Learn Data Skills
John Pan

John Pan

Informatics Scientist

Pan Informatics LLC


My Portfolio Highlights

My New Course

Data Manipulation with pandas

My New Workspace

Competition - hospital readmissions

My New Workspace

Course Notes: Introduction to Network Analysis in Python

Analytical luminary, illuminating the path to data-driven enlightenment.

My Work

Take a look at my latest work.


Competition - hospital readmissions


Course Notes: Introduction to Network Analysis in Python


Data Manipulation with pandas

My Certifications

These are the industry credentials that I’ve earned.

Other Certificates

University Of California, Irvine Data Science

DataCamp Course Completion

Take a look at all the courses I’ve completed on DataCamp.

My Work Experience

Where I've interned and worked during my career.

Data2Discovery Inc | Mar 2018 - Oct 2019

Bioinformatics Consultant

Melding expertise in biology, software engineering, data science and information technology to help scientists advance drug discovery by exploiting public life sciences data
Show More

Pan Informatics LLC | Mar 2018 - Present

Informatics Scientist

Pan Informatics LLC offers customized informatics consulting services revolving around Image Analytics, Digital Pathology, Data Science and Life Science IT. We are scientists before we are technologists and enable your scientists by understanding, translating, automating and transforming your particular scientific and business problems into working products Interesting Projects •Developed an image and data analysis pipeline which uses an ensemble machine learning classifier to distill TCGA-BRCA(Breast Invasive Carcinoma) diagnostic biopsies into an informative feature that can help predict patient survival status. • Worked with scientists to develop and put into production fully custom Java software to automate analysis of their specific in-house animal model. • Worked directly with research scientists to develop and put into production Matlab software to quantitate Optical Coherence Tomography (OCT) data in 3D. Allowing for the first-time quantitative measurement of a formerly subjective endpoint. • Developed internally normalized digital H-Score quantification methodology allowing objective automated image analysis of histology slides. • Quantification of real world drug delivery from prototype drug delivery devices through image analysis of post-delivery devices. • Deep Dived into the code-base and technology stack of a non-functioning home-brewed LIMS platform in order to rescue, maintain and update the system at a medium sized biotech. • Provided independent third-party evaluation of scientific data coming from a Contract Research Organization for a large Pharma.

Allergan | Nov 2012 - Mar 2018

Bioinformatics Specialist

• Member of the Research Informatics and Competitive Intelligence team • Directly provided data analytics and bioinformatics support to scientific and business teams at Allergan • Helped develop and build an oracle database and visualization application of all drugs worldwide which reached human trials • Worked directly with R&D scientists to find repurposable and repositionable drugs which fit their mechanism of action hypotheses • Authored white papers with business development to describe the drug landscape for therapeutic areas. • Lead Image Analytics Developer (Digital Pathology) • Performed full software life cycle from business analysis, requirements gathering, design, development, training, roll out and maintenance of novel algorithms for automated or semi-automated quantitative image analysis of histology, immunohistochemistry slides and other high content images. • Wrote a Lab application from the ground up to quantitate Optical Coherence Tomography Data in 3D. • Image analysis algorithms reduce technician analysis workload, reduce outsourcing costs, increase data reproducibility and reliability, and allows for quantification of endpoints which are not human measurable. • Responsible for design of UI/UX and direct training of scientists on newly developed image analysis software. • Advanced/Expert user on Definiens Developer XD Image Analysis Platform • Involved in some early NGS and Genomics efforts

Genomic Health | Jun 2012 - Sep 2012

Bioinformatics Research Intern

• US Patent Application 14/440582 (US20150302143A1) Gene fusions and alternatively spliced junctions associated with breast cancer • Bioinformatics/Computational Biology/Genomics Research • Wrote RNA-SEQ (NGS) analysis program to find and classify alternative splicing biomarkers in a cancer data set with known outcomes. The outcome data allowed for biomarkers to be statistically correlated with prognostic value. • Project Lead/Manager for test pilot of Bina Technologies’ Sequencing Data Analysis platform. • Programming and algorithm development in Perl, Python, R and Bash • High Performance Computing (HPC) Cluster experience

Cedars-Sinai Medical Center | Jun 2011 - Sep 2012

Temporary Research BioAnalyst / Bioinformatics Graduate Intern

Programming in Perl, Python and Bash Script Analysis, transformation, manipulation and processing of multiple types of Genomic Data in search for the causative agents for novel skeletal dysplasia diseases. Analysis of Next Generation Sequencing Data • Whole Exome Data • RNA-SEQ Data Analysis of Microarray Data • SNP Genotyping Array Data • Gene Expression Data •Compiled new genome reference from a non-redundant combination of GENCODEV9, REFSEQ and miRBase. •Data Mining using UCSC Genome Browser, Ensembl, SeattleSEQ, dbSNP, 1000Genomes, MiRbase, OMIM, and UniProt •Use of Bioinformatics software including Cufflinks, CLC Genomics WorkBench, IBDfinder, PennCNV, Illumina Genome Studio, and Integrated Genome Viewer(IGV)

Independent | Oct 2009 - Jul 2011


• Expertise in finding areas of inefficiency in your current business processes and building computational pipelines to alleviate them. • Previously engaged with the UCSF Genome Analysis Core to automate an experimental protocol on their SEQUENOM MassARRAY. o Developed custom MS Excel macro to perform automated data processing. o Trained a Research Associate on the basics of programming. • Tutored MS Access and SQL queries for the explicit purpose of building reporting dashboards.

IDBS | Oct 2007 - Sep 2009

BioBook Consultant

IDBS is a leading worldwide provider of advanced data management and data analytics solutions for the Biotechnology and Pharmaceutical and industries. IDBS Biobook & E-workbook specialist. Professional Services Consultant providing end to end technical implementation services including 1) Requirements and scope gathering 2) Technical Implementation of all aspects of Biobook & Eworkbook 3) Database Setup 4) User administration 5) Catalog setup and maintenance. 6) Conducting training courses 7) Communication liaison between Scientists, IT and Management.

UC San Francisco | Jan 2006 - Jan 2007

Staff Research Associate II

The UCSF Genome Analysis Core provides high quality, customizable services for illuminating the genome and transcriptome. I provided expertise in Quantitative Real Time PCR directly to researchers of the UCSF Comprehensive Cancer Center as well as outside clients. I performed and analyzed a wide range of Q-PCR assays using SYBR Green and Taqman chemistries including Relative Gene Expression, Copy Number Analysis, DNA Quantification, Allelic Discrimination, and SNP Analysis. For novel genes I would also help design and optimize primers. During my time at the Genome Analysis Core I identified a bottleneck in our workflow. To solve this problem I independently proposed, designed, authored, implemented and validated a software solution. ROI was immediately realized when analysis time per assay was reduced from an hour to a few minutes. I built the solution to be both robust and flexible and it is still performing maintenance free despite my leave from UCSF.

Clinical Investigation Facility: David Grant USAF Medical Center | May 2005 - Aug 2005

USAF Undergraduate Research Fellow

At the Clinical Investigation facility I interned with Captain Morris Jones, Chief of Molecular Virology. I helped work on a project to create a robust RT-PCR assay for detecting Norwalk Virus. To that end I learned the basics of assay design and optimization, how to work in a Biosafety Level 2 environment with live Norwalk virus and how to perform and analyze Real-Time Quantitative PCR.

My Education

Take a look at my formal education

Master's, Biotechnology with Concentration in BioinformaticsCalifornia State Polytechnic University-Pomona | 2013
B.S, BiotechnologyUniversity of California, Davis | 2006

About Me

John Pan

Bioinformatics Scientist and Research IT Engineer open to changing industries.

Powered by

  • Work
  • Certifications
  • Courses
  • Experience
  • Education
  • About Me
  • Create Your Data Portfolio for Free