OLB-AC: toward optimizing ligand bioactivities through deep graph learning and activity cliffs.

MOTIVATION: Deep graph learning (DGL) has been widely employed in the realm of ligand-based virtual screening. Within this field, a key hurdle is the existence of activity cliffs (ACs), where minor chemical alterations can lead to significant changes in bioactivity. In response, several DGL models have been developed to enhance ligand bioactivity prediction in the presence of ACs. Yet, there remains a largely unexplored opportunity within ACs for optimizing ligand bioactivity, making it an area ripe for further investigation. RESULTS: We present a novel approach to simultaneously predict and optimize ligand bioactivities through DGL and ACs (OLB-AC). OLB-AC possesses the capability to optimize ligand molecules located near ACs, providing a direct reference for optimizing ligand bioactivities with the matching of original ligands. To accomplish this, a novel attentive graph reconstruction neural network and ligand optimization scheme are proposed. Attentive graph reconstruction neural network reconstructs original ligands and optimizes them through adversarial representations derived from their bioactivity prediction process. Experimental results on nine drug targets reveal that out of the 667 molecules generated through OLB-AC optimization on datasets comprising 974 low-activity, noninhibitor, or highly toxic ligands, 49 are recognized as known highly active, inhibitor, or nontoxic ligands beyond the datasets' scope. The 27 out of 49 matched molecular pairs generated by OLB-AC reveal novel transformations not present in their training sets. The adversarial representations employed for ligand optimization originate from the gradients of bioactivity predictions. Therefore, we also assess OLB-AC's prediction accuracy across 33 different bioactivity datasets. Results show that OLB-AC achieves the best Pearson correlation coefficient (r2) on 27/33 datasets, with an average improvement of 7.2%-22.9% against the state-of-the-art bioactivity prediction methods. AVAILABILITY AND IMPLEMENTATION: The code and dataset developed in this work are available at github.com/Yueming-Yin/OLB-AC.

AFSE: towards improving model generalization of deep graph learning of ligand bioactivities targeting GPCR proteins.

Ligand molecules naturally constitute a graph structure. Recently, many excellent deep graph learning (DGL) methods have been proposed and used to model ligand bioactivities, which is critical for the virtual screening of drug hits from compound databases in interest. However, pharmacists can find that these well-trained DGL models usually are hard to achieve satisfying performance in real scenarios for virtual screening of drug candidates. The main challenges involve that the datasets for training models were small-sized and biased, and the inner active cliff cases would worsen model performance. These challenges would cause predictors to overfit the training data and have poor generalization in real virtual screening scenarios. Thus, we proposed a novel algorithm named adversarial feature subspace enhancement (AFSE). AFSE dynamically generates abundant representations in new feature subspace via bi-directional adversarial learning, and then minimizes the maximum loss of molecular divergence and bioactivity to ensure local smoothness of model outputs and significantly enhance the generalization of DGL models in predicting ligand bioactivities. Benchmark tests were implemented on seven state-of-the-art open-source DGL models with the potential of modeling ligand bioactivities, and precisely evaluated by multiple criteria. The results indicate that, on almost all 33 GPCRs datasets and seven DGL models, AFSE greatly improved their enhancement factor (top-10%, 20% and 30%), which is the most important evaluation in virtual screening of hits from compound databases, while ensuring the superior performance on RMSE and $r^2$. The web server of AFSE is freely available at http://noveldelta.com/AFSE for academic purposes.

A Machine Learning Study on Internal Force Characteristics of the Anti-Slide Pile Based on the DOFS-BOTDA Monitoring Technology.

Long-term monitoring of constructed anti-slide piles can help in understanding the processes by which anti-slide piles are subjected to the thrust of landslides. This paper examined the landslide control project of Badong No. 3 High School. The internal force of an anti-slide pile subjected to long-term action of landslide thrust was studied by Distributed Optical Fiber Sensing (DOFS) technology. The BP neural network was used for model training on the monitored strain values and the calculated bending moment values. The results show the following: (1) The monitoring results of the sensor fibers reflect the actual situation more accurately than steel rebar meters do and can locate the position of the sliding zone more accurately. (2) The bending moments distributed along the anti-slide pile have staged characteristics under the long-term action of landslide thrust. Three stages can be summarized according to the development trend of the bending moment values. These three stages can be divided into two change periods of landslide thrust. (3) The model produced by the BP neural network training can predict the bending moment values. In this paper, the sensing fibers monitoring over a long time interval provides a basis for long-term performance analysis of anti-slide piles and stability evaluation of landslides. Using the BP neural network for training relevant data can provide directions for future engineering monitoring. More novel methods can be devised and utilized that will be both accurate and convenient.

RealVS: Toward Enhancing the Precision of Top Hits in Ligand-Based Virtual Screening of Drug Leads from Large Compound Databases.

Accurate modeling of compound bioactivities is essential for the virtual screening of drug leads. In real-world scenarios, pharmacists tend to choose from the top-k hit compounds ranked by predicted bioactivities from a large database with interest to continue wet experiments for drug discovery. Significant improvement of the precision of the top hits in ligand-based virtual screening of drug leads is more valuable than conventional schemes for accurately predicting the bioactivities of all compounds from a large database. Here, we proposed a new method, RealVS, to significantly improve the top hits' precision and learn interpretable key substructures associated with compound bioactivities. The features of RealVS involve the following points. (1) Abundant transferable information from the source domain was introduced for alleviating the insufficiency of inactive ligands associated with drug targets. (2) The adversarial domain alignment was adopted to fit the distribution of generated features of compounds from the training data set and that from the screening database for greater model generalization ability. (3) A novel objective function was proposed to simultaneously optimize the classification loss, regression loss, and adversarial loss, where most inactive ligands tend to be screened out before activity regression prediction. (4) Graph attention networks were adopted for learning key substructures associated with ligand bioactivities for better model interpretability. The results on a large number of benchmark data sets show that our method has significantly improved the precision of top hits under various k values in ligand-based virtual screening of drug leads from large compound databases, which is of great value in real-world scenarios. The web server of RealVS is freely available at noveldelta.com/RealVS for academic purposes, where virtual screening of hits from large compound databases is accessible.

Modeling of Red Blood Cells in Capillary Flow Using Fluid-Structure Interaction and Gas Diffusion.

Red blood cell (RBC) distribution, RBC shape, and flow rate have all been shown to have an effect on the pulmonary diffusing capacity. Through this study, a gas diffusion model and the immersed finite element method were used to simulate the gas diffusion into deformable RBCs running in capillaries. It has been discovered that when RBCs are deformed, the CO flux across the membrane becomes nonuniform, resulting in a reduced capacity for diffusion. Additionally, when compared to RBCs that were dispersed evenly, our simulation showed that clustered RBCs had a significantly lower diffusion capability.