Asim Bikas Das
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Asim Bikas Das has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Urmila Saxena
Department of Biotechnology, National Institute of Technology Warangal, Warangal 506004, Telangana, India
7 shared publications Sana Munquad
Department of Biotechnology, National Institute of Technology Warangal
5 shared publicationsB. Sumithra
Department of Biotechnology, National Institute of Technology Warangal, Warangal, India
3 shared publications- Pradipta Purkayastha
Department of Chemical Sciences and Centre for Advanced Functional Materials, Indian Institute of Science Education and Research (IISER) Kolkata, Mohanpur 741246, West Bengal, India
2 shared publications Subit Kumar Saha
2 shared publicationsTapas Si
Department of Computer Science and Engineering, Bankura Unnayani Institute of Engineering , Bankura 722146, West Bengal , India
2 shared publications
Latest Publications
- Open Access
- 22 September 2026
- Published by Frontiers Media SA in Frontiers in Bioinformatics
- Vol. 6, 1811813
The impact of deep learning and omics data in transforming precision therapy for brain cancer
The combination of AI with high-throughput genomics has revolutionized oncology, particularly in the case of brain cancer, a diagnostically complicated and heterogeneous tumor. With the explosion of omics data and computational power, deep learning (DL) has evolved as a powerful computational approach for the interpretation of the molecular topography of brain tumors. Utilizing mono-omics and multi-omics data, including gene expression, somatic mutations, DNA methylation, copy number alterations, and miRNA profiles, deep learning algorithms can detect complex, nonlinear patterns underlying tumor biology and clinical behavior. Several DL architectures have been used in recent studies for classification, biomarker discovery, and subtype prediction in brain cancer. The combination of multi-omics data has been especially useful, since oncogenic changes arise at several molecular levels; therefore, the omission of any specific omics aspect might undermine diagnostic accuracy and therapeutic prediction. Here, in this review, DL-based approaches to various omics modalities are reviewed, covering the tools constructed, architectures, and performance levels, and then delving into integrative multi-omics frameworks that maximize the accuracy and interpretability of diagnostic models. It also discusses the significance of AI-based approaches in advancing personalized treatment for brain cancer, emphasizing their capacity to predict patient-specific drug responses. Notwithstanding these breakthroughs, some major challenges remain, which include data heterogeneity, explainability of models, computational requirements, and ethical issues related to the use of genomic data. Together, the review highlights the potential of DL and multi-omics integration in advancing precision oncology for brain cancer by enhancing diagnostic precision, prognostic accuracy, and personalized therapy development.
- 22 September 2026
- Published by Frontiers Media SA in Frontiers in Bioinformatics
- Vol. 6, 1811813
Open AccessThe impact of deep learning and omics data in transforming precision therapy for brain cancer
The combination of AI with high-throughput genomics has revolutionized oncology, particularly in the case of brain cancer, a diagnostically complicated and heterogeneous tumor. With the explosion of omics data and computational power, deep learning (DL) has evolved as a powerful computational approach for the interpretation of the molecular topography of brain tumors. Utilizing mono-omics and multi-omics data, including gene expression, somatic mutations, DNA methylation, copy number alterations, and miRNA profiles, deep learning algorithms can detect complex, nonlinear patterns underlying tumor biology and clinical behavior. Several DL architectures have been used in recent studies for classification, biomarker discovery, and subtype prediction in brain cancer. The combination of multi-omics data has been especially useful, since oncogenic changes arise at several molecular levels; therefore, the omission of any specific omics aspect might undermine diagnostic accuracy and therapeutic prediction. Here, in this review, DL-based approaches to various omics modalities are reviewed, covering the tools constructed, architectures, and performance levels, and then delving into integrative multi-omics frameworks that maximize the accuracy and interpretability of diagnostic models. It also discusses the significance of AI-based approaches in advancing personalized treatment for brain cancer, emphasizing their capacity to predict patient-specific drug responses. Notwithstanding these breakthroughs, some major challenges remain, which include data heterogeneity, explainability of models, computational requirements, and ethical issues related to the use of genomic data. Together, the review highlights the potential of DL and multi-omics integration in advancing precision oncology for brain cancer by enhancing diagnostic precision, prognostic accuracy, and personalized therapy development.
- Open Access
A lightweight codon-based DNA Transformer for Regulatory Region Identification in the Genome
We developed a lightweight codon-based DNA Transformer equipped with multi-head self-attention and an adaptive classifier head, which achieves exon intron classification with high accuracy and also has moderate accuracy in CDS classification and splice site recognition. We named this model as ExIT (Exon-Intron Transformer). We have implemented codon tokenization for this model. This has been validated on the human genome with external validation from the chimpanzee genome. Further benchmarking has implied that our model is better than the existing models in the above tasks.
Open AccessA lightweight codon-based DNA Transformer for Regulatory Region Identification in the Genome
We developed a lightweight codon-based DNA Transformer equipped with multi-head self-attention and an adaptive classifier head, which achieves exon intron classification with high accuracy and also has moderate accuracy in CDS classification and splice site recognition. We named this model as ExIT (Exon-Intron Transformer). We have implemented codon tokenization for this model. This has been validated on the human genome with external validation from the chimpanzee genome. Further benchmarking has implied that our model is better than the existing models in the above tasks.
- Open Access
- 18 November 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15  (1) , 40627
Biologically explainable multi-omics feature demonstrates greater learning potential by identifying tissue of origin, stages, and subtypes for pan-cancer classification
Cancer is a complex disease characterized by uncontrolled cell growth, which can invade surrounding tissues and spread to distant organs. Most of the conventional methods of diagnosis fails to identify the primary organ when cancer spreads to other organs, thereby adding another level of complexity for cancer detection. It is also critical to determine the stages and subtypes of cancer, and develop a clinically applicable model for precision therapy. With a dataset of 7632 samples from 30 different cancer originating from distinct organs, we have constructed a deep learning framework to solve all of these challenges. We have applied a hybrid feature selection method to identify cancer-associated features in the transcriptome, methylome, and microRNA datasets. This was achieved by combining both gene set enrichment analysis and Cox regression analysis to build an explainable AI model. We performed the early integration using an autoencoder to embed the cancer-associated multi-omics data into a lower-dimensional space; an ANN classifier was constructed using the latent features. In addition to correctly classifying 30 different cancer types by their tissue of origin, our framework also identifies individual subtypes and stages of cancer with an accuracy ranging from 87.31% to 94.0% and 83.33% to 93.64%, respectively. The current model demonstrates higher accuracy even when tested with external datasets, and shows better stability and accuracy in making predictions compared to the existing models. This approach offers explainable strategies for selecting features in AI-based prediction of tumor types for personalized therapy, aiding clinicians in making real-time treatment decisions.
- 18 November 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15  (1) , 40627
Open AccessBiologically explainable multi-omics feature demonstrates greater learning potential by identifying tissue of origin, stages, and subtypes for pan-cancer classification
Cancer is a complex disease characterized by uncontrolled cell growth, which can invade surrounding tissues and spread to distant organs. Most of the conventional methods of diagnosis fails to identify the primary organ when cancer spreads to other organs, thereby adding another level of complexity for cancer detection. It is also critical to determine the stages and subtypes of cancer, and develop a clinically applicable model for precision therapy. With a dataset of 7632 samples from 30 different cancer originating from distinct organs, we have constructed a deep learning framework to solve all of these challenges. We have applied a hybrid feature selection method to identify cancer-associated features in the transcriptome, methylome, and microRNA datasets. This was achieved by combining both gene set enrichment analysis and Cox regression analysis to build an explainable AI model. We performed the early integration using an autoencoder to embed the cancer-associated multi-omics data into a lower-dimensional space; an ANN classifier was constructed using the latent features. In addition to correctly classifying 30 different cancer types by their tissue of origin, our framework also identifies individual subtypes and stages of cancer with an accuracy ranging from 87.31% to 94.0% and 83.33% to 93.64%, respectively. The current model demonstrates higher accuracy even when tested with external datasets, and shows better stability and accuracy in making predictions compared to the existing models. This approach offers explainable strategies for selecting features in AI-based prediction of tumor types for personalized therapy, aiding clinicians in making real-time treatment decisions.
- 18 April 2024
- Published by Elsevier in Current Opinion in Toxicology
- Vol. 38
Network medicine and artificial intelligence in cancer precision therapy: Path to prevent drug-induced toxic side effect
- 18 April 2024
- Published by Elsevier in Current Opinion in Toxicology
- Vol. 38
Network medicine and artificial intelligence in cancer precision therapy: Path to prevent drug-induced toxic side effect
- Open Access
- 15 November 2023
- Published by Springer Nature in BioData Mining
- Vol. 16  (1) , 1-18
DeepAutoGlioma: a deep learning autoencoder-based multi-omics data integration and classification tools for glioma subtyping
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.
- 15 November 2023
- Published by Springer Nature in BioData Mining
- Vol. 16  (1) , 1-18
Open AccessDeepAutoGlioma: a deep learning autoencoder-based multi-omics data integration and classification tools for glioma subtyping
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.
- 3 August 2022
- Published by Oxford University Press (OUP) in Briefings in Functional Genomics
- Vol. 21  (5) , 408-421
Subtyping and grading of lower-grade gliomas using integrated feature selection and support vector machine
Classifying lower-grade gliomas (LGGs) is a crucial step for accurate therapeutic intervention. The histopathological classification of various subtypes of LGG, including astrocytoma, oligodendroglioma and oligoastrocytoma, suffers from intraobserver and interobserver variability leading to inaccurate classification and greater risk to patient health. We designed an efficient machine learning-based classification framework to diagnose LGG subtypes and grades using transcriptome data. First, we developed an integrated feature selection method based on correlation and support vector machine (SVM) recursive feature elimination. Then, implementation of the SVM classifier achieved superior accuracy compared with other machine learning frameworks. Most importantly, we found that the accuracy of subtype classification is always high (>90%) in a specific grade rather than in mixed grade (~80%) cancer. Differential co-expression analysis revealed higher heterogeneity in mixed grade cancer, resulting in reduced prediction accuracy. Our findings suggest that it is necessary to identify cancer grades and subtypes to attain a higher classification accuracy. Our six-class classification model efficiently predicts the grades and subtypes with an average accuracy of 91% (±0.02). Furthermore, we identify several predictive biomarkers using co-expression, gene set enrichment and survival analysis, indicating our framework is biologically interpretable and can potentially support the clinician.
- 3 August 2022
- Published by Oxford University Press (OUP) in Briefings in Functional Genomics
- Vol. 21  (5) , 408-421
Subtyping and grading of lower-grade gliomas using integrated feature selection and support vector machine
Classifying lower-grade gliomas (LGGs) is a crucial step for accurate therapeutic intervention. The histopathological classification of various subtypes of LGG, including astrocytoma, oligodendroglioma and oligoastrocytoma, suffers from intraobserver and interobserver variability leading to inaccurate classification and greater risk to patient health. We designed an efficient machine learning-based classification framework to diagnose LGG subtypes and grades using transcriptome data. First, we developed an integrated feature selection method based on correlation and support vector machine (SVM) recursive feature elimination. Then, implementation of the SVM classifier achieved superior accuracy compared with other machine learning frameworks. Most importantly, we found that the accuracy of subtype classification is always high (>90%) in a specific grade rather than in mixed grade (~80%) cancer. Differential co-expression analysis revealed higher heterogeneity in mixed grade cancer, resulting in reduced prediction accuracy. Our findings suggest that it is necessary to identify cancer grades and subtypes to attain a higher classification accuracy. Our six-class classification model efficiently predicts the grades and subtypes with an average accuracy of 91% (±0.02). Furthermore, we identify several predictive biomarkers using co-expression, gene set enrichment and survival analysis, indicating our framework is biologically interpretable and can potentially support the clinician.
- Open Access
- 28 March 2022
- Published by Frontiers Media SA in Frontiers in Genetics
- Vol. 13, 855420
A Deep Learning–Based Framework for Supporting Clinical Diagnosis of Glioblastoma Subtypes
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.
- 28 March 2022
- Published by Frontiers Media SA in Frontiers in Genetics
- Vol. 13, 855420
Open AccessA Deep Learning–Based Framework for Supporting Clinical Diagnosis of Glioblastoma Subtypes
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.
- Open Access
- 17 September 2021
- Published by Springer Nature in BMC Medical Genomics
- Vol. 14  (1) , 1-14
Lung disease network reveals impact of comorbidity on SARS-CoV-2 infection and opportunities of drug repurposing
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.
- 17 September 2021
- Published by Springer Nature in BMC Medical Genomics
- Vol. 14  (1) , 1-14
Open AccessLung disease network reveals impact of comorbidity on SARS-CoV-2 infection and opportunities of drug repurposing
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.
- Open Access
- 10 December 2020
- Published by Springer Nature in Research Square
Lung Disease Network Reveals the Impact of Comorbidity on SARS-CoV-2 Infection and Opportunities of Drug Repurposing
Higher mortality of COVID-19 patients with comorbidity is the formidable challenge faced by the health care system. In response to the present crisis, understanding the molecular basis of comorbidity is essential to accelerate the development of drugs. To address this, the genetic association between COVID-19 and various lung disorders was measured and notable molecular resemblance was observed. 141 lung diseases were linked to a neighborhood network of SARS-CoV-2 targets, and 59 lung diseases topologically overlapped with COVID-19 module. This demonstrates the clustering of lung diseases with COVID-19 in the same network vicinity, indicating the potential threat for lung patients upon SARS-CoV-2 infection. Pathobiological similarities between lung diseases and COVID-19, and clinical evidences suggest that shared molecular features probably the reason for comorbidity. Additionally, topological overlap with various lung disorders provides an opportunity to repurpose the drugs used for lung disease to hit the closely associated COVID-19 module. Further analysis showed that the functional protein-protein interaction modules in the lungs, substantially hijacked by SARS-CoV-2, were connected to several lung disorders. The network-based proximity measure identified the FDA approved targets in hijacked protein modules which can be hit by existing drugs to rescue these modules from viral possessions, and can lead to the improvement of clinical conditions.
- 10 December 2020
- Published by Springer Nature in Research Square
Open AccessLung Disease Network Reveals the Impact of Comorbidity on SARS-CoV-2 Infection and Opportunities of Drug Repurposing
Higher mortality of COVID-19 patients with comorbidity is the formidable challenge faced by the health care system. In response to the present crisis, understanding the molecular basis of comorbidity is essential to accelerate the development of drugs. To address this, the genetic association between COVID-19 and various lung disorders was measured and notable molecular resemblance was observed. 141 lung diseases were linked to a neighborhood network of SARS-CoV-2 targets, and 59 lung diseases topologically overlapped with COVID-19 module. This demonstrates the clustering of lung diseases with COVID-19 in the same network vicinity, indicating the potential threat for lung patients upon SARS-CoV-2 infection. Pathobiological similarities between lung diseases and COVID-19, and clinical evidences suggest that shared molecular features probably the reason for comorbidity. Additionally, topological overlap with various lung disorders provides an opportunity to repurpose the drugs used for lung disease to hit the closely associated COVID-19 module. Further analysis showed that the functional protein-protein interaction modules in the lungs, substantially hijacked by SARS-CoV-2, were connected to several lung disorders. The network-based proximity measure identified the FDA approved targets in hijacked protein modules which can be hit by existing drugs to rescue these modules from viral possessions, and can lead to the improvement of clinical conditions.