Our Work – Sprout Informatics

Our Work

Flexible partnerships built around your needs

Data and data analyses live at the heart of drug discovery programs. Below, find some ways in which Sprout Informatics has leveraged a variety of data and analytical approaches to drive programs forward.

Recent work

With our core competencies spanning multiple data modalities, therapeutic areas, and infrastructure development, we can work with our clients in numerous flexible ways to best augment their internal capabilities.

Some of the ways in which we have partnered with our clients include:

Embedding within larger Data Science teams to focus on high-priority exploratory analyses and building novel analytical pipelines that lack resourcing internally
Building out computational infrastructure from scratch to support scaling of internal data generation, while providing analysis and guidance on assay readouts
Partnering on developing compelling case studies for internal data, focusing on driving value proposition of novel data modalities
Advising on, developing, and implementing data architecture plans to support scaling up ad-hoc pipelines

Case Studies

Below, find some more in-depth examples of problems we've worked on at previous companies.

Case Study 1

A state-of-the-art neural network to predict novel RNA processing drug targets

Mining over 400,000 public RNA sequencing datasets to identify poison exons and building a deep learning framework to predict the best candidates for drug target screening.

Case Study 2

Large-scale data mining and development of target profiling dashboards to enable indication selection

Mining over 36,000 samples spanning common and rare cancers to identify indications with the greatest differential gene expression and build interactive dashboards for target profiling.

Case Study 3

Deconvoluting phenotypic mechanism of action using public data

Leveraging external public data to uncover the mechanism of action for unknown chemical matter by analyzing transcriptomic fingerprints and overlaying them on known pathway networks.

Case Study 4

Target profiling in bulk and single-cell RNA-seq expression data reveals differential co-expression patterns by data type

A large-scale meta-analysis of bulk and single-cell RNA-seq data showing how Siglec-15 and PD-L1 co-expression varies across cancer indications, informing combination immunotherapy strategies.

Case Study 5

Development of a novel single-cell RNA-seq quantification pipeline for a target gene isoform enables target profiling by cell type

Creating a novel algorithm and pipeline for pseudo-bulk isoform-level quantification at the single-cell level to identify cell types producing target proteins.

Case Study 6

Clinical analysis support in late-stage microbiome therapeutics elucidates the relationship between engraftment and therapeutic response

Building a best-in-class bacterial classification pipeline that enabled unprecedented resolution for the first FDA-approved oral microbiome therapeutic.