A5022184264- Computational Drug Discovery Methods
- Physiological and biochemical adaptations
- Protein Structure and Dynamics
- Machine Learning in Materials Science
- Erythrocyte Function and Pathophysiology
- Advanced Chemical Sensor Technologies
- Neural dynamics and brain function
- vaccines and immunoinformatics approaches
- Neurobiology and Insect Physiology Research
- Anomaly Detection Techniques and Applications
- Chemical Synthesis and Analysis
- Animal Behavior and Reproduction
- Perovskite Materials and Applications
- Molecular Biology Techniques and Applications
- Circadian rhythm and melatonin
- RNA and protein synthesis mechanisms
- Cellular transport and secretion
- Single-cell and spatial transcriptomics
- Biochemical Analysis and Sensing Techniques
- Advanced Memory and Neural Computing
- Zebrafish Biomedical Research Applications
- Species Distribution and Climate Change
- Transition Metal Oxide Nanomaterials
- Lysosomal Storage Disorders Research
- Animal Vocal Communication and Behavior
Tsinghua University
2018-2024
Center for Life Sciences
2018-2024
Chinese Institute for Brain Research
2021-2023
McGovern Institute for Brain Research
2022
King Center
2022
Abstract Cells sense physical forces and convert them into electrical or chemical signals, a process known as mechanotransduction. Whereas extensive studies focus on mechanotransduction at the plasma membrane, little is about whether how intracellular organelles mechanical force physiological functions of organellar mechanosensing. Here we identify Drosophila TMEM63 ( Dm TMEM63) ion channel an intrinsic mechanosensor lysosome, major degradative organelle. Endogenous proteins localize to...
Orchestration of diverse synaptic plasticity mechanisms across different timescales produces complex cognitive processes. To achieve comparable complexity in memristive neuromorphic systems, devices that are capable to emulate short- and long-term (STP LTP, respectively) concomitantly essential. However, this fundamental bionic trait has not been reported any existing memristors where STP LTP can only be induced selectively because the inability decoupled using loci mechanisms. In work, we...
Fast and accurately characterizing animal behaviors is crucial for neuroscience research. Deep learning models are efficiently used in laboratories behavior analysis. However, it has not been achieved to use an end-to-end unsupervised neural network extract comprehensive discriminative features directly from social video frames annotation analysis purposes. Here, we report a self-supervised feature extraction (Selfee) convolutional with multiple downstream applications process of way....
Abstract Spiders are renowned for their efficient capture of flying insects using intricate aerial webs. How the spider nervous systems evolved to cope with this specialized hunting strategy and various environmental clues in an space remains unknown. Here we report a brain-cell atlas >30,000 single-cell transcriptomes from web-building ( Hylyphantes graminicola ). Our analysis revealed preservation ancestral neuron types spiders, including potential coexistence noradrenergic...
Abstract Numerous protein-coding genes are associated with human diseases, yet approximately 90% of them lack targeted therapeutic intervention. While conventional computational methods such as molecular docking have facilitated the discovery potential hit compounds, development genome-wide virtual screening against expansive chemical space remains a formidable challenge. Here we introduce DrugCLIP, novel framework that combines contrastive learning and dense retrieval to achieve rapid...
Atomic interactions are fundamental to molecular structures and functions. We constructed PocketXMol, an all-atom AI model, learn these for general pocket-interacting generative tasks. PocketXMol unified distinct tasks under a single computational framework without re-quiring fine-tuning. It was evaluated on 11 typical tasks, covering docking design of small molecules peptides, compared against 49 baselines using 45 metrics. outperformed state-of-the-art methods in 9 competitive the...
Pocket representations play a vital role in various biomedical applications, such as druggability estimation, ligand affinity prediction, and de novo drug design. While existing geometric features pretrained have demonstrated promising results, they usually treat pockets independent of ligands, neglecting the fundamental interactions between them. However, limited pocket-ligand complex structures available PDB database (less than 100 thousand non-redundant pairs) hampers large-scale...
Virtual screening, which identifies potential drugs from vast compound databases to bind with a particular protein pocket, is critical step in AI-assisted drug discovery. Traditional docking methods are highly time-consuming, and can only work restricted search library real-life applications. Recent supervised learning approaches using scoring functions for binding-affinity prediction, although promising, have not yet surpassed due their strong dependency on limited data reliable labels. In...
The binding between proteins and ligands plays a crucial role in the realm of drug discovery. Previous deep learning approaches have shown promising results over traditional computationally intensive methods, but resulting poor generalization due to limited supervised data. In this paper, we propose learn protein-ligand representation self-supervised manner. Different from existing pre-training which treat individually, emphasize discern intricate patterns fine-grained interactions....
Abstract Discrimination for sound frequency is essential auditory communications in animals. Here, by combining vivo calcium imaging and behavioral assay, we found that Drosophila larvae can sense a wide range of the specificity mediated with selectivity lch5 chordotonal organ neurons to sounds forms combinatorial coding frequency. We also disclosed Brivido1 (Brv1) Piezo-like (Pzl), each expresses subset mediate hearing sensation certain ranges. Intriguingly, mouse Piezo2 rescue pzl...
ABSTRACT Fast and accurately characterizing animal behaviors is crucial for neuroscience research. Deep learning models are efficiently used in laboratories behavior analysis. However, it has not been achieved to use a fully unsupervised method extract comprehensive discriminative features directly from raw video frames annotation analysis purposes. Here, we report self-supervised feature extraction (Selfee) convolutional neural network with multiple downstream applications process of an...