Commit 27a551d2 authored by Ayse Berceste Dincer's avatar Ayse Berceste Dincer
Browse files

pipeline

parent 98356dbe
No preview for this file type
This diff is collapsed.
%% Cell type:code id: tags:
``` python
import numpy as np
import pandas as pd
```
%% Cell type:code id: tags:
``` python
HIERARCHY = pd.read_table('GO_CC_Hierarchy_FINAL.tsv', index_col = 0)
print("All pathways ", HIERARCHY.shape)
for i in range(HIERARCHY.shape[1]):
print("Layer ", i + 1)
print(len(np.unique(HIERARCHY.iloc[:, i].values.astype(str))))
```
%% Cell type:code id: tags:
``` python
HIERARCHY = pd.read_table('GO_MF_Hierarchy_FINAL.tsv', index_col = 0)
print("All pathways ", HIERARCHY.shape)
for i in range(HIERARCHY.shape[1]):
print("Layer ", i + 1)
print(len(np.unique(HIERARCHY.iloc[:, i].values.astype(str))))
```
%% Cell type:code id: tags:
``` python
HIERARCHY = pd.read_table('GO_BP_Hierarchy_FINAL.tsv', index_col = 0)
print("All pathways ", HIERARCHY.shape)
for i in range(HIERARCHY.shape[1]):
print("Layer ", i + 1)
print(len(np.unique(HIERARCHY.iloc[:, i].values.astype(str))))
```
%% Cell type:code id: tags:
``` python
```
%% Cell type:code id: tags:
``` python
```
This diff is collapsed.
This diff is collapsed.
No preview for this file type
......@@ -247,18 +247,18 @@
plt.hist(np.unique(coms, return_counts=True)[1])
```
%%%% Output: execute_result
(array([9., 9., 5., 5., 4., 1., 0., 1., 1., 1.]),
array([ 6. , 54.8, 103.6, 152.4, 201.2, 250. , 298.8, 347.6, 396.4,
445.2, 494. ]),
(array([ 9., 10., 5., 4., 4., 1., 0., 1., 1., 1.]),
array([ 4. , 54.7, 105.4, 156.1, 206.8, 257.5, 308.2, 358.9, 409.6,
460.3, 511. ]),
<a list of 10 Patch objects>)
%%%% Output: display_data
![](data:image/png;base64,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)
![](data:image/png;base64,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)
%% Cell type:code id: tags:
``` python
if not os.path.isdir("Full_graph_louvain_with_weights_community_labels/%s"%str(res)):
......@@ -283,18 +283,18 @@
KEGG_ASCORBATE_AND_ALDARATE_METABOLISM 0
KEGG_FATTY_ACID_METABOLISM 0
KEGG_STEROID_BIOSYNTHESIS 0
KEGG_PRIMARY_BILE_ACID_BIOSYNTHESIS 0
KEGG_STEROID_HORMONE_BIOSYNTHESIS 0
KEGG_OXIDATIVE_PHOSPHORYLATION 2
KEGG_PURINE_METABOLISM 3
KEGG_PYRIMIDINE_METABOLISM 3
KEGG_OXIDATIVE_PHOSPHORYLATION 0
KEGG_PURINE_METABOLISM 2
KEGG_PYRIMIDINE_METABOLISM 2
KEGG_ALANINE_ASPARTATE_AND_GLUTAMATE_METABOLISM 0
KEGG_GLYCINE_SERINE_AND_THREONINE_METABOLISM 0
KEGG_CYSTEINE_AND_METHIONINE_METABOLISM 0
KEGG_VALINE_LEUCINE_AND_ISOLEUCINE_DEGRADATION 0
KEGG_VALINE_LEUCINE_AND_ISOLEUCINE_BIOSYNTHESIS 4
KEGG_VALINE_LEUCINE_AND_ISOLEUCINE_BIOSYNTHESIS 3
KEGG_LYSINE_DEGRADATION 0
KEGG_ARGININE_AND_PROLINE_METABOLISM 0
KEGG_HISTIDINE_METABOLISM 0
KEGG_TYROSINE_METABOLISM 0
KEGG_PHENYLALANINE_METABOLISM 0
......@@ -303,40 +303,40 @@
KEGG_TAURINE_AND_HYPOTAURINE_METABOLISM 0
KEGG_SELENOAMINO_ACID_METABOLISM 0
KEGG_GLUTATHIONE_METABOLISM 0
KEGG_STARCH_AND_SUCROSE_METABOLISM 0
... ..
GO_CARBOHYDRATE_DERIVATIVE_TRANSMEMBRANE_TRANSP... 17
GO_CARBOHYDRATE_DERIVATIVE_TRANSMEMBRANE_TRANSP... 10
GO_FATTY_ACID_DERIVATIVE_BINDING 0
GO_PHOSPHATIDYLGLYCEROL_BINDING 8
GO_CARDIOLIPIN_BINDING 8
GO_VOLTAGE_GATED_POTASSIUM_CHANNEL_ACTIVITY_INV... 17
GO_VOLTAGE_GATED_POTASSIUM_CHANNEL_ACTIVITY_INV... 10
GO_CERAMIDE_1_PHOSPHATE_BINDING 8
GO_CUPROUS_ION_BINDING 14
GO_MRNA_BINDING_INVOLVED_IN_POSTTRANSCRIPTIONAL... 4
GO_S_ADENOSYL_L_METHIONINE_BINDING 35
GO_PEPTIDE_TRANSMEMBRANE_TRANSPORTER_ACTIVITY 17
GO_CUPROUS_ION_BINDING 15
GO_MRNA_BINDING_INVOLVED_IN_POSTTRANSCRIPTIONAL... 18
GO_S_ADENOSYL_L_METHIONINE_BINDING 33
GO_PEPTIDE_TRANSMEMBRANE_TRANSPORTER_ACTIVITY 10
GO_CORECEPTOR_ACTIVITY_INVOLVED_IN_WNT_SIGNALIN... 1
GO_POLYSOME_BINDING 4
GO_POLYSOME_BINDING 3
GO_PHOSPHATIDIC_ACID_TRANSPORTER_ACTIVITY 8
GO_HISTONE_METHYLTRANSFERASE_BINDING 32
GO_STEROID_HORMONE_BINDING 17
GO_N6_METHYLADENOSINE_CONTAINING_RNA_BINDING 4
GO_KERATIN_FILAMENT_BINDING 26
GO_LYS48_SPECIFIC_DEUBIQUITINASE_ACTIVITY 15
GO_HISTONE_METHYLTRANSFERASE_BINDING 27
GO_STEROID_HORMONE_BINDING 10
GO_N6_METHYLADENOSINE_CONTAINING_RNA_BINDING 3
GO_KERATIN_FILAMENT_BINDING 22
GO_LYS48_SPECIFIC_DEUBIQUITINASE_ACTIVITY 16
GO_PROTEIN_ADP_RIBOSYLASE_ACTIVITY 1
GO_PROTEIN_ANTIGEN_BINDING 23
GO_EXTRACELLULAR_MATRIX_PROTEIN_BINDING 21
GO_U1_SNRNP_BINDING 4
GO_TRANSFERRIN_RECEPTOR_BINDING 16
GO_PROTEIN_BINDING_BRIDGING_INVOLVED_IN_SUBSTRA... 15
GO_ARRESTIN_FAMILY_PROTEIN_BINDING 12
GO_RNA_ADENYLYLTRANSFERASE_ACTIVITY 6
GO_SEQUENCE_SPECIFIC_MRNA_BINDING 4
GO_U1_SNRNP_BINDING 3
GO_TRANSFERRIN_RECEPTOR_BINDING 28
GO_PROTEIN_BINDING_BRIDGING_INVOLVED_IN_SUBSTRA... 7
GO_ARRESTIN_FAMILY_PROTEIN_BINDING 13
GO_RNA_ADENYLYLTRANSFERASE_ACTIVITY 5
GO_SEQUENCE_SPECIFIC_MRNA_BINDING 3
GO_SEQUENCE_SPECIFIC_DOUBLE_STRANDED_DNA_BINDING 19
GO_PROMOTER_SPECIFIC_CHROMATIN_BINDING 19
GO_UBIQUITIN_LIGASE_INHIBITOR_ACTIVITY 4
GO_UBIQUITIN_LIGASE_INHIBITOR_ACTIVITY 3
[4847 rows x 1 columns]
%% Cell type:code id: tags:
......
......@@ -18,11 +18,11 @@
``` python
if pathway_group=="KEGG":
pway_subfolder = "c2.all.v7.0.symbols_JustK"
HIERARCHY = pd.read_csv("../curated_hiararchies/KEGG/HIERARCHY.txt", delimiter="\t", names=["0","1","2"])
HIERARCHY = pd.read_csv("../curated_hierarchies/KEGG/HIERARCHY.txt", delimiter="\t", names=["0","1","2"])
#we want the bigger group
HIERARCHY["0"] = HIERARCHY["1"]
KEEP_CATEGORIES = np.unique(HIERARCHY["0"].values)
elif pathway_group == "REACTOME":
......@@ -33,38 +33,38 @@
"REACTOME_DISEASE", "REACTOME_DNA_REPAIR", "REACTOME_DNA_REPLICATION", "REACTOME_EXTRACELLULAR_MATRIX_ORGANIZATION", "REACTOME_GENE_EXPRESSION_TRANSCRIPTION",
"REACTOME_HEMOSTASIS", "Immune System", "Metabolism", 'Metabolism of proteins', 'REACTOME_METABOLISM_OF_RNA', "REACTOME_MUSCLE_CONTRACTION",
"REACTOME_NEURONAL_SYSTEM", "REACTOME_ORGANELLE_BIOGENESIS_AND_MAINTENANCE", "REACTOME_PROGRAMMED_CELL_DEATH", "REACTOME_PROTEIN_LOCALIZATION",
"REACTOME_REPRODUCTION", "Signal Transduction", "REACTOME_TRANSPORT_OF_SMALL_MOLECULES", "REACTOME_VESICLE_MEDIATED_TRANSPORT"]
HIERARCHY = pd.read_csv("../curated_hiararchies/REACTOME/HIERARCHY.txt", delimiter="\t", index_col=0)
HIERARCHY = pd.read_csv("../curated_hierarchies/REACTOME/HIERARCHY.txt", delimiter="\t", index_col=0)
elif pathway_group == "GO_MF":
pway_subfolder = "c5.mf.v7.0.symbols"
HIERARCHY = pd.read_csv("../curated_hiararchies/GO/GO_MF_Hierarchy_FINAL.tsv",
HIERARCHY = pd.read_csv("../curated_hierarchies/GO/GO_MF_Hierarchy_FINAL.tsv",
delimiter="\t", index_col = 0)
HIERARCHY.iloc[:, 0] = HIERARCHY.iloc[:, 3]
KEEP_CATEGORIES = np.unique(HIERARCHY.iloc[:, 0].values.astype(str))
print(len(KEEP_CATEGORIES))
elif pathway_group == "GO_CC":
pway_subfolder = "c5.cc.v7.0.symbols"
HIERARCHY = pd.read_csv("../curated_hiararchies/GO/GO_CC_Hierarchy_FINAL.tsv",
HIERARCHY = pd.read_csv("../curated_hierarchies/GO/GO_CC_Hierarchy_FINAL.tsv",
delimiter="\t", index_col = 0)
HIERARCHY.iloc[:, 0] = HIERARCHY.iloc[:, 2]
KEEP_CATEGORIES = np.unique(HIERARCHY.iloc[:, 0].values.astype(str))
print(len(KEEP_CATEGORIES))
elif pathway_group == "GO_BP":
pway_subfolder = "c5.bp.v7.0.symbols_SHORT"
HIERARCHY = pd.read_csv("../curated_hiararchies/GO/GO_BP_SHORT_Hierarchy_FINAL.tsv",
HIERARCHY = pd.read_csv("../curated_hierarchies/GO/GO_BP_SHORT_Hierarchy_FINAL.tsv",
delimiter="\t", index_col = 0)
HIERARCHY.iloc[:, 0] = HIERARCHY.iloc[:, 2]
KEEP_CATEGORIES = np.unique(HIERARCHY.iloc[:, 0].values.astype(str))
......@@ -194,11 +194,17 @@
len(toplev_names)
```
%%%% Output: execute_result
228
64
%% Cell type:code id: tags:
``` python
```
%% Cell type:code id: tags:
``` python
......
......@@ -124,7 +124,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 3,
"metadata": {},
"outputs": [
{
......@@ -143,8 +143,8 @@
"7\n",
"8\n",
"9\n",
"Average number of communities [119.4 88.6 72.7 54.8 46.3 41.3 34.5 32.1 29. 26.2]\n",
"Difference to true categories [81.4 50.6 34.7 16.8 8.3 3.3 3.5 5.9 9. 11.8]\n",
"Average number of communities [119.7 88.5 72. 55.4 45.8 41.1 35.2 32.4 29.7 26.1]\n",
"Difference to true categories [81.7 50.5 34. 17.4 7.8 3.1 2.8 5.6 8.3 11.9]\n",
"Resolution with number of communities closest to true labels [0.6 0.7]\n",
"All resolution values [0.6 0.61 0.62 0.63 0.64 0.65 0.66 0.67 0.68 0.69 0.7 ]\n",
"0\n",
......@@ -157,9 +157,9 @@
"7\n",
"8\n",
"9\n",
"Average number of communities [40.5 41. 40.3 38.8 38.9 37.8 36.4 36.4 36.4 34.6 34.2]\n",
"Difference to true categories [2.5 3. 2.3 0.8 0.9 0.2 1.6 1.6 1.6 3.4 3.8]\n",
"Resolution with number of communities closest to true labels 0.65\n"
"Average number of communities [40.8 40.4 40.6 38.5 38.8 36.3 37. 36.9 36.4 34.6 34.6]\n",
"Difference to true categories [2.8 2.4 2.6 0.5 0.8 1.7 1. 1.1 1.6 3.4 3.4]\n",
"Resolution with number of communities closest to true labels 0.63\n"
]
}
],
......@@ -169,7 +169,7 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"metadata": {},
"outputs": [
{
......@@ -192,7 +192,32 @@
"text": [
"All resolution values [0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1. ]\n",
"0\n",
"1\n"
"1\n",
"2\n",
"3\n",
"4\n",
"5\n",
"6\n",
"7\n",
"8\n",
"9\n",
"Average number of communities [211.1 104.3 60. 32.8 22.9 19.2 18.2 17.1 15.8 14. ]\n",
"Difference to true categories [184.1 77.3 33. 5.8 4.1 7.8 8.8 9.9 11.2 13. ]\n",
"Resolution with number of communities closest to true labels [0.4 0.5]\n",
"All resolution values [0.4 0.41 0.42 0.43 0.44 0.45 0.46 0.47 0.48 0.49]\n",
"0\n",
"1\n",
"2\n",
"3\n",
"4\n",
"5\n",
"6\n",
"7\n",
"8\n",
"9\n",
"Average number of communities [32.4 32.2 29.5 28.5 27.3 26. 25.4 23.5 23.3 22.3]\n",
"Difference to true categories [5.4 5.2 2.5 1.5 0.3 1. 1.6 3.5 3.7 4.7]\n",
"Resolution with number of communities closest to true labels 0.44000000000000006\n"
]
}
],
......@@ -202,18 +227,116 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 5,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of true categories: 64\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/berceste/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:40: RuntimeWarning: divide by zero encountered in log10\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"All resolution values [0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1. ]\n",
"0\n",
"1\n",
"2\n",
"3\n",
"4\n",
"5\n",
"6\n",
"7\n",
"8\n",
"9\n",
"Average number of communities [257.6 121.6 70.4 46.4 31.7 22.7 19. 15.1 11.6 9.1]\n",
"Difference to true categories [193.6 57.6 6.4 17.6 32.3 41.3 45. 48.9 52.4 54.9]\n",
"Resolution with number of communities closest to true labels [0.3 0.4]\n",
"All resolution values [0.3 0.31 0.32 0.33 0.34 0.35 0.36 0.37 0.38 0.39]\n",
"0\n",
"1\n",
"2\n",
"3\n",
"4\n",
"5\n",
"6\n",
"7\n",
"8\n",
"9\n",
"Average number of communities [70.4 67.5 63.6 60.6 58.2 54.9 53.8 51.1 49.5 46.7]\n",
"Difference to true categories [ 6.4 3.5 0.4 3.4 5.8 9.1 10.2 12.9 14.5 17.3]\n",
"Resolution with number of communities closest to true labels 0.32000000000000006\n"
]
}
],
"source": [
"createPlot('GO_BP')"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 6,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of true categories: 69\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/berceste/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:40: RuntimeWarning: divide by zero encountered in log10\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"All resolution values [0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1. ]\n",
"0\n",
"1\n",
"2\n",
"3\n",
"4\n",
"5\n",
"6\n",
"7\n",
"8\n",
"9\n",
"Average number of communities [139.7 73.6 46.8 37. 28.9 25. 20.8 18.3 17.5 15.9]\n",
"Difference to true categories [70.7 4.6 22.2 32. 40.1 44. 48.2 50.7 51.5 53.1]\n",
"Resolution with number of communities closest to true labels [0.2 0.3]\n",
"All resolution values [0.2 0.21 0.22 0.23 0.24 0.25 0.26 0.27 0.28 0.29 0.3 ]\n",
"0\n",
"1\n",
"2\n",
"3\n",
"4\n",
"5\n",
"6\n",
"7\n",
"8\n",
"9\n",
"Average number of communities [72.7 69.9 66.4 62.8 59.2 57.8 53.2 52.7 50.5 48.7 46.8]\n",
"Difference to true categories [ 3.7 0.9 2.6 6.2 9.8 11.2 15.8 16.3 18.5 20.3 22.2]\n",
"Resolution with number of communities closest to true labels 0.21000000000000002\n"
]
}
],
"source": [
"createPlot('GO_MF')"
]
......
......@@ -247,18 +247,18 @@
plt.hist(np.unique(coms, return_counts=True)[1])
```
%%%% Output: execute_result
(array([9., 9., 5., 5., 4., 1., 0., 1., 1., 1.]),
array([ 6. , 54.8, 103.6, 152.4, 201.2, 250. , 298.8, 347.6, 396.4,
445.2, 494. ]),
(array([ 9., 10., 5., 4., 4., 1., 0., 1., 1., 1.]),
array([ 4. , 54.7, 105.4, 156.1, 206.8, 257.5, 308.2, 358.9, 409.6,
460.3, 511. ]),
<a list of 10 Patch objects>)
%%%% Output: display_data
![](data:image/png;base64,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)
![](data:image/png;base64,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)
%% Cell type:code id: tags:
``` python
if not os.path.isdir("Full_graph_louvain_with_weights_community_labels/%s"%str(res)):
......@@ -283,18 +283,18 @@
KEGG_ASCORBATE_AND_ALDARATE_METABOLISM 0
KEGG_FATTY_ACID_METABOLISM 0
KEGG_STEROID_BIOSYNTHESIS 0
KEGG_PRIMARY_BILE_ACID_BIOSYNTHESIS 0
KEGG_STEROID_HORMONE_BIOSYNTHESIS 0
KEGG_OXIDATIVE_PHOSPHORYLATION 2
KEGG_PURINE_METABOLISM 3
KEGG_PYRIMIDINE_METABOLISM 3
KEGG_OXIDATIVE_PHOSPHORYLATION 0
KEGG_PURINE_METABOLISM 2
KEGG_PYRIMIDINE_METABOLISM 2
KEGG_ALANINE_ASPARTATE_AND_GLUTAMATE_METABOLISM 0
KEGG_GLYCINE_SERINE_AND_THREONINE_METABOLISM 0
KEGG_CYSTEINE_AND_METHIONINE_METABOLISM 0
KEGG_VALINE_LEUCINE_AND_ISOLEUCINE_DEGRADATION 0
KEGG_VALINE_LEUCINE_AND_ISOLEUCINE_BIOSYNTHESIS 4
KEGG_VALINE_LEUCINE_AND_ISOLEUCINE_BIOSYNTHESIS 3
KEGG_LYSINE_DEGRADATION 0
KEGG_ARGININE_AND_PROLINE_METABOLISM 0
KEGG_HISTIDINE_METABOLISM 0
KEGG_TYROSINE_METABOLISM 0
KEGG_PHENYLALANINE_METABOLISM 0
......@@ -303,40 +303,40 @@
KEGG_TAURINE_AND_HYPOTAURINE_METABOLISM 0
KEGG_SELENOAMINO_ACID_METABOLISM 0
KEGG_GLUTATHIONE_METABOLISM 0
KEGG_STARCH_AND_SUCROSE_METABOLISM 0
... ..
GO_CARBOHYDRATE_DERIVATIVE_TRANSMEMBRANE_TRANSP... 17
GO_CARBOHYDRATE_DERIVATIVE_TRANSMEMBRANE_TRANSP... 10
GO_FATTY_ACID_DERIVATIVE_BINDING 0
GO_PHOSPHATIDYLGLYCEROL_BINDING 8
GO_CARDIOLIPIN_BINDING 8
GO_VOLTAGE_GATED_POTASSIUM_CHANNEL_ACTIVITY_INV... 17
GO_VOLTAGE_GATED_POTASSIUM_CHANNEL_ACTIVITY_INV... 10
GO_CERAMIDE_1_PHOSPHATE_BINDING 8
GO_CUPROUS_ION_BINDING 14
GO_MRNA_BINDING_INVOLVED_IN_POSTTRANSCRIPTIONAL... 4
GO_S_ADENOSYL_L_METHIONINE_BINDING 35
GO_PEPTIDE_TRANSMEMBRANE_TRANSPORTER_ACTIVITY 17
GO_CUPROUS_ION_BINDING 15
GO_MRNA_BINDING_INVOLVED_IN_POSTTRANSCRIPTIONAL... 18
GO_S_ADENOSYL_L_METHIONINE_BINDING 33
GO_PEPTIDE_TRANSMEMBRANE_TRANSPORTER_ACTIVITY 10
GO_CORECEPTOR_ACTIVITY_INVOLVED_IN_WNT_SIGNALIN... 1
GO_POLYSOME_BINDING 4
GO_POLYSOME_BINDING 3
GO_PHOSPHATIDIC_ACID_TRANSPORTER_ACTIVITY 8
GO_HISTONE_METHYLTRANSFERASE_BINDING 32
GO_STEROID_HORMONE_BINDING 17
GO_N6_METHYLADENOSINE_CONTAINING_RNA_BINDING 4
GO_KERATIN_FILAMENT_BINDING 26
GO_LYS48_SPECIFIC_DEUBIQUITINASE_ACTIVITY 15
GO_HISTONE_METHYLTRANSFERASE_BINDING 27
GO_STEROID_HORMONE_BINDING 10
GO_N6_METHYLADENOSINE_CONTAINING_RNA_BINDING 3
GO_KERATIN_FILAMENT_BINDING 22
GO_LYS48_SPECIFIC_DEUBIQUITINASE_ACTIVITY 16
GO_PROTEIN_ADP_RIBOSYLASE_ACTIVITY 1
GO_PROTEIN_ANTIGEN_BINDING 23
GO_EXTRACELLULAR_MATRIX_PROTEIN_BINDING 21
GO_U1_SNRNP_BINDING 4
GO_TRANSFERRIN_RECEPTOR_BINDING 16
GO_PROTEIN_BINDING_BRIDGING_INVOLVED_IN_SUBSTRA... 15
GO_ARRESTIN_FAMILY_PROTEIN_BINDING 12
GO_RNA_ADENYLYLTRANSFERASE_ACTIVITY 6
GO_SEQUENCE_SPECIFIC_MRNA_BINDING 4
GO_U1_SNRNP_BINDING 3
GO_TRANSFERRIN_RECEPTOR_BINDING 28
GO_PROTEIN_BINDING_BRIDGING_INVOLVED_IN_SUBSTRA... 7
GO_ARRESTIN_FAMILY_PROTEIN_BINDING 13
GO_RNA_ADENYLYLTRANSFERASE_ACTIVITY 5
GO_SEQUENCE_SPECIFIC_MRNA_BINDING 3
GO_SEQUENCE_SPECIFIC_DOUBLE_STRANDED_DNA_BINDING 19
GO_PROMOTER_SPECIFIC_CHROMATIN_BINDING 19
GO_UBIQUITIN_LIGASE_INHIBITOR_ACTIVITY 4
GO_UBIQUITIN_LIGASE_INHIBITOR_ACTIVITY 3
[4847 rows x 1 columns]
%% Cell type:code id: tags:
......
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment