Ajay Pavan R.

Bioengineer and former Founding R&D Engineer at BioCompute Inc., with ~4 years of experience across startups and international research labs in computational biology, bioinformatics, and genomic data analysis. Named inventor on a US patent filing. I build computational pipelines and analytical systems for biological data: NGS, WGS, long-read sequencing, and high-dimensional experimental outputs. My work combines bioinformatics, statistical modeling, signal processing, and machine learning to extract interpretable patterns from complex biological systems, often within larger pipelines that integrate APIs, containerized environments, and multiple software components. My experience spans genome assembly, variant analysis, methylation detection, structural bioinformatics, raw signal analysis, and physiological signal analysis. Because I work across both experimental genomics and computational analysis, I can quickly diagnose issues at the interface between sequencing workflows and downstream data interpretation. I also take on biostatistics consulting work including experimental design, hypothesis testing, and SBIR grant statistical review. At BioCompute, I built a sequencing based proof-of-concept system integrating native DNA workflows with a custom bioinformatics decoding pipeline developed from scratch, validated on real sequencing runs and contributing to a US patent filing where I am a named inventor. I also delivered genome assembly, methylation analysis, and structured analytical reporting to external customers. What I work with: - Next-generation sequencing (short and long-read, WGS) - Oxford Nanopore (MinION Mk1B/Mk1D, PromethION; wet lab + analysis) - Genome assembly and annotation (bacterial and small genomes) - Variant analysis and mutation interpretation - RNA-seq analysis (Bulk and scRNA) - Structural bioinformatics (AlphaFold, DSSP, molecular docking) - Modified-base and methylation analysis (pysam, modkit, SAMtools) - Time series and signal processing (FFT, ML-based approaches) - Physiological and biosignal data analysis - Biological image analysis (cell segmentation, microscopy, CV quantification) - Statistical modeling and biostatistics (regression, hypothesis testing, experimental data interpretation) - Lab automation (Opentrons-style JSON protocol systems) - Python bioinformatics pipelines (Linux, Bash) - Containerized and reproducible workflows (Docker, Snakemake) - API-driven data pipelines and backend integrations - Workflow engine development and debugging (Rust-based pipeline migration, concurrency bug fixes) Tools and technologies: - Python scientific stack (NumPy, SciPy, Pandas, scikit-learn) - Deep learning (PyTorch, TensorFlow) - Image/video analysis (OpenCV, scikit-image) - Docker, Snakemake - Linux, Bash, REST APIs, JSON-based services Wet lab and experimental consulting: Experimental design for sequencing-based studies. Troubleshooting PCR, cloning, library prep, and sequencing workflows. Guidance on protein expression and molecular cloning workflows. Connecting wet lab outputs with downstream computational analysis. Genomics research and analytical consulting: Technical and market research on genomics and sequencing technologies. Variant impact assessment and interpretation workflows. Literature analysis and publication mapping. Translating computational outputs into structured reports and slide decks for both technical and non-technical stakeholders. What you get: - Reproducible, well-documented bioinformatics workflows - Systems-level thinking across wet lab and computational layers - Clear outputs with strong attention to data integrity - Fast turnaround If you're working with sequencing data, complex biological signals, clinical or experimental datasets, or need grant-level analytical support, let's talk.