MassNet: A Foundational Resource for Advancing AI in Proteomics

It integrates 27,643 mass spectrometry files sourced from authoritative repositories such as PRIDE and iProX, comprising approximately 30 TB of raw data and more than 1.5 billion MS/MS spectra across 35 species, including animals, plants, and microorganism.

In the human subset, MassNet covers nearly 20,000 proteins, representing 98% of all annotated proteins in UniProt. Model organisms such as mouse, rat, C. elegans, and D. melanogaster also show high protein coverage, supporting cross-species functional studies. In the plant domain, high-quality data for Arabidopsis, rice, soybean, and other key species significantly expands the spectral foundation of plant proteomics. For microbes, the dataset includes core model organisms such as yeast (S. cerevisiae), E. coli, and B. subtilis , and further extends to archaea, actinomycetes, and fungi, providing broad phylogenetic representation.

Beyond its extensive taxonomic breadth, MassNet achieves high standards in PSM count, peptide diversity, and annotation completeness, establishing a robust foundation for training and deploying AI models in proteomics.

Database
Animal
H. sapiens

286 million PSMs;

1.7 million precursors;

890,994 peptides;

19,966 proteins;

M. musculus

217 million PSMs;

1.3 million precursors;

731,537 peptides;

16,943 proteins;

R. norvegicus

4.4 million PSMs;

153,750 precursors;

102,620 peptides;

6238 proteins;

C. elegans

1.5 million PSMs;

112,894 precursors;

73,279 peptides;

3348 proteins;

D. melanogaster

977,357 PSMs;

64,827 precursors;

47,188 peptides;

2776 proteins;

O. cuniculus

749,228 PSMs;

15,965 precursors;

12,669 peptides;

750 proteins;

X. laevis

432,394 PSMs;

13,095 precursors;

9258 peptides;

1066 proteins;

B. taurus

266,534 PSMs;

32,980 precursors;

24,972 peptides;

2581 proteins;

S. scrofa

223,988 PSMs;

17,960 precursors;

12,116 peptides;

932 proteins;

E. caballus

155,342 PSMs;

5613 precursors;

3320 peptides;

125 proteins;

Z. rerio

104,030 PSMs;

11,335 precursors;

8766 peptides;

1255 proteins;

G. gallus

84,229 PSMs;

6406 precursors;

4792 peptides;

677 proteins;

C. jacchus

34,327 PSMs;

3616 precursors;

2116 peptides;

71 proteins;

C. familiaris

23,635 PSMs;

5091 precursors;

3379 peptides;

282 proteins;

Plant
A. thaliana

7.0 million PSMs;

291,806 precursors;

182,971 peptides;

11,710 proteins;

O. sativa

846,482 PSMs;

34,258 precursors;

34,439 peptides;

2842 proteins;

G. max

54,620 PSMs;

3785 precursors;

2764 peptides;

291 proteins;

C. arabica

129,718 PSMs;

1837 precursors;

1228 peptides;

64 proteins;

C. annuum

24,310 PSMs;

795 precursors;

582 peptides;

52 proteins;

Microorganism
S. cerevisiae

23.0 million PSMs;

372,414 precursors;

223,397 peptides;

7218 proteins;

E. coli

6.0 million PSMs;

131,698 precursors;

73,770 peptides;

20,765 proteins;

B. subtilis

4.3 million PSMs;

80,682 precursors;

44,385 peptides;

3530 proteins;

T. gondii

843,691 PSMs;

68,230 precursors;

51,428 peptides;

5706 proteins;

S. aureus

807,100 PSMs;

39,363 precursors;

21,621 peptides;

9499 proteins;

T. brucei

78,749 PSMs;

24,408 precursors;

19,164 peptides;

2736 proteins;

B. cereus

723,891 PSMs;

24,102 precursors;

15,107 peptides;

3763 proteins;

Z. mobilis

570,739 PSMs;

15,962 precursors;

9456 peptides;

351 proteins;

A. baumannii

561,939 PSMs;

14,561 precursors;

8934 peptides;

1792 proteins;

P. aeruginosa

417,192 PSMs;

43,032 precursors;

26,069 peptides;

2975 proteins;

C. reinhardtii

411,247 PSMs;

20,819 precursors;

11,909 peptides;

330 proteins;

S. epidermidis

396,042 PSMs;

21,871 precursors;

13,749 peptides;

1387 proteins;

M. thermoacetica

102,443 PSMs;

7917 precursors;

5591 peptides;

325 proteins;

L. pneumophila

97,877 PSMs;

7742 precursors;

4971 peptides;

353 proteins;

R. palustris

39,152 PSMs;

6009 precursors;

3942 peptides;

366 proteins;

S. coelicolor

26,745 PSMs;

3336 precursors;

2844 peptides;

430 proteins;