Search

In this editorial, we summarize the 2023 International Conference on Intelligent Biology and Medicine (ICIBM 2023) conference which was held on July 16–19, 2023 in Tampa, Florida, USA. We then briefly describe the nine research articles included in this special issue. ICIBM 2023 scientific program included four tutorials and workshops, four keynote lectures, four eminent scholars’ presentations, 11 concurrent scientific sessions, and a poster session. We had total of 88 scientific oral presentations, including 62 regular oral presentations and 26 flash talks, as well as 46 poster presentations. The topics of these presentations covered artificial intelligence (AI), data sciences, bioinformatics, computational biology, genomics, biomedical informatics, among others. This special issue included nine peer reviewed manuscripts selected from those submitted to our conference. These articles cover a range of topics on the methods and applications of ML and AI models in the biomedical domain.

Abstract Advances in mass spectrometry accelerates the characterization of HLA ligandome, necessitating the development of efficient methods for immunopeptidomics analysis and (neo)antigen prediction. We develop ImmuneApp, an interpretable deep learning framework trained on extensive HLA ligand datasets, which improves the prediction of HLA-I epitopes, prioritizes neoepitopes, and enhances immunopeptidomics deconvolution. ImmuneApp extracts informative embeddings and identifies key residues for pHLA binding. We also present a more accurate model-based deconvolution approach and systematically analyzed 216 multi-allelic immunopeptidomics samples, identifying 835,551 ligands restricted to over 100 HLA-I alleles. Our investigation reveals the effectiveness of the composite model, denoted as ImmuneApp-MA, which integrates mono- and multi-allelic data to enhance predictive performance. Leveraging ImmuneApp-MA as a pre-trained model, we built ImmuneApp-Neo, an immunogenicity predictor that outperforms existing methods for prioritizing immunogenic neoepitope. ImmuneApp demonstrates its utility across various immunopeptidomics datasets, which will promote the discovery of novel neoantigens and the development of new immunotherapies.

Abstract Advanced pancreatic ductal adenocarcinomas (PDACs) respond poorly to all therapies, including the first-line treatment, chemotherapy, the latest immunotherapies, and KRAS-targeting therapies. Despite an enormous effort to improve therapeutic efficacy in late-stage PDAC patients, effective treatment modalities remain an unmet medical challenge. To change the status quo, we explored the key signaling networks underlying the universally poor response of PDAC to therapy. Here, we report a previously unknown chemo-induced symbiotic signaling circuit that adaptively confers chemoresistance in patients and mice with advanced PDAC. By integrating single-cell transcriptomic data from PDAC mouse models and clinical pathological information from PDAC patients, we identified Yap1 in cancer cells and Cox2 in stromal fibroblasts as two key nodes in this signaling circuit. Co-targeting Yap1 in cancer cells and Cox2 in stroma sensitized PDAC to Gemcitabine treatment and dramatically prolonged survival of mice bearing late-stage PDAC, whereas simultaneously inhibiting Yap1 and Cox2 only in cancer cells was ineffective. Mechanistically, chemotherapy triggers non-canonical Yap1 activation by nemo-like kinase in 14-3-3ζ-overexpressing PDAC cells and increases secretion of CXCL2/5, which bind to CXCR2 on fibroblasts to induce Cox2 and PGE2 expression, which reciprocally facilitate PDAC cell survival. Finally, analyses of PDAC patient data revealed that patients who received Statins, which inhibit Yap1 signaling, and Cox2 inhibitors (including Aspirin) while receiving Gemcitabine displayed markedly prolonged survival compared to others. The robust anti-tumor efficacy of Statins and Aspirin, which co-target the chemo-induced adaptive circuit in the tumor cells and stroma, signifies a unique therapeutic strategy for PDAC.

Abstract Purpose Liver disease causes two million deaths annually, accounting for 4% of all deaths globally. Prediction or early detection of the disease via machine learning algorithms on large clinical data have become promising and potentially powerful, but such methods often have some limitations due to the complexity of the data. In this regard, ensemble learning has shown promising results. There is an urgent need to evaluate different algorithms and then suggest a robust ensemble algorithm in liver disease prediction. Method Three ensemble approaches with nine algorithms are evaluated on a large dataset of liver patients comprising 30,691 samples with 11 features. Various preprocessing procedures are utilized to feed the proposed model with better quality data, in addition to the appropriate tuning of hyperparameters and selection of features. Results The models’ performances with each algorithm are extensively evaluated with several positive and negative performance metrics along with runtime. Gradient boosting is found to have the overall best performance with 98.80% accuracy and 98.50% precision, recall and F1-score for each. Conclusions The proposed model with gradient boosting bettered in most metrics compared with several recent similar works, suggesting its efficacy in predicting liver disease. It can be further applied to predict other diseases with the commonality of predicate indicators.

Abstract Parkinson's disease (PD) is challenging for clinicians to accurately diagnose in the early stages. Quantitative measures of brain health can be obtained safely and non-invasively using medical imaging techniques like magnetic resonance imaging (MRI) and single photon emission computed tomography (SPECT). For accurate diagnosis of PD, powerful machine learning and deep learning models as well as the effectiveness of medical imaging tools for assessing neurological health are required. This study proposes four deep learning models with a hybrid model for the early detection of PD. For the simulation study, two standard datasets are chosen. Further to improve the performance of the models, grey wolf optimization (GWO) is used to automatically fine-tune the hyperparameters of the models. The GWO-VGG16, GWO-DenseNet, GWO-DenseNet + LSTM, GWO-InceptionV3 and GWO-VGG16 + InceptionV3 are applied to the T1,T2-weighted and SPECT DaTscan datasets. All the models performed well and obtained near or above 99% accuracy. The highest accuracy of 99.94% and AUC of 99.99% is achieved by the hybrid model (GWO-VGG16 + InceptionV3) for T1,T2-weighted dataset and 100% accuracy and 99.92% AUC is recorded for GWO-VGG16 + InceptionV3 models using SPECT DaTscan dataset.

Summary: Pancreatic cancer is associated with an oncogenic KRAS mutation in approximately 90% of cases. However, a non-negligible proportion of pancreatic cancer cases harbor wild-type KRAS (KRAS-WT). This study establishes genetically engineered mouse models that develop spontaneous pancreatic cancer in the context of KRAS-WT. The Trp53loxP/loxP;Smad4loxP/loxP;Pdx1-Cre (PPSSC) mouse model harbors KRAS-WT and loss of Trp53/Smad4. The Trp53loxP/loxP;Tgfbr2loxP/loxP;Pdx1-Cre (PPTTC) mouse model harbors KRAS-WT and loss of Trp53/Tgfbr2. We identify that either Trp53/Smad4 loss or Trp53/Tgfbr2 loss can induce spontaneous pancreatic tumor formation in the absence of an oncogenic KRAS mutation. The Trp53/Smad4 loss and Trp53/Tgfbr2 loss mouse models exhibit distinct pancreatic tumor histological features, as compared to oncogenic KRAS-driven mouse models. Furthermore, KRAS-WT pancreatic tumors with Trp53/Smad4 loss reveal unique histological features of pancreatic adenosquamous carcinoma (PASC). Single-cell RNA sequencing (scRNA-seq) analysis reveals the distinct tumor immune microenvironment landscape of KRAS-WT (PPSSC) pancreatic tumors as compared with that of oncogenic KRAS-driven pancreatic tumors.

Abstract Background Lung cancer is the second most common cancer worldwide, with over two million new cases per year. Early identification would allow healthcare practitioners to handle it more effectively. The advancement of computer-aided detection systems significantly impacted clinical analysis and decision-making on human disease. Towards this, machine learning and deep learning techniques are successfully being applied. Due to several advantages, transfer learning has become popular for disease detection based on image data. Methods In this work, we build a novel transfer learning model (VER-Net) by stacking three different transfer learning models to detect lung cancer using lung CT scan images. The model is trained to map the CT scan images with four lung cancer classes. Various measures, such as image preprocessing, data augmentation, and hyperparameter tuning, are taken to improve the efficacy of VER-Net. All the models are trained and evaluated using multiclass classifications chest CT images. Results The experimental results confirm that VER-Net outperformed the other eight transfer learning models compared with. VER-Net scored 91%, 92%, 91%, and 91.3% when tested for accuracy, precision, recall, and F1-score, respectively. Compared to the state-of-the-art, VER-Net has better accuracy. Conclusion VER-Net is not only effectively used for lung cancer detection but may also be useful for other diseases for which CT scan images are available.

Summary: Orofacial clefts (OFCs) are among the most common human congenital birth defects. Previous multiethnic studies have identified dozens of associated loci for both cleft lip with or without cleft palate (CL/P) and cleft palate alone (CP). Although several nearby genes have been highlighted, the “casual” variants are largely unknown. Here, we developed DeepFace, a convolutional neural network model, to assess the functional impact of variants by SNP activity difference (SAD) scores. The DeepFace model is trained with 204 epigenomic assays from crucial human embryonic craniofacial developmental stages of post-conception week (pcw) 4 to pcw 10. The Pearson correlation coefficient between the predicted and actual values for 12 epigenetic features achieved a median range of 0.50–0.83. Specifically, our model revealed that SNPs significantly associated with OFCs tended to exhibit higher SAD scores across various variant categories compared to less related groups, indicating a context-specific impact of OFC-related SNPs. Notably, we identified six SNPs with a significant linear relationship to SAD scores throughout developmental progression, suggesting that these SNPs could play a temporal regulatory role. Furthermore, our cell-type specificity analysis pinpointed the trophoblast cell as having the highest enrichment of risk signals associated with OFCs. Overall, DeepFace can harness distal regulatory signals from extensive epigenomic assays, offering new perspectives for prioritizing OFC variants using contextualized functional genomic features. We expect DeepFace to be instrumental in accessing and predicting the regulatory roles of variants associated with OFCs, and the model can be extended to study other complex diseases or traits.

Summary: Orofacial clefts (OFCs) are common congenital birth defects with various etiologies, including genetic variants. Online Mendelian Inheritance in Man (OMIM) annotated several hundred genes involving OFCs. Furthermore, several hundreds of de novo variants (DNVs) have been identified from individuals with OFCs. Some DNVs are related to known OFC genes or pathways, but there are still many DNVs whose relevance to OFC development is unknown. To explore novel gene functions and their cellular expression profiles, we focused on DNVs in genes that were not listed in OMIM. We collected 960 DNVs in 853 genes from published studies and curated these genes, based on the DNVs’ deleteriousness, into 230 and 23 genes related to cleft lip with or without cleft palate (CL/P) and cleft palate only (CPO), respectively. For comparison, we curated 178 CL/P and 277 CPO genes from OMIM. In CL/P, the pathways enriched in DNV and OMIM genes were significantly overlapped (p = 0.002). Single-cell RNA sequencing (scRNA-seq) analysis of mouse lip development revealed that both gene sets had abundant expression in the ectoderm (DNV genes: adjusted p = 0.032, OMIM genes: adjusted p

Summary: Circadian rhythms are internal biological rhythms driving temporal tissue-specific, metabolic programs. Loss of the circadian transcription factor BMAL1 in the paraventricular nucleus (PVN) of the hypothalamus reveals its importance in metabolic rhythms, but its functions in individual PVN cells are poorly understood. Here, loss of BMAL1 in the PVN results in arrhythmicity of processes controlling energy balance and alters peripheral diurnal gene expression. BMAL1 chromatin immunoprecipitation sequencing (ChIP-seq) and single-nucleus RNA sequencing (snRNA-seq) reveal its temporal regulation of target genes, including oxytocin (OXT), and restoring circulating OXT peaks in BMAL1-PVN knockout (KO) mice rescues absent activity rhythms. While glutamatergic neurons undergo day/night changes in expression of genes involved in cell morphogenesis, astrocytes and oligodendrocytes show gene expression changes in cytoskeletal organization and oxidative phosphorylation. Collectively, our findings show diurnal gene regulation in neuronal and non-neuronal PVN cells and that BMAL1 contributes to diurnal OXT secretion, which is important for systemic diurnal rhythms.

Abstract Brexucabtagene autoleucel CAR-T therapy is highly efficacious in overcoming resistance to Bruton’s tyrosine kinase inhibitors (BTKi) in mantle cell lymphoma. However, many patients relapse post CAR-T therapy with dismal outcomes. To dissect the underlying mechanisms of sequential resistance to BTKi and CAR-T therapy, we performed single-cell RNA sequencing analysis for 66 samples from 25 patients treated with BTKi and/or CAR-T therapy and conducted in-depth bioinformatics™ analysis. Our analysis revealed that MYC activity progressively increased with sequential resistance. HSP90AB1 (Heat shock protein 90 alpha family class B member 1), a MYC target, was identified as early driver of CAR-T resistance. CDK9 (Cyclin-dependent kinase 9), another MYC target, was significantly upregulated in Dual-R samples. Both HSP90AB1 and CDK9 expression were correlated with MYC activity levels. Pharmaceutical co-targeting of HSP90 and CDK9 synergistically diminished MYC activity, leading to potent anti-MCL activity. Collectively, our study revealed that HSP90-MYC-CDK9 network is the primary driving force of therapeutic resistance.

Abstract Background Recently, single-nucleus RNA-seq (snRNA-seq) analyses have revealed important cellular and functional features of Alzheimer's disease (AD), a prevalent neurodegenerative disease. However, our knowledge regarding intercellular communication mediated by dysregulated ligand-receptor (LR) interactions remains very limited in AD brains. Methods We systematically assessed the intercellular communication networks by using a discovery snRNA-seq dataset comprising 69,499 nuclei from 48 human postmortem prefrontal cortex (PFC) samples. We replicated the findings using an independent snRNA-seq dataset of 56,440 nuclei from 18 PFC samples. By integrating genetic signals from AD genome-wide association studies (GWAS) summary statistics and whole genome sequencing (WGS) data, we prioritized AD-associated Gene Ontology (GO) terms containing dysregulated LR interactions. We further explored drug repurposing for the prioritized LR pairs using the Therapeutic Targets Database. Results We identified 190 dysregulated LR interactions across six major cell types in AD PFC, of which 107 pairs were replicated. Among the replicated LR signals, we found globally downregulated communications in the astrocytes-to-neurons signaling axis, characterized, for instance, by the downregulation of APOE-related and Calmodulin (CALM)-related LR interactions and their potential regulatory connections to target genes. Pathway analyses revealed 44 GO terms significantly linked to AD, highlighting Biological Processes such as ‘amyloid precursor protein processing’ and ‘ion transmembrane transport,’ among others. We prioritized several drug repurposing candidates, such as cromoglicate, targeting the identified dysregulated LR pairs. Conclusions Our integrative analysis identified key dysregulated LR interactions in a cell type-specific manner and the associated GO terms in AD, offering novel insights into potential therapeutic targets involved in disrupted cell–cell communication in AD.

Abstract Perturbations in gene regulation during palatogenesis can lead to cleft palate, which is among the most common congenital birth defects. Here, we perform single-cell multiome sequencing and profile chromatin accessibility and gene expression simultaneously within the same cells (n = 36,154) isolated from mouse secondary palate across embryonic days (E) 12.5, E13.5, E14.0, and E14.5. We construct five trajectories representing continuous differentiation of cranial neural crest-derived multipotent cells into distinct lineages. By linking open chromatin signals to gene expression changes, we characterize the underlying lineage-determining transcription factors. In silico perturbation analysis identifies transcription factors SHOX2 and MEOX2 as important regulators of the development of the anterior and posterior palate, respectively. In conclusion, our study charts epigenetic and transcriptional dynamics in palatogenesis, serving as a valuable resource for further cleft palate research.

Abstract Breast cancer is one of the most common cancers in women and the second foremost cause of cancer death in women after lung cancer. Recent technological advances in breast cancer treatment offer hope to millions of women in the world. Segmentation of the breast’s Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) is one of the necessary tasks in the diagnosis and detection of breast cancer. Currently, a popular deep learning model, U-Net is extensively used in biomedical image segmentation. This article aims to advance the state of the art and conduct a more in-depth analysis with a focus on the use of various U-Net models in lesion detection in women’s breast DCE-MRI. In this article, we perform an empirical study of the effectiveness and efficiency of U-Net and its derived deep learning models including ResUNet, Dense UNet, DUNet, Attention U-Net, UNet++, MultiResUNet, RAUNet, Inception U-Net and U-Net GAN for lesion detection in breast DCE-MRI. All the models are applied to the benchmarked 100 Sagittal T2-Weighted fat-suppressed DCE-MRI slices of 20 patients and their performance is compared. Also, a comparative study has been conducted with V-Net, W-Net, and DeepLabV3+. Non-parametric statistical test Wilcoxon Signed Rank Test is used to analyze the significance of the quantitative results. Furthermore, Multi-Criteria Decision Analysis (MCDA) is used to evaluate overall performance focused on accuracy, precision, sensitivity, F $$_1$$ 1 -score, specificity, Geometric-Mean, DSC, and false-positive rate. The RAUNet segmentation model achieved a high accuracy of 99.76%, sensitivity of 85.04%, precision of 90.21%, and Dice Similarity Coefficient (DSC) of 85.04% whereas ResNet achieved 99.62% accuracy, 62.26% sensitivity, 99.56% precision, and 72.86% DSC. ResUNet is found to be the most effective model based on MCDA. On the other hand, U-Net GAN takes the least computational time to perform the segmentation task. Both quantitative and qualitative results demonstrate that the ResNet model performs better than other models in segmenting the images and lesion detection, though computational time in achieving the objectives varies.

Abstract Thyroid cancer is a life-threatening condition that arises from the cells of the thyroid gland located in the neck’s frontal region just below the adam’s apple. While it is not as prevalent as other types of cancer, it ranks prominently among the commonly observed cancers affecting the endocrine system. Machine learning has emerged as a valuable medical diagnostics tool specifically for detecting thyroid abnormalities. Feature selection is of vital importance in the field of machine learning as it serves to decrease the data dimensionality and concentrate on the most pertinent features. This process improves model performance, reduces training time, and enhances interpretability. This study examined binary variants of FOX-optimization algorithms for feature selection. The study employed eight transfer functions (S and V shape) to convert the FOX-optimization algorithms into their binary versions. The vision transformer-based pre-trained models (DeiT and Swin Transformer) are used for feature extraction. The extracted features are transformed using locally linear embedding, and binary FOX-optimization algorithms are applied for feature selection in conjunction with the Naïve Bayes classifier. The study utilized two datasets (ultrasound and histopathological) related to thyroid cancer images. The benchmarking is performed using the half-quadratic theory-based ensemble ranking technique. Two TOPSIS-based methods (H-TOPSIS and A-TOPSIS) are employed for initial model ranking, followed by an ensemble technique for final ranking. The problem is treated as multi-objective optimization task with accuracy, F2-score, AUC-ROC and feature space size as optimization goals. The binary FOX-optimization algorithm based on the $$V_1$$ V 1 transfer function achieved superior performance compared to other variants using both datasets as well as feature extraction techniques. The proposed framework comprised a Swin transformer to extract features, a Fox optimization algorithm with a V1 transfer function for feature selection, and a Naïve Bayes classifier and obtained the best performance for both datasets. The best model achieved an accuracy of 94.75%, an AUC-ROC value of 0.9848, an F2-Score of 0.9365, an inference time of 0.0353 seconds, and selected 5 features for the ultrasound dataset. For the histopathological dataset, the diagnosis model achieved an overall accuracy of 89.71%, an AUC-ROC score of 0.9329, an F2-Score of 0.8760, an inference time of 0.05141 seconds, and selected 12 features. The proposed model achieved results comparable to existing research with small features space.

Abstract This Supplement issue, presents five research articles which are distributed, mainly due to the subject they address, from the 8th International Work-Conference on Bioinformatics and Biomedical Engineering (IWBBIO 2020), which was held on line, during September, 30th–2nd October, 2020. These contributions have been chosen because of their quality and the importance of their findings. Those contributions were then invited to participate in this supplement for the following journals of BMC: BMC Bioinformatics and BMC Genomics. In the present Editorial in BMC journal, we summarize the contributions that provide a clear overview of the thematic areas covered by the IWBBIO conference, ranging from theoretical/review aspects to real-world applications of bioinformatic and biomedical engineering.

Abstract With advances in tissue engineering and bioelectronics, flexible electronic hydrogels that allow conformal tissue integration, online precision diagnosis, and simultaneous tissue regeneration are expected to be the next-generation platform for the treatment of myocardial infarction. Here, we report a functionalized polyaniline-based chronological adhesive hydrogel patch (CAHP) that achieves spatiotemporally selective and conformal embedded integration with a moist and dynamic epicardium surface. Significantly, CAHP has high adhesion toughness, rapid self-healing ability, and enhanced electrochemical performance, facilitating sensitive sensing of cardiac mechanophysiology-mediated microdeformations and simultaneous improvement of myocardial fibrosis-induced electrophysiology. As a result, the flexible CAHP platform monitors diastolic-systolic amplitude and rhythm in the infarcted myocardium online while effectively inhibiting ventricular remodeling, promoting vascular regeneration, and improving electrophysiological function through electrocoupling therapy. Therefore, this diagnostic and therapeutic integration provides a promising monitorable treatment protocol for cardiac disease.

Introduction: Frailty is the most common medical condition affecting the aging population, and its prevalence increases in the population aged 65 or more. Frailty is commonly diagnosed using the frailty index (FI) or frailty phenotype (FP) assessments. Observational studies have indicated the association of frailty with Alzheimer’s disease (AD). However, the shared genetic and biological mechanism of these comorbidity has not been studied.Methods: To assess the genetic relationship between AD and frailty, we examined it at single nucleotide polymorphism (SNP), gene, and pathway levels.Results: Overall, 16 genome-wide significant loci (15 unique loci) (pmeta-analysis < 5 × 10−8) and 22 genes (21 unique genes) were identified between AD and frailty using cross-trait meta-analysis. The 8 shared loci implicated 11 genes: CLRN1-AS1, CRHR1, FERMT2, GRK4, LINC01929, LRFN2, MADD, RP11-368P15.1, RP11-166N6.2, RNA5SP459, and ZNF652 between AD and FI, and 8 shared loci between AD and FFS implicated 11 genes: AFF3, C1QTNF4, CLEC16A, FAM180B, FBXL19, GRK4, LINC01104, MAD1L1, RGS12, ZDHHC5, and ZNF521. The loci 4p16.3 (GRK4) was identified in both meta-analyses. The colocalization analysis supported the results of our meta-analysis in these loci. The gene-based analysis revealed 80 genes between AD and frailty, and 4 genes were initially identified in our meta-analyses: C1QTNF4, CRHR1, MAD1L1, and RGS12. The pathway analysis showed enrichment for lipoprotein particle plasma, amyloid fibril formation, protein kinase regulator, and tau protein binding.Conclusion: Overall, our results provide new insights into the genetics of AD and frailty, suggesting the existence of non-causal shared genetic mechanisms between these conditions.

Abstract Acute myeloid leukemia (AML) is a heterogeneous disease characterized by high rate of therapy resistance. Since the cell of origin can impact response to therapy, it is crucial to understand the lineage composition of AML cells at time of therapy resistance. Here we leverage single-cell chromatin accessibility profiling of 22 AML bone marrow aspirates from eight patients at time of therapy resistance and following subsequent therapy to characterize their lineage landscape. Our findings reveal a complex lineage architecture of therapy-resistant AML cells that are primed for stem and progenitor lineages and spanning quiescent, activated and late stem cell/progenitor states. Remarkably, therapy-resistant AML cells are also composed of cells primed for differentiated myeloid, erythroid and even lymphoid lineages. The heterogeneous lineage composition persists following subsequent therapy, with early progenitor-driven features marking unfavorable prognosis in The Cancer Genome Atlas AML cohort. Pseudotime analysis further confirms the vast degree of heterogeneity driven by the dynamic changes in chromatin accessibility. Our findings suggest that therapy-resistant AML cells are characterized not only by stem and progenitor states, but also by a continuum of differentiated cellular lineages. The heterogeneity in lineages likely contributes to their therapy resistance by harboring different degrees of lineage-specific susceptibilities to therapy.

Longstanding evidence implicate glioma stem-like cells as the main drivers contributing toward glioblastoma (GBM) therapy resistance and tumor recurrence. Although oncolytic herpes simplex virus (oHSV) viral therapy is a promising biological therapy recently approved for melanoma (in the United States and Europe) and GBM (in Japan); however, the impact of this therapy on GBM stem-like cells (GSCs) is understudied. Here we show that post-oHSV virotherapy activated AKT signaling results in an enrichment of GSC signatures in glioma, which mimics the enrichment in GSC observed after radiation treatment. We also uncovered that a second-generation oncolytic virus armed with PTEN-L (oHSV-P10) decreases this by moderating IL6/JAK/STAT3 signaling. This ability was retained in the presence of radiation treatment and oHSV-P10-sensitized intracranial GBM to radiotherapy. Collectively, our findings uncover potential mechanisms to overcome GSC-mediated radiation resistance via oHSV-P10.

Abstract Circulating metabolite levels may reflect the state of the human organism in health and disease, however, the genetic architecture of metabolites is not fully understood. We have performed a whole-genome sequencing association analysis of both common and rare variants in up to 11,840 multi-ethnic participants from five studies with up to 1666 circulating metabolites. We have discovered 1985 novel variant-metabolite associations, and validated 761 locus-metabolite associations reported previously. Seventy-nine novel variant-metabolite associations have been replicated, including three genetic loci located on the X chromosome that have demonstrated its involvement in metabolic regulation. Gene-based analysis have provided further support for seven metabolite-replicated loci pairs and their biologically plausible genes. Among those novel replicated variant-metabolite pairs, follow-up analyses have revealed that 26 metabolites have colocalized with 21 tissues, seven metabolite-disease outcome associations have been putatively causal, and 7 metabolites might be regulated by plasma protein levels. Our results have depicted the genetic contribution to circulating metabolite levels, providing additional insights into understanding human disease.

The incidence of bladder cancer and patient survival vary greatly among different populations, but the influence of the associated molecular features and evolutionary processes on its clinical treatment and prognostication remains unknown. Here, we analyze the genomic architectures of 505 bladder cancer patients from Asian/Black/White populations. We identify a previously unknown association between AHNAK mutations and activity of the APOBEC‐a mutational signature, the activity of which varied substantially across populations. All significantly mutated genes but only half of arm‐level somatic copy number alterations (SCNAs) are enriched with clonal events, indicating large‐scale SCNAs as rich sources of bladder cancer clonal diversities. The prevalence of TP53 and ATM clonal mutations as well as the associated burden of SCNAs is significantly higher in Whites/Blacks than in Asians. We identify a trans‐ancestry prognostic subtype of bladder cancer characterized by enrichment of non‐muscle‐invasive patients and muscle‐invasive patients with good prognosis, increased CREBBP/FGFR3/HRAS/NFE2L2 mutations, decreased intra‐tumor heterogeneity and genome instability, and an activated tumor microenvironment.

Prostate cancer is morphologically and molecularly heterogeneous, which poses obstacles for early diagnosis and treatment. Advancements in understanding the heterogeneity of prostate cancer will help navigate through these challenges and ultimately benefit patients. In this study, we integrated single-cell sequencing for transposase-accessible chromatin and whole transcriptome in prostate cancer cell lines, aiming to decode the epigenetic plasticity upon enzalutamide (ENZ) treatment. By comparing the cell populations representing early-treatment response or resistance to the initial tumor cells, we identified seven signature gene sets; they present consistent trends of chromatin closing co-occurred with down-regulated genes during early response and chromatin opening with up-regulated genes upon maintaining drug resistance. In the molecular signatures, we found genes ZNF337, MAPK15, and ESRRG are favorable in progression-free prognosis during early response, while genes CCDC150, CCDC18, and POC1A marked poor prognosis underpinning the pre-existing drug resistance in The Cancer Genome Atlas prostate adenocarcinoma cohort. Ultimately, drug-target analyses nominated combinatory drug candidates to either enhance early-treatment response or potentially overcome ENZ resistance. Together, our integrative, single-cell multi-omics approach in pre-clinical models is effective in identifying informative signatures from complex molecular events, illustrating diverse drug responses in prostate cancer, and invoking novel combinatory drug strategies to inform clinical decision making.

The dysregulation of the m6A epitranscriptomic networks have been reported to contribute to the development of gliomas. Here, the authors utilize induced pluripotent stem cell-derived astrocytes with a p53 mutation and demonstrate that mutant p53 upregulates the m6A reader YTHDF2, resulting in the initiation of gliomas.

Abstract Background Clinical interpretation of genetic test results is complicated by variants of uncertain significance (VUS) that have an unknown impact on health but can be clarified through reclassification. There is little empirical evidence regarding VUS reclassification in oncology care settings, including the prevalence and outcomes of reclassification, and racial/ethnic differences. Methods This was a retrospective analysis of persons with and without a personal history of cancer carrying VUS (with or without an accompanying pathogenic or likely pathogenic [P/LP] variant) in breast, ovarian, and colorectal cancer predisposition genes seen at four cancer care settings (in Texas, Florida, Ohio, and New Jersey) between 2013 and 2019. Results In 2715 individuals included in the study, 3261 VUS and 313 P/LP variants were reported; 8.1% of all individuals with VUS experienced reclassifications and rates varied significantly among cancer care settings from 4.81% to 20.19% (overall p

Abstract The Human Activity Recognition (HAR) problem leverages pattern recognition to classify physical human activities as they are captured by several sensor modalities. Remote monitoring of an individual’s activities has gained importance due to the reduction in travel and physical activities during the pandemic. Research on HAR enables one person to either remotely monitor or recognize another person’s activity via the ubiquitous mobile device or by using sensor-based Internet of Things (IoT). Our proposed work focuses on the accurate classification of daily human activities from both accelerometer and gyroscope sensor data after converting into spectrogram images. The feature extraction process follows by leveraging the pre-trained weights of two popular and efficient transfer learning convolutional neural network models. Finally, a wrapper-based feature selection method has been employed for selecting the optimal feature subset that both reduces the training time and improves the final classification performance. The proposed HAR model has been tested on the three benchmark datasets namely, HARTH, KU-HAR and HuGaDB and has achieved 88.89%, 97.97% and 93.82% respectively on these datasets. It is to be noted that the proposed HAR model achieves an improvement of about 21%, 20% and 6% in the overall classification accuracies while utilizing only 52%, 45% and 60% of the original feature set for HuGaDB, KU-HAR and HARTH datasets respectively. This proves the effectiveness of our proposed wrapper-based feature selection HAR methodology.

Extrachromosomal circular DNA (eccDNA) is a special class of DNA derived from linear chromosomes. It coexists independently with linear chromosomes in the nucleus. eccDNA has been identified in multiple organisms, including Homo sapiens, and has been shown to play important roles relevant to tumor progression and drug resistance. To date, computational tools developed for eccDNA detection are only applicable to bulk tissue. Investigating eccDNA at the single-cell level using a computational approach will elucidate the heterogeneous and cell-type-specific landscape of eccDNA within cellular context. Here, we performed the first eccDNA analysis at the single-cell level using data generated by single-cell Assay for Transposase-Accessible Chromatin with sequencing (scATAC-seq) in adult and pediatric glioblastoma (GBM) samples. Glioblastoma multiforme (GBM) is an aggressive tumor of the central nervous system with a poor prognosis. Our analysis provides an overview of cellular origins, genomic distribution, as well as the differential regulations between linear and circular genome under disease- and cell-type-specific conditions across the open chromatin regions in GBM. We focused on some eccDNA elements that are potential mobile enhancers acting in a trans-regulation manner. In summary, this pilot study revealed novel eccDNA features in the cellular context of brain tumor, supporting the strong need for eccDNA investigation at the single-cell level.

The assessment of functional effect of amino acid variants is a critical biological problem in proteomics for clinical medicine and protein engineering. Although natively occurring variants offer insights into deleterious variants, high-throughput deep mutational experiments enable comprehensive investigation of amino acid variants for a given protein. However, these mutational experiments are too expensive to dissect millions of variants on thousands of proteins. Thus, computational approaches have been proposed, but they heavily rely on hand-crafted evolutionary conservation, limiting their accuracy. Recent advancement in transformers provides a promising solution to precisely estimate the functional effects of protein variants on high-throughput experimental data. Here, we introduce a novel deep learning model, namely Rep2Mut-V2, which leverages learned representation from transformer models. Rep2Mut-V2 significantly enhances the prediction accuracy for 27 types of measurements of functional effects of protein variants. In the evaluation of 38 protein datasets with 118,933 single amino acid variants, Rep2Mut-V2 achieved an average Spearman’s correlation coefficient of 0.7. This surpasses the performance of six state-of-the-art methods, including the recently released methods ESM, DeepSequence and EVE. Even with limited training data, Rep2Mut-V2 outperforms ESM and DeepSequence, showing its potential to extend high-throughput experimental analysis for more protein variants to reduce experimental cost. In conclusion, Rep2Mut-V2 provides accurate predictions of the functional effects of single amino acid variants of protein coding sequences. This tool can significantly aid in the interpretation of variants in human disease studies.

Abstract The application of single-cell RNA sequencing in COVID-19 research has greatly improved our understanding of COVID-19 pathogenesis and immunological characteristics. In this commentary, we discuss the current challenges, limitations, and perspectives in harnessing the power of single-cell RNA sequencing to accelerate both basic research and therapeutic development for COVID-19 and other emerging infectious diseases.

Summary: Understanding the factors that regulate T cell infiltration and functional states in solid tumors is crucial for advancing cancer immunotherapies. Here, we discovered that the expression of interferon regulatory factor 4 (IRF4) was a critical T cell intrinsic requirement for effective anti-tumor immunity. Mice with T-cell-specific ablation of IRF4 showed significantly reduced T cell tumor infiltration and function, resulting in accelerated growth of subcutaneous syngeneic tumors and allowing the growth of allogeneic tumors. Additionally, engineered overexpression of IRF4 in anti-tumor CD8+ T cells that were adoptively transferred significantly promoted their tumor infiltration and transition from a naive/memory-like cell state into effector T cell states. As a result, IRF4-engineered anti-tumor T cells exhibited significantly improved anti-tumor efficacy, and inhibited tumor growth either alone or in combination with PD-L1 blockade. These findings identify IRF4 as a crucial cell-intrinsic driver of T cell infiltration and function in tumors, emphasizing the potential of IRF4-engineering as an immunotherapeutic approach.

Alzheimer’s Disease (AD) is a complex disease and the leading cause of dementia in older people. We aimed to uncover aspects of AD’s pathogenesis that may contribute to drug repurposing efforts by integrating DNA methylation and genetic data. Implementing the network-based tool, a dense module search of genome-wide association studies (dmGWAS), we integrated a large-scale GWAS dataset with DNA methylation data to identify gene network modules associated with AD. Our analysis yielded 286 significant gene network modules. Notably, the foremost module included the BIN1 gene, showing the largest GWAS signal, and the GNAS gene, the most significantly hypermethylated. We conducted Web-based Cell-type-Specific Enrichment Analysis (WebCSEA) on genes within the top 10% of dmGWAS modules, highlighting monocyte as the most significant cell type (p < 5 × 10−12). Functional enrichment analysis revealed Gene Ontology Biological Process terms relevant to AD pathology (adjusted p < 0.05). Additionally, drug target enrichment identified five FDA-approved targets (p-value = 0.03) for further research. In summary, dmGWAS integration of genetic and epigenetic signals unveiled new gene interactions related to AD, offering promising avenues for future studies.

Abstract Background The rapid accumulation of single-cell RNA sequencing (scRNA-seq) data presents unique opportunities to decode the genetically mediated cell-type specificity in complex diseases. Here, we develop a new method, scGWAS, which effectively leverages scRNA-seq data to achieve two goals: (1) to infer the cell types in which the disease-associated genes manifest and (2) to construct cellular modules which imply disease-specific activation of different processes. Results scGWAS only utilizes the average gene expression for each cell type followed by virtual search processes to construct the null distributions of module scores, making it scalable to large scRNA-seq datasets. We demonstrated scGWAS in 40 genome-wide association studies (GWAS) datasets (average sample size N ≈ 154,000) using 18 scRNA-seq datasets from nine major human/mouse tissues (totaling 1.08 million cells) and identified 2533 trait and cell-type associations, each with significant modules for further investigation. The module genes were validated using disease or clinically annotated references from ClinVar, OMIM, and pLI variants. Conclusions We showed that the trait-cell type associations identified by scGWAS, while generally constrained to trait-tissue associations, could recapitulate many well-studied relationships and also reveal novel relationships, providing insights into the unsolved trait-tissue associations. Moreover, in each specific cell type, the associations with different traits were often mediated by different sets of risk genes, implying disease-specific activation of driving processes. In summary, scGWAS is a powerful tool for exploring the genetic basis of complex diseases at the cell type level using single-cell expression data.

Identification of B-cell epitopes (BCEs) plays an essential role in the development of peptide vaccines and immuno-diagnostic reagents, as well as antibody design and production. In this work, we generated a large benchmark dataset comprising 124,879 experimentally supported linear epitope-containing regions in 3567 protein clusters from over 1.3 million B cell assays. Analysis of this curated dataset showed large pathogen diversity covering 176 different families. The accuracy in linear BCE prediction was found to strongly vary with different features, while all sequence-derived and structural features were informative. To search more efficient and interpretive feature representations, a ten-layer deep learning framework for linear BCE prediction, namely NetBCE, was developed. NetBCE achieved high accuracy and robust performance with the average area under the curve (AUC) value of 0.8455 in five-fold cross-validation through automatically learning the informative classification features. NetBCE substantially outperformed the conventional machine learning algorithms and other tools, with more than 22.06% improvement of AUC value compared to other tools using an independent dataset. Through investigating the output of important network modules in NetBCE, epitopes and non-epitopes tended to be presented in distinct regions with efficient feature representation along the network layer hierarchy. The NetBCE is freely available at https://github.com/bsml320/NetBCE.

Summary: Monochorionic-diamniotic twin pregnancies are susceptible to unique complications arising from a single placenta shared by two fetuses. Twin-twin transfusion syndrome (TTTS) is a constellation of disturbances caused by unequal blood flow within the shared placenta giving rise to a major hemodynamic imbalance between the twins. Here, we applied TTTS as a model to uncover fetal metabolic adaptations to cardiovascular stress. We compared untargeted metabolomic analyses of amniotic fluid samples from severe TTTS cases vs. singleton controls. Amniotic fluid metabolites demonstrated alterations in fatty acid, glucose, and steroid hormone metabolism in TTTS. Among TTTS cases, unsupervised principal component analysis revealed two distinct clusters of disease defined by levels of glucose metabolites, amino acids, urea, and redox status. Our results suggest that the human fetal heart can adapt to hemodynamic stress by modulating its glucose metabolism and identify potential differences in the ability of individual fetuses to respond to cardiovascular stress.

Breast cancer is the second leading cause of cancer death in women among all cancer types. It is highly heterogeneous in nature, which means that the tumors have different morphologies and there is heterogeneity even among people who have the same type of tumor. Several staging and classifying systems have been developed due to the variability of different types of breast cancer. Due to high heterogeneity, personalized treatment has become a new strategy. Out of all breast cancer subtypes, triple-negative breast cancer (TNBC) comprises ∼10%–15%. TNBC refers to the subtype of breast cancer where cells do not express estrogen receptors, progesterone receptors, or human epidermal growth factor receptors (ERs, PRs, and HERs). Tumors in TNBC have a diverse set of genetic markers and prognostic indicators. We scanned the Cancer Cell Line Encyclopedia (CCLE) and Genomics of Drug Sensitivity in Cancer (GDSC) databases for potential drugs using human breast cancer cell lines and drug sensitivity data. Three different machine-learning approaches were used to evaluate the prediction of six effective drugs against the TNBC cell lines. The top biomarkers were then shortlisted on the basis of their involvement in breast cancer and further subjected to testing for radion resistance using data from the Cleveland database. It was observed that Panobinostat, PLX4720, Lapatinib, Nilotinib, Selumetinib, and Tanespimycin were six effective drugs against the TNBC cell lines. We could identify potential derivates that may be used against approved drugs. Only one biomarker (SETD7) was sensitive to all six drugs on the shortlist, while two others (SRARP and YIPF5) were sensitive to both radiation and drugs. Furthermore, we did not find any radioresistance markers for the TNBC. The proposed biomarkers and drug sensitivity analysis will provide potential candidates for future clinical investigation.

Objectives: The kynurenine (KYN) pathway has been attracting attention as a relevant pathway in schizophrenia (SZ), bipolar disorder (BD), and major depressive disorder (MDD). We conducted a systematic review and meta-analysis of studies examining KYN pathway metabolites from cerebrospinal fluid (CSF) samples in SZ, BD, and MDD. Methods: The PubMed and Scopus databases were systematically searched to identify peer-reviewed case-control studies published until April 2022 that assessed KYN metabolites, namely, tryptophan (TRP), KYN, kynurenic acid (KA), quinolinic acid (QA), and 3-hydroxykynurenine (3-HK), in subjects with SZ, BD, or MDD compared with healthy controls (HC). The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. The random effects model method was selected for comparison of standardized mean differences (SMD) between two groups. Results: Twenty-three articles met the inclusion criteria (k = 8, k = 8, k = 11, for SZ, BD, and MDD, respectively). In SZ, KA levels were increased (SMD = 2.64, confidence interval [CI] = 1.16 to 4.13, p = 0.0005, I2 = 96%, k = 6, n=384). TRP (k = 5) and KYN (k = 4) did not differ significantly. In BD, TRP levels (k = 7) did not differ significantly. The level of KA was increased in MDD (k = 2), but the small number of studies precluded evaluation of statistical significance. Finally, in MDD, although some studies tended to show an increased level of KYN in those with remission vs. decreased levels in those with current depression, no significant difference was found in any KYN metabolite levels. Similarly, an increased level of QA was found, but the number of studies (k = 2) was small. Conclusion: KA, which has possibly neuroprotective effects, is increased in SZ. QA, which has neurotoxic effects, may be increased in MDD. There were no alterations in BD. Alterations in the KYN pathway may occur based on population characteristics and mood states. Future studies should explore the utility of these metabolites as biomarkers.

Introduction: Association rule mining (ARM) is a powerful tool for exploring the informative relationships among multiple items (genes) in any dataset. The main problem of ARM is that it generates many rules containing different rule-informative values, which becomes a challenge for the user to choose the effective rules. In addition, few works have been performed on the integration of multiple biological datasets and variable cutoff values in ARM.Methods: To solve all these problems, in this article, we developed a novel framework MOOVARM (multi-objective optimized variable cutoff-based association rule mining) for multi-omics profiles.Results: In this regard, we identified the positive ideal solution (PIS), which maximized the profit and minimized the loss, and negative ideal solution (NIS), which minimized the profit and maximized the loss for all gene sets (item sets), belonging to each extracted rule. Thereafter, we computed the distance (d +) from PIS and distance (d −) from NIS for each gene set or product. These two distances played an important role in determining the optimized associations among various pairs of genes in the multi-omics dataset. We then globally estimated the relative closeness to PIS for ranking the gene sets. When the relative closeness score of the rule is greater than or equal to the pre-defined threshold value, the rule can be considered a final resultant rule. Moreover, MOOVARM evaluated the relative score of the rule based on the status of all genes instead of individual genes.Conclusions:MOOVARM produced the final rank of the extracted (multi-objective optimized) rules of correlated genes which had better disease classification than the state-of-the-art algorithms on gene signature identification.

Abstract Background Multiple sclerosis (MS) is a debilitating immune-mediated disease of the central nervous system that affects over 2 million people worldwide, resulting in a heavy burden to families and entire communities. Understanding the genetic basis underlying MS could help decipher the pathogenesis and shed light on MS treatment. We refined a recently developed Bayesian framework, Integrative Risk Gene Selector (iRIGS), to prioritize risk genes associated with MS by integrating the summary statistics from the largest GWAS to date (n = 115,803), various genomic features, and gene–gene closeness. Results We identified 163 MS-associated prioritized risk genes (MS-PRGenes) through the Bayesian framework. We replicated 35 MS-PRGenes through two-sample Mendelian randomization (2SMR) approach by integrating data from GWAS and Genotype-Tissue Expression (GTEx) expression quantitative trait loci (eQTL) of 19 tissues. We demonstrated that MS-PRGenes had more substantial deleterious effects and disease risk. Moreover, single-cell enrichment analysis indicated MS-PRGenes were more enriched in activated macrophages and microglia macrophages than non-activated ones in control samples. Biological and drug enrichment analyses highlighted inflammatory signaling pathways. Conclusions In summary, we predicted and validated a high-confidence MS risk gene set from diverse genomic, epigenomic, eQTL, single-cell, and drug data. The MS-PRGenes could further serve as a benchmark of MS GWAS risk genes for future validation or genetic studies.

Abstract Background As many complex omics data have been generated during the last two decades, dimensionality reduction problem has been a challenging issue in better mining such data. The omics data typically consists of many features. Accordingly, many feature selection algorithms have been developed. The performance of those feature selection methods often varies by specific data, making the discovery and interpretation of results challenging. Methods and results In this study, we performed a comprehensive comparative study of five widely used supervised feature selection methods (mRMR, INMIFS, DFS, SVM-RFE-CBR and VWMRmR) for multi-omics datasets. Specifically, we used five representative datasets: gene expression (Exp), exon expression (ExpExon), DNA methylation (hMethyl27), copy number variation (Gistic2), and pathway activity dataset (Paradigm IPLs) from a multi-omics study of acute myeloid leukemia (LAML) from The Cancer Genome Atlas (TCGA). The different feature subsets selected by the aforesaid five different feature selection algorithms are assessed using three evaluation criteria: (1) classification accuracy (Acc), (2) representation entropy (RE) and (3) redundancy rate (RR). Four different classifiers, viz., C4.5, NaiveBayes, KNN, and AdaBoost, were used to measure the classification accuary (Acc) for each selected feature subset. The VWMRmR algorithm obtains the best Acc for three datasets (ExpExon, hMethyl27 and Paradigm IPLs). The VWMRmR algorithm offers the best RR (obtained using normalized mutual information) for three datasets (Exp, Gistic2 and Paradigm IPLs), while it gives the best RR (obtained using Pearson correlation coefficient) for two datasets (Gistic2 and Paradigm IPLs). It also obtains the best RE for three datasets (Exp, Gistic2 and Paradigm IPLs). Overall, the VWMRmR algorithm yields best performance for all three evaluation criteria for majority of the datasets. In addition, we identified signature genes using supervised learning collected from the overlapped top feature set among five feature selection methods. We obtained a 7-gene signature (ZMIZ1, ENG, FGFR1, PAWR, KRT17, MPO and LAT2) for EXP, a 9-gene signature for ExpExon, a 7-gene signature for hMethyl27, one single-gene signature (PIK3CG) for Gistic2 and a 3-gene signature for Paradigm IPLs. Conclusion We performed a comprehensive comparison of the performance evaluation of five well-known feature selection methods for mining features from various high-dimensional datasets. We identified signature genes using supervised learning for the specific omic data for the disease. The study will help incorporate higher order dependencies among features.