Qualification: 
M.Tech, B-Tech
m_manu@cb.amrita.edu

Manu Madhavan currently serves as Assistant Professor at the Department of Computer Science & Engineering, School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore Campus. He is doing Ph. D. at the Department of Computer Science and Engineering, National Institute of Technology Calicut.  

Education

  • 2011-2013: M.Tech Computational Linguistics
    Govt. Engineering College, Palakkad.
  • 2006-2010: B. Tech. Computer Science and Engineering
    Nehru College of Engineering and Research Center, Thrissur.

Professional Appointments

Year Affiliation
2013-2015 Assistant Professor, Department of Computer Science and Engineering, Sreepathy Institute of Management and Technology, Palakkad.
  Project Intern at Center for Artificial Intelligence and Robotics, DRDO, Bangalore

Publications

Publication Type: Conference Proceedings

Year of Conference Publication Type Title

2020

Conference Proceedings

Manu Madhavan, Reshma Stephen, and Gopakumar G., “Prediction of lncRNA-disease association using Topic Model using Graph”, MoSiCOM 2020 (Springer), BITs Pilani, Dubai Campus, January 29-31. 2020.

2018

Conference Proceedings

Manu Madhavan and Gopakumar G., “A tf-idf based topic model for identifying lncRNAs from genomic background”, SAC '18: Proceedings of the 33rd Annual ACM Symposium on Applied Computing. pp. 40 - 46, 2018.[Abstract]


The developments in high throughput technologies identified a large number of long non-coding RNAs (lncRNAs) whose functional characterization remains an open problem. The available research confirmed that lncRNA plays a major role in genetic and epigenetic regulation, and its expression level has a significant association with some complex diseases like cancers. The identification of lncRNA and their functional characterization is an important task in RNA Bioinformatics. In spite of their abundance in the cell, lncRNAs are less conserved at their sequence level which makes the analysis challenging. Many machine learning based models are developed in the literature for the identification and analysis of lncRNAs. This paper proposes a topic model based method for the identification of lncRNAs. To investigate the applicability of topic model in lncRNA analysis, this work develops an LDA based topic model to group lncRNAs from a collection of transcriptome sequences. The features derived from transformed k-mer patterns and secondary structure of lncRNA sequences are used for the topic model. The results are promising compared to the classic algorithms and prove that the topic models are reasonable for lncRNA analysis.

More »»

2018

Conference Proceedings

C. M. Sreeshma, Manu Madhavan, and Gopakumar G., “Identification of Long Non-coding RNA from inherent features using Machine Learning Techniques”, 2018 International Conference on Bioinformatics and Systems Biology (BSB)2018 International Conference on Bioinformatics and Systems Biology (BSB). 2018.[Abstract]


Long non-coding RNAs are a distinctive class of non-coding RNAs of length greater than 200 nucleotides and no protein coding potential. LncRNA plays an important role in genetic and epigenetic regulation. Major studies reveal that IncRNAs are less conserved in their primary sequences and shows more functional characteristics at secondary structure level. The objective of this work is to identify an optimal sequencestructure combination for computational analysis of IncRNAs. We also propose a novel secondary structure quantization which consider the existence of various structure elements. The feature combinations when used as input to classification of IncRNAs from coding RNAs, significant improvement in the results were obtained. More »»

2013

Conference Proceedings

Manu Madhavan and Mujeeb Rehman O., “Computing Prosodic Pattern for Malayalam”, NCILC, CUSAT, Cochin. pp. 1-4, 2013.[Abstract]


Virtta or Chandas in languages like Sanskrit,Malayalam is a set of well defined rules that give rhythm to thepoetry. The basic unit in this analysis is short-long (laghu-guru)letters and this can be viewed as a mathematical measure inwhich the prosody of poetry is made. The computation of theseprosodic patterns has many advantages in various fields of NLP.This paper discusses the computation of prosodic patterns andpresents a rule-based system for identifying short-long (laghu-guru) patterns from input Malayalam strings.

More »»

2013

Conference Proceedings

Manu Madhavan, Robert Jesuraj, and Reghu Raj P. C., “Design of Scalable Natural Language Report Management System”, International Conference on NLP (ICON). 2013.[Abstract]


Understanding natural language text by automated systems is becoming popular as the need for conversion of unstructured text to structured text increases. We report the design of a scalable Natural Language Report Management System in which information is collected from unstructured texts is done using statistical natural language processing tools like NLTK (Bird S, 2009), Stanford CoreNLP (Stanford CoreNLP, 2013) etc. The extracted information is then stored in a graph database to form the knowledge base. More information is added to this knowledge base using semantic web technology, DBpedia, and Geo-ontology. Reasoners like Pellet are used to improve the reasoning capabilities of the system. The query processing system, with the query being in natural language, will search for an absolute match in the stored knowledge base. A Natural language generation module is integrated with the system, using which the processed query result is articulated to produce answers in natural language.

More »»

2012

Conference Proceedings

Manu Madhavan and Reghuraj P. C., “Applications of Karaka Relations in Natural Language Generations”, NCILC, CUSAT, Cochin. pp. 1-3, 2012.[Abstract]


Natural language Generation (NLG) is the compu-tational process of automatically producing sentences in somehuman languages. NLG systems use machine understandablelogical form as input and produces syntactically and semanticallyvalid sentences in natural language. The effectiveness of the NLGdepends on the efficiency of input knowledge representation. Thispaper analyses the scope of Indian concepts of language andmeaning, especially Karaka for better knowledge representationfor NLG systems.

More »»

Publication Type: Journal Article

Year of Conference Publication Type Title

2018

Journal Article

Manu Madhavan and Gopakumar Gopalakrishnan Nair, “An Effective Sequence Structure Representation for Long Non-Coding RNA Identification and Cancer Association Using Machine Learning Methods”, SIGAPP Appl. Comput. Rev., vol. 18, no. 3, pp. 49–58, 2018.[Abstract]


The invent of high-throughput technologies and consequent developments in Bioinformatics research unveiled many important non-coding transcript molecules such as Long non-coding RNAs (lncRNAs). The available studies confirmed that lncRNAs play important genetic and epigenetic roles in higher-order species like the human and their differential expressions leads to complex diseases like cancer. Even though there are arrays of studies and related tools for the analysis, less conserved patterns in the sequences and intractable structural properties challenge the understanding of varying functionalities of lncRNAs. For the better approximation of these characteristics, higher quality feature representation is required. This paper proposes an extended hybrid sequence-structure feature set for machine learning based lncRNA analysis. Here, the sequence features are derived from various frequencies of k-mer patterns, GC content and molecular weight. The structure representations consider the context of different secondary structure elements which include stems, interior loops, multi-loops and hairpin loops. These features are used for the classification of lncRNA/mRNA and cancerous/non-cancerous lncRNAs. The classifications use machine learning algorithms such as LDA based topic model, Random Forest, SVM and Naïve Bayes. The results show that the proposed feature set is effective in classifying lncRNAs and provide a direction towards the analysis of the role of secondary structure elements in cancer-related lncRNAs.

More »»