AI-Assisted DNA Basecalling for Genomic Surveillance
What it is for
- Used by the Public Health Laboratory to process clinical and surveillance specimens for genomic analysis, including COVID-19 sequencing to support outbreak detection and public health response.
NYC Automated Decision Systems — Guppy (2025 Register Entry)
- Supports genomic surveillance and outbreak analysis by converting raw nanopore sequencing signals into sequence data suitable for epidemiological research and public health monitoring.
NYC Automated Decision Systems — Guppy (2025 Register Entry)
- Run by
- Department of Health and Mental Hygiene (DOHMH)
- Where
- No fixed location
- Kept
- Not stated by the NYC Office of Technology and Innovation.
- Shared with
- Not stated by the NYC Office of Technology and Innovation.
- Your copy
- You cannot see the data it holds about you. What you can do
What it is for
Guppy is a neural network tool used by the NYC Department of Health and Mental Hygiene's Public Health Laboratory to convert raw electrical signals from DNA sequencing instruments into readable genetic sequences. It is used a few times per month on clinical and surveillance specimens — including for COVID-19 genomic analysis — and does not collect or disclose any identifying information about individuals. The resulting sequence data is used for downstream outbreak analysis and public health surveillance.
What it collects and what happens to it
Data taken in
- Raw electrical signal data generated by Oxford Nanopore sequencing instruments from clinical or surveillance specimens. These are continuous current measurements recorded as DNA strands pass through protein nanopores — no personally identifying information is attached to the signal data.
NYC Automated Decision Systems — Guppy (2025 Register Entry)
Processing
- A neural network-based basecaller that classifies each raw electrical signal reading as a nucleotide base (A, T, G, or C) using models trained by Oxford Nanopore Technologies on proprietary nanopore signal-to-nucleotide mapping datasets.
NYC Automated Decision Systems — Guppy (2025 Register Entry)
- In addition to basecalling, Guppy performs quality filtering: reads that fall below quality thresholds are identified as low-quality and excluded from further analysis, ensuring only reliable sequence data proceeds to downstream genomic surveillance pipelines.
NYC Automated Decision Systems — Guppy (2025 Register Entry)
What it does
- Classifies each electrical signal reading as a specific nucleotide base (A, T, G, C) and assigns quality scores; low-quality reads are flagged and filtered. Results are reviewed by laboratory personnel before use in downstream genomic analyses.
NYC Automated Decision Systems — Guppy (2025 Register Entry)
- Reads raw electrical current signals produced by Oxford Nanopore sequencing instruments as DNA strands pass through nanopores, converting the continuous signal stream into discrete nucleotide character strings for downstream processing.
NYC Automated Decision Systems — Guppy (2025 Register Entry)
Outputs
- Basecalled nucleotide sequences (strings of A, T, G, C characters) with per-read quality metrics, representing the genetic content of the specimen. Low-quality reads are filtered out. These outputs are used for downstream COVID-19 sequencing analysis and other genomic surveillance workflows; no identifying information is included.
NYC Automated Decision Systems — Guppy (2025 Register Entry)
Run by
- The Disease Control - Public Health Laboratory division of the NYC Department of Health and Mental Hygiene operates Guppy for genomic surveillance, including COVID-19 sequencing analysis.
NYC Automated Decision Systems — Guppy (2025 Register Entry)
Built by
- Oxford Nanopore Technologies developed and maintains the Guppy basecalling tool and its underlying neural network models, trained on proprietary nanopore signal datasets.
NYC Automated Decision Systems — Guppy (2025 Register Entry)
Kept for
Not stated by the NYC Office of Technology and Innovation.
Shared with
- The register states that no identifying information is collected or disclosed. The output is genomic sequence data used internally by the Public Health Laboratory for surveillance; there is no individual-facing access mechanism.
NYC Automated Decision Systems — Guppy (2025 Register Entry)
Stored
Not stated by the NYC Office of Technology and Innovation.
How to read the colours
Can it identify you?
- Anonymized data
- Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
- Pseudonymous data
- Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
- Identifiable data
- The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.
Who completes the loop?
- Human decides
- This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
- Human executes
- This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
- Autonomous
- This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.
Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)NYC Department of Health and Mental Hygiene, Disease Control - Public Health Laboratory, Year Reported: 2025.
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- AI registerNYC Automated Decision Systems — Guppy (2025 Register Entry)
- Register entryPublished by the NYC Office of Technology and Innovation. Reference 93e67ece. This disclosure was drafted with AI assistance.Schema: ai@2026-05-06-beta
What you can do
Ask about this system
Questions go to the NYC Office of Technology and Innovation, not the vendor.
Your rights
- Right to Algorithmic TransparencyThis tool is listed in the NYC Automated Decision Systems public register. Members of the public may learn how it works by consulting the register entry and the Oxford Nanopore Technologies documentation at https://nanoporetech.com/software/other/guppy. Because no individual identifying data is processed, no personal-data-specific rights (access, correction, deletion) apply to Guppy's operation.
Risks and safeguards
No risks or safeguards have been published for this system yet.