Hello, I'm Ana Lujan.
A computational scientist with an experimental background. 
I have experience with synthetic biology, data science and bioinformatics.  My focus has been platform & technology development  for antibody discovery and engineering. 

I am Mexican-American, born in Mexico and raised in South Florida. Since I was a child I have been driven by deep curiosity and hunger for knowledge, once introduced to science I became fascinated with understanding the natural world. I completed my education at the University of Pennsylvania in 2018, earning degrees in Biochemistry and Biophysics. Subsequently, I ventured into the biotech industry, dedicating the last five years to platform development for early-stage antibody discovery at Twist Biosciences. My professional journey has spanned a diverse range of responsibilities, a few of which are highlighted below:

​

1. Protein Sciences: During my initial two years in protein sciences, I established lab protocols, workflows, databases, and computational pipelines for high-throughput small-scale antibody (IgG) production and characterization. This miniaturization effort reduced costs by 40% and increased throughput by over 10x. I led the protein production team, supporting internal platform validation and external revenue projects. Collaborating closely with product, business, and computational teams, we developed this workflow into a commercially launched product.

2. Antibody Discovery: Intrigued by the upstream workflow of antibody discovery, I trained with senior members of the antibody engineering group, delving into phage display, library design, and sequence analysis techniques. I developed scripts for sequence processing, significantly reducing "hands-on" analysis time by > 10x and preventing project delays and re-work costs by including validation steps in the workflows. My contributions included supporting major discovery projects (>$5M) and leading my own display-platform development project (>$2M). I proposed, designed, built, and validated anti-SARS-COV-2 multi-specific variant libraries, resulting in two filed patents.

3. Computational Integration: Seeking more quantitative and rational approaches to antibody design, I collaborated closely with the bioinformatics scientist in our team. Together, we implemented NGS protocols in the lab, and in conjunction with computational pipelines, achieved a >30% boost in discovery "hit" rates. Outside of work, I dedicated my time to data science and ML bootcamps, researching bioinformatics tools, and studying Python documentation. As an increasing number of revenue projects opted for NGS add-ons I worked to scale our NGS workflows from a static EC2 to Databricks, reducing compute time by >20x, facilitating simultaneous processing, and ultimately increasing project throughput by >10x. I became the lead in NGS-based projects and worked with the product and business teams to align our offerings with customer needs, compute COGS and define requirements. 

4. Technology Development Leadership: Energized by efficiency gains I developed workflows to automate additional resource-intensive bottlenecks and transitioned into a fully computational role. With the team expansion, we established a Technology Development group, where I currently serve as the bioinformatics lead. In this role, I oversee a bioinformatics engineer & closely collaborate with a machine learning engineer & support the evolving computational needs of the scientific team. My focus includes identifying, evaluating, and integrating emerging ML and bioinformatics tools, and developing them into commercially relevant opportunities.