Related papers: ViDa: Visualizing DNA hybridization trajectories w…
Synthetic biologists and molecular programmers design novel nucleic acid reactions, with many potential applications. Good visualization tools are needed to help domain experts make sense of the complex outputs of folding pathway…
This dissertation explores how deep generative models can advance the analysis of challenging biological problems by integrating domain knowledge with deep learning. It focuses on two areas: DNA reaction kinetics and cryogenic electron…
Drug-target interaction is fundamental in understanding how drugs affect biological systems, and accurately predicting drug-target affinity (DTA) is vital for drug discovery. Recently, deep learning methods have emerged as a significant…
Contemporary materials science research is heavily conducted in silico, involving massive simulations of the atomic-scale evolution of materials. Cataloging basic patterns in the atomic displacements is key to understanding and predicting…
Conventional unsupervised domain adaptation (UDA) studies the knowledge transfer between a limited number of domains. This neglects the more practical scenario where data are distributed in numerous different domains in the real world. The…
Using random walk sampling methods for feature learning on networks, we develop a method for generating low-dimensional node embeddings for directed graphs and identifying transition states of stochastic chemical reacting systems. We…
Biologists are leading current research on genome characterization (sequencing, alignment, transcription), providing a huge quantity of raw data about many genome organisms. Extracting knowledge from this raw data is an important process…
Interactive molecular graphics applications facilitate analysis of three dimensional protein structures. Naturally, non-interactive 2-D snapshots of the protein structures do not convey the same level of geometric detail. Several 2-D…
Constructing latent vector representation for nodes in a network through embedding models has shown its practicality in many graph analysis applications, such as node classification, clustering, and link prediction. However, despite the…
Two-dimensional embeddings obtained from dimensionality reduction techniques such as MDS, t-SNE, or UMAP, are widely used to visualize high-dimensional data and support researchers in visually identifying clusters, outliers, and other…
Recently vision transformers (ViT) have been applied successfully for various tasks in computer vision. However, important questions such as why they work or how they behave still remain largely unknown. In this paper, we propose an…
Transition state or minimum energy path finding methods constitute a routine component of the computational chemistry toolkit. Standard analysis involves trajectories conventionally plotted in terms of the relative energy to the initial…
Vision-Language-Action (VLA) models built upon Chain-of-Thought (CoT) have achieved remarkable success in advancing general-purpose robotic agents, owing to its significant perceptual comprehension. Recently, since text-only CoT struggles…
Predicting drug-target binding affinity (DTA) is essential for identifying potential therapeutic candidates in drug discovery. However, most existing models rely heavily on static protein structures, often overlooking the dynamic nature of…
Advances in spatial omics and high-resolution imaging enable the creation of three-dimensional (3D) tissue maps that capture cellular organization and interactions in situ. While these data provide critical insights into tissue function and…
In understanding and redesigning the function of proteins in modern biochemistry, protein engineers are increasingly focusing on exploring regions in proteins called loops. Analyzing various characteristics of these regions helps the…
Complementary DNA strands in solution reliably hybridize to form stable duplexes. We study the kinetics of the hybridization process and the mechanisms by which two initially isolated strands come together to form a stable double helix. We…
Virtual screening (VS) is an essential task in drug discovery, focusing on the identification of small-molecule ligands that bind to specific protein pockets. Existing deep learning methods, from early regression models to recent…
Formal representations of the visualization design space, such as knowledge bases and graphs, consolidate design practices into a shared resource and enable automated reasoning and interpretable design recommendations. However, prior…
Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification. However, the development of high-quality deep models typically relies on a substantial amount…