Dr. Nithya Ramakrishnan

Dr. Nithya Ramakrishnan

Assistant Professor, Information Theory, Algorithms and Machine Learning in Biology
Joined IBAB in 2023

Research Focus Keywords:

Computational biology, probabilistic modelling, genomics, mathematical techniques for understanding cancer, immunology, and other biological phenomena


Dr. Nithya Ramakrishnan obtained her Bachelor of Engineering. in Electronics and Communication Engineering from Thiagarajar College of Engineering, Madurai. Subsequently, she completed her PhD in Electrical Engineering from IIT Delhi in the inter-disciplinary area of information theory-based analysis of biological data, with a focus on intron-exon segmentation and cancer detection based on epigenetic information. During her post-doctoral terms at IIT
Bombay and Dalhousie University (Canada), she has worked on modelling epigenetic phenomena and chromatin inheritance using information theory, statistical analyses of multi-omics data and bioinformatic pipelines. Prior to her research career, she worked in the software industry (Sun Microsystems/Oracle) as a lead software developer.

She joined IBAB in Feb 2023.


  • B.E (Electronics and Communication Engineering) – Thiagarajar College of Engineering, Madurai
  • PhD – Dept. of Electrical Engineering, IIT Delhi
  • Post-doctoral research – Dept of Biosciences and Bioengineering, IIT Bombay
  • Post-doctoral research – Dalhousie University, Halifax, Canada.

Professional experience:

  • Lead software developer – Cognizant Solutions/Sun Microsystems/Oracle
  • Institute Post-doctoral Fellow – Dept of Biosciences and Bioengineering, IIT Bombay
  • Post-doctoral Fellow – Dalhousie University, Halifax, Canada

Research interest profile

We apply Machine Learning, Deep Learning, Information theoretic and Algorithmic techniques to model biological problems and analyze biological datasets

Graph algorithms for  Bioinformatic Analysis.

We used concepts based on Graph theory, Statistics and Information theory for analysis of biological datasets. Using mathematical principles obtained from the above listed areas, we develop efficient techniques for unsupervised bioinformatic approaches such as clustering and feature selection for genomic / epigenetic datasets.

Gene Expression Prediction

We model the epigenetic factors associated with gene expression regulation such as DNA methylation, histone Post Translational modifications and their relationships using Information theory. We develop deep learning models based on the above measures and data to predict expression of genes.

Developing a Deep Reinforcement Learning Model for Somatic Hypermutation – in Design of Hyper Antibodies

Antibody diversity in response to an invading infection is created from numerous combinations of V,D,J regions of the genome . Upon activation, a B-cell undergoes somatic hypermutation – a process of repeated mutations and cloning leading to several B-cells competing to fit the antigen best. This process in which a B-cell learns to mutate itself towards the best fit with the antigen is being modelled as a Reinforcement Learning problem. 

Pembrolizumab is an antibody designed to inhibit PD1-based signaling to boost immune response in cancer patients. The crystal structure of PD1-pembrolizumab and hundreds of other antibody-antigen complexes are now known. Through the Deep Learning based RL model of Somatic Hypermutations, we show how the Pembrolizumab can learn to bias its mutations so that it can achieve better binding with the PD1 antigen. This can be later extended to other antibody-antigen pairs. 

Modeling epigenetic inheritance using Information Theory

During cell division, the histone PTMs (Post Translational Modifications) are dislodged before the replication fork and are reassembled in the daughter chromatins. The reconstruction of histone PTMs in the daughter chromatins with only partial parental nucleosomes involves a complex web of enzyme machinery. We model how these gene regulating histone PTMs are reconstructed in the daughter through parallel concepts from communication theory – decoding signal from a noisy channel. We extend the case to study antagonistic modifications and asymmetric inheritance as seen in specific model systems using deep learning models. 

Candidates willing to do PhD pls contact me on email. 

Looking for interested students/researchers to work in some of the above areas – If interested, please reach me at nithya[at]ibab.ac.in, with your CV and a brief write-up on your academic interests.


  1. Dr. Tobias Karakach and Dr. Shashi Gujar – Dalhousie University, Canada.
  2. Dr. Sanjay Chandrasekharan – Homi Bhabha Center for Science Education, TIFR, Mumbai
  3. Dr. Sibi Raj B. Pillai – Professor, Dept of Electrical Engg, IIT Bombay, Mumbai
  4. Dr. Tripti Bameta, Scientist, ACTREC, Tata Memorial Hospital, Mumbai
  5. Dr. Deepak Modi, Scientist F, NIRRH, Mumbai 


  • Prabhu, BN Balakrishna, Sibi Raj Bhaskaran Pillai, and Nithya Ramakrishnan. “Antagonistic histone post-translational modifications improve the fidelity of epigenetic inheritance-a Bayesian perspective.” bioRxiv (2024)
  • Aamir Sahil Chandroth, Nithya Ramakrishnan, Sanjay Chandrasekharan, “The self-organisation of selfishness: Reinforcement Learning shows how selfish behavior can emerge from agent-environment interaction dynamics”, arXiv, 2023
  • Ramakrishnan N, Sibi Raj B Pillai, Padinhateeri R, “High fidelity epigenetic inheritance: Information theoretic model predicts k-threshold filling of histone modifications post replication, PLoS Comput Biol. 18(2): e1009861, 2022
  • N. Ramakrishnan and R. Bose, “Analysis of healthy and tumor DNA methylation distributions in kidney-renal-clear-cell-carcinoma using Kullback–Leibler and Jensen–Shannon distance measures”, IET Systems Biology, vol. 11, no. 3, pp. 99-104, 2017
  • Nithya Ramakrishnan and R. Bose, “Analysis of distribution of DNA methylation in kidney-renal-clear-cell-carcinoma specific genes using entropy”, Genomic Data, vol. 10, pp. 110-116, 2016
  • N. Ramakrishnan and R. Bose, “Dipole entropy-based techniques for segmentation of introns and exons in DNA”, Appl. Phys. Lett., vol. 101, no. 8, p. 083701, 2012
  • N. Subramanian and R. Bose, “Dipole angular entropy techniques for intron- exon segregation in DNA”, Euro Physics Letters, vol. 98, no. 2, p. 28002, 2012

Conference proceedings

  • Nithya Ramakrishnan, Mayuri Rege, Dibyendu Das, Sibiraj B. Pillai and Ranjith P., Computational Analysis of Histone Post-translational Modification Pairs, and their Influence on Genes, EMBO Conference on Histone Chaperones, Crete, Greece, Oct 2019
  • Nithya Ramakrishnan and R. Bose, “An Algorithm for the Generation of Random Numbers from DNA Methylation Data”, Presented at the Quantitative Principles in Biology Conference at European Molecular Biological Institute (Heidelberg) pp. 181, 2017
  • Nithya Ramakrishnan and R. Bose, “Analysis of DNA Methylation in Tumor Suppressor Genes using Information Theory”, Presented at the Cancer Genomics Conference at European Molecular Biological Institute (Heidelberg) pp. 161, 2015

Past Group Members

  1. Shankhanabha Ghosh , 3 rd year, Integrate BTech – MTech, IIT Madras 
  2. Kshitiz Saurav, 3 rd year, Integrate BTech – MTech, IIT Madras
  3. Nikshep Grampurohit, 3 rd year, Integrate BTech – MTech, IIT Madras

Current Group Members

  1. Balakrishnaprabhu B.N – Project Assistant
  2. Anmol Singh – MSc student
  3. Kanika Gandhi – MSc student
  4. Akshatha Shetty – MSc Intern (Reva University)
  5. Krithika S – BTech Intern (VIT) 


Institute of Bioinformatics and Applied Biotechnology
Biotech Park, Electronic City Phase I,
Bengaluru 560100,