Wheeler Lab

What Wheeler Lab does

Wheeler Lab is an academic research laboratory housed in the College of Pharmacy at the University of Arizona, founded by Travis Wheeler and relocated from the University of Montana in 2022. The lab designs algorithms, statistical models, and AI/ML systems for problems motivated by biological data, with primary focus on sequence annotation, large-scale biological database search, transposable element analysis, virtual drug screening, and multi-animal tracking. It maintains a portfolio of roughly 18 open-source tools and web services including NINJA (phylogeny inference), nail/NEAR/BATH (protein sequence annotation), ULTRA (tandem repeat detection), DIPLOMAT (deep-learning multi-animal tracking), DISCO (acoustic signal segmentation), Drugsniffer and Simpatico (virtual drug screening), plus foundational resources Dfam (transposable element database), MDRepo (molecular dynamics warehouse), TE Hub, Skylign, and the HMMER webserver. The lab co-develops Dfam with the Institute for Systems Biology and contributes to global consortia including TE Hub, the Human Pangenome Reference Consortium, and the Vertebrate Genomes Project.

The lab employs approximately 10-15 people including research staff, software engineers, data scientists, and PhD students. All software is released as open source under permissive licensing with no commercial pricing model. Operating funding derives entirely from competitive federal research grants — primarily NIH (multiple R01, R21, U01 awards) and DOE (PerCon SFA) — supporting defined project scopes such as pattern HMM acceleration, RepeatMasker/RepeatModeler maintenance, Dfam infrastructure expansion, human virome analysis, and engineered soil microbiome persistence. Go-to-market is community-led: distribution occurs through GitHub (TravisWheelerLab), web-accessible databases, peer-reviewed publications, and consortium channels. Customer segments are academic researchers, bioinformatics core facilities, and drug discovery researchers who consume the tools at zero cost. The lab has no equity investors, no commercial customers, and no recurring revenue in the traditional sense.

Name

Wheeler Lab

Legal name

Wheeler Lab

Website

https://wheelerlab.org

Company type

Private

Founded year

2015

Operating status

Operating

Headcount range

1–10 employees

Short description

Wheeler Lab is an academic research laboratory at the University of Arizona that develops open-source computational genomics, drug discovery, and AI-based animal-tracking tools for the global bioinformatics research community.

Ownership category

akta.pro rank

Product category

Computational Genomics Software

NAICS

Research and Development in Biotechnology (except Nanobiotechnology) (541714), Scientific Research and Development Services (5417)

SIC

Services-Commercial Physical & Biological Research (8731)

akta.pro primary industry

AI/ML Platforms for Drug Discovery & Experiment Optimization (HLAGAJAO)

akta.pro secondary industries

Lab Automation, Instrument Control & Workflow Orchestration Software (HLAGAJAG), Cheminformatics & Molecular Modeling / CADD (HLAGAJAE), High-Throughput Screening & Assay Platforms (HTS/HCS, phenotypic screening) (HLAAAIAA)

Keywords

• Computational genomics
• Bioinformatics software
• Sequence alignment
• Drug discovery tools
• Transposable elements

Headquarters

HQ city

Tucson

HQ country

United States

HQ region

North America

Offices1 record

Markets served

GTM type

B2B

Offering type

Software

Cost components

Personnel, Technology or R&D, Infrastructure, Operations, Others

Revenue model

1. Research Grants: Primary funding from federal agencies including NIH (multiple R01, R21, U01 grants) and DOE (PerCon SFA). Lab develops tools and publishes research funded by grants.

Go-to-market motion2 records

Distribution channels3 records

Marketing channels5 records

Core offering

Wheeler Lab is an academic research laboratory in the University of Arizona Department of Computer Science that designs algorithms, statistical methods, and open-source software tools for biological sequence analysis, drug discovery, and animal tracking. The lab maintains community web-accessible databases (Dfam, MDRepo, TE Hub) and develops standalone tools including NINJA for phylogeny inference, nail/NEAR/BATH for protein search, DISCO for acoustic classification, DIPLOMAT for multi-animal tracking, and Drugsniffer/Simpatico for virtual drug screening.

Product overview

Wheeler Lab is a computational genomics and drug discovery research laboratory that develops a comprehensive suite of bioinformatics software tools, web services, and databases. The portfolio includes: (1) Sequence analysis tools - NINJA for phylogeny inference, nail/NEAR/BATH for protein sequence annotation and search, ULTRA for tandem repeat detection, MIRAGE for splice-aware alignment; (2) Drug discovery tools - Drugsniffer and Simpatico for virtual screening of billions of molecules for protein binding affinity; (3) Visualization and annotation tools - SODA library for sequence annotation visualization; (4) Deep learning tools - DIPLOMAT for multi-animal video tracking, DISCO for audio classification; (5) Web databases - Dfam for transposable element families, MDRepo for molecular dynamics simulations, TE Hub for community collaboration, Skylign for sequence logos; (6) Infrastructure libraries - AWFM-index for fast pattern matching, sufr for suffix array construction in Rust. The tools are primarily developed in C/C++, Java, Python, and Rust, with open-source distribution via GitHub.

Differentiator

Problem solved

Functional benefit

Brands

• Dfam: A database of repetitive DNA based on profile hidden Markov models, developed in collaboration with Institute for Systems Biology.
• TE Hub
• MDRepo

Products and services

• NINJA Algorithm for large-scale phylogeny inference from distance matrices, designed to be both fast and sensitive for difficult phylogenetic cases.
• nail Library for protein sequence search and alignment.
• NEAR Protein search tool that uses neural embeddings for biological sequence search.
• BATH Frameshift-aware translated HMMER implementation for protein search handling ribosomal frameshifts.
• ULTRA Tool for detecting tandem repeats in biological sequences.
• DIPLOMAT Deep-learning multi-animal tracking tool with integrations to MARS, Loop, CellProfiler, and Colab.
• Drugsniffer Virtual drug screening tool capable of screening billion-molecule libraries.
• DISCO Acoustic signal classification tool that uses deep learning.
• SODA Sequence annotation visualization library for biological sequence analysis.
• Simpatico Graph neural network tool for virtual drug screening.
• sofr Suffix array implementation in Rust for high-performance sequence indexing.
• MIRAGE Splice-aware sequence alignment tool.
• AWFM-index library AVX2-accelerated FM-index library for fast biological sequence search.
• Dfam Public web-accessible database of repetitive DNA elements, serving as a community consortium resource for transposable element annotation.
• MDRepo Web-accessible molecular dynamics simulations repository.
• TE Hub Web-accessible transposable element collaboration platform.
• Skylign Web-accessible sequence logo creation and visualization tool.
• HMMER Web-accessible biological sequence analysis service using profile hidden Markov models.

Quantifiable outcome

• NINJA is 10x faster than canonical neighbor-joining implementations for large sequence sets
• +2 more outcomes

Segments3 records

Ideal customer profiles3 records

Technology focussed Yes

API detail

Has API

Yes

API docs

API detail

Core technology

AI maturity

App detail

Integration2 records

AI capability10 records

Feature13 records

Partnerships

Seven partnerships are on record, tiered core and minor.

• Pacific Northwest National Laboratory (PNNL)coreStrategic or Co-development Partner · 1 January 2024Multiple collaborative projects including: DOE PerCon SFA (2023-2026) for persistence control in soil microbiomes; NIH project on computational tools for illuminating the human virome (2024-2028); DOE project on learning approaches for integrating multi-omics data (2020-2023). Dr. Jason McDermott serves as PI on some grants with Wheeler Lab developing ML methods.
• Human Pangenome Reference ConsortiumcoreStrategic or Co-development Partner · 1 January 2024Clément Goubert represents Wheeler Lab in this major initiative for improving human genome references with diverse population representations.
• Vertebrate Genomes Project (VGP)coreStrategic or Co-development Partner · 1 January 2024Consortium effort to generate high-quality reference genomes for all vertebrate species. Wheeler Lab contributes through repeat element annotation and analysis tools.
• University of Colorado Anschutz (Blake Hill Lab)minorStrategic or Co-development Partner · 1 January 2023Skaggs Scholars Program project on Generative AI to Predict and Drug Pathological Mitochondrial Fission. Wheeler Lab contributes computational approaches for structural ensemble development.
• TE Hub ConsortiumcoreStrategic or Co-development Partner · 1 January 2021International consortium dedicated to facilitating access to and training in bioinformatic analyses of transposable elements. Wheeler Lab contributes to wiki pages and community resources.
• University of Montana - Psychology (Nathan Insel Lab)minorStrategic or Co-development Partner · 1 January 2019NIH grant on Learning and Neural Coding of Social Expectations (2019-2022). Wheeler Lab developed ML methods for tracking multiple animals in video and behavior classification.
• Institute for Systems Biology (Arian Smit, Robert Hubley)coreStrategic or Co-development Partner · 1 January 2012Long-standing collaboration on Dfam database (since 2012), RepeatMasker and RepeatModeler development (2022-2027), and Dfam sustainable growth project (2018-2028). Joint multi-PI grants for transposable element research infrastructure.

Scale indicators5 records

Recent moves7 records

Expansion highlights6 records

Emerging players

• Atomwise: AI-focused small-molecule drug-discovery company using deep learning for virtual screening. Atomwise's AtomNet platform competes in the same problem space as Simpatico and Drugsniffer but with venture funding and pharma partnerships.
• Recursion Pharmaceuticals: AI-driven drug-discovery company combining high-throughput biology with ML — comparable trajectory to Wheeler Lab's ML-based virtual screening work (Simpatico, Drugsniffer), though operating at vastly larger capital scale.
• Isomorphic Labs: Alphabet-backed AI drug-discovery company spun out of DeepMind, applying foundation models to molecular design and protein-ligand prediction. Represents the frontier commercial counterpart to Wheeler Lab's graph-neural-network and neural-embedding research.

Broad incumbents

• Schrödinger, Inc. Commercial computational chemistry and drug-discovery platform whose molecular simulation and virtual screening capabilities directly overlap with Wheeler Lab's Drugsniffer and Simpatico tools, but at commercial scale with proprietary product offerings.
• European Bioinformatics Institute (EMBL-EBI): Major public bioinformatics infrastructure provider hosting widely-used open-source databases and tools (Ensembl, UniProt, InterPro). Operates at much larger scale but shares the open-data, community-resource mission that defines Wheeler Lab's Dfam and MDRepo work.
• Benchling: Commercial cloud platform for life sciences R&D, providing lab informatics and sequence/biomolecule management. Comparable customer base (academic and industry researchers needing sequence tools) but commercial productized offering versus Wheeler Lab's open-source approach.
• DNAnexus: Cloud-based genomic data management and analytics platform. Comparable in serving the bioinformatics community with infrastructure tools, but operates commercially while Wheeler Lab distributes via open-source and web services (Dfam, MDRepo, HMMER).

Direct peers

• Pacific Northwest National Laboratory (PNNL): Active DOE and NIH collaborator with Wheeler Lab on multiple ML-for-biology projects (PerCon SFA, human virome, multi-omics integration). PNNL's biology and computational sciences divisions pursue comparable federal-grant-funded computational genomics and ML work.
• Institute for Systems Biology: Long-standing co-developer of the Dfam transposable-element database and RepeatMasker/RepeatModeler tools with Wheeler Lab. ISB's Arian Smit and Robert Hubley are multi-PI partners on multiple NIH grants covering TE research infrastructure, making them the most directly comparable collaborator/peer in scope and activity.
• HHMI Janelia Research Campus: Academic research campus where Travis Wheeler did his postdoc under Sean Eddy (HMMER creator). Janelia pursues computational biology and neuroscience tool development with similar open-source ethos and grant-based funding, making it a strong institutional peer.

Market position

Strengths5 records

Weaknesses5 records

Competitive moat4 records

Key risks7 records

Key highlights7 records

Customer concentration

• GitHubgithub.com/TravisWheelerLab
• LinkedInlinkedin.com/company/wheeler-lab

Revenue estimate

Valuation estimate

Number of profiles

Profiles16 records

Funding overview

Funding rounds

Investors

Funding detail is available on the Subscription and Enterprise plan.Contact sales →

M&A

Investments

M&A and investment is available on the Subscription and Enterprise plan.Contact sales →

Frequently asked questions about Wheeler Lab