Hire the Best Scientific Computation Specialists

I help genomics companies, academic research labs, and PhD researchers turn complex sequencing and clinical datasets into publication-ready results, grant-winning insights, and actionable biological discoveries. With hands-on expertise in bulk RNA-Seq, single-cell RNA-Seq, multi-omics integration, and clinical biostatistics, I deliver more than analysis; I provide scientific interpretation, reproducible pipelines, and clear visualisations that accelerate decision-making. Whether you're: Identifying novel therapeutic targets Dissecting cellular heterogeneity Integrating transcriptomics with epigenomics Validating biomarkers for clinical studies Preparing figures for high-impact journals I ensure your data becomes a defensible scientific asset — not just processed output. Let's transform your raw data into meaningful biological insight. 🧬 Core Services 1️⃣ Bulk RNA-Seq & Transcriptome Analysis Tools: HISAT2, STAR, DESeq2, edgeR Deliverables: Differential expression analysis Pathway & enrichment analysis Publication-ready plots Reproducible pipelines Best For: Mechanistic studies, biomarker discovery, therapeutic target identification. 2️⃣ Single-Cell RNA-Seq (scRNA-Seq) Tools: Cell Ranger, Seurat, Monocle Deliverables: Clustering & annotation Trajectory analysis Rare cell population detection Integration of multiple datasets Best For: Tumour microenvironment, immune profiling, tissue heterogeneity. 3️⃣ Multi-Omics Data Integration Transcriptomics + Epigenomics RNA-Seq + Clinical Metadata Cross-platform data harmonisation Outcome: Systems-level biological insight and stronger mechanistic conclusions. 4️⃣ Clinical Biostatistics & Modelling Logistic regression Survival analysis Bayesian models ML classifiers (Random Forest, XGBoost, LASSO) Clinical dataset interpretation Outcome: Robust statistical validation for publications, diagnostics, and trials. 🧪 Technical Expertise Programming: Python, R, Bash, SQL Bioinformatics: GATK, STAR, DESeq2, Seurat, QIIME, MACS2 Statistics & ML: Regression, Bayesian modelling, AI/ML pipelines Visualization: ggplot2, Matplotlib Infrastructure: HPC environments, reproducible workflows, Git 🎯 Stronger Call to Action If you need reliable bioinformatic support for your lab, startup, or thesis, let's discuss your dataset and research goals. Prioritise clarity, reproducibility, and scientific rigour.

I help research teams and technical founders build and validate reliable, testable scientific and quantitative systems — research prototypes, backtesting frameworks, production execution systems, simulation engines, and performance-critical pipelines. I also conduct independent technical review of quantitative models and research frameworks. If you're dealing with slow code, messy data, a model you can't trust, or a research prototype that needs to become production, I can turn it into a robust, reproducible result. Background: PhD Physics (NYU, 2018). Quantitative Research at JPMorgan Chase — derivatives pricing on a 1M+ LOC C++ library. Max Planck Institute postdoc — general-relativistic hydrodynamics on 1,000+ core HPC clusters. 13 peer-reviewed publications, 1,300+ citations, h-index 12. WHAT I DELIVER ▸ Quant & Options Engineering Backtesting frameworks (event-driven or vectorized), walk-forward, leakage checks Options analytics: Greeks, IV surfaces, Black–Scholes and numerical methods Research → production pipelines (clean architecture, tests, logging, monitoring) Execution integrations (e.g., IBKR) and robust order / risk handling Market data ingestion, cleaning, corporate actions, quality control ML and statistical time-series models with proper cross-validation (no leakage) ▸ Scientific Computing & Research Tooling For physics, chemistry, biology, engineering, and any domain where the core problem is mathematical or computational. Custom numerical solvers (finite volume / finite difference, spectral, particle methods) with stability and convergence analysis Optimization engines (Bayesian, gradient-based, evolutionary) for experimental design, formulation, and parameter search Simulation frameworks from prototype to production grade Scientific data pipelines: ingestion, transformation, quality control, reproducible workflows Verification and validation: benchmarks, unit / regression tests, convergence studies Analysis tools, dashboards, and reporting infrastructure for research workflows Air-gapped and reproducible deployments where IP sensitivity or regulatory context requires it ▸ Quantitative & Mathematical Review (NDA-protected) Independent technical review of quantitative models, frameworks, and research Verification of internal consistency, identifiability, hidden assumptions, and mathematical correctness Assessment of whether the formal structure supports the conclusions drawn from it Implementation review against specification: numerical stability, edge cases, code-to-spec fidelity ▸ HPC & Performance Engineering Distributed computing (MPI / OpenMP / CUDA), GPU optimization, memory and I/O tuning Inference and training infrastructure at scale Profiling, refactors, and speedups for codebases that need to run reliably under production load WHY CLIENTS WORK WITH ME - Trustworthy work — research prototypes turned into tested, reproducible production code; models reviewed against their own claims - De-risking — failure modes surfaced early (leakage, overfitting, edge cases, scaling bottlenecks) - Maintainability — clean architecture, docs, handover-ready delivery your team can extend - Communication — clear milestones, concise updates, realistic timelines, no surprises - Math ↔ engineering bridge — strong intuition for both theory and implementation IDEAL PROJECTS - Quant strategy development, backtesting, and research infrastructure - Options analytics and derivatives tooling - Mathematical review of quantitative manuscripts, white papers, or research frameworks - Independent validation of production models against specification - Market data pipelines and reproducibility upgrades - Performance optimization of slow Python / C++ codebases - Distributed training, GPU optimization, and inference serving for ML workloads - Custom scientific or industrial simulation and numerical software - Internal R&D tooling for research labs and technical teams If this sounds like a fit, message me with a brief on your current setup and success criteria — I'll let you know how I can help.

**************Genomics & Informatics Lab (GIL) ***************** **************Your Trusted Partner in Advanced Bioinformatics & AI-Driven Multi-Omics****** I lead a distinguished team at Genomics & Informatics Lab (GIL), specializing in Biotechnology, Bioinformatics, Computational Biology, and AI-powered Multi-Omics. At GIL, we offer a comprehensive suite of cutting-edge services tailored to meet the evolving demands of genomics, transcriptomics, proteomics, metagenomics, pharmacogenomics, and precision medicine. Our Expertise: AI-Powered Bioinformatics & Multi-Omics Data Analysis 🔬 1. Bioinformatics & Genomics: AI/ML-powered Next-Generation Sequencing (NGS) data analysis Comparative & Population Genomics for evolutionary insights Genetic variant detection & annotation Functional Genomics (Gene Ontology, KEGG Pathway analysis) Phylogenetics & Evolutionary Genomics miRNA structure prediction & target analysis 🧬 2. AI-Driven Transcriptomics & Epigenomics: RNA-Seq & Single-Cell Transcriptomics Differential Expression & Alternative Splicing Analysis Epigenomics: DNA Methylation & Histone Modification Analysis 💊 3. Computational Pharmacogenomics & Precision Medicine: AI-assisted drug-gene interaction prediction Pharmacogenomic modeling for personalized medicine Toxicogenomics & Drug Response Prediction 🦠 4. Metagenomics & Microbiome Data Science: Whole-genome & 16S rRNA sequencing-based microbiome analysis Microbiome-host interaction modeling AI-powered taxonomic & functional profiling ⚛ 5. AI in Structural & Systems Biology: Protein-Protein Interaction Analysis & Docking Molecular Dynamics (MD) & Simulation Studies AI-driven protein structure prediction (AlphaFold, Rosetta, etc.) 🤖 6. AI & Machine Learning in Multi-Omics Integration: Deep learning for biomarker discovery Multi-omics data integration (Genomics, Proteomics, Metabolomics, Epigenomics) Network-based systems biology approaches 🚀 State-of-the-Art Computing Infrastructure GIL is equipped with high-performance computing (HPC) clusters, multi-core processing, and cloud-based analytics, ensuring scalable, fast, and accurate bioinformatics solutions. 💡 Why Choose GIL? ✅ Expert Team: Decades of experience in computational biology & AI ✅ Cutting-Edge Technologies: AI, ML, and HPC-powered analytics ✅ Proven Track Record: Successful projects in academia & industry ✅ Custom Solutions: Tailored pipelines for diverse research needs Let GIL be your trusted partner in advancing your research! Contact us today to explore how we can support your next breakthrough in computational biology and AI-driven bioinformatics. 🔍💻🧬

🧠 𝗔𝗜 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿 + 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 + 𝗕𝗶𝗼𝗹𝗼𝗴𝗶𝘀𝘁 PhD Biologist turned AI Engineer. Based in Germany. 60+ peer-reviewed publications in Gut (IF>25), JAMA Cardiology, and Neurology. Led international GWAS consortia. 20+ production ML projects in computer vision, NLP, time series, and MLOps. 5.0 stars across 100+ clients. 15+ years leading genetics, genomics, and clinical AI research across top European institutions. 🚀 𝗪𝗵𝗮𝘁 𝗜 𝗗𝗼 - Build RAG systems and LLM agents for medical, scientific, and enterprise workflows - Build ML models: classification, computer vision, NLP, time series, recommendation - Analyse genomes: RNA-seq, scRNA-seq, microbiome, GWAS, NGS variant calling - Run biostatistics and epidemiology: survival analysis, meta-analysis, causal inference - Write manuscripts, systematic reviews, grants, and scientific reports - Build Excel dashboards, Power BI reports, and automated data pipelines - Tutor in R, Python, biostatistics, bioinformatics, and ML fundamentals 🤖 𝗔𝗜 𝗦𝗲𝗿𝘃𝗶𝗰𝗲𝘀 - RAG pipelines: LangChain, ChromaDB, Pinecone, Supabase Vector, GraphRAG, RAGAS - Agents: LangGraph, Claude Code WAT framework (40+ Python tools), n8n, Make, VAPI - Full-stack: FastAPI, Streamlit, React, TypeScript, Supabase, Docker - 89 live platforms across AI, genomics, automation, and healthcare (see Portfolio section) 📈 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 & 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 - Classification/regression: scikit-learn, XGBoost, LightGBM, GNN - Computer vision: pneumonia detection, COVID X-ray, steel defect segmentation - Time series: energy forecasting (167M rows), fire response, retail sales - NLP: supply chain satisfaction, form NER, multimodal classification (27 classes) - MLOps: federated learning, model registry, CI/CD, anomaly detection pipelines - Data engineering: OHLCV pipelines, OCR extraction, production ETL 🧬 𝗕𝗶𝗼𝗹𝗼𝗴𝘆 & 𝗕𝗶𝗼𝗶𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗰𝘀 - RNA-seq and scRNA-seq: STAR, DESeq2, Seurat, Scanpy, trajectory analysis - Spatial transcriptomics, ATAC-seq, multiomics (SIB Swiss Institute trained) - Microbiome: QIIME2, DADA2, 16S/ITS amplicon, shotgun metagenomics - GWAS: PLINK, PRSice, Mendelian randomization - led COURAGE-PD consortium - NGS: GATK, VCF, WES/WGS, pharmacogenomics, methylation (EPIC array) - Pipelines: Snakemake, Nextflow, HPC/SLURM, Docker, Conda 📊 𝗕𝗶𝗼𝘀𝘁𝗮𝘁𝗶𝘀𝘁𝗶𝗰𝘀 & 𝗘𝗽𝗶𝗱𝗲𝗺𝗶𝗼𝗹𝗼𝗴𝘆 - Cox regression, mixed models, survival analysis, logistic, causal inference - Meta-analysis, PRISMA systematic reviews, health economics, QALY - R, Python, SPSS, SAS, Stata - Lecturer in Applied Regression at Masters level (Lübeck) 📋 𝗘𝘅𝗰𝗲𝗹, 𝗗𝗮𝘀𝗵𝗯𝗼𝗮𝗿𝗱𝘀 & 𝗥𝗲𝗽𝗼𝗿𝘁𝗶𝗻𝗴 - Advanced Excel, VBA, Power BI, Tableau, Google Sheets, Looker Studio - Clinical KPI dashboards, automated XLSX pipelines via Python, financial modeling 📝 𝗪𝗿𝗶𝘁𝗶𝗻𝗴, 𝗚𝗿𝗮𝗻𝘁𝘀 & 𝗗𝗲𝘀𝗶𝗴𝗻 - Manuscripts, systematic reviews, grant proposals (NIH, EU Horizon, DFG) - Scientific figures, posters, graphical abstracts, slides from papers ⭐ "Best researcher and data analyst I have ever worked with." ⭐ "Professional, understands both the science and the data." ⭐ "Great at both writing and R, brings creative AI solutions." Send your goal, timeline, and data. I will reply with exactly what I can deliver. SKILLS TAGS Artificial Intelligence RAG Claude Code Medical Writing Biostatistics Epidemiology Systematic Review Genetics Bioinformatics Scientific Writing Python React Supabase Grant Writing Web Development

I'm a full-blooded mathematician with scientific background in math, physics and computer science and basically interested in everything. :-) I worked for several years at university, did my PhD in the field of statistical image and data analysis, gave lectures and tutorials and supervised several students and theses. I'm very familiar with Boolean and linear algebra, analysis, probability theory, statistics, linear and nonlinear (convex) optimization and of course image and data analysis. Now, I'm working in the field of IT security, especially cryptography and side-channel analysis with machine learning and AI methods. Besides math (or more general, science), I‘m personally very interested in sports, fitness and health topics. I like to help with math assignments or programming tasks (including reimplementing the results of papers, e.g. in Python, R or Matlab), proofreading publications or theses, writing résumés and typing/formatting texts with LaTeX, and creating graphics with Tikz. Furthermore, due to my background in image processing, I have comprehensive experience in photo and video editing. As a native German I‘m happy to support in any translation or proofreading tasks involving German. At school I studied Latin for 9 years and really like the language, so I gladly offer any kind of support here as well. I’m also fluent in English and Swedish. Furthermore, I love writing calligraphy and handlettering and would be happy to realize your individual project. As I like thinking about mathematical problems, I enjoy solving logical quizzes, puzzles, riddles etc. and will be happy to support you with any kind of related projects (e.g. reviewing them for correctness, difficulty, clearity,…). Finally, I can also assist with tasks regarding the German tax system (e.g. Elster online, tax returns, VAT).

I'm a Top Rated freelancer and Computer Science graduate who works at the intersection of three fields most people treat separately: Statistics & Machine Learning, Bioinformatics, and AI. That combination is exactly what messy, high-dimensional data needs — the statistical rigor to trust the result, the ML to find the pattern, and the biological context to know what it means. With 3+ years of experience and 24 successful projects (4.98/5 avg. rating), here's what I bring: 📊 Statistics & Machine Learning Rigorous statistical inference and predictive modeling — hypothesis testing, causal inference (Mendelian Randomization), feature engineering, and ensemble models (XGBoost, LightGBM, Random Forest). I don't just build models that score well; I build models you can defend. Example: a coronary artery disease prediction model reaching 0.956 AUC, with feature ablation to prove what actually drives it. 🧬 Bioinformatics & Omics End-to-end analysis of complex biological data — scRNA-seq, RNA-seq, WGS/WES — using reproducible pipelines (Nextflow, Snakemake). From raw reads to normalized matrices to differential expression and biomarker discovery. Example: cut analysis time by 40% on large genomic projects through custom automated pipelines. 🤖 AI & Deep Learning Deep learning frameworks for real diagnostic problems — computer vision, medical image analysis, NLP, and LLM-based tools. ✨ What ties it together Most freelancers do one of these. I connect them — applying AI and ML to biological and clinical data with statistical discipline, then communicating the findings in publication-ready visuals that both scientists and stakeholders can act on. 🛠️ Tech Stack Python (Pandas, Scikit-learn, TensorFlow, PyTorch) · R (Tidyverse, Bioconductor) · Bash · SQL · Linux · Git · Docker · Cloud 💡 Ready to turn your raw data into discoveries you can trust? Let's talk.