DeepNovo-DIA

algorithm · CNN + RNN

DeepNovo-DIA: algorithm · CNN + RNN. First de novo for DIA

First de novo for DIA

Kind	algorithm
Deep learning	yes
Acquisition	DIA
Family	CNN + RNN

Code

https://github.com/nh2tran/DeepNovo-DIA

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

Checkpoints

Version	Trained on	Host	Licence	Size	Checked	Backup
train.urine_pain.ioncnn.lstm	—	Google Drive	Non-commercial use (custom)	184 MB	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.

Data

What the papers describing this method trained it on and reported its results on, as each paper states it. A version is named only where the paper names one.

Patents (1)

US11694769B2 Systems and methods for de novo peptide sequencing from data-independent acquisition using deep learning ↗ (Bioinformatics Solutions Inc., priority 2017-07-17, active)

Patent families that claim this method, matched by hand. A patent’s status is Google Patents’ reading of its legal events.

Compared against in other papers (4)

5 tables from 4 papers that report this method as a baseline, newest first. The caveats of the comparisons above hold twice over: each paper ran, retrained or quoted this method its own way, so its number here is that paper’s claim, not a measurement of the method. Where a paper says which it did, the word follows the method’s name.

DiffNovo: A Transformer-Diffusion Model for De Novo Peptide Sequencing (2025) · 2 tables

Table 2

DiffNovo: A Transformer-Diffusion Model for De Novo Peptide Sequencing, page 8: Comparison of DiffNovo and other state-of-the-art (SOTA) methods on peptide precision across three DIA datasets.

De novo sequencing of DIA data	Peptide precision
De novo sequencing of DIA data	UTI	OC	Plasma
DiffNovo	0.659	0.735	0.632
DeepNovo-DIA	0.403	0.417	0.351
PepNet	0.296	0.368	0.550
Cascadia	0.291	0.301	0.736

PepNet, Plasma: the printed cell reads “0.550/0.530*/0.664+”, and only 0.550 is in the table. The paper’s note: “+ Indicates the filtered peptide-level accuracy, and * indicates the peptide-level accuracy reported in [10].”

Table 1

DiffNovo: A Transformer-Diffusion Model for De Novo Peptide Sequencing, page 7: Comparison of DiffNovo and other state-of-the-art (SOTA) methods on amino acid recall and precision across three DIA datasets.

De novo sequencing of DIA data	Amino acid recall			Amino acid precision
De novo sequencing of DIA data	UTI	OC	Plasma	UTI	OC	Plasma
DiffNovo	0.665	0.749	0.663	0.675	0.743	0.675
DeepNovo-DIA	0.566	0.547	0.689	0.612	0.601	0.702
PepNet	0.396	0.455	0.509	0.391	0.451	0.491
Cascadia	0.293	0.286	0.704	0.341	0.349	0.782

PepNet, Plasma: the printed cell reads “0.491 / 0.725*”, and only 0.491 is in the table. The paper’s note: “* Indicates the positional accuracy reported in [10].”

BiATNovo: An Attention-based Bidirectional De Novo Sequencing Framework for Data-Independent-Acquisition Mass Spectrometry (2024) · 1 table

Table 2

BiATNovo: An Attention-based Bidirectional De Novo Sequencing Framework for Data-Independent-Acquisition Mass Spectrometry, page 8: Comparison of DeepNovo-DIA, PepNet and BiATNovo

De novo sequencing of DIA data	Amino acid precision			Amino acid recall			Peptide precision
De novo sequencing of DIA data	OC	UTI	Plasma	OC	UTI	Plasma	OC	UTI	Plasma
DeepNovo-DIA	0.5562	0.6286	0.4354	0.5596	0.6243	0.4335	0.5098	0.5525	0.3322
BiATNovo	0.6817	0.7108	0.4525	0.6746	0.7076	0.4511	0.6439	0.6584	0.3691
PepNet			0.4008			0.4004			0.3064

Transformer-Based De Novo Peptide Sequencing for Data-Independent Acquisition Mass Spectrometry (2024) · 1 table

TABLE I

Transformer-Based De Novo Peptide Sequencing for Data-Independent Acquisition Mass Spectrometry, page 5: Precision comparison of Transformer-DIA, DeepNovo-DIA and PepNet.

De novo sequencing of DIA data	Peptide precision			Amino acid precision
De novo sequencing of DIA data	UTI	OC	Plasma	UTI	OC	Plasma
DiaTrans	0.663	0.798	0.672	0.731	0.829	0.78
DeepNovo-DIA	0.403	0.417	0.383	0.566	0.547	0.702
PepNet	0.296	0.368	0.351	0.396	0.455	0.509

BiATNovo: A Self-Attention based Bidirectional Peptide Sequencing Method (2023) · 1 table

Table 2

BiATNovo: A Self-Attention based Bidirectional Peptide Sequencing Method, page 7: Results of BiATNovo and Baseline.

De novo sequencing of DIA data	Amino acid precision			Amino acid recall			Peptide precision
De novo sequencing of DIA data	OC	UTI	Plasma	OC	UTI	Plasma	OC	UTI	Plasma
DeepNovo-DIA	0.6812	0.6581	0.6379	0.6822	0.6598	0.6430	0.5240	0.5106	0.3740
BiATNovo	0.7457	0.7078	0.6628	0.7513	0.7151	0.6707	0.6147	0.5760	0.4364

Paper describing it

Deep learning enables de novo peptide sequencing from data-independent-acquisition mass spectrometry (2018, Nature Methods, peer-reviewed)

Authors (9)

Ngoc Hieu Tran, Rui Qiao, Lei Xin, Xin Chen (Waterloo), Chuyi Liu, Xianglilan Zhang, Baozhen Shan, Ali Ghodsi, Ming Li

Seen in the charts

Back to the full map

Code

Checkpoints

Data

Trained on

Evaluated on

Deposited

Patents (1)

Compared against in other papers (4)

Table 2

Table 1

Table 2

TABLE I

Table 2

Paper describing it

Authors (9)

Seen in the charts