Integration of multi-omics data using adaptive graph learning and attention mechanism for patient classification and biomarker identification

NNBGWO-BRCA marker: Neural Network and binary grey wolf optimization based Breast cancer biomarker discovery framework using multi-omics dataset

BACKGROUND AND OBJECTIVE

Breast cancer is a multifaceted condition characterized by diverse features and a substantial mortality rate, underscoring the imperative for timely detection and intervention. The utilization of multi-omics data has gained significant traction in recent years to identify biomarkers and classify subtypes in breast cancer. This kind of research idea from part to whole will also be an inevitable trend in future life science research. Deep learning can integrate and analyze multi-omics data to predict cancer subtypes, which can further drive targeted therapies. However, there are few articles leveraging the nature of deep learning for feature selection. Therefore, this paper proposes a Neural Network and Binary grey Wolf Optimization based BReast CAncer bioMarker (NNBGWO-BRCAMarker) discovery framework using multi-omics data to obtain a series of biomarkers for precise classification of breast cancer subtypes.

METHODS

NNBGWO-BRCAMarker consists of two phases: in the first phase, relevant genes are selected using the weights obtained from a trained feedforward neural network; in the second phase, the binary grey wolf optimization algorithm is leveraged to further screen the selected genes, resulting in a set of potential breast cancer biomarkers.

RESULTS

The SVM classifier with RBF kernel achieved a classification accuracy of 0.9242 ± 0.03 when trained using the 80 biomarkers identified by NNBGWO-BRCAMarker, as evidenced by the experimental results. We conducted a comprehensive gene set analysis, prognostic analysis, and druggability analysis, unveiling 25 druggable genes, 16 enriched pathways strongly linked to specific subtypes of breast cancer, and 8 genes linked to prognostic outcomes.

CONCLUSIONS

The proposed framework successfully identified 80 biomarkers from the multi-omics data, enabling accurate classification of breast cancer subtypes. This discovery may offer novel insights for clinicians to pursue in further studies.

Deep pan-cancer analysis and multi-omics evidence reveal that ALG3 inhibits CD8+ T cell infiltration by suppressing chemokine secretion and is associated with 5-fluorouracil sensitivity

BACKGROUND

α-1,3-mannosyltransferase (ALG3) holds significance as a key member within the mannosyltransferase family. Nevertheless, the exact function of ALG3 in cancer remains ambiguous. Consequently, the current research aimed to examine the function and potential mechanisms of ALG3 in various types of cancer.

METHODS

Deep pan-cancer analyses were conducted to investigate the expression patterns, prognostic value, genetic variations, single-cell omics, immunology, and drug responses associated with ALG3. Subsequently, in vitro experiments were executed to ascertain the biological role of ALG3 in breast cancer. Moreover, the link between ALG3 and CD8+ T cells was verified using immunofluorescence. Lastly, the association between ALG3 and chemokines was assessed using qRT-PCR and ELISA.

RESULTS

Deep pan-cancer analysis demonstrated a heightened expression of ALG3 in the majority of tumors based on multi-omics evidence. ALG3 emerges as a diagnostic and prognostic biomarker across diverse cancer types. In addition, ALG3 participates in regulating the tumor immune microenvironment. Elevated levels of ALG3 were closely linked to the infiltration of bone marrow-derived suppressor cells (MDSC) and CD8+ T cells. According to in vitro experiments, ALG3 promotes proliferation and migration of breast cancer cells. Moreover, ALG3 inhibited CD8+ T cell infiltration by suppressing chemokine secretion. Finally, the inhibition of ALG3 enhanced the responsiveness of breast cancer cells to 5-fluorouracil treatment.

CONCLUSION

ALG3 shows potential as both a prognostic indicator and immune infiltration biomarker across various types of cancer. Inhibition of ALG3 may represent a promising therapeutic strategy for tumor treatment.

Omics data classification using constitutive artificial neural network optimized with single candidate optimizer

Recent technical advancements enable omics-based biological study of molecules with very high throughput and low cost, such as genomic, proteomic, and microbionics'. To overcome this drawback, Omics Data Classification using Constitutive Artificial Neural Network Optimized with Single Candidate Optimizer (ODC-ZOA-CANN-SCO) is proposed in this manuscript. The input data is pre-processing by using Adaptive variational Bayesian filtering (AVBF) to replace missing values. The pre-processing data is fed to Zebra Optimization Algorithm (ZOA) for dimensionality reduction. Then, the Constitutive Artificial Neural Network (CANN) is employed to classify omics data. The weight parameter is optimized by Single Candidate Optimizer (SCO). The proposed ODC-ZOA-CANN-SCO method attains 25.36%, 21.04%, 22.18%, 26.90%, and 28.12% higher accuracy when analysed to the existing methods like multi-omics data integration utilizing adaptive graph learning and attention mode for patient categorization with biomarker identification (MOD-AGL-AM-PABI), deep learning method depending upon multi-omics data integration to create risk stratification prediction mode for skin cutaneous melanoma (DL-MODI-RSP-SCM), Deep belief network-base model for identifying Alzheimer's disease utilizing multi-omics data (DDN-DAD-MOD), hybrid cancer prediction depending upon multi-omics data and reinforcement learning state action reward state action (HCP-MOD-RL-SARSA), machine learning basis method under omics data including biological knowledge database for cancer clinical endpoint prediction (ML-ODBKD-CCEP) methods, respectively.

Selenium Decipher: Trapping of Native Selenomethionine-Containing Peptides in Selenium-Enriched Milk and Unveiling the Deterioration after Ultrahigh-Temperature Treatment

Selenopeptide identification relies on databases to interpret the selenopeptide spectra. A common database search strategy is to set selenium as a variable modification instead of sulfur on peptides. However, this approach generally detects only a fraction of selenopeptides. An alternative approach, termed Selenium Decipher, is proposed in the present study. It involves identifying collision-induced dissociation-cleavable selenomethionine-containing peptides by iteratively matching the masses of seleno-amino acids in selenopeptide spectra. This approach uses variable-data-independent acquisition (vDIA) for peptide detection, providing a flexible and customizable window for secondary mass spectral fragmentation. The attention mechanism was used to capture global information on peptides and determine selenomethionine-containing peptide backbones. The core structure of selenium on selenomethionine-containing peptides generates a series of fragment ions, namely, C3H7Se+, C4H10NSe+, C5H7OSe+, C5H8NOSe+, and C7H11N2O2Se+, with known mass gaps during higher-energy collisional dissociation (HCD) fragmentation. De-selenium spectra are generated by removing selenium originating from selenium replacement and then reassigning the precursors to peptides. Selenium-enriched milk is obtained by feeding selenium-rich forage fed to cattle, which leads to the formation of native selenium through biotransformation. A novel antihypertensive selenopeptide Thr-Asp-Asp-Ile-SeMet-Cys-Val-Lys TDDI(Se)MCVK was identified from selenium-enriched milk. The selenopeptide (IC50 = 60.71 μM) is bound to four active residues of the angiotensin-converting enzyme (ACE) active pocket (Ala354, Tyr523, His353, and His513) and two active residues of zinc ligand (His387 and Glu411) and exerted a competitive inhibitory effect on the spatial blocking of active sites. The integration of vDIA and the iteratively matched seleno-amino acids was applied for Selenium Decipher, which provides high validity for selenomethionine-containing peptide identification.