Computomics

Great science deserves great marketing 🧬🌱
We’re looking for a full-time Marketing Manager (Strategy & Ex*****on) on-site in . If you combine strategic thinking and market understanding with creativity and hands-on ex*****on, a great team would love to hear from you! 🥳

👉 https://www.computomics.com/company/career.html

"I think the model in detail might change, but not the general idea of how to model for this environment. What changes is what kind of goals we go for."

🌱 A promising crop variety can look great in the data and still fail in the real world.

In our new podcast episode, Felix Sattler shares an example from pearl millet 🌾 breeding in Niger: red-grain varieties offered nutritional benefits and were less attractive to birds, but consumers did not like the darker color of the porridge they produced.

It is a simple example of a much bigger point: successful plant breeding depends on more than genetics, AI, and predictive models. 🙌🏼 Local preferences, infrastructure, environmental conditions, and trust matter too.

In Season 8, Episode 1 of the Computomics Podcast, we explore what it takes to make AI-driven breeding useful and accessible across very different environments.

Listen now: “Can AI Make Plant Breeding More Accessible?”
https://www.computomics.com/news-reader/podcast-s8e1-felix-sattler.html

Great varieties don't come from more data. They come from understanding it 🧑🏻‍💻

brings genotype, phenotype, and trial metadata together and turns them into interactive visualizations that make patterns visible at a glance. Right on top of your existing Breeding Management Software.

Spot top performers faster, compare across environments with ease, and select varieties that thrive where they're planted 🌱

See what to expect 👉 https://lnkd.in/dCd4H76n

Can machine learning predict how a crop will perform in a field it has never grown in?�

In the Center for Data Innovation's latest "5 Q's," Sebastian Schultheiss, CEO of Computomics, explains how nonlinear ML combines genetics, field trials, and environmental data to speed up plant breeding.

The questions cover:�
🌱 What sets Computomics apart in plant breeding�
📊 Which data feeds its crop-performance predictions�
✔️ How to tell when a prediction is reliable enough to act on�
🔒 How proprietary plant data stays protected�
💡 The biggest misconceptions about ML in breeding

Spoiler: it doesn't replace field trials.

Read the full interview: https://www.computomics.com/news-reader/itif-5-qs.html��

🧬 Genomic prediction pricing has become a rumor market. The figures traded at breeding conferences can differ a hundredfold, and they say almost nothing about your own program.

The better question: what is it worth to you?

🌱 Price it against your own trialing budget, not someone else's crop.
🌱 Count the entries you could drop before planting, then add the value of reaching market sooner.
🌱 Check your data first. If pulling a few seasons of linked trial records takes a month, start there.

The breeding programs seeing real returns sorted out their data before buying a model (two seasons can be enough), and kept their existing breeding system.

Read the full SeedWorld article 👉 https://www.computomics.com/news-reader/seedworld-what-genomic-prediction-is-worth-to-your-program.html

🌱 Heading to Euroseeds 2026 in Valencia (25–28 Oct)? So are we! 🇪🇸
Meet Computomics at trade table #134 to talk predictive breeding - smarter parent selection, faster genetic gain, and better-adapted varieties, before full field data is in.

Stop by our table #134, or schedule a meeting with us ahead of time! Vesna Tabakovic and Juan M. Montes are looking forward to connecting with you.

👉 https://www.computomics.com/events-reader/euroseeds-2026.html

Welcome to the eighth episode of our “Breed, Sow, Grow” series 🌱
Plants, like humans, face challenges that threaten their health and growth. Understanding these stresses and their impact is crucial, particularly as climate change amplifies their intensity. In this blog episode, we look closer into how to equip our crops to withstand these pressures. Also, what are some tools and technologies for modern plant breeders?��

👉 https://www.computomics.com/news-reader/blog-s1e8-under-pressure.html

�

For biotech companies developing genetically improved crops, discovering disease-resistance traits is the first step. Next comes turning large-scale genetic data into practical breeding decisions, and SNPs alone don't tell the whole story.�

🧬 captures the full spectrum of genetic diversity across your germplasm, genotyping structural variants alongside conventional markers for a more complete variant set.�

🌱 links this improved variant set to phenotypic data, translating those insights into predictive breeding values that rank the most promising candidates for your traits of interest.�

Together, our technologies create a direct path from trait discovery to targeted selection, so you can breed on better variants, not just more markers.

Which problems are you trying to solve? �Explore https://www.computomics.com/customer-scenarios.html�