Topia Life Sciences
Website:
topialifesciences.com
Job details:
POSITION OVERVIEW
The Data Scientist - Drug Repurposing will design and apply Natural Language Processing (NLP), graph-based, and deep learning models to identify new therapeutic applications for existing drugs. Working within a multidisciplinary team of researchers, data scientists, and bioinformaticians, this role will mine large-scale biomedical data including literature, clinical trial records, and multi-omics datasets to surface hidden patterns and translate them into actionable drug repurposing hypotheses.
KEY RESPONSIBILITIES
- NLP for Biomedical Text: Develop and apply NLP pipelines (named entity recognition, relation extraction, literature mining) to extract drug, gene, disease, and pathway information from biomedical literature, clinical trial registries, and electronic health records.
- Graph-Based Modelling: Design and implement knowledge graphs and graph neural network (GNN) models to represent drug-target-disease interactions and uncover novel repurposing candidates.
- Deep Learning for Efficacy & Safety Prediction: Build and validate deep learning models to predict drug efficacy, safety signals, and potential new indications from heterogeneous datasets.
- Multi-Omics Data Integration: Integrate and analyze genomic, proteomic, transcriptomic, and phenotypic data alongside clinical and real-world evidence to identify and priorities repurposing opportunities.
- Cross-Functional Collaboration: Partner with bioinformaticians, clinical scientists, and product teams to translate model outputs into validated, actionable insights and communicate findings clearly to non-technical stakeholders.
- Model Lifecycle Ownership: Own model development end-to-end data acquisition, preprocessing, training, validation, deployment, and monitoring with attention to reproducibility and documentation.
- Staying Current: Track and evaluate emerging methods in NLP, graph learning, deep learning, and computational drug repurposing, recommending adoption where relevant.
REQUIREMENTS
Education & Experience
- Bachelor's or Master's degree in Computer Science, Data Science, Computational Biology, or a related field.
- 2–3 years of professional experience in Python and applied AI/ML.
Technical Skills
- Strong programming skills in Python (or a similar language).
- Demonstrated experience applying NLP, graph theory, and deep learning to biomedical data.
- Hands-on experience with NLP frameworks such as spaCy, NLTK, or transformer-based models (e.g., BERT, GPT).
- Proficiency with ML/DL frameworks and platforms such as TensorFlow, PyTorch, Keras, or Spark MLlib.
- Familiarity with graph libraries/frameworks (e.g., NetworkX, PyTorch Geometric, DGL) is an advantage.
Core Competencies
- Excellent problem-solving skills, with the ability to analyze complex, multi-modal datasets and derive actionable insights.
- Strong written and verbal communication skills, able to convey technical findings to a multidisciplinary, non-technical audience.
- Proven ability to collaborate effectively within cross-functional, multidisciplinary teams.
Click on Apply to know more.