mevol commited on
Commit
9ec3066
1 Parent(s): 7702937

clean model card

Browse files
Files changed (1) hide show
  1. README.md +0 -79
README.md CHANGED
@@ -1,79 +0,0 @@
1
- ---
2
- license: mit
3
- language:
4
- - en
5
- tags:
6
- - biology
7
- - protein structure
8
- - token classification
9
- widget:
10
- - text: "N-terminal acetylation (Nt-acetylation), carried out by N-terminal acetyltransferases (NATs), is a conserved and primary modification of nascent peptide chains. Naa60 (also named NatF) is a recently identified NAT found only in multicellular eukaryotes. This protein was shown to locate on the Golgi apparatus and mainly catalyze the Nt-acetylation of transmembrane proteins, and it also harbors lysine Nε-acetyltransferase (KAT) activity to catalyze the acetylation of lysine ε-amine. Here, we report the crystal structures of human Naa60 (hNaa60) in complex with Acetyl-Coenzyme A (Ac-CoA) or Coenzyme A (CoA). The hNaa60 protein contains an amphipathic helix following its GNAT domain that may contribute to Golgi localization of hNaa60, and the β7-β8 hairpin adopted different conformations in the hNaa60(1-242) and hNaa60(1-199) crystal structures. Remarkably, we found that the side-chain of Phe 34 can influence the position of the coenzyme, indicating a new regulatory mechanism involving enzyme, co-factor and substrates interactions. Moreover, structural comparison and biochemical studies indicated that Tyr 97 and His 138 are key residues for catalytic reaction and that a non-conserved β3-β4 long loop participates in the regulation of hNaa60 activity."
11
- model-index:
12
- - name: Bioformer8L-ProteinStructure-NER-v0.1
13
- results:
14
- - task:
15
- name: NER
16
- type: token-classification
17
- metrics:
18
- - name: NER Precision
19
- type: precision
20
- value: 0.88
21
- - name: NER Recall
22
- type: recall
23
- value: 0.92
24
- - name: NER F Score
25
- type: f_score
26
- value: 0.90
27
- ---
28
-
29
-
30
- | Feature | Description |
31
- | --- | --- |
32
- | **Name** | `Bioformer8L-ProteinStructure-NER-v0.1` |
33
- | **Default Pipeline** | `transformer`, `ner` |
34
- | **Components** | `transformer`, `ner` |
35
- | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
36
- | **Sources** | n/a |
37
- | **License** | n/a |
38
- | **Author** | [Melanie Vollmar]() |
39
-
40
- ### Label Scheme
41
-
42
- <details>
43
-
44
- <summary>View label scheme (20 labels for 1 components)</summary>
45
-
46
- | Component | Labels |
47
- | --- | --- |
48
- | **`ner`** | "bond_interaction", "chemical", "complex_assembly", "evidence", "experimental_method", "gene", "mutant", "oligomeric_state", "protein", "protein_state", "protein_type", "ptm", "residue_name", "residue_name_number", "residue_number", "residue_range", "site", "species", "structure_element", "taxonomy_domain" |
49
-
50
- </details>
51
-
52
- ### Scores for entity types
53
- | entity type | precision | recall | F1 | sample number|
54
- | --- | --- | --- | --- | --- |
55
- | "bond_interaction" | 0.93 | 0.88 | 0.88 | 47 |
56
- | "chemical" | 0.87 | 0.91 | 0.89 | 839 |
57
- | "complex_assembly" | 0.88 | 0.91 | 0.90 | 340 |
58
- | "evidence" | 0.81 | 0.90 | 0.85 | 421 |
59
- | "experimental_method" | 0.81 | 0.82 | 0.81 | 406 |
60
- | "gene" | 0.71 | 0.87 | 0.78 | 54 |
61
- | "mutant" | 0.92 | 0.95 | 0.93 | 512 |
62
- | "oligomeric_state" | 0.93 | 0.99 | 0.96 | 143 |
63
- | "protein" | 0.94 | 0.97 | 0.96 | 1750 |
64
- | "protein_state" | 0.80 | 0.86 | 0.82 | 556 |
65
- | "protein_type" | 0.82 | 0.86 | 0.84 | 453 |
66
- | "ptm" | 0.71 | 0.69 | 0.70 | 54 |
67
- | "residue_name" | 0.87 | 0.92| 0.89| 92 |
68
- | "residue_name_number" | 0.93 | 0.99| 0.96 | 600 |
69
- | "residue_number" | 0.77 | 0.91 | 0.83 | 33 |
70
- | "residue_range" | 0.79 | 0.75 | 0.77 | 44 |
71
- | "site" | 0.86 | 0.88 | 0.87 | 282 |
72
- | "species" | 0.97 | 0.96 | 0.96 | 90 |
73
- | "structure_element" | 0.90 | 0.92 | 0.91 | 1032 |
74
- | "taxonomy_domain" | 0.98 | 0.95 | 0.96 | 84 |
75
-
76
-
77
- ### Data and annotations
78
-
79
- The dataset can be found here: https://huggingface.co/datasets/mevol/protein_structure_NER_model_v2.1