Molecular representation learning has become a fundamental component of modern AI-driven drug discovery. Although 2D graph-based models have advanced this field, they often fail to capture the 3D geometric structures essential for many molecular properties, including ADMET. To address this limitation, we propose TheProperty, a self-supervised framework that integrates 2D topological information with 3D geometry. We introduce a distance denoising pre-training objective, which trains the model to recover the original euclidean distance matrix from a noised 3D conformer. For the fine-tuning, we designed a StructureInformed Attention mechanism that effectively fuses pre-trained 2D atom embeddings with the learned 3D distance embeddings, where the distance embeddings are injected as a structural pair bias into the attention mechanism. TheProperty demonstrated significant performance improvements across 22 tasks in the TDC benchmark. Furthermore, various analytical experiments verified that our proposed model effectively learns 3D structural consistency and pharmacological properties. TheProperty provides a robust, 3D-aware, and interpretable molecular representation that effectively integrates 2D topology with 3D geometry for enhanced ADMET prediction.

Generative Flow Networks (GFlowNets) are designed to generate diverse, high-quality samples by sampling proportionally to rewards using flow conservation constraints. However, they suffer from mode collapse, the very problem they were designed to address. We identify that the root cause is forced terminal states arising from artificial trajectory truncation in vast state spaces. Unlike natural terminal states, forced terminals violate flow conservation boundary constraints, causing flow leakage that biases generation toward maximum-length trajectories and triggers mode collapse. We propose Pruning Loss, a novel training objective that enforces flow conservation at forced terminals by requiring both sink flow and total outflow to equal the reward. This dual constraint implicitly drives unnecessary action flows to zero while maintaining non-vanishing gradients for stable convergence. Our theoretical analysis demonstrates that Pruning Loss recovers proper flow conservation in truncated spaces while guaranteeing gradient persistence. Empirical evaluation on molecular generation tasks validates our theoretical predictions. On sparse-reward kinase protein targets, our method achieves substantial improvements over standard objectives. On dense-reward drug-likeness tasks, all methods perform comparably well, validating that flow leakage specifically limits performance in sparse reward landscapes where diverse exploration is critical. Our results establish that correcting boundary constraints at forced terminals is more fundamental than refining balance equations. This principle provides a new foundation for addressing mode collapse in GFlowNets.

Protein representation learning is a research field that converts proteins into numerical representations that computational models can process, playing a crucial role in areas such as structure-based drug development and protein function prediction. However, existing methods struggle to integrate global information from protein language models with local structure and surface data, particularly on protein surfaces which are key to interactions. We propose a novel surface feature initialization method that maps ESM embeddings onto the protein surface and TheProtein, a novel multimodal architecture that integrates global evolutionary context with local structure and surface information. This is achieved through a new surface feature initialization method using ESM embeddings and dedicated TheProtein blocks. TheProtein achieved new state-of-the-art performance on the Atom3D benchmark, with ablation studies and visualizations confirming its effective integration of global ESM information with local data. Our work highlights the importance of evolutionary context in multimodal protein representation and offers a significant methodological advance.

Recent advances in Structure-based Drug Design (SBDD) have leveraged generative models for 3D molecular generation, predominantly evaluating model performance by binding affinity to target proteins. However, practical drug discovery necessitates high binding affinity along with synthetic feasibility and selectivity, critical properties that were largely neglected in previous evaluations. To address this gap, we identify fundamental limitations of conventional diffusion-based generative models in effectively guiding molecule generation toward these diverse pharmacological properties. We propose $\texttt{CByG}$, a novel framework extending Bayesian Flow Network into a gradient-based conditional generative model that robustly integrates property-specific guidance. Additionally, we introduce a comprehensive evaluation scheme incorporating practical benchmarks for binding affinity, synthetic feasibility, and selectivity, overcoming the limitations of conventional evaluation methods. Extensive experiments demonstrate that our proposed $\texttt{CByG}$, framework significantly outperforms baseline models across multiple essential evaluation criteria, highlighting its effectiveness and practicality for real-world drug discovery applications.

Identifying new compounds that interact with a target is a crucial time-limiting step in the initial phases of drug discovery. Compound-protein complex structure-based affinity prediction models can expedite this process; however, their dependence on high-quality three-dimensional (3D) complex structures limits their practical application. Prediction models that do not require 3D complex structures for binding-affinity estimation offer a theoretically attractive alternative; however, accurately predicting affinity without interaction information presents significant challenges. We introduce BlendNet, a framework that employs a knowledge transfer strategy to improve affinity prediction accuracy by learning the interdependent relationships between compounds and proteins without relying on 3D complex structures. Compared with state-of-the-art models for affinity prediction, BlendNet demonstrated superior performance across various cold-start cases. The ability of BlendNet to interpret compound-protein interactions without utilizing complex structure data highlights its potential to accelerate and streamline drug development.

This article presents case studies using two wave function collapse (WFC) methods, graph-based WFC and simple tiled WFC, to create playable levels for two logic puzzle games:Strimko(Latin Squares) andFlow(connecting dots with pipes). We then evaluate the quality of the generated levels through extensive experiments. Our results indicate that WFC-generated levels are high quality, follow the graph structures' constraints, and are generated faster than levels generated by depth-first search and genetic algorithms. WFC methods can also adapt to new system specifications, common in puzzle games, by changing only the data instead of the code. This increases the stability of content production based on procedural content generation since it relies on data rather than procedures. Furthermore, WFC methods increase the efficiency of the manual process of creating in-game puzzle levels, allowing game designers to complete more tasks in the same amount of time and create a wider variety of assets.

Finding potential drug candidates with high binding affinity for the specific target protein presents an important goal in early drug discovery. Although compound-protein complex structure-based affinity prediction methods have shown promising prediction accuracy, their dependency on high-resolution three-dimensional (3D) complex structure data considerably limits their practical application. Alternatively, many complex-free binding affinity prediction methods have been proposed; however, there is still room for improvement to compensate effectively for the lack of binding information. In particular, the interpretability of compound-protein interactions is a significant challenge that needs to be addressed. To alleviate the limitations of current complex-free models, we propose PretrainedBA, a predictive model that uses pre-training strategies on large-scale datasets, including interaction data. PretrainedBA pre-trains the interdependent relationships between compounds and proteins, rather than the independent pre-training of compounds and proteins utilized in existing studies. PretrainedBA consists of six modules and is designed to effectively model compound-protein interactions within identified binding pockets. Comparisons with state-of-the-art complex-free models on seven external benchmark datasets demonstrate that this pre-training strategy improves binding affinity prediction accuracy. In particular, the outstanding interpretive power of compound-protein interaction mechanisms compared with the previous method further emphasizes the value of PretrainedBA. Real-world application evaluation using the Database of Useful Decoys-Enhanced (DUD-E) dataset confirmed PretrainedBA’s practical applicability, demonstrating its utility in drug discovery.

Traditional image-to-image translation methods effectively change the style; however, these methods have several limitations in shape changing. Particularly, current image-to-image translation technology is not effective for changing a real-world face image to the face of a virtual character. To solve this problem, we propose a novel unsupervised image-to-image translation method that is specialized in facial changes accompanied by radical shape changes. We apply two feature loss functions specialized for faces in an image-to-image translation technique based on the generative adversarial network framework. The experimental results show that the proposed method is superior to other recent image-to-image algorithms in case of face deformations.

This paper describes graph-based Wave Function Collapse algorithm for procedural content generation. The goal of this system is to enable a game designer to procedurally create key content elements in the game level through simple association rule input. To do this, we propose a graph-based data structure that can be easily integrated with a navigation mesh data structure in a three-dimensional world. With our system, if the user inputs the minimum association rule, it is possible to effectively perform procedural content generation in the three-dimensional world. The experimental results show that the Wave Function Collapse algorithm, which is a texture synthesis algorithm, can be extended to a non-grid shape with high controllability and scalability.