The realization of many protein functions requires binding with ligands. As a significant protein-binding ligand, ATP plays crucial role in various biological processes. Currently, the precise prediction residues remains challenging. Based on sequence information, this paper introduces method called S-DCNN for predicting residues, utilizing deep convolutional neural network (DCNN) enhanced synthetic minority over-sampling technique (SMOTE). incorporation additional feature parameters such as...

Abstract Metal ions are significant ligands that bind to proteins and play crucial roles in cell metabolism, material transport, signal transduction. Predicting the protein‐metal ion ligand binding residues (PMILBRs) accurately is a challenging task theoretical calculations. In this study, authors employed fused amino acids their derived information as feature parameters predict PMILBRs using three classical machine learning algorithms, yielding favourable prediction results. Subsequently,...

The prediction of ion ligand binding residues on proteins helps to understand the specific functions in life processes. At present, it is a challenge work predict ligands studies protein functions. In this paper, we constructed datasets with 14 residues, including 4 acid radical and 10 metal ligands. Based amino sequence information, selected composition position conservation information acids, predicted structural physicochemical properties acids as basic feature parameters. We then made...

Abstract The advancement of spatial transcriptomics (ST) technology contributes to a more profound comprehension the properties gene expression within tissues. However, due challenges high dimensionality, pronounced noise and dynamic limitations in ST data, integration information accurately identify domains remains challenging. This paper proposes SpaNCMG algorithm for purpose achieving precise domain description localization based on neighborhood-complementary mixed-view graph...

Abstract Background Proteins perform their functions by interacting with acid radical ions. Recently, it was a challenging work to precisely predict the binding residues of ion ligands in research field molecular drug design. Results In this study, we proposed an improved method using K-nearest Neighbors classifier. Meanwhile, constructed datasets four ligand (NO 2 − , CO 3 2− SO 4 PO 3− ) from BioLip database. Then, based on optimal window length for each ligand, refined composition...

Abstract Background In many important life activities, the execution of protein function depends on interaction between proteins and ligands. As an binding ligand, identification site ion ligands plays role in study function. Results this study, four acid radical (NO 2 − ,CO 3 2− ,SO 4 ,PO 3− ) ten metal (Zn 2+ ,Cu ,Fe 3+ ,Ca ,Mg ,Mn ,Na + ,K ,Co are selected as research object, Sequential minimal optimization (SMO) algorithm based sequence information was proposed, better prediction results...

The recognition of protein folds is an important step for the prediction structure and function. After 27-class in 2001 by Ding Dubchak, algorithms, parameters, new datasets have been improved. However, influences interactions from predicted secondary segments motif information on folding not considered. Therefore, with interaction very important. Based dataset built Liu et al., amino acid composition, segments, frequency, were extracted. Using Random Forest algorithm ensemble classification...

The recognition of protein folds is an important step in the prediction structure and function. Recently, increasing number researchers have sought to improve methods for fold recognition. Following construction a dataset consisting 27 classes by Ding Dubchak 2001, algorithms, parameters new datasets improved folds. In this study, we reorganized 76-fold constructed Liu et al. used values increment diversity, average chemical shifts secondary elements motifs as feature multi-class With...

Prior studies have shown that the performance of amplify-and-forward (AF) relay systems can be considerably improved by using multiple antennas and low complexity linear processing at nodes. However, there is still a lack analysis for cases where based on limited feedback (LFB). Motivated this, we derive closed-form expression outage probability AF with LFB beamforming in this letter. Simulation results are also provided to confirm analytical studies.

Many proteins realize their special functions by binding with specific metal ion ligands during a cell's life cycle. The ability to correctly identify ligand-binding residues is valuable for the human health and design of molecular drug. Precisely identifying these residues, however, remains challenging work. We have presented an improved computational approach predicting 10 (Zn2+, Cu2+, Fe2+, Fe3+, Co2+, Ca2+, Mg2+, Mn2+, Na+, K+) adding reclassified relative solvent accessibility (RSA)....

[Background: Rational drug molecular design based on virtual screening requires the ligand binding site to be known. Recently, recognition of ion has become an important research direction in pharmacology.In this work, we selected residues 4 acid radical ligands (NO2-, CO32-, SO42- and PO43-) 10 metal (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, K+ Co2+) as objects. Based protein sequence information, extracted amino features, energy, physicochemical, structure features. Then,...

β-Hairpins in enzyme, a kind of special protein with catalytic functions, contain many binding sites which are essential for the functions enzyme. With increasing number observed enzyme sequences, it is especial importance to use bioinformatics techniques quickly and accurately identify β-hairpin further advanced annotation structure function In this work, proposed method was trained tested on non-redundant database containing 2818 β-hairpins 1098 non-β-hairpins. 5-fold cross-validation...

Accurate identification of ligand‐binding sites and discovering the protein–ligand interaction mechanism are important for understanding proteins' functions designing new drugs. Meanwhile, accurate computational prediction research two grand challenges in proteomics. In this article, residues five ligands (ATP, ADP, GTP, GDP, NAD) predicted as a group, due to their similar chemical structures close biological function relations. The data set binding by collated from Biolip database. Then,...

Proteins need to interact with different ligands perform their functions. Among the ligands, metal ion is a major ligand. At present, prediction of protein ligand binding residues challenge. In this study, we selected Zn2+, Cu2+, Fe2+, Fe3+, Co2+, Mn2+, Ca2+ and Mg2+ from BioLip database as research objects. Based on amino acids, physicochemical properties predicted structural information, introduced disorder value feature parameter. addition, based component position weight matrix...

Abstract Ferroptosis, a newly discovered irondependent form of regulated cell death caused by excessive accumulation lipid peroxides, is linked to the development and treatment response various types cancer, including gastric cancer (GC). Noncoding RNAs (ncRNAs), as key regulators in have both oncogenic tumor suppressive roles. However, studies on ferroptosis-related ncRNA networks GC are still lacking. Here, we first identified 61 differentially expressed genes associated with ferroptosis...

Spatial Transcriptomics leverages gene expression profiling while preserving spatial location and histological images. However, processing the vast noisy image data in transcriptomics (ST) for precise recognition of domains remains a challenge. In this study, we propose method EfNST recognizing domains, which employs an efficient composite scaling network EfficientNet to learn multi-scale features. Compared with other relevant algorithms on six sets from three sequencing platforms, exhibits...

Immune clone selection algorithm (ICSA) and the multi-user detection based on ICSA are studied. Similar to evolutionary algorithms, is an efficient tool in searching for global optimum representation of solutions as binary code. It shows better potential capability solve optimization problem than evolution algorithm. Two novel detectors presented which basic detector hybrid with multi-stage (ICSA-MSD-MUD). For ICSA-MSD-MUD, MSD considered operator inside The can reach excellent performance...

The realization of many protein functions is inseparable from the interaction with ligands; in particular, combination and metal ion ligands performs an important biological function. Currently, it a challenging work to identify ligand-binding residues accurately by computational approaches. In this study, we proposed improved method predict binding 10 (Zn2+, Cu2+, Fe2+, Fe3+, Co2+, Mn2+, Ca2+, Mg2+, Na+, K+). Based on basic feature parameters amino acids, physicochemical predicted...

Abstract Background Alkaline earth metal ions are important protein binding ligands in human body, and it is of great significance to predict their residues. Results In this paper, Mg 2+ Ca taken as the research objects. Based on characteristic parameters sequences, amino acids, physicochemical characteristics acids predicted structural information, deep neural network algorithm used sites proteins. By optimizing hyper-parameters learning algorithm, prediction results by fivefold...

Recently, it has been shown in the literature that a relaying network utilizing multiple relay precoding techniques, signal-to-noise ratio (SNR) at each destination node will scale linearly with number of relays K, which is referred to as distributed array gain (DAG) K. In this paper, we focus on performance based limited channel state information (CSI) feedback, different from prior studies assume perfect CSI nodes. Our analysis shows conventional feedback scheme fails obtain DAG...