Bikash (Ranjan) S.
Research Data Curator, Semantics & Ontology Engineering Team
Experience
Apr 2025 - Present
8 monthsHybrid
Research Data Curator, Semantics & Ontology Engineering Team
Novo Nordisk
- Built a semantic search engine for the team by leveraging diverse embedding models, hybrid combinations of embeddings, and integrating LLMs to deliver intelligent, context-aware search capabilities.
- Curated and managed ELN research data to maintain accuracy, consistency, and FAIR compliance.
- Utilized natural language processing to automate metadata extraction and annotation.
- Designed and implemented knowledge graphs and semantic frameworks to enhance data connectivity and retrieval.
- Integrated LLMs with knowledge graphs for intelligent, context-aware data curation.
- Collaborated across multidisciplinary teams to streamline research data workflows and ensure high-quality curation standards.
Nov 2024 - Mar 2025
5 monthsIndia
Research Scientist II, Prof. Balamurugan Ramadass’s Lab
All India Institute of Medical Sciences Bhubaneswar
- Worked on developing microbial consortia using active learning to optimize the production of anti-mycobacterial metabolite.
- Performed simulation based on the Lotka-Volterra model to check possible stable states for the consortia.
- Performed comprehensive metagenomics and microbiome network analysis for clinical samples.
- Managed patient intervention in clinical trials.
- Guided doctoral and master students in bioinformatics analysis and in performing NGS runs.
- Assisted in drafting research grant proposals.
Oct 2020 - Sep 2024
4 yearsBelgium
Bioinformatician, Prof. Katleen De Preter’s Lab
Ghent University | Centre for Medical Biotechnology VIB-UGent
- Developed interpretable deep learning models to predict drug sensitivity in cancer cell lines and identify potential drug repurposing opportunities.
- Leveraged artificial neural network architectures mirroring biological networks for enhanced interpretability.
- Employed neuron weights, neuron embeddings, and gradient analysis to reveal multiple layers of interpretability within the model.
- Utilized transcriptomic, mutational, and methylation data to train robust predictive models.
- Published an article on “Opportunities and challenges in interpretable deep learning for drug sensitivity prediction of cancer cells” (DOI: 10.3389/fbinf.2022.1036963).
- Developed a bioinformatic pipeline for analyzing NGS data of plasma cell-free DNA from cancer patients to infer diagnostic and prognostic outcomes.
- Extracted and utilized genetic and epigenetic features such as structural variants (SNV, CNV, indels), nucleosome footprints, and sequence motifs from cfDNA whole genome sequence data for predictive modeling.
- Analyzed ATAC-seq and cfRRBS data for selection of genomic regions for predictive modeling.
- Employed deconvolution algorithms to estimate tumoral DNA and subclonal fraction in patient blood.
- Isolated cell-free DNA from patient and mice PDX blood samples and characterized DNA concentration and size profiles.
- Cultured cancer cell lines in pre-conditioned media and characterized DNA concentration and size profiles from media supernatant.
- Isolated extracellular vesicles from blood and cell line culture media, extracted DNA from EV lysates, and characterized and sequenced the DNA.
Sep 2019 - Sep 2020
1 year 1 monthFrance
Bioinformatician, Prof. Jean-Loup Faulon’s Lab
MICALIS, INRAe Jouy-en-Josas
- Applied deep learning to train on enzymatic reactions from the BRENDA database and predict feasibility of de novo reactions.
- Utilized generative adversarial networks to create protein sequences tailored to specific enzymatic reactions.
- Conducted comprehensive protein sequence analysis, including Pfam detection, calculation of conservation scores, and physicochemical features for predictive modeling.
- Implemented an active learning loop to enhance flavonoid production in cell-free systems.
Jul 2018 - Mar 2019
9 monthsIndia
Master Student & Teaching Assistant, Prof. Ranjit Prasad Bahadur’s Lab
Indian Institute of Technology Kharagpur
- Devised a more accurate classification model for intrinsic subtypes of breast cancer based on gene expression profiles using supervised machine learning.
- Reconstructed individual gene regulatory networks for each subtype using a supervised machine learning approach, leveraging multi-omics data including gene expression, methylation, CNV, and miRNA expression data.
- Analyzed subtype-specific regulatory patterns to identify distinctive features and critical targets within the gene regulatory networks.
Languages
English
AdvancedEducation
Oct 2017 - Jun 2019
Indian Institute of Technology Kharagpur
MTech · Biotechnology and Biochemical Engineering · Kharagpur, India
Oct 2013 - Jun 2017
Odisha University of Technology and Research
BTech · Biotechnology · Bhubaneswar, India
Need a freelancer? Find your match in seconds.
Try FRATCH GPT More actions
Similar Freelancers
Discover other experts with similar qualifications and experience
- English
- Deutsch
2025 © FRATCH.IO GmbH. All rights reserved.