Qualification: 
Ph.D, MSc
nidheesh@am.amrita.edu

Dr. Nidheesh M. currently serves as Assistant Professor at the School of Biotechnology. He received his masters in Computer Science from Amrita Vishwa Vidyapeetaham, Amritapuri in 2005.

Dr. Nidheesh Melethadathil has been a long-time associate of Amrita Institutions with more than 25 years of experience in teaching and research. Dr. Melethadathil obtained his Ph.D. from Faculty of Sciences of Amrita Vishwa Vidyapeetham, in the area of Bioinformatics. His Ph.D. thesis under the guidance of Dr. Shyam Diwakar involved designing and developing a semantic information retrieval system using Biomedical Natural Language Processing and document clustering methods to mine scientific articles from open-access databases. Presently his research focuses on biological named entity recognition using artificial intelligence and its application in genome sequencing.

Dr. Melethadathil is currently hold the position of Assistant Professor at Amrita School of Biotechnology, Amritapuri campus.

Awards / Recognition

  • Recipient of Best Faculty Award, Amrita Institute of Computer Technology, 1997
  • Recipient of Best Faculty Achievement Award, School of Biotechnology, Amrita University, 2010.

Publications

Publication Type: Conference Paper

Year of Publication Publication Type Title

2020

Conference Paper

J. Alphonse, Binosh, A. N., Raj, S., Pal, S., and Nidheesh Melethadathil, “Semantic Retrieval of Microbiome Information Based on Deep Learning”, in Fourth International Conference on Computing and Network Communications (CoCoNet'20) & International Conference on Applied Soft Computing and Communication Networks (ACN'20) , 2020.

2017

Conference Paper

Nidheesh Melethadathil, Nair, B., Diwakar, S., and Pazhanivelu, S., “Assessing short-term social media marketing outreach of a healthcare organization using machine learning”, in 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017.[Abstract]


Social networking portals serve as an ideal platform for a person or an organization, to accomplish self-presentation and self-enhancement goals there by to understand their social relevance and hence, there have been many studies attempting to identify the relationship between different aspects of social media articles. Machine learning methods play a critical role in social media data analytics. This study evaluates the efficiency of predictive analytics with social media data of a private healthcare institution using classification and clustering algorithms. In this study, we also investigated the influence of system specific feature set and user generated features of social media articles to identify relevant data mining algorithms that are suitable for identifying knowledge-related patterns in dataset. Among the classification methods it is found that Bayesian algorithm performs better compared to other classification techniques. K-Means and Filtered cluster among the clustering techniques have better predictive analytics efficiency compared to other algorithms. Identifying the predictive analytics efficacy of these algorithms helps healthcare institution to build a model with most appropriate characteristics of social media articles.

More »»

2015

Conference Paper

Nidheesh Melethadathil, Priya Chellaiah, Dr. Bipin G. Nair, and Dr. Shyam Diwakar, “Classification and Clustering for Neuroinformatics: Assessing the efficacy on reverse-mapped NeuroNLP data using standard ML techniques”, in Proceedings of the Fourth International Conference on Advances in Computing, Communications and Informatics (ICACCI-2015), Kochi, India, 2015.[Abstract]


NeuroinformaticsNatural Language Processing (NeuroNLP) relies on clustering and classification for information categorization of biologically relevant extraction targets and for interconnections to knowledge-related patterns in event and text mined datasets. The accuracy of machine learning algorithms depended on quality of text-mined data while efficacy relied on the context of the choice of techniques. Although developments of automated keyword extraction methods have made differences in the quality of data selection, the efficacy of the Natural Language Processing (NLP) methods using verified keywords remain a challenge. In this paper, we studied the role of text classification and document clustering algorithms on datasets, where features were obtained by mapping to manually verified MESH terms published by National Library of Medicine (NLM). In this study, NLP data classification involved comparing 8techniques and unsupervised learning was performed with 6 clustering algorithms. Most classification techniques except meta-based algorithms namely stacking and vote, allowed 90% or higher training accuracy. Test accuracy was high (=>95%) probably due to limited test dataset. Logistic Model Trees had 30-fold higher runtime compared to other classification algorithms including Naive Bayes, AdaBoost, Hoeffding Tree. Grouped error rate in clustering was 0-4%. Runtime-wise, clustering was faster than classification algorithms on MESH-mapped NLP data suggesting clustering methods as adequate towards Medline-related datasets and text-mining big data analytic systems. © 2015 IEEE.

More »»
PDF iconclassification-and-clustering-for-neuroinformatics-assessing-the-efficacy-on-reverse-mapped-neuronlp-data-using-standard-ml-techniques.pdf

2014

Conference Paper

Nidheesh Melethadathil, Dr. Bipin G. Nair, and Dr. Shyam Diwakar, “Facilitating Neuroscience Surveys using a Meta Path based Neuroinformatics Text-Mining Platform”, in Proceedings of the International symposium on Translational Neuroscience & XXXII Annual Conference of the Indian Academy of Neurosciences, NIMHANS, Bangalore , India, 2014.

2011

Conference Paper

Dr. Bipin G. Nair, Dr. Shyam Diwakar, Parasuram H., Medini C, Manjusha Nair, Nidheesh Melethadathil, Naldi G., and D’Angelo E., “Modeling evoked local field potentials in the cerebellum granular layer and plasticity changes reveal single neuron effects in neural ensembles”, in Acta Physiologica, 2011.

2011

Conference Paper

Nidheesh Melethadathil, Dr. Bipin G. Nair, and Dr. Shyam Diwakar, “Neuroinformatics database for multi-level physiological mapping based on sematic clustering”, in Proceedings of the International symposium on `Recent Trends in Neurosciences & XXIX Annual Conference of Indian Academy of Neurosciences, 2011.

2010

Conference Paper

Dr. Manitha B. Nair, Nidheesh Melethadathil, Dr. Bipin G. Nair, Dr. Shyam Diwakar, and Manjusha Nair, “Information processing via post-synaptic EPSP-spike complex and model-based predictions of induced changes during plasticity in cerebellar granular neuron”, in Proceedings of the 1st Amrita ACM-W Celebration of Women in Computing in India, A2CWiC'10, Coimbatore, 2010.[Abstract]


Understanding functional role of spike bursts in the brain circuits is vital in analyzing coding of sensory information. Information coding in neurons or brain cells happen as spikes or action potentials and excitatory post-synaptic potentials (EPSPs). Information transmission at the Mossy fiber- Granule cell synaptic relay is crucial to understand mechanisms of signal coding in the cerebellum. We analyzed spiking in granule cells via a detailed computational model and computed the spiking-potentiation contributing to signal recoding in granular layer. Plasticity is simulated in the granule cell model by changing the intrinsic excitability and release probability of the cells. Excitatory post synaptic potentials and spikes on varying Golgi cell (GoC) inhibition and Mossy fiber(MF) excitation were analyzed simultaneously with the effect of induced plasticity changes based on the timing and amplitude of the postsynaptic signals. It is found that a set of EPSPs reaching maximum threshold amplitude are converted to less number of high amplitude EPSPs or spikes. Exploring the EPSP-spike complex in granular neurons reveal possible mechanisms and quantification of information encoding in individual neurons of the cerebellar granular layer. Therefore, our study is potentially an important estimation of cerebellar function. © 2010 ACM.

More »»
PDF iconinformation-processing-via-post-synaptic-epsp-spike-complex-and-model-based-predictions-of-induced-changes-during-plasticity-in-cerebellar-granular-neuron.pdf

Publication Type: Journal Article

Year of Publication Publication Type Title

2019

Journal Article

Nidheesh Melethadathil, Dr. Bipin G. Nair, Dr. Shyam Diwakar, and Jaap Heringa, “Mining inter-relationships in online scientific articles and its visualization: Natural language processing for systems biology modeling”, International Journal of Online Engineering, vol. 15, no. 2, pp. 39-59, 2019.[Abstract]


With the rapid growth in the numbers of scientific publications in domains such as neuroscience and medicine, visually interlinking documents in online databases such as PubMed with the purpose of indicating the context of a query results can improve the multi-disciplinary relevance of the search results. Translational medicine and systems biology rely on studies relating basic sciences to applications, often going through multiple disciplinary domains. This paper focuses on the design and development of a new scientific document visualization platform, which allows inferring translational aspects in biosciences within published articles using machine learning and natural language processing (NLP) methods. From online databases, this software platform effectively extracted relationship connections between multiple subdomains within neuroscience derived from abstracts related to user query. In our current implementation, the document visualization platform employs two clustering algorithms namely Suffix Tree Clustering (STC) and LINGO. Clustering quality was improved by mapping top-ranked cluster labels derived from an UMLS-Metathesaurus using a scoring function. To avoid non-clustered documents, an iterative scheme, called auto-clustering was developed and this allowed mapping previously uncategorized documents during the initial grouping process to relevant clusters. The efficacy of this document clustering and visualization platform was evaluated by expert-based validation of clustering results obtained with unique search terms. Compared to normal clustering, auto-clustering demonstrated better efficacy by generating larger numbers of unique and relevant cluster labels. Using this implementation, a Parkinson's disease systems theory model was developed and studies based on user queries related to neuroscience and oncology have been showcased as applications. © 2019 Kassel University Press GmbH.

More »»

2017

Journal Article

H. Sasidharakurup, Nidheesh Melethadathil, Nair, B., and Diwakar, S., “A Systems Model of Parkinson's Disease Using Biochemical Systems Theory.”, OMICS, vol. 21, no. 8, pp. 454-464, 2017.[Abstract]


Parkinson's disease (PD), a neurodegenerative disorder, affects millions of people and has gained attention because of its clinical roles affecting behaviors related to motor and nonmotor symptoms. Although studies on PD from various aspects are becoming popular, few rely on predictive systems modeling approaches. Using Biochemical Systems Theory (BST), this article attempts to model and characterize dopaminergic cell death and understand pathophysiology of progression of PD. PD pathways were modeled using stochastic differential equations incorporating law of mass action, and initial concentrations for the modeled proteins were obtained from literature. Simulations suggest that dopamine levels were reduced significantly due to an increase in dopaminergic quinones and 3,4-dihydroxyphenylacetaldehyde (DOPAL) relating to imbalances compared to control during PD progression. Associating to clinically observed PD-related cell death, simulations show abnormal parkin and reactive oxygen species levels with an increase in neurofibrillary tangles. While relating molecular mechanistic roles, the BST modeling helps predicting dopaminergic cell death processes involved in the progression of PD and provides a predictive understanding of neuronal dysfunction for translational neuroscience.

More »»

2011

Journal Article

P. K. Kab Namboori, Vineeth, K. Vb, Rohith, Vb, Hassan, Ia, Sekhar, La, Sekhar, Aa, and Nidheesh Melethadathil, “The ApoE gene of Alzheimer's disease (AD)”, Functional and Integrative Genomics, vol. 11, pp. 519-522, 2011.[Abstract]


The ApoE gene responsible for the Alzheimer's disease has been examined to identify functional consequences of single-nucleotide polymorphisms (SNPs). Eighty-eight SNPs have been identified in the ApoE gene in which 31 are found to be nonsynonymous, 8 of them are coding synonymous, 33 are found to be in intron, and 3 are in untranslated region. The SNPs found in the untranslated region consisted of two SNPs from 5' and one SNP from the 3'. Twenty-nine percent of the identified nsSNPs have been reported as damaging. In the analysis of SNPs in the UTR regions, it has been recognized that rs72654467 from 5' and rs71673244 from 5' and 3' are responsible for the alteration in levels of expression. Both native and mutant protein structures were analyzed along with the stabilization residues. It has been concluded that among all SNPs of ApoE, the mutation in rs11542041 (R132S) has the most significant effect on functional variation. © Springer-Verlag 2011.

More »»