# SqueezeCall: nanopore basecalling using a Squeezeformer network

## TL;DR

SqueezeCall is a new model for nanopore sequencing that improves accuracy by using a Squeezeformer network to handle electrical current data.

## Contribution

The novel use of a Squeezeformer network for nanopore basecalling, which outperforms existing models.

## Key findings

- SqueezeCall improves basecalling accuracy by effectively handling noise in nanopore sequencing data.
- Combining three types of loss during training enhances basecalling performance.
- SqueezeCall outperforms recurrent and Transformer-based models in basecalling accuracy.

## Abstract

Nanopore sequencing, a third-generation sequencing technique, enables direct RNA sequencing, real-time analysis, and long-read length. Nanopore sequencers measure electrical current changes as nucleotides pass through nanopores; a basecaller identifies base sequences according to the raw current measurements. However, accurate basecalling remains challenging due to molecular variations and sequencing noise. Here, we introduce SqueezeCall, a novel Squeezeformer-based model for accurate nanopore basecalling. SqueezeCall uses convolution layers to down-sample raw signals and model local dependencies. A Squeezeformer network captures the global context, and a connectionist temporal classification (CTC) decoder with beam search generates DNA sequences. Experimental results demonstrated SqueezeCall’s ability to resist noise, improving basecalling accuracy. We trained SqueezeCall combining three types of loss, and found that all three loss types contribute to basecalling accuracy. Experiments across multiple species demonstrated the potential of a Squeezeformer-based model to improve basecalling accuracy and its superiority over recurrent neural network-based models and Transformer-based models.