Dr. Rishika Sen

Dr. Rishika Sen is a Data Scientist III at Ericsson. She obtained her Ph.D. in Computer Science from Machine Intelligence Unit, Indian Statistical Institute, Kolkata, under Dr. Rajat Kumar De. Her domain of research is Data Science, Data Analysis, Bioinformatics, and Machine Learning. She developes algorithms, discovers data preprocessing techniques and designs machine learning pipelines to solve real world problems. She has published on various internationally reputed journals as the first author.

My Résumé

You can download my résumé in word or pdf formats.

Work Experience

2024 July – present: Data Scientist III at Ericsson, Bengaluru.
Working on Knowledge distillation techniques of LLMs to SLMs and fine-tuning SLMs to create a more refined model suited for specific use cases.

2022 March – 2024 June: Data Scientist II at Ericsson, Bengaluru.
Worked on Trustworthy AI, Responsible AI and Explainable AI techniques. Implemented ChatBot using RAG technique to deal with telecommunication data using AWS Claude model with dockerization and interfacing with vertical database. Developed automated compliance detection system for AI systems to adhere to trustworthy AI guidelines. Contributed in the development of an in-house python package for application of explainability on various data using various explainable techniques like SHAP, LIME, etc. Implemented anomaly detection on time series telecom data, eventually bringing new business to the company.

2021 February – 2022 February: Research Investigator at Syngene International Limited, Bengaluru. Responsibilities include analysing real-world datasets to build useful machine learning models for multiple clients in various domains, including bioinformatics and chemistry.

Education:

2014 – 2021: PhD in Computer Science, Machine Intelligence Unit, Indian Statistical Institute, Kolkata, under the supervision of Prof. Rajat Kumar De.

2012 – 2014: Master of Science (MSc) in Computer and Information Science, College of Science and Technology, University of Calcutta. University rank 9, 75.8% (First Class).

2009 – 2012: Bachelor of Science (BSc Honours) in Computer Science, Bethune College, University of Calcutta. University rank 6, 74.6% (First Class).

2009: Higher Secondary (ISC) from Calcutta Girls' High School, 90.2%

2007: Secondary School (ICSE) from Calcutta Girls' High School, 90%

Publications:

Journal Articles:

Rishika Sen, Somnath Tagore, and Rajat Kumar De. "Cluster Quality based Non-Reductional (CQNR) oversampling technique and Effector Protein Predictor based on 3D structure (EPP3D) of proteins." Computers in Biology and Medicine, (2019), Elsevier, doi: 10.1016/j.compbiomed.2019.103374.

Rishika Sen, Losiana Nayak, and Rajat Kumar De. "PyPredT6: A Python based Prediction Tool for Identification of Type VI Effector Proteins." Journal of Bioinformatics and Computational biology (2019), World Scientific, doi: 10.1142/S0219720019500197.

Rishika Sen, Somnath Tagore, and Rajat Kumar De. "ASAPP: Architectural Similarity-based Automated Pathway Prediction System and its Application in Host-Pathogen Interactions." IEEE/ACM Transactions on Computational Biology and Bioinformatics, (2018), IEEE, doi: 10.1109/TCBB.2018.2872527.

Rishika Sen, Losiana Nayak, and Rajat Kumar De. "A review on host–pathogen interactions: classification and prediction." European Journal of Clinical Microbiology & Infectious Diseases 35.10 (2016): 1581-1599, Springer, doi: 10.1007/s10096-016-2716-7.

Rishika Sen and Rajat Kumar De. "BNRA: A Boolean logic based Network Robustness Analyzer and its application in the aspect of Host-Pathogen interactions" (To be communicated)

Rishika Sen and Rajat Kumar De. "DeepT7: A Deep Neural Network based System for Identification of Type VII Effector Proteins" (To be communicated)

Posters and Presentations:

Rishika Sen, Losiana Nayak, and Rajat Kumar De. "Classification, Prediction and Analysis of Type VI Secreted Effector Proteins". Advanced Lecture Course - Molecular Mechanisms of Host-Pathogens Interactions and Virulence in Human Fungal Pathogens, University of Aberdeen, Nice, France. (2017)

Rishika Sen, Losiana Nayak, and Rajat Kumar De. "Signature Pattern Mining of Type VI effector Proteins". EMBO Global Exchange Lecture Course: Malaria Genomics and Public Health. (2017) DOI: 10.13140/RG.2.2.15231.61601

Talks given

‘Trustworthy AI – Is it just a buzzword?’ at IIM Bengaluru [link to talk advertisement]

Other Projects:

  • Kolkata Guide.
  • (2012): an application to help navigate in Kolkata, Bethune College, Kolkata.
  • Transport Management Website: (2013): using HTML, PHP, CSS, and MySQL; University of Calcutta.
  • Any Guess (2013): A guessing game using Java Swing, University of Calcutta.
  • Image Processing (2013): filtering and Averaging methods used to remove noise from an image. Developed using Java Swing. University of Calcutta.
  • Deployment of Web Services (2014): using IIS server, University of Calcutta.

Research

Currently, my role in Syngene International involves building machine learning models for chemoinformatics data. Before this, I obtained a Ph.D. in Computer Science from Machine Intelligence Unit of Indian Statistical Institute, Kolkata. My research interests are in Data Engineering, Data Science, Data Analysis, with a focus on designing algorithms, data pre-processing techniques and pipelines using machine learning algorithms.

  • Designed a system based on Boolean networks that analyses biological networks.
  • Invented an over-sampling algorithm for an ensemble learning classifier for effector proteins.
  • Designed a novel graph based system to predict the effect of toxins on unknown metabolic pathways.
  • Developing deep learning and ensemble models for the identification of effector proteins.

Coursework:

PhD: Data and File Structures, Computer Organization, Database Management Systems, Neural Networks, Operating Systems, Pattern Recognition, Research Methodology.

MSc: Advanced Computer Architecture, Database Management Systems, Data Structures, Data Communications, Computer Networks, Design and Analysis of Algorithms, Computer Graphics and Image Processing, Software Engineering, Object oriented Systems, Automata Theory and Compiler Design, Internet and Multimedia Technology, Advanced Operating System, Soft Computing, Information Security.

Technical Skills:

Languages: Python, PHP, HTML, SQL, C, C++.
Servers: Oracle 10g, MySQL, WAMP.
Proficient in: English, Bengali, Hindi.

Honors and Awards:

  • Rank 6 in BSc(Honours) Computer Science in The University Of Calcutta Mar 2013, University Of Calcutta
  • First Class First In Computer Science Honours in BSc Part 2 Jan 2013, Department of Computer Science,Bethune College
  • Kamalini Sharma Memorial Prize: First Class First BSc(Honours) Computer Science In Bethune College Jan 2013, Bethune College
  • Special Staff Prize: For securing First Class in Bsc Honours Examination Jan 2013, Department of Computer Science, Bethune College
  • First Class First In Computer Science Honours in BSc Part 1 Jan 2011, Department of Computer Science,Bethune College
  • Certificate of Merit:For securing an overall percentage of 87.28%(above 85%) in ICSE(Class 10) Aug 2007, Calcutta Girls' High School

Volunteer Work:

Indian Science Congress (2013).