Bioinformatics Engineer · Graduate Student Researcher · Biotechnologist

Tokyo, Japan 🇯🇵 · From Indonesia 🇮🇩 · Microbiome, genomics & health data systems · Open to collaboration and part-time projects

I work at the intersection of bioinformatics, software engineering, and applied biology, building systems that turn biological data into decisions.

I'm a Master's student in the Integrated Doctoral Education Program (International Graduate Program A) at the Institute of Science Tokyo (formerly Tokyo Tech), in the Laboratory of Genome Informatics, funded by the MEXT Scholarship. Before that, I spent two years as a Bioinformatics Engineer at Regene Genomics, and I graduated Cum Laude (GPA 3.86) in Biology from Universitas Gadjah Mada.

My focus areas:

• 🦠 Computational microbiome & metagenomics: cross-cohort biomarker validation, explainable machine learning, strain-level and functional analysis
• 🧬 Precision genomics & nutrition: polygenic risk score pipelines, GWAS analysis, genomic testing APIs
• 🏥 Health information systems: multi-tenant electronic medical record platforms with international medical coding standards (ICD-10, LOINC, KFA)
• 🌿 Microalgae bioinformatics & sustainability: strain characterisation, growth kinetics modelling, IoT-based monitoring systems

• microbiome-xai: a tested Python toolkit that checks whether a gut microbiome biomarker holds up across populations, with leakage-free cross-validation, cross-cohort transfer, out-of-fold SHAP explanations and confounder checks. Case studies show a type 2 diabetes signature that fails to transfer between Sweden and China (partly driven by metformin), and a liver cirrhosis signature (AUROC 0.92) that recovers the original study's oral-bacteria finding.

• microalgae_growth_kinetics_model: Python implementation of kinetic models (Monod, Logistic, Gompertz) for microalgae growth. Used in my undergraduate thesis on Euglena sp. from wastewater treatment plants.
• kinetic_modeling_of_LIRA-toehold-switch_expression_system_EcN: in silico modelling of LIRA (Loop-Initiated RNA Activator) toehold-switch response to miRNA biomarkers, developed as part of iGEM 2023.

• iGEM-UGM-2023-drylab: computational lab documentation for ColDBlu, a colorectal cancer screening biodevice. 🥇 Gold Medal, Top 5 Best Diagnostic Project, iGEM 2023 Paris.

• Languages Python · Go (Gin / Fiber) · Bash · R
• Bioinformatics PLINK · PRSice-2 · LDpred-2 · Lassosum · NUPACK · Benchling · GATK · curatedMetagenomicData
• Data & ML Scikit-learn · SHAP · Statsmodels · Pandas · NumPy · TensorFlow · Streamlit
• Infrastructure Docker · Drone CI · GitHub Actions · Docker Swarm · MongoDB · MySQL · Flask · REST API
• Health Data Standards ICD-10 · ICD-9-CM · LOINC · KFA (Satu Sehat / Kemenkes)
• Lab DNA isolation & electrophoresis · PCR · Microalgae cultivation and characterisation

• 🎓 MEXT Scholarship (University Recommendation): Institute of Science Tokyo (2026)
• 🥇 GOGEC 2024: Gold Medal · Best Computational Project · Best Human-Centred Design
• 🥇 iGEM 2023 Paris: Gold Medal · Top 5 Best Diagnostic Project · Inclusivity Award
• 🥇 BIOS 2022: Gold Medal · Top 3 Best Elevator Pitch
• 📚 Cargill Global Scholar: one of 10 national awardees (2022–2024)
• 🎓 Bangkit Academy ML Path graduate (Google, Gojek, Tokopedia, Traveloka)

• Characterization of Lipids, Pigments, and Growth Kinetics of Euglena sp. Isolated from Sewage and Rice Field, Malaysian Journal of Microbiology (under revision)
• Effect of Red and Blue Light on Lipid, Protein, Carbohydrate, and Pigment Contents of Navicula sp., Makara Journal of Science (2023, published)

I am working towards building rigorous bioinformatics infrastructure for Indonesian biodiversity: systems that can validate, characterise, and translate the country's megabiodiversity into health and environmental solutions. This spans microalgae as a sustainable bioplatform (food, fuel, carbon capture), precision health for underrepresented populations, and environmental monitoring through distributed sensor systems.

• ✉️ maulanasofyan0712@gmail.com
• 💼 LinkedIn: Sofyan Maulana
• 🌐 Based in Tokyo · Open to research collaboration and part-time or contract bioinformatics work (remote or onsite)