23 December 2024 in Communications Biology
Recent years have witnessed the remarkable progress of deep learning within the realm of scientific disciplines, yielding a wealth of promising outcomes. A prominent challenge within this domain has been the task of predicting enzyme function, a complex problem that has seen the development of numerous computational methods, particularly those rooted in deep learning techniques. However, the majority of these methods have primarily focused on either amino acid sequence data or protein structure data, neglecting the potential synergy of combining both modalities. To address this gap, we propose a Contrastive Learning framework for Enzyme functional ANnotation prediction combined with protein amino acid sequences and Contact maps (CLEAN-Contact). We rigorously evaluate the performance of our CLEAN-Contact framework against the state-of-the-art enzyme function prediction models using multiple benchmark datasets. Using CLEAN-Contact, we predict previously unknown enzyme functions within the proteome of Prochlorococcus marinus MED4. Our findings convincingly demonstrate the substantial superiority of our CLEAN-Contact framework, marking a significant step forward in enzyme function prediction accuracy.
18 January 2022 in IEEE Transactions on Geoscience and Remote Sensing
Deep learning and data-driven approaches have shown great potential in scientific domains. The promise of data-driven techniques relies on the availability of a large volume of high-quality training datasets. Due to the high cost of obtaining data through expensive physical experiments, instruments, and simulations, data augmentation techniques for scientific applications have emerged as a new direction for obtaining scientific data recently. However, existing data augmentation techniques originating from computer vision yield physically unacceptable data samples that are not helpful for the domain problems that we are interested in. In this article, we develop new data augmentation techniques based on convolutional neural networks. Specifically, our generative models leverage different physics knowledge (such as governing equations, observable perception, and physics phenomena) to improve the quality of the synthetic data. To validate the effectiveness of our data augmentation techniques, we apply them to solve a subsurface seismic full-waveform inversion using simulated CO 2 leakage data. Our interest is to invert for subsurface velocity models associated with very small CO 2 leakage. We validate the performance of our methods using comprehensive numerical tests. Via comparison and analysis, we show that data-driven seismic imaging can be significantly enhanced by using our data augmentation techniques. Particularly, the imaging quality has been improved by 15% in test scenarios of general-sized leakage and 17% in small-sized leakage when using an augmented training set obtained with our techniques.
28 January 2026 in Advanced Science
Molecular foundation models hold promise to provide accurate predictions for a large and diverse set of downstream tasks in bio‐medical research. Quality molecular representations are key and foundation model development has typically focused on a single representation or molecular view, which may have strengths or weaknesses on a given task. We develop Multi‐view Molecular Embedding with Late Fusion (MMELON), an approach that integrates pre‐trained graph, image and text foundation models and may be readily extended to additional views and models. The multi‐view model performs robustly and is validated on over 120 tasks, including molecular solubility, ADME properties, and activity against G Protein‐Coupled receptors (GPCRs). The GPCR model array is leveraged to perform a virtual screen in search of ligands binding to Alzheimer's disease related GPCRs. We identify a number of such targets and employ the multi‐view model to select strong binders from a compound screen. Predictions are validated through structure‐based modeling and identification of key binding motifs.