The cost of tomatoes

I don’t know whether the article in The Media Line ((Strap line: Trusted Mideast News.)) a few days ago entitled “Israeli Scientists Develop Drought-Resistant Tomatoes in Response to Climate Change” was based on a press release. But if it wasn’t, it’s a pretty good catch, given the paper on which it is based is called “Epistatic QTLs for yield heterosis in tomato.” ((It’s part of the PNAS Special Feature: Harnessing Crop Diversity.))

Anyway, what the authors of the paper did was cross a wild tomato with a cultivated one, which conjured up about 1,500 different progenies, each with a different bit of wild genome. They then figured out which of those bits of genome were good at allowing their possessor to grow well with less water than normal.

According to our Trusted Mideast News source:

The study found that two specific areas in the plant’s genome lead to a 20%-50% increase in the overall yield in both regular and dry conditions. The overall size of the plant also was improved.

According to the researchers, the findings demonstrate the effectiveness of using wild species to enhance agricultural output. They could also prove to be widely applicable to other plants in the future.

Which got me thinking. Effective, sure. But how long did it take? Digging a little deeper revealed that the work relied on a genome of the wild tomato Solanum pennellii that was published in 2017. But that’s not where it all started:

…we sequenced and assembled the accession LA5240 (LYC1722) of the wild tomato species Solanum pennellii, an accession that was identified spuriously. Unlike the Solanum pennellii accession LA0716, for which we have previously generated a high quality draft genome, the accession LA5240 does not appear to exhibit any dwarfed, necrotic leaf phenotype when introgressed into modern tomato cultivars.

And that LA0716 was sequenced in 2014.

So our new climate-change-proof tomato was almost 10 years in the making and relied on a “spuriously” identified accession. Well done and all, but gosh, I hope the next one is easier.

Oh, and here’s a nice detail to close. The LA in LA5204? It stands for “Lost Accession.” What’s the story there, I wonder?

Brainfood: Traits & environment, Acacia growth, Local extinction risk, Lebanese CWR priorities, Malawi CWR payments, Bread wheat origins, Wild lettuce, Ethiopian forages, Editing forages

Quick takes

A couple of hot takes. Maybe I’ll circle back with the missing nuance when I have more time.

From the World Bank: Coming Together to Address the Global Food Crisis

Take home message: Food insecurity was already on the rise because of climate change before the pandemic and the Ukraine war, and it will continue to worsen through 2027. To boost food and nutrition security, the World Bank is scaling up both short- and long-term responses in 4 priority areas: 1. Support production and producers; 2. Facilitate increased trade in food and agriculture inputs; 3. Support vulnerable households; 4. Invest in sustainable food and nutrition security. No word specifically on crop diversity or genebanks.

It’s possible to reduce greenhouse gas emissions from agriculture and make our food systems more resilient and adapt to climate change. But doing so requires a major transformation of how we produce, distribute and consume food.

From the IPCC: AR6 Synthesis Report Climate Change 2023

Take home message: While food, land, and water systems are being severely impacted by climate change, they are also a source of solutions, for mitigation, for adaptation and to build resilience and reduce inequity. No word specifically on crop diversity or genebanks.

A.3.2 Effectiveness of adaptation in reducing climate risks is documented for specific contexts, sectors and regions (high confidence). Examples of effective adaptation options include: cultivar improvements, on-farm water management and storage, soil moisture conservation, irrigation, agroforestry, community-based adaptation, farm and landscape level diversification in agriculture, sustainable land management approaches, use of agroecological principles and practices and other approaches that work with natural processes (high confidence)…

Here’s CGIAR’s take. No word specifically on crop diversity or genebanks.

And no, AI was not used in the preparation of this invaluable blogpost.

What will AI ever do for us?

Ever since ChatGPT hit the internet a few weeks ago AI has been all over what we are now obliged to call the discourse, so I figured I’d wade in. Jumping in right at the deep end, I asked it the following: Which barley genebank accessions are the most drought tolerant? Here’s what I got.

Determining the most drought-tolerant barley genebank accessions would require a comprehensive analysis of multiple factors, such as yield performance, physiological traits, genetic diversity, and environmental adaptation. However, there are some barley genebank accessions that have been reported to exhibit high levels of drought tolerance based on various studies and evaluations. Here are a few examples:

  1. CI 9835: This barley accession from Ethiopia has shown high levels of drought tolerance in several studies. It has been found to maintain high yields and exhibit drought avoidance traits such as early maturity and reduced plant height.
  2. Himalaya 10: This Indian barley accession has demonstrated good drought tolerance and yield stability in multiple environments. It has also been found to possess traits such as deep rooting, reduced stomatal conductance, and high water use efficiency.
  3. Hordeum vulgare L. subsp. spontaneum: This wild barley subspecies from Israel has been found to possess high levels of genetic diversity and adaptability to harsh environments, including drought-prone areas. It has also been shown to possess traits such as deep roots, reduced leaf area, and efficient water uptake.

These are just a few examples, and there are likely many other barley genebank accessions that exhibit high levels of drought tolerance. The specific characteristics that contribute to drought tolerance can vary depending on the accession and the environment, so it is important to evaluate multiple traits and consider multiple environments when assessing drought tolerance in barley genebank accessions.

I mean, that’s not too bad I guess, as far as it goes. CI 9835 is a bona fide genebank accession, and it is from Ethiopia. But I can’t locate a study which highlighted it as being particularly drought tolerant. Himalaya 10 is an elite hulless barley, not a genebank accessions, and from Tibet rather than India, but it does seem to be drought tolerant. As for wild barley, some accessions do have potential.

I then tried Consensus, which is a sort of AI-driven Google Scholar type thing. Like Scholar, it returned a bunch of papers evaluating different barleys for drought tolerance, which one could obviously scour for specific accessions. But, intriguingly, it also provides a sort of summary of what it found:

These studies suggest that STI, GMP, MP indices, two wild Iranian genotypes, and early seedling stage accessions are the most drought-tolerant barley genebank accessions.

Which unfortunately is not much use, let’s be honest. For now. It’s in beta, so it will no doubt get better.

So someone tackling the problem from scratch has a place to start, but clearly what we need next is a way to apply AI directly to genebank databases. Or even for AI to understand a bit better what a genebank accessions is.

Going with the genebank workflows

I suspect everyone working in genebanks and other sorts of biorepositories will welcome the new book “Biodiversity Biobanking – a Handbook on Protocols and Practices” by Carolina Corrales and Jonas Astrin.

We compiled extensive information on … workflows from throughout most of the biodiversity and environmental biobanking communities. Publications, grey literature, and Internet sources were reviewed, and proven experts consulted. By linking to protocols and practices from many different types of biobanks we hope to inspire interdisciplinary approaches and interconnect biobankers, and to serve as an aggregated resource for incipient and thematically expanding biobanks. Maybe the compilation of practices can also contribute to processes of method validation and standardisation.

Here’s hoping…