Anticancer peptides (ACPs) have been emerged as a potential safe therapeutic agent for treating cancer. Identifying novel ACPs is crucial for understanding deep insight their functional mechanisms ...and vaccine production. Conventional wet-lab technological methods for finding ACPs are overpriced, slow, and resource-intensive. Thus, fast and accurate ACPs prediction through computational approach is highly desired because of massive peptide sequences accumulated in the post-genomic era. Recently, several intelligent statistical approaches have been designed for discriminating ACPs from non-ACPs. Although remarkable achievements have been accomplished, available methods still have inadequate feature descriptors and learning algorithms, thereby restricting the predictive performance. To address this, we develop a novel predictor called Stack-ACPred for the correct identification of ACPs. More specifically, the proposed method possesses three nominal feature encoding strategies i.e., evolutionary-profile and physicochemical information as segmented position-specific scoring matrix (SegPSSM), pseudo (PsePSSM), and extended pseudo amino acid composition (PseAAC). The extracted features are serially fused and further optimized through a powerful support vector machine recursive feature elimination and correlation bias reduction (SVM-RFE + CBR) algorithm. The optimal selected attributes are provided to build the stacking-base ensemble model for targeting effective ACPs. The proposed StackACPred attained 84.45% and 86.21% accuracy based on ACP740 and ACP240 datasets with 5-fold cross-validation test, which was 2.97% and 0.79% higher than other existing studies, respectively. The empirical outcomes of our developed automated tool demonstrate the excellent discriminative power for annotating large scale ACPs in particular and other peptides in general.
•We developed an intelligent predictor named StackACPred for correct identification of ACPs.•Three nominal feature encoding strategies on the bases of evolutionary-profile and physicochemical information as: N-Segmentation position-specific scoring matrix (N-SegPSSM), pseudo (PsePSSM), and extended pseudo amino acid composition (PseAAC).•Powerful support vector machine recursive feature elimination and correlation bias reduction (SVM-RFE + CBR) algorithm was used to select the optimal features.•LightGMB and stacking-base ensemble classifiers were used for predicting ACPs with k-fold cross-validation test.•StackACPred produced better results than others state-of-the-art predictors.
RNA 5-methylcytosine (m5C) is an important post-transcriptional modification that plays an indispensable role in biological processes. The accurate identification of m5C sites from primary RNA ...sequences is especially useful for deeply understanding the mechanisms and functions of m5C. Due to the difficulty and expensive costs of identifying m5C sites with wet-lab techniques, developing fast and accurate machine-learning-based prediction methods is urgently needed. In this study, we proposed a new m5C site predictor, called M5C-HPCR, by introducing a novel heuristic nucleotide physicochemical property reduction (HPCR) algorithm and classifier ensemble. HPCR extracts multiple reducts of physical-chemical properties for encoding discriminative features, while the classifier ensemble is applied to integrate multiple base predictors, each of which is trained based on a separate reduct of the physical-chemical properties obtained from HPCR. Rigorous jackknife tests on two benchmark datasets demonstrate that M5C-HPCR outperforms state-of-the-art m5C site predictors, with the highest values of MCC (0.859) and AUC (0.962). We also implemented the webserver of M5C-HPCR, which is freely available at http://cslab.just.edu.cn:8080/M5C-HPCR/.
The role of antithymocyte globulin (ATG) in preventing acute graft-versus-host disease (aGVHD) after HLA-matched sibling donor transplantation (MSDT) is still controversial.
We performed a ...prospective, multicenter, open-label, randomized controlled trial (RCT) across 23 transplantation centers in China. Patients ages 40-60 years with standard-risk hematologic malignancies with an HLA-matched sibling donor were randomly assigned to an ATG group (4.5 mg/kg thymoglobulin plus cyclosporine CsA, methotrexate MTX, and mycophenolate mofetil MMF) and a control group (CsA, MTX, and MMF). The primary end point of this study was grade 2-4 aGVHD on day 100.
From November 2013 to April 2018, 263 patients were enrolled. The cumulative incidence rate of grade 2-4 aGVHD was significantly reduced in the ATG group (13.7%; 95% CI, 13.5% to 13.9%) compared with the control group (27.0%; 95% CI, 26.7% to 27.3%;
= .007). The ATG group had significantly lower incidences of 2-year overall chronic GVHD (27.9% 95% CI, 27.6% to 28.2%
52.5% 95% CI, 52.1% to 52.9%;
< .001) and 2-year extensive chronic GVHD (8.5% 95% CI, 8.4% to 8.6%
23.2% 95% CI, 22.9% to 23.5%;
= .029) than the control group. There were no differences between the ATG and control groups with regard to cytomegalovirus reactivation, Epstein-Barr virus reactivation, 3-year nonrelapse mortality (NRM), 3-year cumulative incidence of relapse (CIR), 3-year overall survival, or 3-year leukemia-free survival. Three-year GVHD relapse-free survival was significantly improved in the ATG group (38.7%; 95% CI, 29.9% to 47.5%) compared with the control group (24.5%; 95% CI, 16.9% to 32.1%;
= .003).
Our study is the first prospective RCT in our knowledge to demonstrate that ATG can effectively decrease the incidence of aGVHD after MSDT in the CsA era without affecting the CIR or NRM.
Abstract
The recent advances of single-cell RNA sequencing (scRNA-seq) have enabled reliable profiling of gene expression at the single-cell level, providing opportunities for accurate inference of ...gene regulatory networks (GRNs) on scRNA-seq data. Most methods for inferring GRNs suffer from the inability to eliminate transitive interactions or necessitate expensive computational resources. To address these, we present a novel method, termed GMFGRN, for accurate graph neural network (GNN)-based GRN inference from scRNA-seq data. GMFGRN employs GNN for matrix factorization and learns representative embeddings for genes. For transcription factor–gene pairs, it utilizes the learned embeddings to determine whether they interact with each other. The extensive suite of benchmarking experiments encompassing eight static scRNA-seq datasets alongside several state-of-the-art methods demonstrated mean improvements of 1.9 and 2.5% over the runner-up in area under the receiver operating characteristic curve (AUROC) and area under the precision–recall curve (AUPRC). In addition, across four time-series datasets, maximum enhancements of 2.4 and 1.3% in AUROC and AUPRC were observed in comparison to the runner-up. Moreover, GMFGRN requires significantly less training time and memory consumption, with time and memory consumed <10% compared to the second-best method. These findings underscore the substantial potential of GMFGRN in the inference of GRNs. It is publicly available at https://github.com/Lishuoyy/GMFGRN.
Application of a molecular catalyst in artificial photosynthesis is confronted with challenges such as rapid deactivation due to photodegradation or detrimental aggregation in harsh conditions. In ...this work, a metal–organic cage Pd6(RuL3)828+ (MOC-16), characteristic of a photochemical molecular device (PMD) concurrently integrating eight Ru2+ light-harvesting centers and six Pd2+ catalytic centers for efficient homogeneous H2 production, is successfully heterogenized through incorporation into a metal–organic framework (MOF) of ZIF-8 and then transformed into a carbonate matrix of Zn x (MeIm) x (CO3) x (CZIF), leading to hybridized MOC-16@CZIF. This MOC@MOF integrated photocatalyst inherits a highly efficient and directional electron transfer in the picosecond domain of MOC-16 and possesses one order increased microsecond magnitude of the triplet excited-state electron in comparison to that of the primitive MOC-16. The carbonate CZIF matrix endows MOC-16@CZIF with water wettability, serving as a proton relay to facilitate proton delivery by virtue of H2O as proton carriers. Electron transfer during the photocatalytic process is also enhanced by infiltration of a sacrificial agent of BIH into the CZIF matrix to promote conductivity, owing to its strong reducing ability to induce free charge carriers. These synergistic effects contribute to the extra high activity for H2 generation, making the turnover frequency of this heterogeneous MOC-16@CZIF photocatalyst maintain a level of ∼0.4 H2·s–1, increased by 50-fold over that of a homogeneous PMD. Meanwhile, it is robust enough to tolerate harsh reaction conditions, presenting an unprecedented heterogenization example of homogeneous PMD with a MOF-derived matrix to mimic catalytic features of a natural photosystem, which may shed light on the design of multifunctional PMD@MOF materials to expand the number of molecular catalysts for practical application in artificial photosynthesis.
Nonsynonymous single-nucleotide polymorphisms (nsSNPs), implicated in over 6000 diseases, necessitate accurate prediction for expedited drug discovery and improved disease diagnosis. In this study, ...we propose FCMSTrans, a novel nsSNP predictor that innovatively combines the transformer framework and multiscale modules for comprehensive feature extraction. The distinctive attribute of FCMSTrans resides in a deep feature combination strategy. This strategy amalgamates evolutionary-scale modeling (ESM) and ProtTrans (PT) features, providing an understanding of protein biochemical properties, and position-specific scoring matrix, secondary structure, predicted relative solvent accessibility, and predicted disorder (PSPP) features, which are derived from four protein sequences and structure-oriented characteristics. This feature combination offers a comprehensive view of the molecular dynamics involving nsSNPs. Our model employs the transformer’s self-attention mechanisms across multiple layers, extracting higher-level and abstract representations. Simultaneously, varied-level features are captured by multiscale convolutions, enriching feature abstraction at multiple echelons. Our comparative analyses with existing methodologies highlight significant improvements made possible by the integrated feature fusion approach adopted in FCMSTrans. This is further substantiated by performance assessments based on diverse data sets, such as PredictSNP, MMP, and PMD, with areas under the curve (AUCs) of 0.869, 0.819, and 0.693, respectively. Furthermore, FCMSTrans shows robustness and superiority by outperforming the current best predictor, PROVEAN, in a blind test conducted on a third-party data set, achieving an impressive AUC score of 0.7838. The Python code of FCMSTrans is available at https://github.com/gc212/FCMSTrans for academic usage.
DNase I Hypersensitive sites (DHS) are the regions that are sensitive to cleavage by the DNase I enzyme. Knowledge regarding these sites is helpful for decryption of the functions of non-coding ...genomic regions. Various biological processes need its intervention. Traditional techniques are laborious and time-consuming to predict DHS sites. Particularly, with the avalanche of DNA sequences generated in the post-genomic era, the development of computational approaches is highly essential to precisely and timely predict DHS sites in DNA sequences. The existing feature encoding schemes such as pseudo dinucleotide composition, pseudo trinucleotide composition etc. cannot effectively express features from DHS sequences. In the current study, we proposed a new computational technique to predict DHS sites which uses Un-biased Pseudo Trinucleotide Composition (Unb-PseTNC) strategy to extract nominal descriptors from the DHS benchmark dataset and avoid biasness among the classes during the classification phase. Several classification algorithm including Support vector machine (SVM), probabilistic neural network and k-nearest neighbor are employed to classify extracted features. It was observed that SVM in conjunction with Unb-PseTNC outperforms other techniques. By comparing with other existing predictors, it was perceived that our proposed method achieved higher prediction rates by applying rigorous jackknife test. This indicates that the proposed model will become a useful tool to predict DHS sites and can also be utilized for in-depth study of DNA and genome analysis.
•A new computational model was established for prediction of DHS sites.•The method used three nominal feature extraction methods called PseDNC, PseTNC and Un-PseTNC.•Classification engines like SVM, PNN and KNN were utilized for classification.•Jackknife cross-validation test was used.•Proposed method produced improved performance than the state-of-art methods.
Accurate identification of protein–DNA binding sites is significant for both understanding protein function and drug design. Machine-learning-based methods have been extensively used for the ...prediction of protein–DNA binding sites. However, the data imbalance problem, in which the number of nonbinding residues (negative-class samples) is far larger than that of binding residues (positive-class samples), seriously restricts the performance improvements of machine-learning-based predictors. In this work, we designed a two-stage imbalanced learning algorithm, called ensembled hyperplane-distance-based support vector machines (E-HDSVM), to improve the prediction performance of protein–DNA binding sites. The first stage of E-HDSVM designs a new iterative sampling algorithm, called hyperplane-distance-based under-sampling (HD-US), to extract multiple subsets from the original imbalanced data set, each of which is used to train a support vector machine (SVM). Unlike traditional sampling algorithms, HD-US selects samples by calculating the distances between the samples and the separating hyperplane of the SVM. The second stage of E-HDSVM proposes an enhanced AdaBoost (EAdaBoost) algorithm to ensemble multiple trained SVMs. As an enhanced version of the original AdaBoost algorithm, EAdaBoost overcomes the overfitting problem. Stringent cross-validation and independent tests on benchmark data sets demonstrated the superiority of E-HDSVM over several popular imbalanced learning algorithms. Based on the proposed E-HDSVM algorithm, we further implemented a sequence-based protein–DNA binding site predictor, called DNAPred, which is freely available at http://csbio.njust.edu.cn/bioinf/dnapred/ for academic use. The computational experimental results showed that our predictor achieved an average overall accuracy of 91.7% and a Mathew’s correlation coefficient of 0.395 on five benchmark data sets and outperformed several state-of-the-art sequence-based protein–DNA binding site predictors.
Abstract
The determination of the absolute and relative position of a spacecraft is critical for its operation, observations, data analysis, scientific studies, as well as deep-space exploration in ...general. A spacecraft that can determine its own absolute position autonomously may perform better than those that must rely on transmission solutions. In this work, we report an absolute navigation accuracy of ∼20 km using 16 day Crab pulsar data observed with Fermi’s Gamma-ray Burst Monitor (GBM). In addition, we propose a new method with the inverse process of the triangulation for joint navigation using repeated bursts like those from the magnetar SGR J1935+2154 observed by the Gravitational-wave High-energy Electromagnetic Counterpart All-sky Monitor and GBM.
The quickly increasing size of the Protein Data Bank is challenging biologists to develop a more scalable protein structure alignment tool for fast structure database search. Although many protein ...structure search algorithms and programs have been designed and implemented for this purpose, most require a large amount of computational time. We propose a novel protein structure search approach, TM-search, which is based on the pairwise structure alignment program TM-align and a new iterative clustering algorithm. Benchmark tests demonstrate that TM-search is 27 times faster than a TM-align full database search while still being able to identify ∼90% of all high TM-score hits, which is 2–10 times more than other existing programs such as Foldseek, Dali, and PSI-BLAST.