Gopakumar Gopalakrishnan
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
Gopakumar Gopalakrishnan has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Jayaraj Pottekkattuvalappil Balakrishnan
National Institute of Technology Calicut
3 shared publications Achuthsankar S. Nair
2 shared publications- K. A. Abdul Nazeer
Department of Computer Science and Engineering, National Institute of Technology Calicut, Calicut 673601, Kerala, India
2 shared publications - Manu Madhavan
Indian Institute of Information Technology, Kottayam, Kottayam, Kerela, India
2 shared publications Meeta Pradhan
School of Informatics, Indiana University Purdue University Indianapolis, Indiana, USA 46202
2 shared publications- SujayKumar Reddy M
B. Tech. Student, SCOPE, VIT University, Vellore,Tamilnadu, India
2 shared publications
Latest Publications
- Open Access
- 22 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 145295-145307
Computational Drug Repurposing Using Power Graph Analysis of Integrated Drug-Target-Disease Network
The drug discovery and development is a complex and expensive process, and the probability of success is low. Nowadays, the philosophy of drug discovery has been transformed from one-drug one-target to multiple-drug multiple-targets , called as Polypharmacology, in order to discover new drugs or novel targets for existing drugs, known as Drug repurposing. In particular, the improvements in drug discovery for complex diseases such as cancer, could be achieved by studying drug action through network biology. These networks has contributed to the genesis of Network pharmacology. Integrating and analyzing heterogeneous genome-scale data is a huge algorithmic challenge for modern systems biology. In this paper Power Graph Analysis (PGA) has been applied to explore the tripartite Drug-Target-Disease networks, which is a lossless transformation of biological networks into a compact, less redundant representation. Specifically, the effectiveness of Power Graph is analysed with state-of-the-art SNS (Shared Neighbourhood Scoring) algorithm, in two case studies. We analysed two separate integrated tripartite biomedical networks from (i) PharmDB, a tripartite pharmacological network database; and (ii) COVIDrugNet, the SARS-CoV-2 Virus–Host–Drug Interactome. Despite very high edge reduction, PGA helps to easily explore much more enriched information without any loss and discover novel potential drugs currently in clinical trial to treat lung cancer - Squamous Cell Carcinoma (SCC) and SARS-CoV-2 diseases. Also it outperformed SNS algorithm in terms of accuracy and efficiency, as the SNS algorithm requires computationally expensive calculations for large networks. Furthermore, it exhibits superior scalability, making it suitable for analyzing large-scale datasets.
- 22 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 145295-145307
Open AccessComputational Drug Repurposing Using Power Graph Analysis of Integrated Drug-Target-Disease Network
The drug discovery and development is a complex and expensive process, and the probability of success is low. Nowadays, the philosophy of drug discovery has been transformed from one-drug one-target to multiple-drug multiple-targets , called as Polypharmacology, in order to discover new drugs or novel targets for existing drugs, known as Drug repurposing. In particular, the improvements in drug discovery for complex diseases such as cancer, could be achieved by studying drug action through network biology. These networks has contributed to the genesis of Network pharmacology. Integrating and analyzing heterogeneous genome-scale data is a huge algorithmic challenge for modern systems biology. In this paper Power Graph Analysis (PGA) has been applied to explore the tripartite Drug-Target-Disease networks, which is a lossless transformation of biological networks into a compact, less redundant representation. Specifically, the effectiveness of Power Graph is analysed with state-of-the-art SNS (Shared Neighbourhood Scoring) algorithm, in two case studies. We analysed two separate integrated tripartite biomedical networks from (i) PharmDB, a tripartite pharmacological network database; and (ii) COVIDrugNet, the SARS-CoV-2 Virus–Host–Drug Interactome. Despite very high edge reduction, PGA helps to easily explore much more enriched information without any loss and discover novel potential drugs currently in clinical trial to treat lung cancer - Squamous Cell Carcinoma (SCC) and SARS-CoV-2 diseases. Also it outperformed SNS algorithm in terms of accuracy and efficiency, as the SNS algorithm requires computationally expensive calculations for large networks. Furthermore, it exhibits superior scalability, making it suitable for analyzing large-scale datasets.
- Open Access
- 7 August 2023
- Published by MDPI AG in Preprints.org
PM-Gati Shakti: A Case Study of Demand Forecasting
PM-Gati-Shakti Initiative, integration of ministries, including railways, ports, waterways, logistic infrastructure, mass transport, airports, and roads. Aimed at enhancing connectivity and bolstering the competitiveness of Indian businesses, the initiative focuses on six pivotal pillars known as "Connectivity for Productivity": comprehensiveness, prioritization, optimization, synchronization, analytical, and dynamic. In this study, we explore the application of these pillars to address the problem of "Maximum Demand Forecasting in Delhi." Electricity forecasting plays a very significant role in the power grid as it is required to maintain a balance between supply and load demand at all times, to provide a quality electricity supply, for Financial planning, generation reserve, and many more. Forecasting helps not only in Production Planning but also in Scheduling like Import / Export which is very often in India and mostly required by the rural areas and North Eastern Regions of India. As Electrical Forecasting includes many factors which cannot be detected by the models out there, We use Classical Forecasting Techniques to extract the seasonal patterns from the daily data of Maximum Demand for the Union Territory Delhi. This research contributes to the power supply industry by helping to reduce the occurrence of disasters such as blackouts, power cuts, and increased tariffs imposed by regulatory commissions. The forecasting techniques can also help in reducing OD and UD of Power for different regions. We use the Data provided by a department from the Ministry of Power and use different forecast models including Seasonal forecasts for daily data.
- 7 August 2023
- Published by MDPI AG in Preprints.org
Open AccessPM-Gati Shakti: A Case Study of Demand Forecasting
PM-Gati-Shakti Initiative, integration of ministries, including railways, ports, waterways, logistic infrastructure, mass transport, airports, and roads. Aimed at enhancing connectivity and bolstering the competitiveness of Indian businesses, the initiative focuses on six pivotal pillars known as "Connectivity for Productivity": comprehensiveness, prioritization, optimization, synchronization, analytical, and dynamic. In this study, we explore the application of these pillars to address the problem of "Maximum Demand Forecasting in Delhi." Electricity forecasting plays a very significant role in the power grid as it is required to maintain a balance between supply and load demand at all times, to provide a quality electricity supply, for Financial planning, generation reserve, and many more. Forecasting helps not only in Production Planning but also in Scheduling like Import / Export which is very often in India and mostly required by the rural areas and North Eastern Regions of India. As Electrical Forecasting includes many factors which cannot be detected by the models out there, We use Classical Forecasting Techniques to extract the seasonal patterns from the daily data of Maximum Demand for the Union Territory Delhi. This research contributes to the power supply industry by helping to reduce the occurrence of disasters such as blackouts, power cuts, and increased tariffs imposed by regulatory commissions. The forecasting techniques can also help in reducing OD and UD of Power for different regions. We use the Data provided by a department from the Ministry of Power and use different forecast models including Seasonal forecasts for daily data.
- Open Access
PM-Gati Shakti: Advancing India's Energy Future through Demand Forecasting -- A Case Study
PM-Gati-Shakti Initiative, integration of ministries, including railways, ports, waterways, logistic infrastructure, mass transport, airports, and roads. Aimed at enhancing connectivity and bolstering the competitiveness of Indian businesses, the initiative focuses on six pivotal pillars known as "Connectivity for Productivity": comprehensiveness, prioritization, optimization, synchronization, analytical, and dynamic. In this study, we explore the application of these pillars to address the problem of "Maximum Demand Forecasting in Delhi." Electricity forecasting plays a very significant role in the power grid as it is required to maintain a balance between supply and load demand at all times, to provide a quality electricity supply, for Financial planning, generation reserve, and many more. Forecasting helps not only in Production Planning but also in Scheduling like Import / Export which is very often in India and mostly required by the rural areas and North Eastern Regions of India. As Electrical Forecasting includes many factors which cannot be detected by the models out there, We use Classical Forecasting Techniques to extract the seasonal patterns from the daily data of Maximum Demand for the Union Territory Delhi. This research contributes to the power supply industry by helping to reduce the occurrence of disasters such as blackouts, power cuts, and increased tariffs imposed by regulatory commissions. The forecasting techniques can also help in reducing OD and UD of Power for different regions. We use the Data provided by a department from the Ministry of Power and use different forecast models including Seasonal forecasts for daily data.
Open AccessPM-Gati Shakti: Advancing India's Energy Future through Demand Forecasting -- A Case Study
PM-Gati-Shakti Initiative, integration of ministries, including railways, ports, waterways, logistic infrastructure, mass transport, airports, and roads. Aimed at enhancing connectivity and bolstering the competitiveness of Indian businesses, the initiative focuses on six pivotal pillars known as "Connectivity for Productivity": comprehensiveness, prioritization, optimization, synchronization, analytical, and dynamic. In this study, we explore the application of these pillars to address the problem of "Maximum Demand Forecasting in Delhi." Electricity forecasting plays a very significant role in the power grid as it is required to maintain a balance between supply and load demand at all times, to provide a quality electricity supply, for Financial planning, generation reserve, and many more. Forecasting helps not only in Production Planning but also in Scheduling like Import / Export which is very often in India and mostly required by the rural areas and North Eastern Regions of India. As Electrical Forecasting includes many factors which cannot be detected by the models out there, We use Classical Forecasting Techniques to extract the seasonal patterns from the daily data of Maximum Demand for the Union Territory Delhi. This research contributes to the power supply industry by helping to reduce the occurrence of disasters such as blackouts, power cuts, and increased tariffs imposed by regulatory commissions. The forecasting techniques can also help in reducing OD and UD of Power for different regions. We use the Data provided by a department from the Ministry of Power and use different forecast models including Seasonal forecasts for daily data.
- 18 May 2023
- Published by Springer Nature in The Protein Journal
- Vol. 42 (4) , 276-287
DeepBindPPI: Protein–Protein Binding Site Prediction Using Attention Based Graph Convolutional Network
Due to the importance of protein-protein interactions in defence mechanism of living body, attempts were made to investigate its attributes, including, but not limited to, binding affinity, and binding region. Contemporary strategies for binding site prediction largely resort to deep learning techniques but turned out to be low precision models. As laboratory experiments for drug discovery tasks utilize this information, increased false positives devalue the computational methods. This emphasize the need to develop enhanced strategies. DeepBindPPI employs deep learning technique to predict the binding regions of proteins, particularly antigen–antibody interaction sites. The results obtained are applied in a docking environment to confirm their correctness. An integration of graph convolutional network with attention mechanism predicts interacting amino acids with improved precision. The model learns the determining factors in interaction from a general pool of proteins and is then fine-tuned using antigen–antibody data. Comparison of the proposed method with existing techniques shows that the developed model has comparable performance. The use of a separate spatial network clearly improved the precision of the proposed method from 0.4 to 0.5. An attempt to utilize the interface information for docking using the HDOCK server gives promising results, with high-quality structures appearing in the top10 ranks.
- 18 May 2023
- Published by Springer Nature in The Protein Journal
- Vol. 42 (4) , 276-287
DeepBindPPI: Protein–Protein Binding Site Prediction Using Attention Based Graph Convolutional Network
Due to the importance of protein-protein interactions in defence mechanism of living body, attempts were made to investigate its attributes, including, but not limited to, binding affinity, and binding region. Contemporary strategies for binding site prediction largely resort to deep learning techniques but turned out to be low precision models. As laboratory experiments for drug discovery tasks utilize this information, increased false positives devalue the computational methods. This emphasize the need to develop enhanced strategies. DeepBindPPI employs deep learning technique to predict the binding regions of proteins, particularly antigen–antibody interaction sites. The results obtained are applied in a docking environment to confirm their correctness. An integration of graph convolutional network with attention mechanism predicts interacting amino acids with improved precision. The model learns the determining factors in interaction from a general pool of proteins and is then fine-tuned using antigen–antibody data. Comparison of the proposed method with existing techniques shows that the developed model has comparable performance. The use of a separate spatial network clearly improved the precision of the proposed method from 0.4 to 0.5. An attempt to utilize the interface information for docking using the HDOCK server gives promising results, with high-quality structures appearing in the top10 ranks.
- 23 August 2022
- Published by Springer Nature in Journal of Molecular Modeling
- Vol. 28 (9) , 1-10
Protein secondary structure assignment using residual networks
Proteins are constructed from amino acid sequences. Their structural classifications include primary, secondary, tertiary, and quaternary, with tertiary and quaternary structures influencing protein function. Because a protein’s structure is inextricably connected to its biological function, machine learning algorithms that can better anticipate the structures have the potential to lead to new scientific discoveries in human health and improve our capacity to develop new treatments. Protein secondary structure assignment enriches the structural and functional understanding of proteins. It helps in protein structure comparison and classification studies, besides facilitating secondary and tertiary structure prediction systems. Several secondary structure assignment methods have been developed since the 1980s, most of which are based on hydrogen bond analysis and atomic coordinate features. However, the assignment process becomes complex when protein data includes missing atoms. Deep neural networks are often referred to as universal function approximators because they can approximate any function to produce the desired output when properly designed and trained. Optimised deep learning architectures have already proven their ability to increase performance in a wide range of problems. Recently, the ResNet architecture has garnered significant interest due to its applicability in various areas, including image classification and protein contact map prediction. The proposed model, which is based on the ResNet architecture, assigns secondary structures using Cα atom coordinates. The model achieved an accuracy of 94% when evaluated against the benchmark and independent test sets. The findings encourage the development of new deep learning-based methods that are more generalised across various protein learning tasks. Furthermore, it allows computational biologists to delve deeper into integrating these techniques with experimental methods. The model codes are available at: https://github.com/jisnava/ResNet_for_Structure_Assignments/.
- 23 August 2022
- Published by Springer Nature in Journal of Molecular Modeling
- Vol. 28 (9) , 1-10
Protein secondary structure assignment using residual networks
Proteins are constructed from amino acid sequences. Their structural classifications include primary, secondary, tertiary, and quaternary, with tertiary and quaternary structures influencing protein function. Because a protein’s structure is inextricably connected to its biological function, machine learning algorithms that can better anticipate the structures have the potential to lead to new scientific discoveries in human health and improve our capacity to develop new treatments. Protein secondary structure assignment enriches the structural and functional understanding of proteins. It helps in protein structure comparison and classification studies, besides facilitating secondary and tertiary structure prediction systems. Several secondary structure assignment methods have been developed since the 1980s, most of which are based on hydrogen bond analysis and atomic coordinate features. However, the assignment process becomes complex when protein data includes missing atoms. Deep neural networks are often referred to as universal function approximators because they can approximate any function to produce the desired output when properly designed and trained. Optimised deep learning architectures have already proven their ability to increase performance in a wide range of problems. Recently, the ResNet architecture has garnered significant interest due to its applicability in various areas, including image classification and protein contact map prediction. The proposed model, which is based on the ResNet architecture, assigns secondary structures using Cα atom coordinates. The model achieved an accuracy of 94% when evaluated against the benchmark and independent test sets. The findings encourage the development of new deep learning-based methods that are more generalised across various protein learning tasks. Furthermore, it allows computational biologists to delve deeper into integrating these techniques with experimental methods. The model codes are available at: https://github.com/jisnava/ResNet_for_Structure_Assignments/.
- 22 October 2021
- Published by Bentham Science Publishers Ltd. in Current Bioinformatics
- Vol. 16 (7) , 983-991
Long Non-coding RNAs in Heart Failure: A Deep Belief Network Based Cluster Analysis
Background: Heart failure (HF) is a leading cause of mortality rate worldwide, but studied less for its underlying biomolecular mechanisms. With the advances in gene sequence analysis, many non-coding RNAs, especially from long non-coding RNA (lncRNA) genre are found to be involved in regulating HF conditions. Recent studies are based on competing endogenous RNA (ceRNA) theory in which lncRNA-miRNA-mRNA compounds control many disease conditions. Method: In this paper, we present a topic model based network cluster analysis to identify the role of lncRNAs in HF. The network is constructed based on the differentially expressed long noncoding RNAs (lncRNAs), micro RNAs (miRNAs), and messenger RNAs (mRNAs) of heart failure patients and control samples from the gene expression omnibus (GEO) database. Further, we extend the primary ceRNA network by adding pathways as additional nodes. Deep belief network based feature learning is used to extract the features from the network automatically. Results: We obtained two clusters where each cluster was a mixture of lncRNAs, mRNAs, miRNAs and pathways. The analysis included the identification of key lncRNAs, enriched pathways, and gene ontology terms from each cluster. Based on the shreds of evidence from literature, one of the clusters obtained was identified to be an essential functional module in HF mechanism. The potential of lncRNA as a diagnostic biomarker in HF was also analysed. Availability: https://github.com/manumad/dbnclust-lnchf
- 22 October 2021
- Published by Bentham Science Publishers Ltd. in Current Bioinformatics
- Vol. 16 (7) , 983-991
Long Non-coding RNAs in Heart Failure: A Deep Belief Network Based Cluster Analysis
Background: Heart failure (HF) is a leading cause of mortality rate worldwide, but studied less for its underlying biomolecular mechanisms. With the advances in gene sequence analysis, many non-coding RNAs, especially from long non-coding RNA (lncRNA) genre are found to be involved in regulating HF conditions. Recent studies are based on competing endogenous RNA (ceRNA) theory in which lncRNA-miRNA-mRNA compounds control many disease conditions. Method: In this paper, we present a topic model based network cluster analysis to identify the role of lncRNAs in HF. The network is constructed based on the differentially expressed long noncoding RNAs (lncRNAs), micro RNAs (miRNAs), and messenger RNAs (mRNAs) of heart failure patients and control samples from the gene expression omnibus (GEO) database. Further, we extend the primary ceRNA network by adding pathways as additional nodes. Deep belief network based feature learning is used to extract the features from the network automatically. Results: We obtained two clusters where each cluster was a mixture of lncRNAs, mRNAs, miRNAs and pathways. The analysis included the identification of key lncRNAs, enriched pathways, and gene ontology terms from each cluster. Based on the shreds of evidence from literature, one of the clusters obtained was identified to be an essential functional module in HF mechanism. The potential of lncRNA as a diagnostic biomarker in HF was also analysed. Availability: https://github.com/manumad/dbnclust-lnchf
- 26 July 2020
- Published by Springer Nature
- p. 311-319
Prediction of lncRNA-Cancer Association Using Topic Model on Graphs
- 26 July 2020
- Published by Springer Nature
- p. 311-319
Prediction of lncRNA-Cancer Association Using Topic Model on Graphs
- 8 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 19 (1) , 255-266
A Heterogeneous Information Network Model for Long Non-Coding RNA Function Prediction
Exciting information on the functional roles played by long non-coding RNA (lncRNA) has drawn substantial research attention these days. With the advent of techniques such as RNA-Seq, thousands of lncRNAs are identified in very short time spans. However, due to the poor annotation rate, only a few of them are functionally characterised. The wet lab experiments to elucidate lncRNA functions are challenging, slow progressing and sometimes prohibitively expensive. This work attempts to solve the crucial problem of developing computational methods to predict lncRNA functions. The model presented here, predicts the functions of lncRNAs by making use of a meta-path based measure, AvgSim on a Heterogeneous Information Network (HIN). The network is constructed from existing protein and function association data of lncRNAs, lncRNA co-expression data and protein protein interaction data.The proposed method predicts possible functions of 2,695 lncRNAs with an accuracy of 73.68% and found to perform better than the other state-of-the-art approaches for an independent test set. A case study of two well-known lncRNAs (HOTAIR and H19) is conducted and the associated functions are identified. The results were validated using experimental evidence from the literature. The script and data used for the implementation of the model is freely available at: http://bdbl.nitc.ac.in/LncFunPred/index.html.
- 8 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 19 (1) , 255-266
A Heterogeneous Information Network Model for Long Non-Coding RNA Function Prediction
Exciting information on the functional roles played by long non-coding RNA (lncRNA) has drawn substantial research attention these days. With the advent of techniques such as RNA-Seq, thousands of lncRNAs are identified in very short time spans. However, due to the poor annotation rate, only a few of them are functionally characterised. The wet lab experiments to elucidate lncRNA functions are challenging, slow progressing and sometimes prohibitively expensive. This work attempts to solve the crucial problem of developing computational methods to predict lncRNA functions. The model presented here, predicts the functions of lncRNAs by making use of a meta-path based measure, AvgSim on a Heterogeneous Information Network (HIN). The network is constructed from existing protein and function association data of lncRNAs, lncRNA co-expression data and protein protein interaction data.The proposed method predicts possible functions of 2,695 lncRNAs with an accuracy of 73.68% and found to perform better than the other state-of-the-art approaches for an independent test set. A case study of two well-known lncRNAs (HOTAIR and H19) is conducted and the associated functions are identified. The results were validated using experimental evidence from the literature. The script and data used for the implementation of the model is freely available at: http://bdbl.nitc.ac.in/LncFunPred/index.html.
- 1 August 2019
- Published by World Scientific Pub Co Pte Ltd in Journal of Bioinformatics and Computational Biology
- Vol. 17 (04) , 1950020
Inferring disease and pathway associations of long non-coding RNAs using heterogeneous information network model
Recent findings from biological experiments demonstrate that long non-coding RNAs (lncRNAs) are actively involved in critical cellular processes and are associated with innumerable diseases. Computational prediction of lncRNA–disease association draws tremendous research attention nowadays. This paper proposes a machine learning model that predicts lncRNA–disease associations using Heterogeneous Information Network (HIN) of lncRNAs and diseases. A Support Vector Machine classifier is developed using the feature set extracted from a meta-path-based parameter, Association Index derived from the HIN. Performance of the model is validated using standard statistical metrics and it generated an AUC value of 0.87, which is better than the existing methods in the literature. Results are further validated using the recent literature and many of the predicted lncRNA–disease associations are identified as actually existing. This paper also proposes an HIN-based methodology to associate lncRNAs with pathways in which they may have biological influence. A case study on the pathway associations of four well-known lncRNAs (HOTAIR, TUG1, NEAT1, and MALAT1) has been conducted. It has been observed that many times the same lncRNA is associated with more than one biologically related pathways. Further exploration is needed to substantiate whether such lncRNAs have any role in determining the pathway interplay. The script and sample data for the model construction is freely available at http://bdbl.nitc.ac.in/LncDisPath/index.html .
- 1 August 2019
- Published by World Scientific Pub Co Pte Ltd in Journal of Bioinformatics and Computational Biology
- Vol. 17 (04) , 1950020
Inferring disease and pathway associations of long non-coding RNAs using heterogeneous information network model
Recent findings from biological experiments demonstrate that long non-coding RNAs (lncRNAs) are actively involved in critical cellular processes and are associated with innumerable diseases. Computational prediction of lncRNA–disease association draws tremendous research attention nowadays. This paper proposes a machine learning model that predicts lncRNA–disease associations using Heterogeneous Information Network (HIN) of lncRNAs and diseases. A Support Vector Machine classifier is developed using the feature set extracted from a meta-path-based parameter, Association Index derived from the HIN. Performance of the model is validated using standard statistical metrics and it generated an AUC value of 0.87, which is better than the existing methods in the literature. Results are further validated using the recent literature and many of the predicted lncRNA–disease associations are identified as actually existing. This paper also proposes an HIN-based methodology to associate lncRNAs with pathways in which they may have biological influence. A case study on the pathway associations of four well-known lncRNAs (HOTAIR, TUG1, NEAT1, and MALAT1) has been conducted. It has been observed that many times the same lncRNA is associated with more than one biologically related pathways. Further exploration is needed to substantiate whether such lncRNAs have any role in determining the pathway interplay. The script and sample data for the model construction is freely available at http://bdbl.nitc.ac.in/LncDisPath/index.html .
- 1 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 98-102
Relrank: An Algorithm for Relevance-Based Ranking of Meta-Paths in a Heterogeneous Information Network
Heterogeneous Information Networks (HIN) are extensively used for mapping heterogeneous data to solve complex real life problems computationally. Meta-path is a key concept used in HIN based research. The efficiency and accuracy of an HIN based task heavily depend on the identification and effective utilisation of meta-paths that are relevant to the problem at hand. Here, we propose an algorithm, Relrank to rank the meta-paths in an HIN in order of their relevance. The algorithm assigns a relevance score to each meta-path under a specific length threshold. The meta-paths are ranked based on the relevance score. The degree of closeness of each meta-path to the actual links present in the HIN acts as the key parameter in determining the rank. We tested the efficiency of the algorithm by applying it on an real world HIN with biological interaction data, to derive novel findings from existing knowledge. The results obtained, justified the correctness of the proposed algorithm. Furthermore, the algorithm design is generic enough to encompass heterogeneous data across various domains.
- 1 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 98-102
Relrank: An Algorithm for Relevance-Based Ranking of Meta-Paths in a Heterogeneous Information Network
Heterogeneous Information Networks (HIN) are extensively used for mapping heterogeneous data to solve complex real life problems computationally. Meta-path is a key concept used in HIN based research. The efficiency and accuracy of an HIN based task heavily depend on the identification and effective utilisation of meta-paths that are relevant to the problem at hand. Here, we propose an algorithm, Relrank to rank the meta-paths in an HIN in order of their relevance. The algorithm assigns a relevance score to each meta-path under a specific length threshold. The meta-paths are ranked based on the relevance score. The degree of closeness of each meta-path to the actual links present in the HIN acts as the key parameter in determining the rank. We tested the efficiency of the algorithm by applying it on an real world HIN with biological interaction data, to derive novel findings from existing knowledge. The results obtained, justified the correctness of the proposed algorithm. Furthermore, the algorithm design is generic enough to encompass heterogeneous data across various domains.