Non-genetic and genetic rewiring underlie adaptation to hypomorphic alleles of an essential gene

A hybrid machine learning model with attention mechanism and multidimensional multivariate feature coding for essential gene prediction

BACKGROUND

Essential genes are crucial for the development, inheritance, and survival of species. The exploration of these genes can unravel the complex mechanisms and fundamental life processes and identify potential therapeutic targets for various diseases. Therefore, the identification of essential genes is significant. Machine learning has become the mainstream approach for essential gene prediction. However, some key challenges in machine learning need to be addressed, such as the extraction of genetic features, the impact of imbalanced data, and the cross-species generalization ability.

RESULTS

Here, we proposed a hybrid machine learning model based on graph convolutional neural networks (GCN) and bi-directional long short-term memory (Bi-LSTM) with attention mechanism and multidimensional multivariate feature coding for essential gene prediction, called EGP Hybrid-ML. In the model, GCN was used to extract feature encoding information from the visualized graphics of gene sequences and the attention mechanism was combined with Bi-LSTM to assess the importance of each feature in gene sequences and analyze the influences of different feature encoding methods and data imbalance. Additionally, the cross-species predictive performance of the model was evaluated through cross-validation. The results indicated that the sensitivity of the EGP Hybrid-ML model reached 0.9122.

CONCLUSIONS

This model demonstrated the superior predictive performance and strong generalization capabilities compared to other models. The EGP Hybrid-ML model proposed in this paper has broad application prospects in bioinformatics, chemical information, and pharmaceutical information. The codes, architectures, parameters, and datasets of the proposed model are available free of charge at GitHub ( https://github.com/gnnumsli/EGP-Hybrid-ML ).

Advances in the understanding of nuclear pore complexes in human diseases

BACKGROUND

Nuclear pore complexes (NPCs) are sophisticated and dynamic protein structures that straddle the nuclear envelope and act as gatekeepers for transporting molecules between the nucleus and the cytoplasm. NPCs comprise up to 30 different proteins known as nucleoporins (NUPs). However, a growing body of research has suggested that NPCs play important roles in gene regulation, viral infections, cancer, mitosis, genetic diseases, kidney diseases, immune system diseases, and degenerative neurological and muscular pathologies.

PURPOSE

In this review, we introduce the structure and function of NPCs. Then We described the physiological and pathological effects of each component of NPCs which provide a direction for future clinical applications.

METHODS

The literatures from PubMed have been reviewed for this article.

CONCLUSION

This review summarizes current studies on the implications of NPCs in human physiology and pathology, highlighting the mechanistic underpinnings of NPC-associated diseases.

Disruption of Leishmania flagellum attachment zone architecture causes flagellum loss

Leishmania are flagellated eukaryotic parasites that cause leishmaniasis and are closely related to the other kinetoplastid parasites such as Trypanosoma brucei. In all these parasites there is a cell membrane invagination at the base of the flagellum called the flagellar pocket, which is tightly associated with and sculpted by cytoskeletal structures including the flagellum attachment zone (FAZ). The FAZ is a complex interconnected structure linking the flagellum to the cell body and has critical roles in cell morphogenesis, function and pathogenicity. However, this structure varies dramatically in size and organisation between these different parasites, suggesting changes in protein localisation and function. Here, we screened the localisation and function of the Leishmania orthologues of T. brucei FAZ proteins identified in the genome-wide protein tagging project TrypTag. We identified 27 FAZ proteins and our deletion analysis showed that deletion of two FAZ proteins in the flagellum, FAZ27 and FAZ34 resulted in a reduction in cell body size, and flagellum loss in some cells. Furthermore, after null mutant generation, we observed distinct and reproducible changes to cell shape, demonstrating the ability of the parasite to adapt to morphological perturbations resulting from gene deletion. This process of adaptation has important implications for the study of Leishmania mutants.

Non-genetic and genetic rewiring underlie adaptation to hypomorphic alleles of an essential gene

Adaptive evolution to cellular stress is a process implicated in a wide range of biological and clinical phenomena. Two major routes of adaptation have been identified: non-genetic changes, which allow expression of different phenotypes in novel environments, and genetic variation achieved by selection of fitter phenotypes. While these processes are broadly accepted, their temporal and epistatic features in the context of cellular evolution and emerging drug resistance are contentious. In this manuscript, we generated hypomorphic alleles of the essential nuclear pore complex (NPC) gene NUP58. By dissecting early and long-term mechanisms of adaptation in independent clones, we observed that early physiological adaptation correlated with transcriptome rewiring and upregulation of genes known to interact with the NPC; long-term adaptation and fitness recovery instead occurred via focal amplification of NUP58 and restoration of mutant protein expression. These data support the concept that early phenotypic plasticity allows later acquisition of genetic adaptations to a specific impairment. We propose this approach as a genetic model to mimic targeted drug therapy in human cells and to dissect mechanisms of adaptation.