Protein-ligand interaction (PLI) is a critical step for drug discovery. Recently, protein pretrained language models (PLMs) have showcased exceptional performance across a wide range of protein-related tasks. However, a significant heterogeneity exists between the PLM and PLI tasks, leading to a degree of uncertainty. In this study, we propose a method that quantitatively assesses the significance of protein PLMs in PLI prediction. Specifically, we analyze the performance of three widely-used protein PLMs (TAPE, ESM-1b, and ProtTrans) on three PLI tasks (PDBbind, Kinase, and DUD-E). The model with pre-training consistently achieves improved performance and decreased time cost, demonstrating that enhance both the accuracy and efficiency of PLI prediction. By quantitatively assessing the transferability, the optimal PLM for each PLI task is identified without the need for costly transfer experiments. Additionally, we examine the contributions of PLMs on the distribution of feature space, highlighting the improved discriminability after pre-training. Our findings provide insights into the mechanisms underlying PLMs in PLI prediction and pave the way for the design of more interpretable and accurate PLMs in the future. Code and data are freely available at https://github.com/brian-zZZ/PLM-PLI.

With the increasing availability of large-scale QSAR (Quantitative Structure-Activity Relationship) datasets, collaborative analysis has become a promising approach for drug discovery. Traditional centralized analysis which typically concentrates data on a central server for training faces challenges such as data privacy and security. Distributed analysis such as federated learning offers a solution by enabling collaborative model training without sharing raw data. However, it may fail when the training data in the local devices are non-independent and identically distributed (non-IID). In this paper, we propose a novel framework for collaborative drug discovery using federated learning on non-IID datasets. We address the difficulty of training on non-IID data by globally sharing a small subset of data among all institutions. Our framework allows multiple institutions to jointly train a robust predictive model while preserving the privacy of their individual data. We leverage the federated learning paradigm to distribute the model training process across local devices, eliminating the need for data exchange. The experimental results on 15 benchmark datasets demonstrate that the proposed method achieves competitive predictive accuracy to centralized analysis while respecting data privacy. Moreover, our framework offers benefits such as reduced data transmission and enhanced scalability, making it suitable for large-scale collaborative drug discovery efforts.

The development of compounds that can selectively bind with non-canonical DNA structures has expanded in recent years. Junction DNA, including three-way junctions (3WJs) and four-way Holliday junctions (HJs), offer an intriguing target for developmental therapeutics as both 3WJs and HJs are involved in DNA replication and repair processes. However, there are a limited number of assays available for the analysis of junction DNA binding. Here, we describe the design and execution of multiplex fluorescent polyacrylamide gel electrophoresis (PAGE) and microscale thermophoresis (MST) assays that enable evaluation of junction-binding compounds. Two well characterised junction-binding compounds-a C6 linked bis-acridine ligand and an iron(II)-bound peptide helicate, which recognise HJs and 3WJs, respectively-were employed as probes for both MST and PAGE experiments. The multiplex PAGE assay expands beyond previously reported fluorescent PAGE as it combines four individual fluorophores that can be combined to visualise single-strands, pseudo-duplexes, and junction DNA present during 3WJ and HJ formation. The use of MST to identify the binding affinity of junction binding agents is, to our knowledge, first reported example of this technique. The combined use of PAGE and MST provides complementary results for the visualisation of 3WJ and HJ formation and the direct binding affinity (Kd and EC50) of these agents. These assays can be used to aid the discovery and design of new therapeutics targeting non-canonical nucleic acid structures.

Use of cationic lipid vesicles (liposomes) can yield large amounts of nucleic acid entrapped inside the vesicles and/or bound to the external surface of the vesicles. To show a method to prepare asymmetric lipid vesicles (liposomes) with high amounts of entrapped nucleic acid is possible, symmetric and asymmetric lipid vesicles composed of mixtures of neutral (zwitterionic), anionic, and/or cationic phospholipids were formed in the presence of oligo DNA. For symmetric large unilamellar vesicles nucleic acid association with vesicles was roughly 100 times greater for vesicles with a net cationic charge than for vesicles having a net neutral or anionic net charge. A high degree of association between nucleic acid and lipid was also achieved using asymmetric large unilamellar vesicles with a net cationic charge in their inner leaflet, even when they had an anionic charge in their outer leaflet. In contrast, asymmetric vesicles in which only the outer leaflet had a net cationic charge had only low amounts of vesicle-associated nucleic acid, similar in amount to the amount of nucleic acid associated with asymmetric vesicles with an outer leaflet having a net anionic charge. These results indicate that in asymmetric vesicles with cationic lipid enriched inner leaflets nucleic acid is largely entrapped inside the vesicle lumen rather than bound to their external surface, and that asymmetric vesicles can be used to trap high amounts of nucleic acid even when using a lipid composition in the outer leaflet of a lipid vesicle that does not associate with nucleic acids. Such asymmetrically charged vesicles should have applications in studies of membrane protein-nucleic acid interactions as well as in studies of how membrane charge asymmetry can influence membrane protein structure, orientation, and function.