You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/tutorials/tutorial_Boltz_bwVisu.md
+4-7Lines changed: 4 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -12,11 +12,8 @@ To start, get access to bwVisu via bwForCluster Helix or SDS. For more informati
12
12
13
13
For technical questions regarding the high performance cluster, see <ahref="https://bw-support.scc.kit.edu"target="_blank"rel="noopener">https://bw-support.scc.kit.edu</a>. Feel free to [contact us](../contact.md) for support.
14
14
15
-
### Step 2: Prepare the Multisequence Alignment
16
15
17
-
The first step of the structure prediction is a multi-sequence alignment (MSA), which provides the basis for the prediction. Boltz relies on external partner, such as the <ahref="https://www.nature.com/articles/s41592-022-01488-1"target="_blank"rel="noopener">colabfold</a> server. To run Boltz on bwVisu, a precomputed MSA file for any given input sequence needs to be provided. You can calculate the MSA locally using <ahref="https://github.com/soedinglab/MMseqs2"target="_blank"rel="noopener">mmseqs2</a>. For this tutorial you can download the `example.a3m` file from our <ahref="https://github.com/ssciwr/BioStructureHub/tree/main/notebooks"target="_blank"rel="noopener">github</a>.
18
-
19
-
### Step 3: Connect to bwVisu and Start Jupyter
16
+
### Step 2: Connect to bwVisu and Start Jupyter
20
17
21
18
Go to <ahref="https://bwvisu.bwservices.uni-heidelberg.de/"target="_blank"rel="noopener">https://bwvisu.bwservices.uni-heidelberg.de/</a> and log in with your credentials and one-time password.
22
19
@@ -36,7 +33,7 @@ You also need to define the `Kernel Path` to the boltz kernel at `/mnt/sds-hd/sd
36
33
37
34
Click on "Launch". This will bring you to a new screen showing your interactive sessions. Wait for your session to be ready, then click on "Connect to Jupyter". This brings you into a JupyterLab environment.
38
35
39
-
### Step 4: Set a Working Directory and Upload Files
36
+
### Step 3: Set a Working Directory and Upload Files
40
37
41
38
Now we need to define a working directory. These will contain all files necessary for the tutorial. A new directory can be created using folder icon on the top left of the file browser:
42
39
@@ -48,7 +45,7 @@ Download the tutorial notebooks from our <a href="https://github.com/ssciwr/BioS
48
45
49
46
You also need a `.fasta` file of your sequence to start. You can use our example `insulin.fasta` from our <ahref="https://github.com/ssciwr/BioStructureHub/tree/main/references/boltz"target="_blank"rel="noopener">github</a>
50
47
51
-
### Step 5: Open the Notebook and Start the Calculation
48
+
### Step 4: Open the Notebook and Start the Calculation
52
49
53
50
Open `Boltz_input.ipynb` and select the `boltz` kernel. You can verify the kernel in the top right corner of your JupyterLab instance:
54
51
@@ -71,7 +68,7 @@ In the output directory, there should be multiple files. The .cif file includes
71
68
{: style="width:268px"}
72
69
73
70
74
-
### Step 6: Analyze your results
71
+
### Step 5: Analyze your results
75
72
76
73
Open the second notebook called `Boltz_Confidence_Levels.ipynb` to get a summary of the models confidence levels. This notebook reads the confidence descriptions and renders its central information.
0 commit comments