides prediction errors via conformal prediction.