Trace reader
Every run, step by step
Gemma 4 E4B was asked to find the variant behind a melon trait among 3,061 candidates, twenty times under each of three toolboxes. These are the recordings. Pick a condition, pick a run, and read what the agent did, call by call. Each final answer is scored outside the model: where the experimentally validated CmEIN3 variant lands, and whether every variant listed exists.
The raw file with 3,061 variants defined by their reference letter, alternate letter and other sequencing information, and nothing else. It reads the beginning of the file, and on that information alone it cannot tell the variants apart, so it stops.
The same file plus a computational biologist toolkit: a sandbox, bcftools and samtools, Ensembl VEP, and public reference files on request. After the first answer, three fixed follow-ups an expert bioinformatician would send. About a third of its tool calls error out, and it recovers in roughly two runs out of three.
The same file and one tool: BOTANIC-1, which returns the log-likelihood ratio between the alternate and the reference base in sequence context. Gemma discards the 567 candidates that are not single-nucleotide substitutions, scores the remaining 2,494 and ranks them.
Use ← and → to step, Home and End to jump. The address bar follows your position, so a link to a step can be shared. Tool output over 6,000 characters and thinking over 4,000 are trimmed in the recordings, and say so where they are.
Both halves on the whole genome
Every run above starts from the 3,061 chromosome-2 candidates, which is a substantial head start. In real-world settings the starting point would be the full set of variants across the entire genome. There, neither bioinformatics tools nor BOTANIC-1 recover the causal variant on their own. Rank all 39,656 scorable variants by BOTANIC-1 alone and the causal one lands sixteenth. Gemma has been given that full set with BOTANIC-1 as its only tool, and in 18 of 20 runs it ranks the causal variant sixteenth too, exactly where the score puts it. Fifteen dramatic-looking changes sit above it, a lost stop codon, a broken splice site, and not one of them is carried by every plant with the trait.
The steps a bioinformatician would take for a recessive trait in a cross remove them. Keep the single-letter substitutions, drop positions with fewer than ten reads in either bulk, keep the variants carried by every plant in the mutant bulk, and drop those also fixed in the wild-type bulk, which separate the parents from the reference rather than the trait. None of these steps orders what survives. Handing the survivors to BOTANIC-1 does. This is not an agentic result: no run has yet had the full set together with the bioinformatics tools. It is the behaviour one would expect from the agentic system in that setting, since every step here is one the agent already performs in the conventional-bioinformatics condition, and the scoring is what it does in the BOTANIC-1 condition.
- The case study pageThe mapping scan, the three conditions, and the genome-wide check.
- The same study, for a plant biologistWhat BOTANIC-1 contributes to the search, without the agent.
- Technical reportMethod, evaluation, and the 545-study causal-variant benchmark this case sits inside.