DIANovo

algorithm · Transformer (AR)

DIANovo: algorithm · Transformer (AR). Transformer-based de novo sequencer for DIA: disentangles coeluted/multiplexed precursor spectra. Presented in Zheng Ma’s arXiv preprint (2024) and his PhD thesis (2025).

Transformer-based de novo sequencer for DIA: disentangles coeluted/multiplexed precursor spectra. Presented in Zheng Ma’s arXiv preprint (2024) and his PhD thesis (2025).

Kind	algorithm
Deep learning	yes
Acquisition	DIA
Family	Transformer (AR)

Code

https://github.com/hearthewind/dianovo

Live stars, open issues and last-push figures are on the Code activity chart.

Checkpoints

Version	Trained on	Host	Licence	Size	Checked	Backup
GNova-Astral_pretrain	—	git-LFS	Apache-2.0	516 MB	verified 2026-10-02	copy
RGNova-Astral_op	—	git-LFS	Apache-2.0	2.1 GB	verified 2026-10-02	copy
RGNova-Astral_sg	—	git-LFS	Apache-2.0	2.1 GB	verified 2026-10-02	copy

A host marked archival has a DOI and keeps what it is given. The others can move or disappear, which is why they are checked rather than merely listed. verified means the bytes were fetched and hashed on the date shown; live means only that the host answered when last asked. Where a copy is linked, it is a backup of someone else’s weights kept in case the original link goes stale; the original is the link to cite and to prefer.

Papers describing it (2)

Disentangling the Complex Multiplexed DIA Spectra in De Novo Peptide Sequencing (2024, arXiv, preprint)
Advancing Proteomic Analyses with Graph-Based Deep Learning: Protein Inference and DIA De Novo Peptide Sequencing (2025, thesis)

Authors (8)

Zheng Ma, Zeping Mao, Ruixue Zhang, Jiazhen Chen, Lei Xin, Baozhen Shan, Ali Ghodsi, Ming Li

Seen in the charts

Back to the full map