Welcome to VectorPredictor

Classify Anopheles age and species from mid-infrared spectra — with transparent probabilities, confidence tiers, and explicit abstention. Simulium screening is a PCR pre-screen: it flags spectra that look Onchocerca-consistent so they can go to confirmatory qPCR.

MIRS Classifications & screening

2 Vector systems

500–4000 cm⁻¹ MIR range

Anopheles gambiae mosquito feeding — Malaria vector: *Anopheles*

Female Simulium blackfly, lateral view — Onchocerciasis vector: *Simulium*. Image © Acarologiste, CC BY-SA 4.0

Why VectorPredictor?

One MIRS workflow supports malaria Anopheles age and species classification and an onchocerciasis Simulium PCR pre-screen.

Anopheles classifications

Assign age-bin and species labels from spectroscopic data, with class probabilities and confidence tiers shown for each spectrum.

Simulium PCR pre-screen Public beta

Screen Simulium MIRS for Onchocerca-consistent signal. The threshold favours high sensitivity (few missed infections, many referrals). Flagged spectra are intended for confirmatory qPCR.

Public beta. Onchocerca-consistent screening is not production-ready. These classifications are shown for researcher evaluation. Send feedback.

Uncertainty-aware outputs

Review confidence tiers, class probabilities, and abstention when model certainty is insufficient for labelling.

How It Works

A structured workflow supports consistent vector spectral analysis.

Upload Data

Choose Anopheles or Simulium, then upload MIRS spectra.

AI Analysis

The matching model classifies Anopheles spectra or pre-screens Simulium spectra for confirmatory qPCR.

Get Results

Receive model classifications with class probabilities, confidence tiers, and explicit abstention when confidence is low.

Review & export

Export results with uncertainty metadata for downstream analysis and independent validation.

Scientific Validation

Peer-reviewed publications describing mid-infrared classification of Anopheles age and species, including field evaluation and model generalisability.

Prediction of mosquito species and population age structure using mid-infrared spectroscopy and supervised machine learning

González Jiménez et al., Wellcome Open Research (2019)
DOI: 10.12688/wellcomeopenres.15201.3

Rapid age-grading and species identification of natural mosquitoes for malaria surveillance

Siria et al., Nature Communications (2022)
DOI: 10.1038/s41467-022-28980-8

Using transfer learning and dimensionality reduction techniques to improve generalisability of machine-learning predictions of mosquito ages from mid-infrared spectra

Mwanga et al., BMC Bioinformatics (2023)
DOI: 10.1186/s12859-022-05128-5