Biology subjects

Zettor, A.

Publications and source records attributed to Zettor, A..

3 recordsLinked to original sources

bioRxiv2026

Deep learning extracts MoA-specific signatures from high-throughput images of chemically and genetically perturbed Corynebacteria

Tuberculosis (TB) is the worldwide leading infectious killer due to a single pathogen and increasing antimicrobial resistance (AMR) makes it imperative to discover and develop new drugs with novel modes of action (MoAs) to treat TB infections. Phenotypic screening of chemical libraries has proven effective at identifying new compounds against bacterial pathogens. However, a major limitation of standard screens is their inability to uncover the MoA of hits thereby preventing targeted selection of compounds with novel MoAs. Linking drug perturbations to mutants from images could potentially enable to predict the targets of compounds that act through novel MoAs. Here, we develop a deep learning (DL)-based method to screen drug-treated Corynebacterium glutamicum (Cglu), a surrogate model for Mycobacterium tuberculosis (Mtb). Our DL model is based on a convolutional neural network architecture that takes high throughput images as input and is trained to distinguish between different MoAs. We show that our approach can robustly differentiate between the MoAs of established antibiotics and correctly recognise the MoA of antibiotics that were not previously seen by the DL model. We also show that inhibitors with the same and previously unseen MoA cluster together and apart from all other reference drugs, allowing for new MoA discovery. Importantly, we show that our model links images of chemical (drugs) and genetic (mutants) perturbations targeting similar pathways, thus paving the way towards mutant-based target prediction of compounds that act through novel MoAs, directly from high-content images. Finally, we explore the phenotypes induced by genetic disruption of pathways and demonstrate that features extracted with our DL model recover known biological relationships from high-throughput images alone using the cell cycle of Cglu as a case study, a finding with promising potential for fundamental mechanistic studies.

microbiology↗

bioRxiv2021

A highly sensitive cell-based luciferase assay for high-throughput automated screening of SARS-CoV-2 nsp5/3CLpro inhibitors

Effective drugs against SARS-CoV-2 are urgently needed to treat severe cases of infection and for prophylactic use. The main viral protease (nsp5 or 3CLpro) represents an attractive and possibly broad-spectrum target for drug development as it is essential to the virus life cycle and highly conserved among betacoronaviruses. Sensitive and efficient high-throughput screening methods are key for drug discovery. Here we report the development of a gain-of-signal, highly sensitive cell-based luciferase assay to monitor SARS-CoV-2 nsp5 activity and show that it is suitable for high-throughput screening of compounds in a 384-well format. A benefit of miniaturisation and automation is that screening can be performed in parallel on a wild-type and a catalytically inactive nsp5, which improves the selectivity of the assay. We performed molecular docking-based screening on a set of 14,468 compounds from an in-house chemical database, selected 359 candidate nsp5 inhibitors and tested them experimentally. We identified four molecules, including the broad-spectrum antiviral merimepodib/VX-497, which show anti-nsp5 activity and inhibit SARS-CoV-2 replication in A549-ACE2 cells with IC50 values in the 4-21 {micro}M range. The here described assay will allow the screening of large-scale compound libraries for SARS-CoV-2 nsp5 inhibitors. Moreover, we provide evidence that this assay can be adapted to other coronaviruses and viruses which rely on a viral protease.

microbiology↗

bioRxiv2019

Large scale active-learning-guided exploration to maximize cell-free production

Lysate-based cell-free systems have become a major platform to study gene expression but batch-to-batch variation makes protein production difficult to predict. Here we describe an active learning approach to explore a combinatorial space of ~4,000,000 cell-free compositions, maximizing protein production and identifying critical parameters involved in cell-free productivity. We also provide a one-step-method to achieve high quality predictions for protein production using minimal experimental effort regardless of the lysate quality.

synthetic biology↗