feat: upload entire 400 proteins script (#102)

* feat: upload all script

* feat: delete script too

* feat: delete too

* docs: add command to docs for upload

* fix: right alpha fold link

backend/init.sql

@@ -46,33 +46,6 @@ CREATE TABLE species (
  PRIMARY KEY (species_id, protein_id)
  );
 
-/*
- * Inserts example proteins into proteins table
- */
-INSERT INTO proteins (name, length, mass, content, refs) VALUES (
- 'Gh_comp271_c0_seq1', 
- 0,
- 0.0,
- null,
- null
-);
-
-INSERT INTO proteins (name, length, mass, content, refs) VALUES (
- 'Lb17_comp535_c2_seq1', 
- 0,
- 0.0,
- null,
- null
-);
-
-INSERT INTO proteins (name, length, mass, content, refs) VALUES (
- 'Lh14_comp2336_c0_seq1', 
- 0,
- 0.0,
- null,
- null
-);
-
 /*
  * Inserts example species into species table
  */
@@ -81,27 +54,4 @@ INSERT INTO species(name) VALUES ('leptopilina boulardi');
 INSERT INTO species(name) VALUES ('leptopilina heterotoma'); 
 INSERT INTO species(name) VALUES ('unknown');
 
-/*
- * Inserts connections between species and proteins
-*/ 
-INSERT INTO species_proteins(species_id, protein_id) VALUES (
- 1, -- 'ganaspis hookeri',
- 1 -- 'Gh_comp271_c0_seq1'
- );
-
- /*
- * Inserts connections between species and proteins
- */ 
-INSERT INTO species_proteins(species_id, protein_id) VALUES (
- 2, -- 'leptopilina boulardi',
- 2 -- 'Lb17_comp535_c2_seq1'
- );
-
- /*
- * Inserts connections between species and proteins
- */ 
-INSERT INTO species_proteins(species_id, protein_id) VALUES (
- 3, -- 'leptopilina heterotoma',
- 3 --'Lh14_comp2336_c0_seq1'
- );
 

backend/src/data/pdbAlphaFold/.gitignore

@@ -0,0 +1 @@
+*.pdb

docs/run.md

@@ -25,6 +25,8 @@ sh run.sh <cmd>
 | `test` | Runs all unit tests |
 | `test_backend` | Runs only backend unit tests |
 | `test_frontend` | Runs only frontend unit tests |
+| `upload_all` | 👉 Uploads all the pdb files to the system via POST requests |
+| `delete_all` | Deletes all protein entries and restarts the server from scratch |
 
 There are actually many more functions, so please check out [`run.sh`](../run.sh).
 

galaxy/delete_all.py

@@ -0,0 +1,13 @@
+import requests
+import os
+
+DIR = "../backend/src/data/pdbAlphaFold"
+
+
+def delete_protein_files():
+ os.system(f"rm -fr {DIR}")
+ os.system(f"mkdir {DIR}")
+ os.system(f"echo *.pdb > {DIR}/.gitignore")
+
+
+delete_protein_files()

galaxy/upload_all.py

@@ -0,0 +1,52 @@
+import requests
+import os
+
+CONTENT = "From the [Venom Biochemistry & Molecular Biology Laboratory](https://venombiochemistrylab.weebly.com/) and predicted using [AlphaFold](https://github.com/google-deepmind/alphafold)."
+REFS = ""
+DIR = "./master_venom_galaxy"
+
+
+def unzip_box():
+ os.system(f"unzip {DIR}.zip")
+
+
+def remove_box():
+ os.system(f"rm -rf {DIR}")
+
+
+def upload_protein_file(path, name, species_name, content="", refs=""):
+ with open(path, "r") as f:
+ pdb_file_str = f.read()
+
+ payload = {
+ "name": name,
+ "species_name": species_name,
+ "content": content,
+ "refs": refs,
+ "pdb_file_str": pdb_file_str,
+ }
+ out = requests.post("http://localhost:8000/protein-upload", json=payload)
+ return out
+
+
+def upload_all():
+ unzip_box()
+ available_species = {
+ "Gh": "ganaspis hookeri",
+ "Lb": "leptopilina boulardi",
+ "Lh": "leptopilina heterotoma",
+ "*": "unknown",
+ }
+ for fn in os.listdir(DIR):
+ if fn.endswith(".pdb"):
+ full_path = os.path.join(DIR, fn)
+ name = fn.split(".")[0].replace("_", " ")
+ species_name = available_species[fn[:2]]
+ upload_protein_file(
+ full_path, name, species_name, content=CONTENT, refs=REFS
+ )
+ print("uploaded", full_path, name, species_name)
+ remove_box()
+
+
+upload_all()

run.sh

@@ -107,6 +107,14 @@ function hard_restart() {
  reload_init_sql
 }
 
+function upload_all() {
+ cd galaxy && python3 upload_all.py
+}
+
+function delete_all() {
+ cd galaxy && python3 delete_all.py && soft_restart
+}
+
 function scrape_func_names() {
  functions=($(grep -oE 'function[[:space:]]+[a-zA-Z_][a-zA-Z_0-9]*' ./run.sh | sed 's/function[[:space:]]*//'))
 }