Biology-First Bioinformatics

Fractional data science for teams pushing scientific boundaries

We partner with founding teams to tackle computational challenges in cutting-edge therapeutics development--no hand-holding required. Biology-first fractional data science with a focus on translation for the questions that keep you up at night, with the speed and agility that industry demands.

Grow with us

What We Do

A biology-first approach to bioinformatics

We built Sprout Informatics with the idea of a "biology-first" approach to bioinformatics, which we found in our own experience to be an underserved niche, particularly for early- and mid-stage startups.

With two decades of combined experience in biotech, both as individual contributors and team leaders, we provide support for the full "data science vertical", from infrastructure to pipelines to downstream analyses.

Most critically, we have the experience to translate and communicate those results to your team. We've tackled diverse questions that often required novel methods—strain-level bacterial fingerprinting, RNA splice junction usage distribution, single cell expression of gene isoforms—these are some of the problems we've encountered and developed novel solutions for.

20+

Years combined experience

Full

Data science vertical

Deep

Domain expertise

Novel

Methods development

Expertise

Deep experience across omics modalities

Transcriptomics

Bulk RNA-seq, single cell RNA-seq, and Nanostring assays. From differential expression to pathway analysis to novel isoform detection.

Microbial Genomics

Whole metagenomic shotgun and 16S rRNA sequencing. Community profiling, strain-level analysis, and functional characterization.

Whole Genome Sequencing

Variant calling, structural variation, and genome assembly. From experimental design through interpretation.

Infrastructure & Pipelines

Cloud infrastructure on AWS and GCP. Reproducible Nextflow and Snakemake pipelines. Databricks and custom solutions.

Downstream Analysis

Statistical modeling, pathway enrichment, visualization, and interpretation. Translating data into biological insight.

Extended Network

Working with a modality not listed? We have an extensive network of data professionals we can tap for specialized expertise.

Our Approach

Built for early-stage biotech

We understand the unique challenges of early- and mid-stage biotech companies. You're pushing scientific boundaries with lean teams, and you need data science support that can move as fast as your science.

Our fractional model means you get experience where you need it, without the overhead of a full-time hire. Whether it's a one-off analysis, building and managing your data infrastructure, guidance on data strategy, or ongoing support as you scale, we adapt to your needs.

Most importantly, we speak your language. We've been in your shoes—leading data science at startups, presenting to partners, supporting IND filings and clinical trials.

We don't just deliver results; we help you tell the story.

Team

Meet the founders

Liyang Diao, PhD

Co-founder

A data science generalist who has worked across diverse indications such as infectious disease, oncology, and autoimmune disease, Liyang brings a well-rounded translational skill set that includes deep expertise in metagenomics and transcriptomics.

Michael Seiler

Co-founder

With over a decade of deep experience in RNA splicing, oncology, and neurodegenerative disease, Michael brings significant disease-relevant subject matter expertise in addition to informatics and infrastructure.

Get in Touch

Let's talk about your data

Whether you have a specific project in mind or just want to explore how we might help, we'd love to hear from you.

info@sproutinformatics.com