I am now on Fiverr. A place to use my expertise in bioinformatics, machine learning, genomic data processing, and automation.

I can design and automate pipelines from any dataset, either genomic (for variant calls) or transcriptomic (for gene expression). Sample size is not an issue. Automation is done on high performance clusters. No need to worry about ram and price of computer performance. The pipelines include most of known databases (UCSC, NCBI, Entrez, UniProt, Swissprot, Prodom, Panther, Tigrfam, Superfamily, Pirsf, Gene3d, Pfam, Smart, Prosite profiles, Prosite patterns, Coils). It also include known tools in sequence analysis. This would require parametrization, metric logging, summarization, and creating full-fledged reports. Data mining is a prerequisite of course. This would be tailored to the available data that will be analyzed. To order help on these subjects, visit this gig: pipeline automation.

For those who are more interested in heavy use of computational biology techniques, machine learning, advanced statistics applied to complex data (clustering, regularization & others) will have to visit this second gig: advanced bioinformatics. As part of improving interpretability as much as pattern recognition from genetic data, visualization techniques and publishable figures are also available to order.