A deep learning framework for predicting disease-gene associations with functional modules and graph augmentation.

BACKGROUND: The exploration of gene-disease associations is crucial for understanding the mechanisms underlying disease onset and progression, with significant implications for prevention and treatment strategies. Advances in high-throughput biotechnology have generated a wealth of data linking diseases to specific genes. While graph representation learning has recently introduced groundbreaking approaches for predicting novel associations, existing studies always overlooked the cumulative impact of functional modules such as protein complexes and the incompletion of some important data such as protein interactions, which limits the detection performance. RESULTS: Addressing these limitations, here we introduce a deep learning framework called ModulePred for predicting disease-gene associations. ModulePred performs graph augmentation on the protein interaction network using L3 link prediction algorithms. It builds a heterogeneous module network by integrating disease-gene associations, protein complexes and augmented protein interactions, and develops a novel graph embedding for the heterogeneous module network. Subsequently, a graph neural network is constructed to learn node representations by collectively aggregating information from topological structure, and gene prioritization is carried out by the disease and gene embeddings obtained from the graph neural network. Experimental results underscore the superiority of ModulePred, showcasing the effectiveness of incorporating functional modules and graph augmentation in predicting disease-gene associations. This research introduces innovative ideas and directions, enhancing the understanding and prediction of gene-disease relationships.

Ca substitution improves the catalytic activity of perovskite LaCoO3 toward toluene: comprehension of electronic structure alteration.

For perovskite La1-xCaxCoO3 (Ca-x, x = 0-0.3), Ca-0.2 with the closest O p band center to the Fermi level, displays the best catalytic activity for toluene oxidation. The O p band center determines the reducibility and active oxygen content. This finding is beneficial for the design of highly active perovskite catalysts.

Development of novel multifunctional adsorbent by effectively hosting both zwitterionic surfactant and hydrated ferric oxides in montmorillonite.

Intercalating various functional species into the interlayer space is an effective strategy to multi-functionalize 2D materials (e.g., montmorillonite, Mnt), but general limitations have emerged therefrom: (1) various intercalated species compete for the limited interlayer space, and (2) the neighboring intercalated species probably inhibit each other's reactivity. Herein, we have synthesized a novel Mnt-based multifunctional adsorbent (HFO-AZ16Mnt) via intercalation of zwitterionic surfactant (Z16), acid activation by chloric acid, and introduction of hydrated ferric oxides (HFOs). The acid activation can lead to formation of porous nanosilica, which serves as the new active sites for supporting HFO nanoparticles. Employing tetrachloroferrate (FeCl4-) as an anionic precursor of HFOs can help preserve the sulfonyl group (SO3-) of Z16 from being electrostatically occupied during the HFO introduction. As a result, HFO-AZ16Mnt can separately and effectively host Z16 and HFOs. The unique structure endows HFO-AZ16Mnt with the efficiency on simultaneous removal of hydrophobic organic contaminants, oxyanions, and heavy metal cations (nitrobenzene, phosphate, and Cd(II), respectively in this study) from water. Particularly, HFO-AZ16Mnt exhibits impressive capacity towards Cd(II) in both the single- (26.1 mg/g) and the multi-contaminant system (30.6 mg/g). This work has demonstrated a new strategy to multi-functionalize Mnt, and provided a promising novel Mnt-based multifunctional adsorbent for simultaneous and effective removal of organic and inorganic contaminants from water.