Many binning methods have been developed
Overview of binning methods in this paragraph. argument for using deep learning is not very persuasive to me.. - Using composition (k-mer) or abundance (coverage) / combined - Hybrid models are "superior" - Integrating such different features efficiently is not easy, so enter the black box/ deep learning stuff.
If the pipeline does not produce a consensus for your target, you can download the raw reads from your dashboard and bin them yourself, but please note that raw reads are much more noisy and error-prone (~98.3% accurate) than consensus reads.
Look for binning tools - Example - LRBinner = reference free binning approach for nanopore. Ref : Wickramarachchi, Anuradha, and Yu Lin. "Binning long reads in metagenomics datasets using composition and coverage information." Algorithms for Molecular Biology 17.1 (2022): 1-15. bmc 202
imagine you were measuring
Discretization (otherwise known as quantization or binning) provides a way to partition continuous features into discrete values.
Binning