I'm Saheed Adeyanju, a UK-based bioinformatician specialising in computational cancer biology, ovarian cancer genomics, and multi-omics integration. I build reproducible next-generation sequencing (NGS) pipelines and apply machine learning to biomarker discovery, bridging computational analysis with a strong molecular-biology background. I hold an MSc in Bioinformatics with Advanced Practice (Distinction, Teesside University), with research experience at Imperial College London and the University of Southampton, and ten peer-reviewed publications and preprints across cancer genomics, multi-omics, and ML in genomics.

Proficient in Python, R, and Bash (shell scripting), plus Nextflow for pipeline development and SQL for data querying. Comfortable working on HPC clusters and Linux/Unix server environments.

• Pipeline development & NGS data analysis

  • Built reproducible Nextflow pipelines based on nf-core/Sarek for somatic variant calling and annotation on ovarian cancer whole-genome sequencing (WGS) data, with containerised GATK, Mutect2, SnpEff, and VEP.
  • Experienced across WGS, WES, bulk RNA-seq, single-cell RNA-seq (scRNA-seq), and microarray data, using Docker and Git/GitHub for reproducible, auditable workflows.
  • Computed homologous recombination deficiency (HRD) scores loss of heterozygosity (LOH), telomeric allelic imbalance (TAI), and large-scale state transitions (LST) to quantify genomic instability and support precision-oncology decisions.

• Machine Learning

  • Benchmarked machine-learning algorithms (Random Forest, XGBoost, CatBoost, SVM, Logistic Regression, K-means) for biomarker discovery, including identifying candidate biomarkers of Pulmonary Arterial Hypertension from microarray data.
  • Applied dimensionality reduction (PCA, t-SNE, UMAP) and deep-learning frameworks (TensorFlow, PyTorch) to genomic and clinical datasets.

• Biological network analysis

  • Constructed protein–protein interaction networks in STRING/Cytoscape, extracted hub genes with CytoHubba (e.g. CXCL9), ran functional enrichment with EnrichR, and performed cross-platform meta-analysis with MetaVolcanoR.
  • Validated candidate-gene druggability through molecular docking (AutoDock Vina).

A strong foundation in molecular biology and clinical science — an MSc in Chemical Pathology (University of Ibadan) and a BSc in Biochemistry (Federal University of Agriculture, Abeokuta) — underpins my computational work, alongside several years of research spanning cancer genomics, respiratory disease, and inflammation.

• Adeyanju, S. A. & Ogunjobi, T. T. (2024). Machine Learning in Genomics: Applications in WGS, WES, Single-Cell Genomics, and Spatial Transcriptomics. Medinformatics.
• Adeyanju, S. (2024). Exploring Inflammatory Dysregulation in Alveolar Macrophages: Implications for Novel Therapeutic Targets in COPD. bioRxiv.
• Adeyanju, S. A. et al. Artificial Intelligence in Autoimmune Disease Genomics: Biomarker Discovery and Pathway Analysis in Multiple Sclerosis. (Accepted, Int. J. Advanced Biological and Biomedical Research.)

• 📫 Email: Saheedadeyanju76@gmail.com
• 💼 LinkedIn: linkedin.com/in/lanre-adeyanju
• 💻 GitHub: @DrSeed

• 🗣️ I speak Yoruba natively and English (IELTS Academic 7.5).
• 🧬 Member of several research communities, including the European Association for Cancer Research, the African Society of Human Genetics, and the Association for Single Cell Analysis (ASCA).
• 🎓 Former STEM tutor — I still enjoy explaining tricky computational-biology ideas in plain language.