-
1دورية أكاديمية
المؤلفون: Sana Munquad, Asim Bikas Das
المصدر: BioData Mining, Vol 16, Iss 1, Pp 1-18 (2023)
مصطلحات موضوعية: Multi-omics, Autoencoder, Lower-grade glioma (LGG), Glioblastoma multiforme (GBM), Convolutional neural network (CNN), Computer applications to medicine. Medical informatics, R858-859.7, Analysis, QA299.6-433
الوصف: Abstract Background and objective The classification of glioma subtypes is essential for precision therapy. Due to the heterogeneity of gliomas, the subtype-specific molecular pattern can be captured by integrating and analyzing high-throughput omics data from different genomic layers. The development of a deep-learning framework enables the integration of multi-omics data to classify the glioma subtypes to support the clinical diagnosis. Results Transcriptome and methylome data of glioma patients were preprocessed, and differentially expressed features from both datasets were identified. Subsequently, a Cox regression analysis determined genes and CpGs associated with survival. Gene set enrichment analysis was carried out to examine the biological significance of the features. Further, we identified CpG and gene pairs by mapping them in the promoter region of corresponding genes. The methylation and gene expression levels of these CpGs and genes were embedded in a lower-dimensional space with an autoencoder. Next, ANN and CNN were used to classify subtypes using the latent features from embedding space. CNN performs better than ANN for subtyping lower-grade gliomas (LGG) and glioblastoma multiforme (GBM). The subtyping accuracy of CNN was 98.03% (± 0.06) and 94.07% (± 0.01) in LGG and GBM, respectively. The precision of the models was 97.67% in LGG and 90.40% in GBM. The model sensitivity was 96.96% in LGG and 91.18% in GBM. Additionally, we observed the superior performance of CNN with external datasets. The genes and CpGs pairs used to develop the model showed better performance than the random CpGs-gene pairs, preprocessed data, and single omics data. Conclusions The current study showed that a novel feature selection and data integration strategy led to the development of DeepAutoGlioma, an effective framework for diagnosing glioma subtypes.
وصف الملف: electronic resource
العلاقة: https://doaj.org/toc/1756-0381Test
-
2دورية أكاديمية
المؤلفون: Sana Munquad, Asim Bikas Das
المصدر: Heliyon, Vol 10, Iss 5, Pp e27190- (2024)
مصطلحات موضوعية: Glioma, Subtype, Disease module, Deep learning, Drug response prediction, Science (General), Q1-390, Social sciences (General), H1-99
الوصف: The poor prognosis of glioma patients brought attention to the need for effective therapeutic approaches for precision therapy. Here, we deployed algorithms relying on network medicine and artificial intelligence to design the framework for subtype-specific target identification and drug response prediction in glioma. We identified the driver mutations that were differentially expressed in each subtype of lower-grade glioma and glioblastoma multiforme and were linked to cancer-specific processes. Driver mutations that were differentially expressed were also subjected to subtype-specific disease module identification. The drugs from the drug bank database were retrieved to target these disease modules. However, the efficacy of anticancer drugs depends on the molecular profile of the cancer and varies among cancer patients due to intratumor heterogeneity. Hence, we developed a deep-learning-based drug response prediction framework using the experimental drug screening data. Models for 30 drugs that can target the disease module were developed, where drug response measured by IC50 was considered a response and gene expression and mutation data were considered predictor variables. The model construction consists of three steps: feature selection, data integration, and classification. We observed the consistent performance of the models in training, test, and validation datasets. Drug responses were predicted for particular cell lines derived from distinct subtypes of gliomas. We found that subtypes of gliomas respond differently to the drug, highlighting the importance of subtype-specific drug response prediction. Therefore, the development of personalized therapy by integrating network medicine and a deep learning-based approach can lead to cancer-specific treatment and improved patient care.
وصف الملف: electronic resource
العلاقة: http://www.sciencedirect.com/science/article/pii/S2405844024032213Test; https://doaj.org/toc/2405-8440Test
-
3دورية أكاديمية
المؤلفون: Asim Bikas Das
المصدر: BMC Medical Genomics, Vol 14, Iss 1, Pp 1-14 (2021)
مصطلحات موضوعية: COVID-19, SARS-CoV-2, Lung disease, Comorbidity, Disease network, Internal medicine, RC31-1245, Genetics, QH426-470
الوصف: Abstract Background Higher mortality of COVID-19 patients with lung disease is a formidable challenge for the health care system. Genetic association between COVID-19 and various lung disorders must be understood to comprehend the molecular basis of comorbidity and accelerate drug development. Methods Lungs tissue-specific neighborhood network of human targets of SARS-CoV-2 was constructed. This network was integrated with lung diseases to build a disease–gene and disease-disease association network. Network-based toolset was used to identify the overlapping disease modules and drug targets. The functional protein modules were identified using community detection algorithms and biological processes, and pathway enrichment analysis. Results In total, 141 lung diseases were linked to a neighborhood network of SARS-CoV-2 targets, and 59 lung diseases were found to be topologically overlapped with the COVID-19 module. Topological overlap with various lung disorders allows repurposing of drugs used for these disorders to hit the closely associated COVID-19 module. Further analysis showed that functional protein–protein interaction modules in the lungs, substantially hijacked by SARS-CoV-2, are connected to several lung disorders. FDA-approved targets in the hijacked protein modules were identified and that can be hit by exiting drugs to rescue these modules from virus possession. Conclusion Lung diseases are clustered with COVID-19 in the same network vicinity, indicating the potential threat for patients with respiratory diseases after SARS-CoV-2 infection. Pathobiological similarities between lung diseases and COVID-19 and clinical evidence suggest that shared molecular features are the probable reason for comorbidity. Network-based drug repurposing approaches can be applied to improve the clinical conditions of COVID-19 patients.
وصف الملف: electronic resource
العلاقة: https://doaj.org/toc/1755-8794Test
-
4دورية أكاديمية
المؤلفون: Sana Munquad, Tapas Si, Saurav Mallik, Asim Bikas Das, Zhongming Zhao
المصدر: Frontiers in Genetics, Vol 13 (2022)
مصطلحات موضوعية: deep learning, glioblastoma multiforme, biomarkers, co-expression gene module, machine learning, Genetics, QH426-470
الوصف: Understanding molecular features that facilitate aggressive phenotypes in glioblastoma multiforme (GBM) remains a major clinical challenge. Accurate diagnosis of GBM subtypes, namely classical, proneural, and mesenchymal, and identification of specific molecular features are crucial for clinicians for systematic treatment. We develop a biologically interpretable and highly efficient deep learning framework based on a convolutional neural network for subtype identification. The classifiers were generated from high-throughput data of different molecular levels, i.e., transcriptome and methylome. Furthermore, an integrated subsystem of transcriptome and methylome data was also used to build the biologically relevant model. Our results show that deep learning model outperforms the traditional machine learning algorithms. Furthermore, to evaluate the biological and clinical applicability of the classification, we performed weighted gene correlation network analysis, gene set enrichment, and survival analysis of the feature genes. We identified the genotype–phenotype relationship of GBM subtypes and the subtype-specific predictive biomarkers for potential diagnosis and treatment.
وصف الملف: electronic resource
العلاقة: https://www.frontiersin.org/articles/10.3389/fgene.2022.855420/fullTest; https://doaj.org/toc/1664-8021Test
-
5دورية أكاديمية
المؤلفون: Asim Bikas Das (11451286)
مصطلحات موضوعية: Biochemistry, Medicine, Genetics, Pharmacology, Biotechnology, Sociology, Cancer, Infectious Diseases, Biological Sciences not elsewhere classified, COVID-19, SARS-CoV-2, Lung disease, Comorbidity, Disease network
الوصف: Additional file 1. Fig.S1. Dot plot shows the number of genes associated with a lung disorder in LDGN. Fig. S2. Dot plot shows the number of shared genes between COVID-19 other lung disorders. Fig.S3. The network view of the Jaccard similarity coefficient between lung diseases and COVID19. Fig.S4. Heat map shows functional protein modules are associated with different disease classes. Fig.S5. Drug repurposing to target functional protein modules.
-
6دورية أكاديمية
المؤلفون: Asim Bikas Das (11451286)
مصطلحات موضوعية: Biochemistry, Medicine, Genetics, Pharmacology, Biotechnology, Sociology, Cancer, Infectious Diseases, Biological Sciences not elsewhere classified, COVID-19, SARS-CoV-2, Lung disease, Comorbidity, Disease network
الوصف: Additional file 4. Table S3. Disease-gene association data of STN.
-
7دورية أكاديمية
المؤلفون: Asim Bikas Das (11451286)
مصطلحات موضوعية: Biochemistry, Medicine, Genetics, Pharmacology, Biotechnology, Sociology, Cancer, Infectious Diseases, Biological Sciences not elsewhere classified, COVID-19, SARS-CoV-2, Lung disease, Comorbidity, Disease network
الوصف: Additional file 5. Table S4. Network-based separation measure between disease modules and statistical significance.
-
8دورية أكاديمية
المؤلفون: Asim Bikas Das (11451286)
مصطلحات موضوعية: Biochemistry, Medicine, Genetics, Pharmacology, Biotechnology, Sociology, Cancer, Infectious Diseases, Biological Sciences not elsewhere classified, COVID-19, SARS-CoV-2, Lung disease, Comorbidity, Disease network
الوصف: Additional file 2. Table S1. Edge list of SARS-CoV-2 target network (STN) from TissueNet v.2 database.
-
9دورية أكاديمية
المؤلفون: Asim Bikas Das (11451286)
مصطلحات موضوعية: Biochemistry, Medicine, Genetics, Pharmacology, Biotechnology, Sociology, Cancer, Infectious Diseases, Biological Sciences not elsewhere classified, COVID-19, SARS-CoV-2, Lung disease, Comorbidity, Disease network
الوصف: Additional file 3. Table S2. Disease-gene association data of lungs from the ORGANizer database.
-
10دورية أكاديمية
المؤلفون: Asim Bikas Das (11451286)
مصطلحات موضوعية: Biochemistry, Medicine, Genetics, Pharmacology, Biotechnology, Sociology, Cancer, Infectious Diseases, Biological Sciences not elsewhere classified, COVID-19, SARS-CoV-2, Lung disease, Comorbidity, Disease network
الوصف: Additional file 7. Table S7. Disease association with functional protein modules.
النص الكامل