Home Blog of Signal Transduction Microbiology Cysteine Protease DEEMD: Drug Efficacy Estimation Against SARS-CoV-2 Based on Cell Morphology With Deep Multiple Instance Learning

Category

Archives

Popular Post

ESKM, a novel therapeutic agent for sensitive and resistant PH+ leukemias

The mechanism of resistance to JAK2 inhibitor in myeloproliferative neoplasms patients

Effects of PARP inhibitors in BRCA gene-mutated ovarian cancer

DASATINIB; An inhibitor of Receptor Tyrosine Kinase

GP130/JAK/STAT3 signaling pathway induces multiple myeloma

DEEMD: Drug Efficacy Estimation Against SARS-CoV-2 Based on Cell Morphology With Deep Multiple Instance Learning

Drug repurposing can accelerate the identification of effective compounds for clinical use against SARS-CoV-2, with the advantage of pre-existing clinical safety data and an established supply chain. RNA viruses such as SARS-CoV-2 manipulate cellular pathways and induce reorganization of subcellular structures to support their life cycle. These morphological changes can be quantified using bioimaging techniques. In this work, we developed DEEMD: a computational pipeline using deep neural network models within a multiple instance learning framework, to identify putative treatments effective against SARS-CoV-2 based on morphological analysis of the publicly available RxRx19a dataset. This dataset consists of fluorescence microscopy images of SARS-CoV-2 non-infected cells and infected cells, with and without drug treatment. DEEMD first extracts discriminative morphological features to generate cell morphological profiles from the non-infected and infected cells. These morphological profiles are then used in a statistical model to estimate the applied treatment efficacy on infected cells based on similarities to non-infected cells. DEEMD is capable of localizing infected cells via weak supervision without any expensive pixel-level annotations. DEEMD identifies known SARS-CoV-2 inhibitors, such as Remdesivir and Aloxistatin, supporting the validity of our approach. DEEMD can be explored for use on other emerging viruses and datasets to rapidly identify candidate antiviral treatments in the future. Our implementation is available online at https://www.github.com/Sadegh-Saberian/DEEMD.

 

Comments:

That sounds like an interesting and innovative approach to identifying potential treatments for SARS-CoV-2 using bioimaging techniques and deep learning. The use of drug repurposing can indeed expedite the identification of effective compounds for clinical use against SARS-CoV-2, and your DEEMD pipeline seems to be a promising tool for identifying such compounds.

It's great to see that DEEMD is capable of localizing infected cells via weak supervision without the need for expensive pixel-level annotations, making it a cost-effective and efficient tool for identifying potential treatments. It's also encouraging to hear that DEEMD was able to identify known SARS-CoV-2 inhibitors, such as Remdesivir and Aloxistatin, thus supporting the validity of your approach.

It will be interesting to see how DEEMD can be used on other emerging viruses and datasets in the future to identify candidate antiviral treatments. Thank you for sharing the link to your implementation on GitHub, which will be a valuable resource for researchers in this field.

Related Products

Cat.No. Product Name Information
S7393 Aloxistatin (E64d) Aloxistatin (E64d) is an irreversible and membrane-permeable cysteine protease inhibitor with blood platelet aggregation inhibiting activity. The cysteine protease cathepsin L is required for SARS-CoV-2 viral entry, and aloxistatin treatment reduced cellular entry of SARS-CoV-2 pseudovirions by 92.3%.

Related Targets

Cysteine Protease COVID-19