Protein-peptide binding residue prediction based on protein language models and cross-attention mechanism.

Accurate identifications of protein-peptide binding residues are essential for protein-peptide interactions and advancing drug discovery. To address this problem, extensive research efforts have been made to design more discriminative feature representations. However, extracting these explicit features usually depend on third-party tools, resulting in low computational efficacy and suffering from low predictive performance.

Improving protein-protein interaction prediction using protein language model and protein network features.

Interactions between proteins are ubiquitous in a wide variety of biological processes. Accurately identifying the protein-protein interaction (PPI) is of significant importance for understanding the mechanisms of protein functions and facilitating drug discovery. Although the wet-lab technological methods are the best way to identify PPI, their major constraints are their time-consuming nature, high cost, and labor-intensiveness.

Cryo-EM structure of human sphingomyelin synthase and its mechanistic implications for sphingomyelin synthesis.

Sphingomyelin (SM) has key roles in modulating mammalian membrane properties and serves as an important pool for bioactive molecules. SM biosynthesis is mediated by the sphingomyelin synthase (SMS) family, comprising SMS1, SMS2 and SMS-related (SMSr) members. Although SMS1 and SMS2 exhibit SMS activity, SMSr possesses ceramide phosphoethanolamine synthase activity.

E2EATP: Fast and High-Accuracy Protein-ATP Binding Residue Prediction via Protein Language Model Embedding.

Identifying the ATP-binding sites of proteins is fundamentally important to uncover the mechanisms of protein functions and explore drug discovery. Many computational methods are proposed to predict ATP-binding sites. However, due to the limitation of the quality of feature representation, the prediction performance still has a big room for improvement.

The cryo-EM structure of the human ERAD retrotranslocation complex.

Endoplasmic reticulum-associated degradation (ERAD) maintains protein homeostasis by retrieving misfolded proteins from the endoplasmic reticulum (ER) lumen into the cytosol for degradation. The retrotranslocation of misfolded proteins across the ER membrane is an energy-consuming process, with the detailed transportation mechanism still needing clarification. We determined the cryo-EM structures of the hetero-decameric complex formed by the Derlin-1 tetramer and the p97 hexamer.

Improving DNA 6mA Site Prediction via Integrating Bidirectional Long Short-Term Memory, Convolutional Neural Network, and Self-Attention Mechanism.

Identifying DNA N6-methyladenine (6mA) sites is significantly important to understanding the function of DNA. Many deep learning-based methods have been developed to improve the performance of 6mA site prediction. In this study, to further improve the performance of 6mA site prediction, we propose a new meta method, called Co6mA, to integrate bidirectional long short-term memory (BiLSTM), convolutional neural networks (CNNs), and self-attention mechanisms (SAM) via assembling two different deep learning-based models.

A novel combined metallurgy-beneficiation method for the facile and low-cost comprehensive resource utilization of low-grade kaolin solid wastes.

Low-grade kaolin is the largest emissions of industrial solid waste that is difficult to dispose of and pollutes the environment seriously. From the perspective of harmless and complete resource utilization, we proposed a novel strategy that combines the wet leaching under mild conditions and physical beneficiation for the facile and low-cost high-valued utilization of low-grade kaolin that involves high-efficiency recovery of aluminum (Al), silicon (Si), and titanium (Ti). The key to successful implementation of this method lies in the new discovery that the residual SiO after Al extraction of kaolinite by acid leaching under specific conditions could be rapidly dissolved in dilute NaOH solution at room temperature 25 °C.

The structural pathology for hypophosphatasia caused by malfunctional tissue non-specific alkaline phosphatase.

Hypophosphatasia (HPP) is a metabolic bone disease that manifests as developmental abnormalities in bone and dental tissues. HPP patients exhibit hypo-mineralization and osteopenia due to the deficiency or malfunction of tissue non-specific alkaline phosphatase (TNAP), which catalyzes the hydrolysis of phosphate-containing molecules outside the cells, promoting the deposition of hydroxyapatite in the extracellular matrix. Despite the identification of hundreds of pathogenic TNAP mutations, the detailed molecular pathology of HPP remains unclear.

Learning Spatio-Temporal Pulse Representation With Global-Local Interaction and Supervision for Remote Prediction of Heart Rate.

Recent studies have demonstrated the benefit of extracting and fusing pulse signals from multi-scale region-of-interests (ROIs). However, these methods suffer from heavy computational load. This paper aims to effectively utilize multi-scale rPPG features with a more compact architecture.

The structural basis of the pH-homeostasis mediated by the Cl/HCO exchanger, AE2.

The cell maintains its intracellular pH in a narrow physiological range and disrupting the pH-homeostasis could cause dysfunctional metabolic states. Anion exchanger 2 (AE2) works at high cellular pH to catalyze the exchange between the intracellular HCO and extracellular Cl, thereby maintaining the pH-homeostasis. Here, we determine the cryo-EM structures of human AE2 in five major operating states and one transitional hybrid state.

C-terminal deletion-induced condensation sequesters AID from IgH targets in immunodeficiency.

In activated B cells, activation-induced cytidine deaminase (AID) generates programmed DNA lesions required for antibody class switch recombination (CSR), which may also threaten genome integrity. AID dynamically shuttles between cytoplasm and nucleus, and the majority stays in the cytoplasm due to active nuclear export mediated by its C-terminal peptide. In immunodeficient-patient cells expressing mutant AID lacking its C-terminus, a catalytically active AID-delC protein accumulates in the nucleus but nevertheless fails to support CSR.

The structural basis for the phospholipid remodeling by lysophosphatidylcholine acyltransferase 3.

As the major component of cell membranes, phosphatidylcholine (PC) is synthesized de novo in the Kennedy pathway and then undergoes extensive deacylation-reacylation remodeling via Lands' cycle. The re-acylation is catalyzed by lysophosphatidylcholine acyltransferase (LPCAT) and among the four LPCAT members in human, the LPCAT3 preferentially introduces polyunsaturated acyl onto the sn-2 position of lysophosphatidylcholine, thereby modulating the membrane fluidity and membrane protein functions therein. Combining the x-ray crystallography and the cryo-electron microscopy, we determined the structures of LPCAT3 in apo-, acyl donor-bound, and acyl receptor-bound states.

PepFormer: End-to-End Transformer-Based Siamese Network to Predict and Enhance Peptide Detectability Based on Sequence Only.

The detectability of peptides is fundamentally important in shotgun proteomics experiments. At present, there are many computational methods to predict the detectability of peptides based on sequential composition or physicochemical properties, but they all have various shortcomings. Here, we present PepFormer, a novel end-to-end Siamese network coupled with a hybrid architecture of a Transformer and gated recurrent units that is able to predict the peptide detectability based on peptide sequences only.

The cryo-EM structure of an ERAD protein channel formed by tetrameric human Derlin-1.

Endoplasmic reticulum-associated degradation (ERAD) is a process directing misfolded proteins from the ER lumen and membrane to the degradation machinery in the cytosol. A key step in ERAD is the translocation of ER proteins to the cytosol. Derlins are essential for protein translocation in ERAD, but the mechanism remains unclear.

ACPred-Fuse: fusing multi-view information improves the prediction of anticancer peptides.

Fast and accurate identification of the peptides with anticancer activity potential from large-scale proteins is currently a challenging task. In this study, we propose a new machine learning predictor, namely, ACPred-Fuse, that can automatically and accurately predict protein sequences with or without anticancer activity in peptide form. Specifically, we establish a feature representation learning model that can explore class and probabilistic information embedded in anticancer peptides (ACPs) by integrating a total of 29 different sequence-based feature descriptors.

Crystal structure of a bacterial homolog to human lysosomal transporter, spinster.

Lysosomes break down various biomolecules and spinster is one of the major efflux carriers removing degradation products from lysosomal lumen to keep it in healthy size and proper function. Although it is well established that a dysfunctional spinster will cause enlarged lysosomes and in turn lead to developmental defects and abnormal behavior in animals, little was known about the transportation mechanism and substrate specificity of spinster. Here, we report a crystal structure of spinster homolog from Hyphomonas neptunium, HnSPNS, in its inward-facing conformation with and without substrate bound.

Miniaturization of the Whole Process of Protein Crystallographic Analysis by a Microfluidic Droplet Robot: From Nanoliter-Scale Purified Proteins to Diffraction-Quality Crystals.

To obtain diffraction-quality crystals is one of the largest barriers to analyze the protein structure using X-ray crystallography. Here we describe a microfluidic droplet robot that enables successful miniaturization of the whole process of crystallization experiments including large-scale initial crystallization screening, crystallization optimization, and crystal harvesting. The combination of the state-of-the-art droplet-based microfluidic technique with the microbatch crystallization mode dramatically reduces the volumes of droplet crystallization reactors to tens nanoliter range, allowing large-scale initial screening of 1536 crystallization conditions and multifactor crystallization condition optimization with extremely low protein consumption, and on-chip harvesting of diffraction-quality crystals directly from the droplet reactors.