easymode training collection
To achieve general networks, we compiled a large and diverse training data collection using private and public data contributions. The table below lists the current data sources.
The training collection currently contains 2292 tomograms, from 49 unique data sources, spanning 22 species, a pixel size range of 0.68 Å to 4.27 Å, and many sample types including purified proteins, cellular lysates, whole cells, fib-milled cultured cells, and high-pressure frozen, lifted-out tissue lamellas.
We're very grateful to the many people who shared their data via EMPIAR and the CryoET Data Portal!
| ID | Contributor / source | Sample type | N (annotated) | Pixel size (Å) |
|---|---|---|---|---|
| 001_HELA | Mart Last | milled H. sapiens (HeLa) | 60 (59) | 1.51 |
| 002_U2OS | Mart Last | milled H. sapiens (U2OS) | 40 (26) | 2.15 |
| 003_HSPERM | Tom Dendooven | milled H. sapiens (spermatozoa) | 56 (41) | 1.50 |
| 004_* | * | * | 23 (20) | 1.68 |
| 005_FIBRO | Tom Hale | milled H. sapiens (fibroblasts) | 52 (47) | 1.33 |
| 006_* | * | * | 20 (16) | 1.69 |
| 007_APOF | EMPIAR-10491 | purified apoferritin | 37 (18) | 0.79 |
| 008_HIV | EMPIAR-10164 | purified HIV particles | 10 (4) | 0.68 |
| 009_SCEREV | Sebastian Tacke, Elisa Lisicki, Tatjana Taubitz, Stefan Raunser |
milled (hpf, pfib) S. cerevisiae | 64 (51) | 1.56 |
| 010_RIBO | EMPIAR-11111 | purified E. coli 70S ribosomes | 25 (19) | 1.07 |
| 011_CHLO | EMPIAR-12612 | milled S. oleracea chloroplasts | 23 (18) | 3.52 |
| 012_CHLAMY | EMPIAR-11830 | milled C. reinhardtii | 52 (50) | 1.96 |
| 013_DIAT | EMPIAR-11747 | milled T. pseudonana | 7 (1) | 1.07 |
| 014_CILIA | EMPIAR-11078 | milled C. reinhardtii ciliary base | 23 (19) | 3.42 |
| 015_MMVOLTA | CDPDS-10452 | whole M. mycoides cells | 15 (15) | 1.53 |
| 016_PHANTOM | CDPDS-10440, CDPDS-10445 | E. coli lysate with added proteins | 19 (17) | 1.53 |
| 017_MYCP | EMPIAR-10499 | whole M. pneunomiae cells | 65 (27) | 1.70 |
| 018_ECM | EMPIAR-11897 | lift-out H. sapiens (extracellular matrix) | 39 (24) | 2.14 |
| 019_ECOLI | EMPIAR-12413 | milled E. coli | 44 (19) | 1.90 |
| 020_* | * | * | 30 (25) | 2.13 |
| 021_* | * | * | 8 (7) | 3.02 |
| 022_SCOV | EMPIAR-10493 | purified SARS-CoV-2 virions | 20 (12) | 1.53 |
| 023_SPORE | EMPIAR-12176 | milled E. intestinalis | 24 (11) | 2.06 |
| 024_* | * | * | 17 (6) | 1.96 |
| 025_RPE | EMPIAR-10989 | cellular periphery H. sapiens (RPE1) | 3 (3) | 3.45 |
| 026_EHV | EMPIAR-11896 | Emiliania huxleyi virus 201 | 40 (10) | 2.08 |
| 027_NUCFT | Forson Gao | milled S. cerevisiae nuclei | 21 (15) | 1.51 |
| 028_ROOF | CDPDS-10434 | cellular periphery H. sapiens (HEK293) | 20 (19) | 2.17 |
| 029_TKIV | EMPIAR-11058 | milled T. kivui | 17 (7) | 3.52 |
| 030_LDN | Mart Last | cellular periphery H. sapiens (U2OS) | 26 (7) | 2.74 |
| 031_MITO | Mart Last | milled H. sapiens (HeLa, mitochondria) | 63 (59) | 1.34 |
| 032_* | * | * | 40 (24) | 1.63 |
| 033_NPC | EMPIAR-11830 (same source as 012_CHLAMY) | milled C. reinhardtii (nuclear envelope) | 36 (36) | 1.96 |
| 034_DICTYO | EMPIAR-11845 | milled D. discoideum | 152 (68) | 2.18 |
| 035_GEM | EMPIAR-11561 | milled H. sapiens (HeLa, mitochondria) | 15 (14) | 3.43 |
| 036_MACRO | EMPIAR-12457 | milled H. sapiens (macrophages) | 39 (21) | 2.41 |
| 037_MESWT | EMPIAR-12460 | milled M. musculus (embryonic stem cell) | 159 (26) | 2.68 |
| 038_POMBE | EMPIAR-10988 | milled S. pombe | 9 (6) | 3.37 |
| 039_JUMBO | EMPIAR-11198 | milled E. amylovora + RAY phage | 32 (4) | 4.27 |
| 040_SLO | CDPDS-10004 | milled (hpf, pfib) C. elegans | 100 (24) | 1.50 |
| 041_RPEM | Cong Yu (MRC LMB) | milled H. sapiens (RPE1) | 17 (7) | 1.57 |
| 042_NPCSC | EMPIAR-10466 | milled S. cerevisiae | 177 (0) | 3.45 |
| 043_DICTY2 | EMPIAR-11899 (to be included after validation) | milled D. discoideum | 0 (0) | 1.22 |
| 044_JURKAT | Mart Last | milled H. sapiens (Jurkat) | 0 (0) | 1.97 |
| 045_NPHL | * | * | 231 (0) | 1.56 |
| 046_ROOF2 | CDPDS-10431 | cellular preiphery H. sapiens (HEK293) | 87 (0) | 2.17 |
| 047_ECPP7 | CDPDS-10455 | E. coli + PP7 virus-like particles | 30 (0) | 1.50 |
| 048_ELSO | CDPDS-10444 | purified human endo-/lysosomes | 30 (0) | 1.54 |
| 049_* | * | * | ||
| 050_* | * | * |