HMD-AMP: Protein Language-Powered Hierarchical Multi-label Deep Forest for Annotating Antimicrobial Peptides

Identifying the targets of an antimicrobial peptide is a fundamental step in studying the innate immuneresponse and combating antibiotic resistance, and more broadly, precision medicine and public health. Therehave been extensive studies on the statistical and computational approaches to identify (i) whether a peptide is anantimicrobial peptide (AMP) or a non-AMP and (ii) which targets are these sequences effective to (Gram-positive,Gram-negative, etc.). Despite the existing deep learning methods on this problem, most of them are unable tohandle the small AMP classes (anti-insect, anti-parasite, etc.). And more importantly, some AMPs can havemultiple targets, which the previous methods fail to consider. In this study, we build a diverse and comprehensivemulti-label protein sequence database by collecting and cleaning amino acids from various AMP databases.To generate efficient representations and features for the small classes dataset, we take advantage of a proteinlanguage model trained on 250 million protein sequences. Based on that, we develop an end-to-end hierarchicalmulti-label deep forest framework, HMD-AMP, to annotate AMP comprehensively. After identifying an AMP, itfurther predicts what targets the AMP can effectively kill from eleven available classes. Extensive experimentssuggest that our framework outperforms state-of-the-art models in both the binary classification task and themulti-label classification task, especially on the minor classes. Compared with the previous deep learning methods,our method improves the performance on macro-AUROC by 11%. The model is robust against reduced featuresand small perturbations and produces promising results. We believe HMD-AMP contribute to both the future wet-lab investigations of the innate structural properties of different antimicrobial peptides and build promising empirical underpinnings for precise medicine with antibiotics.

MAC30 Knockdown Inhibits Proliferation and Enhance Apoptosis of Gastric Cancer by Suppressing Wnt/β-Cateninsignaling Pathway

Gastric cancer is one of the most frequently diagnosed cancer and poses a serious threat to health system in the world. Upregulation of meningioma-associated protein (MAC30) has been found in many solid tumors and can regulate the proliferation, differentiation, and apoptosis of different tumor cells. Quantitative polymerase chain reaction (qPCR) was used to detect the expression of MAC30 in 68 patients with gastric cancer and their adjacent tissues. Lentiviral vector pGCSIL-shMAC30-GFP of the RNA interference (RNAi) of the MAC30 gene was transfected into gastric cancer BGC-823 cell line and the expression of lentivirus label protein GFP was observed via fluorescence microscope, while cell proliferation and apoptosis were determined with flow cytometry and MTT assay, respectively. Also, related protein expressions on Wnt/β-catenin signaling pathway were analyzed by Western blot method. The expression of MAC30 was abnormally elevated in gastric cancer tissues, while interfering of its expression could significantly inhibit the proliferation of gastric cancer BGC-823 cell line. However, the promotion of apoptosis by mitochondrial pathway was mediated by Bax/Bcl-2 upregulation. Present work showed the effect of downregulated MAC30 expression on proliferation and apoptosis of gastric cancer cell through Wnt/β-catenin signaling pathway. Thus, this investigation provides an experimental basis for future development of chemotherapeutic agent on gastric cancer.

DMLDA-LocLIFT: Identification of multi-label protein subcellular localization using DMLDA dimensionality reduction and LIFT classifier

ABSTRACTBackgroundMulti-label proteins occur in two or more subcellular locations, which play a vital part in cell development and metabolism. Prediction and analysis of multi-label subcellular localization (SCL) can present new angle with drug target identification and new drug design. However, the prediction of multi-label protein SCL using biological experiments is expensive and labor-intensive. Therefore, predicting large-scale SCL with machine learning methods has turned into a hot study topic in bioinformatics.MethodsIn this study, a novel multi-label learning means for protein SCL prediction, called DMLDA-LocLIFT, is proposed. Firstly, the dipeptide composition, encoding based on grouped weight, pseudo amino acid composition, gene ontology and pseudo position specific scoring matrix are employed to encode subcellular protein sequences. Then, direct multi-label linear discriminant analysis (DMLDA) is used to reduce the dimension of the fused feature vector. Lastly, the optimal feature vectors are input into the multi-label learning with Label-specIfic FeaTures (LIFT) classifier to predict the location of multi-label proteins.ResultsThe jackknife test showed that the overall actual accuracy on Gram-negative bacteria, Gram-positive bacteria, and plant datasets are 98.60%, 99.60%, and 97.90% respectively, which are obviously better than other state-of-the-art prediction methods.ConclusionThe proposed model can effectively predict SCL of multi-label proteins and provide references for experimental identification of SCL. The source codes and data are publicly available at https://github.com/QUST-AIBBDRC/DMLDA-LocLIFT/.

CRISPR-Tag: an Efficient DNA Tagging System in Living Cells

Main textA lack of efficient tools to image non-repetitive genes in living cells has limited our ability to explore the functional impact of spatiotemporal dynamics of genes. Here, we addressed this issue by developing the CRISPR-Tag system as a new DNA tagging strategy to label protein-coding genes with high signal-to-noise ratio under wild-field fluorescence microscopy by using 1 to 4 highly active sgRNAs. The CRISPR-Tag, with minimal size of ∼ 250 bp, represents an easily and broadly applicable technique to study spatiotemporal organization of genomic elements in living cells.