Life sciences · Genomics

Which protein is defeating the drug.

Sequencing tells you what an organism carries. It does not tell you which of it is doing the work. That is the gap we closed.

01 / The strand

Four letters. Four million times.

A bacterial genome is almost entirely context. A sequencing run returns all of it and ranks none of it.

Escherichia coli reference genome: 4,641,652 bp
02 / The determinant

The part that matters is very small.

A resistance determinant is often fewer than a thousand bases. Finding it is a search problem. That was solved years ago.

blaNDM-1 coding sequence: 813 bp
03 / The limit

Presence is not resistance.

A gene can sit silent. Truncated. On a plasmid the organism no longer maintains. Presence and phenotype disagree often enough that presence alone cannot be reported as a result.

This is where a catalogue stops.

04 / The call

We name the protein.

The model reads context rather than identity. It returns the protein doing the work, and the drug class it defeats.

Output: the protein, and the drug class it defeats

Why speed is the clinical argument

Culture takes days. The organism does not wait.

Phenotypic susceptibility testing is still the reference method, and it is still slow. A sequence-based call arrives while empiric therapy is being chosen, which is when broad-spectrum agents get used by default.

Narrowing therapy at that point does two things at once. It helps the patient in front of the clinician, and it is the mechanism by which a stewardship programme actually reduces selective pressure across a hospital rather than just reporting on it.

Laboratory and research enquiries.

Evaluation on your own samples, and integration detail, under agreement.