Motivation: Drug combination therapy plays a pivotal role in addressing the molecular heterogeneity of cancer, improving treatment efficacy, minimizing resistance, and reducing toxicity. Deep learning approaches have significantly advanced drug combination discovery by addressing the limitations of conventional laboratory experiments, which are time-consuming and costly. While most existing models rely on the molecular structure of drugs and gene expression data, incorporating protein-level expression provides a more accurate representation of cellular behavior and drug responses. In this study, we introduce SynProtX, an enhanced deep learning model that explicitly integrates large-scale proteomics with deep neural networks (DNNs) and the molecular structure of drugs with graph neural networks (GNNs). Results: The SynProtX-GATFP model, which combines molecular graphs and fingerprints through a graph attention network architecture, demonstrated superior predictive performance for the FRIEDMAN study dataset. We further evaluated its cell line–specific performance, which achieved accuracy across diverse tissue and study datasets. By incorporating protein expression data, the model consistently enhanced predictive performance over gene expression–only models, reflecting the functional state of cancer cells. The generalizability of SynProtX was rigorously validated using cold-start prediction, including leave-drug-combination-out, leave-drug-out, and leave-cell-line-out validation strategies, highlighting its robust performance and potential for clinical applicability. Additionally, SynProtX identified key cancer-associated proteins and molecular substructures, offering novel insights into the biological mechanisms underlying drug synergy. These findings highlight the potential of integrating large-scale proteomics and multiomics data to advance anticancer drug design and combination therapy strategies for personalized medicine. Availability and implementation: https://github.com/manbaritone/SynProtX.

Villin is an actin filament nucleating, severing, capping and bundling protein; however, the structural basis for villin’s functions and the characteristics of the actin polymerization nucleus remain poorly understood. Here, we present the structure of vent-worm villin bound to a trimeric actin nucleus. Villin wraps around and caps the barbed end of the actin trimer. Its headpiece domain interacts at the junction of two laterally associated actin protomers, leaving the pointed-end subunits open for elongation. Within the actin trimer, the two longitudinally associated subunits adopt barbed and pointed-end subunit conformations, while the lateral protomer exhibits a monomeric conformation. This provides the first view of an actin-filament nucleus, revealing that the transition into the filamentous form is stimulated and stabilized by the interactions with the pointed-end subunits. Our results also illuminate mechanisms of actin-filament dynamics and villin capping and severing, suggesting that F-to-G actin conformational transitions facilitate the later process.

A bstract: Motivation: Lung cancer is a chronic non-communicable disease and is the cancer with the world’s highest incidence in the 21 ^st century. One of the leading mechanisms underlying the development of lung cancer in nonsmokers is an amplification of the epidermal growth factor receptor (EGFR) gene. However, laboratories employing conventional processes of drug discovery and development for such targets encounter several pain-points that are cost- and time-consuming. Moreover, high failure rates are caused by efficacy and safety problems during research and development. Therefore, it is imperative to develop improved methods for drug discovery. Herein, we developed a deep learning model with spatial graph embedding and molecular descriptors based on predicting pIC ₅₀ potency estimates of small molecules and classifying hit compounds against the human epidermal growth factor receptor (LigEGFR). The model was generated with a large-scale cell line-based dataset containing broad lists of chemical features. Results: LigEGFR outperformed baseline machine learning models for predicting pIC ₅₀ . Our model was notable for higher performance in hit compound classification, compared to molecular docking and machine learning approaches. The proposed predictive model provides a powerful strategy that potentially helps researchers overcome major challenges in drug discovery and development processes, leading to a reduction of failure to discover novel hit compounds. Availability: We provide an online prediction platform and the source code that are freely available at https://ligegfr.vistec.ist , and https://github.com/scads-biochem/LigEGFR , respectively. Key points: LigEGFR is a regression model for predicting pIC ₅₀ that was developed for the human EGFR target. It can also be applied to hit compound classification (pIC ₅₀ ≥ 6) and has a higher performance than baseline machine learning algorithms and molecular docking approaches. Our spatial graph embedding and molecular descriptors based approach notably exhibited a high performance in predicting pIC ₅₀ of small molecules against human EGFR. Non-hashed and hashed molecular descriptors were revealed to have the highest predictive performance by using in a convolutional layers and a fully connected layers, respectively. Our model used a large-scale and non-redundant dataset to enhance the diversity of the small molecules. The model showed robustness and reliability, which was evaluated by y-randomization and applicability domain analysis (ADAN), respectively. We developed a user-friendly online platform to predict pIC ₅₀ of small molecules and classify the hit compounds for the drug discovery process of the EGFR target.

Vibrio campbellii (formerly Vibrio harveyi) is a marine pathogen that causes vibriosis, a major disease affecting global aquaculture. This bacterium inhabits chitin-rich environments and uses chito-oligosaccharides as a main nutrient source. Here, we identify the novel outer membrane protein OmpV25 as a porin mediating broad-spectrum oligosaccharide uptake in V. campbellii. OmpV25 was heterologously expressed in Escherichia coli BL21 (DE3) Omp8, purified by nickel affinity and size exclusion chromatography, and crystallized. The resulting 2.70 Å crystal structure revealed the 25-kDa OmpV25 to be a monomeric β-barrel composed of 12 β-strands connected by six extracellular loops and five periplasmic turns. Single-channel electrophysiology demonstrated that OmpV25 forms stable monomeric pores in artificial lipid bilayers characterized by a conductance of 0.19 ± 0.003 nS in 1 M KCl. The channel facilitated binding of mono-, di-, tri- and tetragalacturonic acids, as well as chitotetraose and maltotetraose. Fluorescence spectroscopy revealed moderate-affinity binding to tetragalacturonic acid (K_d = 3.04 ± 0.42 μM), chitotetraose (K_d = 6.79 ± 0.27 μM), and maltotetraose (K_d = 5.21 ± 0.78 μM). A liposome swelling assay confirmed that OmpV25 enables translocation of a broad range of oligosaccharides beyond oligogalacturonic acids. These findings define the physiological role of OmpV25 as a broad-specificity sugar channel that may support environmental resilience of Vibrio species in nutrient-variable marine habitats.