add sasa and plddt selection

README.md

@@ -4,7 +4,7 @@ emoji: ⚡
 colorFrom: red
 colorTo: pink
 sdk: gradio
-sdk_version: 3.0.11
+sdk_version: 3.1
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -1,33 +1,30 @@
 import json, time, os, sys, glob
-
-import gradio as gr
-
-sys.path.append("/home/user/app/ProteinMPNN/vanilla_proteinmpnn")
-
-sys.path.append("/home/duerr/phd/08_Code/ProteinMPNN/ProteinMPNN/vanilla_proteinmpnn")
-
-import matplotlib.pyplot as plt
+import urllib
 import shutil
 import warnings
-import numpy as np
-import torch
-from torch import optim
-from torch.utils.data import DataLoader
-from torch.utils.data.dataset import random_split, Subset
 import copy
-import torch.nn as nn
-import torch.nn.functional as F
 import random
-import os
+import re
+
 import os.path
 
+import torch
+import ray
+import jax
+
+import gradio as gr
+import pandas as pd
+import numpy as np
 import plotly.express as px
-import urllib
 import jax.numpy as jnp
 import tensorflow as tf
+import matplotlib.pyplot as plt
+import colabfold as cf
+import plotly.graph_objects as go
 
+import torch.nn as nn
+import torch.nn.functional as F
 
-from moleculekit.molecule import Molecule
 
 if "/home/user/app/af_backprop" not in sys.path:
     sys.path.append("/home/user/app/af_backprop")
@@ -36,24 +33,22 @@ if "/home/user/app/af_backprop" not in sys.path:
 if "/home/duerr/phd/08_Code/ProteinMPNN/af_backprop" not in sys.path:
     sys.path.append("/home/duerr/phd/08_Code/ProteinMPNN/af_backprop")
 
-from utils import *
 
-# import libraries
-import colabfold as cf
+from torch import optim
+from torch.utils.data import DataLoader
+from torch.utils.data.dataset import random_split, Subset
+from moleculekit.molecule import Molecule
 from alphafold.common import protein
 from alphafold.data import pipeline
 from alphafold.model import data, config
 from alphafold.model import model as afmodel
 from alphafold.common import residue_constants
 
+from utils import *
 
-import plotly.graph_objects as go
-import ray
-
-import re
+sys.path.append("/home/user/app/ProteinMPNN/vanilla_proteinmpnn")
+sys.path.append("/home/duerr/phd/08_Code/ProteinMPNN/ProteinMPNN/vanilla_proteinmpnn")
 
-import numpy as np
-import jax
 
 tf.config.set_visible_devices([], "GPU")
 
@@ -322,10 +317,43 @@ def preprocess_mol(pdb_code="", filepath=""):
     mol.write("cleaned.pdb")
     return "cleaned.pdb", df
 
+def assign_sasa(mol):
+    from moleculekit.projections.metricsasa import MetricSasa
+    metr = MetricSasa(
+                mode="residue", filtersel="protein"
+            ) 
+    sasaR = metr.project(mol)[0]
+    is_prot = mol.atomselect("protein")
+    resids=pd.DataFrame.from_dict({"resid":mol.resid, "is_prot":is_prot})
+    new_masses=[]
+    i_without_non_prot = 0
+    for i, g in resids.groupby((resids['resid'].shift() != resids['resid']).cumsum()):
+        if g["is_prot"].unique()[0]==True:
+            g["sasa"]=sasaR[i_without_non_prot]
+            i_without_non_prot+=1
+        else:
+            g["sasa"]=0
+        new_masses.extend(list(g.sasa))
+    return np.array(new_masses)
+
+def process_atomsel(atomsel):
+    """everything lowercase and replace some keywords not relevant for protein design"""
+    atomsel=re.sub('sasa', 'mass',atomsel, flags=re.I)
+    atomsel=re.sub('plddt', 'beta',atomsel, flags=re.I)
+    return atomsel
+
+
 def make_fixed_positions_dict(atomsel, residue_index_df):
     # we use the uploaded file for the selection
     mol = Molecule('original.pdb')
     # use index for selection as resids will change
+
+  
+    # set sasa to 0 for all non protein atoms (all non protein atoms are deleted later)
+    mol.masses = assign_sasa(mol)
+    print(mol.masses.shape)
+    print(assign_sasa(mol).shape)
+    atomsel = process_atomsel("chain B or (chain A and Sasa < 30)")
     selected_residues = mol.get("index",atomsel)
 
     # clean up
@@ -1123,7 +1151,13 @@ with proteinMPNN:
                  - <code>resid 94 96 119</code> Residues 94, 94 and 119
                  - <code>within 5 of resname ZN</code> All residues with any atom <5 Å of zinc ion
                  - <code>chain A and within 5 of chain B </code> All residues of chain A that are part of the interface with chain B
-                 - <code>protein and within 5 of nucleic </code> All residues that bind to DNA (if present in structure)""")
+                 - <code>protein and within 5 of nucleic </code> All residues that bind to DNA (if present in structure)
+                 - <code>not (chain A and within 5 of chain B) </code>  only modify residues that are in the interface with the fixed chain, not further away
+                 - <code>chain A or (chain B and sasa < 20) </code> Keep chain A and all core residues fixeds
+                 - <code>pLDDT >70 </code> Redesign all residues with low pLDDT
+                 
+                 Note that <code>sasa</code> and <code>pLDDT</code> selectors modify default VMD behavior. SASA is calculated using moleculekit and written to the mass attribute. Selections based on mass do not work. 
+                 pLDDT is an alias for beta, it only works correctly with structures that contain the appropriate values in the beta column of the PDB file. """)
             atomsel = gr.Textbox(placeholder="Specify atom selection ", label="Fixed positions")
 
         btn = gr.Button("Run")
@@ -1145,6 +1179,7 @@ with proteinMPNN:
             ["Redesign of Homomer to Heteromer", "3HTN", "A,B", "C", False, 2, 0.1, ""],
             ["Redesign of MID1 scaffold keeping binding site fixed", "3V1C", "A,B", "", False, 2, 0.1, "within 5 of resname ZN"],
             ["Redesign of DNA binding protein", "3JRD", "A,B", "", False, 2, 0.1, "within 8 of nucleic"],
+            ["Surface Redesign of miniprotein", "7JZM", "A,B", "", False, 2, 0.1, "chain B or (chain A and sasa < 20)"],
         ],
     )
 

requirements.txt

@@ -18,6 +18,6 @@ plotly
 GPUtil
 ray
 tqdm
-gradio==3.0.11
+gradio==3.1
 protobuf<4
--f https://storage.googleapis.com/jax-releases/jax_releases.html
+-f https://storage.googleapis.com/jax-releases/jax_releases.html