AI's largest biological dataset

AI's understanding of biology was limited by the data it was trained on. To change this, we established partnerships across all seven continents to create BaseData™; the largest and most diverse evolutionary genetic dataset ever built.

Watch Documentary

explore THE TRILLION GENE ATLAS

The data wall holding back AI in biology

Today's biological datasets are narrow, repetitive, and heavily biased toward a small number of well studied organisms.

Much of biology's diversity remains entirely absent from the data used to train AI models.

68

%

of public data comes from just five species

70

%

of it oiginates from only ten countries

<

10

%

annual growth rate of the most widely used AI training database

So we built BaseData™

By establishing a network of biodiversity partners across all 7 continents, we created an evolutionary dataset of over 10 billion genes and a million uncharacterised species. This dataset gives AI models an unprecedented view of biology.

read the BaseData paper

>100 billion novel genes

>10 million new species, unknown to science

>100x larger than public datasets

The Trillion Gene Atlas

The Trillion Gene Atlas is one of the most ambitious biological data initiatives ever undertaken, expanding known evolutionary genetic diversity by 1000-fold across more than 100 million species worldwide.

Read the press release

1,000

x

expansion of known evolutionary genetic diversity

100

x

growth on the current BaseData corpus

100

M+

species reached worldwide

Built with

Advised by

Kerstin Howe, PhD

Head of Production Genomics at the Wellcome Sanger Institute and Chair of the EBP International Scientific Committee

Jill Banfield, PhD FRS

Director of Microbiology at Innovative Genomics Institute, UC Berkeley

Chris Mason, PhD

Professor at Weill Cornell Medicine and Founder of MetaSUB International Consortium

Timothy Hodges, PhD

Co-Chair of Access and Benefit-Sharing negotiations under the Convention on Biological Diversity

Martha Mphatso Kalemba, PhD

ABS & CBD National Focal Point and Co-Chair of the UN OEWG on Digital Sequence Information

Maui Hudson, PhD

Co-Director at the Kotahi Research Institute and Co-founder of Global Indigenous Data Alliance

Thulani Makhalanyane, PhD

Chair of African Microbiome Project and Director or the ISME Ambassador Program

A global data network built through partnership

watch our collaborations in practice

At the core of our data are our biodiversity partners. Every sample is collected under informed-consent and benefit-sharing agreements so that the countries and communities who steward this biodiversity share in the value it creates.

We actively contribute to discussions shaping the frameworks and policies that govern access to genetic resources, and the sharing of benefits arising from their use. This policy engagement helps ensure that our partnerships remain aligned with evolving international biodiversity governance frameworks.

200

+

ABS agreements

130

+

royalties paid to 21 countries

100

+

scientists trained

7

continents

across 30+ countries