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.
SuperResNET is an integrated machine learning‐based analysis software for visualizing and quantifying 3D point cloud data acquired by single‐molecule localization microscopy (SMLM). SuperResNET computational modules include correction for multiple blinking of single fluorophores, denoising, segmentation (clustering), feature extraction used for cluster group identification, modularity analysis, blob retrieval, and visualization in 2D and 3D. Here, a graphical user interface version of SuperResNET was applied to publicly available direct stochastic optical reconstruction microscopy (dSTORM) data of nucleoporin Nup96 and Nup107 labeled nuclear pores that present a highly organized octagon structure of eight corners. SuperResNET effectively segments nuclear pores and Nup96 corners based on differential proximity threshold analysis from 2D and 3D SMLM datasets. SuperResNET quantitatively analyzes features from segmented nuclear pores, including complete structures with eightfold symmetry, and from segmented corners. SuperResNET modularity analysis of segmented corners from 2D SMLM distinguishes two modules at 10.7 ± 0.1 nm distance, corresponding to two individual Nup96 molecules. SuperResNET is therefore a model‐free tool that can reconstruct network architecture and molecular distribution of subcellular structures without the bias of a specified prior model, attaining molecular resolution from dSTORM data. SuperResNET provides flexibility to report on structural diversity in situ within the cell, providing opportunities for biological discovery.
SuperResNET is a network analysis pipeline for the analysis of point cloud data generated by single-molecule localization microscopy (SMLM). Here, we applied SuperResNET network analysis of SMLM direct stochastic optical reconstruction microscopy (dSTORM) data to determine how the clathrin endocytosis inhibitors pitstop 2, dynasore and latrunculin A (LatA) alter the morphology of clathrin-coated pits. SuperResNET analysis of HeLa and Cos7 cells identified three classes of clathrin structures: small oligomers (class I), pits and vesicles (class II), and larger clusters corresponding to fused pits or clathrin plaques (class III). Pitstop 2 and dynasore treatment induced distinct homogeneous populations of class II structures in HeLa cells, suggesting that they arrest endocytosis at different stages. Inhibition of endocytosis was not via actin depolymerization, as the actin-depolymerizing agent LatA induced large, heterogeneous clathrin structures. Ternary analysis of SuperResNET shape features presented a distinct more planar profile for blobs from pitstop 2-treated cells, which aligned with clathrin pits identified with high-resolution minimal photon fluxes (MINFLUX) microscopy, whereas control structures resembled MINFLUX clathrin vesicles. SuperResNET analysis therefore showed that pitstop 2 arrests clathrin pit maturation at early stages of pit formation, representing an approach to detect the effect of small molecules on target structures in situ in the cell from SMLM datasets.
Single‐molecule localization microscopy (SMLM) achieves nanoscale imaging of complex protein structures in the cell. However, the ability to capture structural variability across cell conditions (cell lines, gene expression, treatment) from 3D point cloud SMLM data remains limited. We present siMILe, a weakly supervised multiple instance learning machine learning method to close this gap in interpretable subcellular discovery. siMILe identifies condition‐specific changes in protein assemblies by leveraging their shape and network features, without requiring structure‐level supervision. siMILe improves structure classification by extending embedded instance selection through adversarial erasing and a symmetric classifier. We validated siMILe by detecting caveolae from caveolin‐1 (Cav1) labeled PC3 prostate cancer cells differentially expressing cavin‐1. In PC3‐CAVIN1 cells, cavin‐1 closely associates with siMILe‐identified caveolae, to a lesser extent with higher‐order noncaveolar Cav1 scaffolds, but not small Cav1 oligomers corresponding to 8S complexes, supporting a role for progressive cavin‐1 interaction in 8S complex oligomerization. We also validated siMILe on simulated SMLM data and in detecting inhibitor‐induced structural variations within clathrin‐coated pit data. These results highlight siMILe's potential to identify differential molecular structures in distinct cell conditions. siMILe extends the SuperResNET SMLM software platform with the ability to detect interpretable structural differences across conditions.
Single-molecule localization microscopy (SMLM) achieves nanoscale imaging of complex protein structures in the cell. However, the ability to capture structural variability across cell conditions (cell lines, gene expression, treatment) from 3D point cloud SMLM data remains limited. We present siMILe, a weakly-supervised multiple instance learning (MIL) machine learning method to close this gap in interpretable subcellular discovery. siMILe identifies condition-specific changes in protein assemblies by leveraging their shape and network features, without requiring structure-level supervision. siMILe improves structure classification by extending embedded instance selection (MILES) through adversarial erasing and a symmetric classifier. We validated siMILe by detecting caveolae from caveolin-1 (Cav1) labeled PC3 prostate cancer cells differentially expressing cavin-1. In PC3-CAVIN1 cells, cavin-1 closely associates with siMILe-identified caveolae, to a lesser extent with higher-order non-caveolar Cav1 scaffolds, but not small Cav1 oligomers corresponding to 8S complexes, supporting a role for progressive cavin-1 interaction in 8S complex oligomerization. We also validated siMILe on simulated SMLM data and in detecting inhibitor-induced structural variations within clathrin-coated pit data. These results highlight siMILe’s potential to identify differential molecular structures in distinct cell conditions. siMILe extends the SuperResNET SMLM software platform with the ability to detect interpretable structural differences across conditions.