Biology subjects

Engkvist, O.

Publications and source records attributed to Engkvist, O..

5 recordsLinked to original sources

bioRxiv2026

Model Validation Protocols for Machine Learning in Small Molecule Drug Discovery

Machine learning (ML) models for molecular property prediction are increasingly deployed in drug discovery, yet their adoption in real-world scenarios requires an understanding of the conditions in which a model succeeds or fails. While standardized benchmarks are powerful instruments to measure and unlock progress in ML research, they should not be blindly treated as the end goal. Especially static and retrospective benchmarks, in which no true unknown test set is employed, limit our ability to robustly validate a model's performance. Building on the collective expertise of a cross-industry consortium, we present a model validation framework consisting of five recommendations that would enable the community to move beyond aggregate metrics toward understanding where and why molecular property prediction models fail. We connect evaluation choices to real-world applications and case studies encountered in pharmaceutical research. The framework proposes splitting strategies that mimic realistic distribution shifts and expose common failure modes. We apply the recommended framework to a recently released dataset of absorption, distribution, metabolism, and excretion (ADME) properties. Across two complementary model algorithms, our case studies reveal four distinct failure modes (extrapolation, interpolation, representation, and evaluation), showing that model errors arise not only from distribution shift but also from limitations in molecular representations. Our results show that commonly used evaluation protocols can significantly overestimate performance and may not detect important model failure modes. All software and data are released via https://github.com/srijitseal/polaris.

bioinformatics↗

bioRxiv2023

JUMP Cell Painting dataset: morphological impact of 136,000 chemical and genetic perturbations

Image-based profiling has emerged as a powerful technology for various steps in basic biological and pharmaceutical discovery, but the community has lacked a large, public reference set of data from chemical and genetic perturbations. Here we present data generated by the Joint Undertaking for Morphological Profiling (JUMP)-Cell Painting Consortium, a collaboration between 10 pharmaceutical companies, six supporting technology companies, and two non-profit partners. When completed, the dataset will contain images and profiles from the Cell Painting assay for over 116,750 unique compounds, over-expression of 12,602 genes, and knockout of 7,975 genes using CRISPR-Cas9, all in human osteosarcoma cells (U2OS). The dataset is estimated to be 115 TB in size and capturing 1.6 billion cells and their single-cell profiles. File quality control and upload is underway and will be completed over the coming months at the Cell Painting Gallery: https://registry.opendata.aws/cellpainting-gallery. A portal to visualize a subset of the data is available at https://phenaid.ardigen.com/jumpcpexplorer/.

bioinformatics↗

bioRxiv2022

Simultaneous inhibition of DNA-PK and Pol{Theta} improves integration efficiency and precision of genome editing

Genome editing tools, especially CRISPR/Cas9-based strategies, have transformed biomedical research and opened opportunities for developing curative treatments for genetic diseases. Despite rapid progress, low efficiency of targeted DNA integration and generation of undesired mutations represent major limitations for genome editing applications. Both issues arise from the interplay between the main DNA Double-Strand Break (DSB) repair pathways, Homology-Directed Repair (HDR), Non-Homologous End Joining (NHEJ), and Microhomology-Mediated End Joining (MMEJ). To improve efficiencies of targeted CRISPR-Cas9 genome editing, we screened a large compound library. This led to the discovery of AZD7648, a DNA-dependent protein kinase (DNA-PK) inhibitor and potent enhancer of CRISPR-Cas9-mediated integration. We demonstrated that AZD7648 increased HDR and decreased mutagenic NHEJ repair, thus resulting in improved performance of precise gene editing. Furthermore, we observed additional improvement of integration efficiency by impairing MMEJ repair through DNA polymerase {ominus} (Pol{ominus}) inhibition. Combined treatment with AZD7648 and Pol{ominus} inhibitors (which we named 2iHDR) substantially increased precision of templated insertions, with efficiencies of up to 80%, and nearly no formation of undesired Insertion-Deletions (InDels). Importantly, 2iHDR also decreased Cas9-associated off-target activity, dramatically improving the performance and fidelity of CRISPR-Cas9 gene editing.

molecular biology↗

bioRxiv2022

Cell morphological profiling enables high-throughput screening for PROteolysis TArgeting Chimera (PROTAC) phenotypic signature

PROTACs (PROteolysis TArgeting Chimeras) use the ubiquitin-proteasome system to degrade a protein of interest for therapeutic benefit. Advances in targeted protein degradation technology have been remarkable with several molecules moving into clinical studies. However, robust routes to assess and better understand the safety risks of PROTACs need to be identified, which is an essential step towards delivering efficacious and safe compounds to patients. In this work, we used Cell Painting, an unbiased high content imaging method, to identify phenotypic signatures of PROTACs. Chemical clustering and model prediction allowed the identification of a mitotoxicity signature that could not be expected by screening the individual PROTAC components. The data highlighted the benefit of unbiased phenotypic methods for identifying toxic signatures and the potential to impact drug design. HighlightsO_LIMorphological profiling detects various PROTACs phenotypic signatures C_LIO_LIPhenotypic signatures can be attributed to diverse biological responses C_LIO_LIChemical clustering from phenotypic signatures separates on drug selection C_LIO_LITrained in-silico machine learning models to predict PROTACs mitochondrial toxicity C_LI

pharmacology and toxicology↗

bioRxiv2017

Applying Mondrian Cross-Conformal Prediction to Estimate Prediction Confidence on Large Imbalanced Bioactivity Datasets

Conformal prediction has been proposed as a more rigorous way to define prediction confidence compared to other application domain concepts that have earlier been used for QSAR modelling. One main advantage of such a method is that it provides a prediction region potentially with multiple predicted labels, which contrasts to the single valued (regression) or single label (classification) output predictions by standard QSAR modelling algorithms. Standard conformal prediction might not be suitable for imbalanced datasets. Therefore, Mondrian cross-conformal prediction (MCCP) which combines the Mondrian inductive conformal prediction with cross-fold calibration sets has been introduced. In this study, the MCCP method was applied to 18 publicly available datasets that have various imbalance levels varying from 1:10 to 1:1000 (ratio of active/inactive compounds). Our results show that MCCP in general performed well on cheminformatics datasets with various imbalance levels. More importantly, the method not only provides confidence of prediction and prediction regions compared to standard machine learning methods, but also produces valid predictions for the minority class. In addition, a compound similarity based nonconformity measure was investigated. Our results demonstrate that although it gives valid predictions, its efficiency is much worse than nonconformity measures obtained from supervised learning.

pharmacology and toxicology↗