Particle identification and selection, which is a prerequisite for high-resolution structure determination of biological macromolecules via single-particle cryo-electron microscopy poses a major bottleneck for automating the steps of structure determination. Here, we present a generalized deep learning tool, CASSPER, for the automated detection and isolation of protein particles in transmission microscope images. This deep learning tool uses Semantic Segmentation and a collection of visually prepared training samples to capture the differences in the transmission intensities of protein, ice, carbon, and other impurities found in the micrograph. CASSPER is a semantic segmentation based method that does pixel-level classification and completely eliminates the need for manual particle picking. Integration of Contrast Limited Adaptive Histogram Equalization (CLAHE) in CASSPER enables high-fidelity particle detection in micrographs with variable ice thickness and contrast. A generalized CASSPER model works with high efficiency on unseen datasets and can potentially pick particles on-the-fly, enabling data processing automation.
The complex nature and structure of the human immunodeficiency virus has rendered the cure for HIV infections elusive. The advances in antiretroviral treatment regimes and the development of highly advanced anti-retroviral therapy, which primarily targets the HIV enzymes, have dramatically changed the face of the HIV epidemic worldwide. Despite this remarkable progress, patients treated with these drugs often witness inadequate efficacy, compound toxicity and non-HIV complications. Considering the limited inventory of druggable HIV proteins and their susceptibility to develop drug resistance, recent attempts are focussed on targeting HIV-host interactomes that are essential for viral reproduction. Noticeably, unlike other viruses, HIV subverts the host nuclear pore complex to enter into and exit through the nucleus. Emerging evidence suggests a crucial role of interactions between HIV-1 proteins and host nucleoporins that underlie the import of the pre-integration complex into the nucleus and export of viral RNAs into the cytoplasm during viral replication. Nevertheless, the interaction of HIV-1 with nucleoporins has been poorly described and the role of nucleoporins during nucleocytoplasmic transport of HIV-1 still remains unclear. In this review, we highlight the advances and challenges in developing a more effective antiviral arsenal by exploring critical host-HIV interactions with a special focus on nuclear pore complex (NPC) and nucleoporins.
Nuclear pore complex (NPC) is the largest multimeric protein assembly of the eukaryotic cell, which mediates the nucleocytoplasmic transport. The constituent proteins of this assembly (nucleoporins) are present in varying copy numbers to give a size from ~ 60 MDa (yeast) to 112 MDa (human) and share common ancestry with other membrane‐associated complexes such as COPI/COPII and thus share the same structural folds. However, the nucleoporins across species exhibit very low percentage sequence similarity and this reflects in their distinct secondary structure and domain organization. We employed thorough sequence and phylogenetic analysis guided from structure‐based alignments of all the nucleoporins from fungi to metazoans to understand the evolution of NPC. Through evolutionary pressure analysis on various nucleoporins, we deduced that these proteins are under differential selection pressure and hence the homologous interacting partners do not complement each other in the in vitro pull‐down assay. The super tree analysis of all nucleoporins taken together illustrates divergent evolution of nucleoporins and notably, the degree of divergence is more apparent in higher order organisms as compared to lower species. Overall, our results support the hypothesis that the protein–protein interactions in such large multimeric assemblies are species specific in nature and hence their structure and function should also be studied in an organism‐specific manner.