Accurately predicting drug-target binding affinity (DTA) is essential for accelerating drug discovery and reducing experimental costs. Existing deep learning-based DTA methods often fail to effectively integrate heterogeneous biological knowledge and structural information, leading to suboptimal generalization across diverse drug-target pairs. In this work, we propose KGPrompt-DTA, a novel framework that injects knowledge graph-driven prompts into a hybrid graph-transformer architecture to enhance molecular and protein representation learning. Specifically, we construct entity-relation-aware prompts from biomedical knowledge graphs and dynamically fuse them with graph-encoded molecular and protein features via a multilevel attention mechanism. This design enables the model to capture both local structural dependencies and high-level semantic associations. Extensive experiments on two benchmark datasets, DAVIS and KIBA, demonstrate that KGPrompt-DTA consistently outperforms state-of-the-art methods, achieving MSE reductions of 15.5 % and 6.5 %, respectively, while also improving CI,$r_{m}^{2}$, and Pearson correlation scores. Ablation studies confirm the contribution of each component, highlighting the effectiveness of integrating knowledge-informed prompts with graph-transformer learning.

The advent of multi-modal large language models (MLLMs) has ushered in a paradigm shift in clinical diagnostics and therapeutic approaches through advanced medical image interpretation. Despite this progress, the majority of extant investigations have focused primarily on two-dimensional medical imagery, overlooking the potential of volumetric data with its inherently richer spatial information. Our research endeavors to push the boundaries of three-dimensional medical image analysis through the novel application of MLLMs. To this end, we present MedTriVision, a meticulously curated dataset designed for a diverse array of volumetric medical tasks, encompassing image-text retrieval, report generation, visual question answering, spatial localization, and anatomical segmentation. Additionally, we introduce TriMedLM, an innovative multi-faceted multi-modal large language model specifically engineered for volumetric medical image analysis. To facilitate rigorous evaluation, we have developed TriMedLM-Bench, a pioneering three-dimensional multimodal medical assessment framework that enables automated performance appraisal across eight distinct tasks. Extensive empirical investigations demonstrate that our proposed methodology represents a robust and versatile paradigm for three-dimensional medical image analysis, consistently outperforming contemporary approaches in both efficacy and adaptability.

Joint injuries, and their long-term consequences, present a substantial global health burden. Wearable prophylactic braces are an attractive potential solution to reduce the incidence of joint injuries by limiting joint movements that are related to injury risk. Given human motion and ground reaction forces, we present a computational framework that enables the design of personalized braces by optimizing the distribution of microstructures and elasticity. As varied brace designs yield different reaction forces that influence kinematics and kinetics analysis outcomes, the optimization process is formulated as a differentiable end-to-end pipeline in which the design domain of microstructure distribution is parameterized onto a neural network. The optimized distribution of microstructures is obtained via a self-learning process to determine the network coefficients according to a carefully designed set of losses and the integrated biomechanical and physical analyses. Since knees and ankles are the most commonly injured joints, we demonstrate the effectiveness of our pipeline by designing, fabricating, and testing prophylactic braces for the knee and ankle to prevent potentially harmful joint movements.

This paper presents a learning based planner for computing optimized 3D printing toolpaths on prescribed graphs, the challenges of which include the varying graph structures on different models and the large scale of nodes & edges on a graph. We adopt an on-the-fly strategy to tackle these challenges, formulating the planner as a Deep Q-Network (DQN) based optimizer to decide the next 'best' node to visit. We construct the state spaces by the Local Search Graph (LSG) centered at different nodes on a graph, which is encoded by a carefully designed algorithm so that LSGs in similar configurations can be identified to re-use the earlier learned DQN priors for accelerating the computation of toolpath planning. Our method can cover different 3D printing applications by defining their corresponding reward functions. Toolpath planning problems in wire-frame printing, continuous fiber printing, and metallic printing are selected to demonstrate its generality. The performance of our planner has been verified by testing the resultant toolpaths in physical experiments. By using our planner, wire-frame models with up to 4.2k struts can be successfully printed, up to 93.3% of sharp turns on continuous fiber toolpaths can be avoided, and the thermal distortion in metallic printing can be reduced by 24.9%.

The physical plausibility of human motions is vital to various applications in fields including but not limited to graphics, animation, robotics, vision, biomechanics, and sports science. While fully simulating human motions with physics is an extreme challenge, we hypothesize that we can treat this complexity as a black box in a data-driven manner if we focus on the ground contact, and have sufficient observations of physics and human activities in the real world. To prove our hypothesis, we present GroundLink, a unified dataset comprised of captured ground reaction force (GRF) and center of pressure (CoP) synchronized to standard kinematic motion captures. GRF and CoP of GroundLink are not simulated but captured at high temporal resolution using force platforms embedded in the ground for uncompromising measurement accuracy. This dataset contains 368 processed motion trials (∼ 1.59M recorded frames) with 19 different movements including locomotion and weight-shifting actions such as tennis swings to signify the importance of capturing physics paired with kinematics. GroundLinkNet, our benchmark neural network model trained with GroundLink, supports our hypothesis by predicting GRFs and CoPs accurately and plausibly on unseen motions from various sources. The dataset, code, and benchmark models are made public for further research on various downstream tasks leveraging the rich physics information at https://csr.bu.edu/groundlink/.

In this paper, we present a new computational pipeline for designing and fabricating 4D garments as knitwear that considers comfort during body movement. This is achieved by careful control of elasticity distribution to reduce uncomfortable pressure and unwanted sliding caused by body motion. We exploit the ability to knit patterns in different elastic levels by single-jersey jacquard (SJJ) with two yarns. We design the distribution of elasticity for a garment by physics-based computation, the optimized elasticity on the garment is then converted into instructions for a digital knitting machine by two algorithms proposed in this paper. Specifically, a graph-based algorithm is proposed to generate knittable stitch meshes that can accurately capture the 3D shape of a garment, and a tiling algorithm is employed to assign SJJ patterns on the stitch mesh to realize the designed distribution of elasticity. The effectiveness of our approach is verified on simulation results and on specimens physically fabricated by knitting machines.