DISI - User contributions [en]

Retro-Blockblaster

2026-07-13T22:09:47Z

Bromero:

= Retro-Blockbalster (BenZinc26) =

== Introduction ==

[[File:Web-interface.png|thumb]]
[[File:Ex._Results_.png|thumb]]
[[File:Example results.png|thumb]]
[[File:Ex results with building blocks.png|thumb]]

As of 7/13/26, Retro-Blockbalster is an internal Irwin Lab web tool for submitting a compound in SMILES format and receiving retro/analoging reaction results (also enumeration)--all info is from Chemistry Commons and uses RDKit.

The current backend runs on Cluster 2 using epyc (port 8001)

== How to Open Website (MUST USE) With SwitchyOmega ==

Start the portal SSH/SOCKS tunnel from your laptop:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 USER@portal3.ucsf.bkslab.org
</pre>

Leave this terminal open.

In Chrome, set SwitchyOmega to:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1080
</pre>

Then open:

<pre>
http://epyc:8001
</pre>

== Where The Website Lives ==

Project directory on epyc:

<pre>
~/Initial-BenZinc26-website
</pre>

Important files:

<pre>
index.html
run_job.py
backend/server_old.py
.env
</pre>

== .env Setup ==

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=...@...com
SMTP_PASSWORD=....(GOOGLE_APP_PASSWORD)
FROM_EMAIL=...@....com
</pre>

== How to Start Backend ==

On epyc:

<pre>
cd ~/Initial-BenZinc26-website
python3 backend/server_old.py
</pre>

The backend currently runs on:

<pre>
http://0.0.0.0:8001
</pre>

Test from epyc:

<pre>
curl http://127.0.0.1:8001
</pre>

== How to Keep Backend Running ==

Use screen:

<pre>
cd ~/Initial-BenZinc26-website
screen -S benzinc26
python3 backend/server_old.py
</pre>

Detach:

<pre>
Ctrl-A
D
</pre>

Reconnect:

<pre>
screen -r benzinc26
</pre>

List screens:

<pre>
screen -ls
</pre>

Stop backend:

<pre>
screen -r benzinc26
Ctrl-C
exit
</pre>

== Test Input ==

A test molecule that returns reaction rows:

<pre>
CN(C)C(=O)NC1=CC=CC=C1
</pre>

Test with curl from epyc:

<pre>
curl -X POST http://127.0.0.1:8001/hello-job \
-H "Content-Type: application/json" \
-d '{"user_input":"CN(C)C(=O)NC1=CC=CC=C1 urea_test","email":"your_email@gmail.com"}'
</pre>

== Environment ==

The backend needs a `.env` file in the project root.

Do not commit `.env` to GitHub.

Example:

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=retro-blockbalster@gmail.com
SMTP_PASSWORD=abcdefghijklmnop
FROM_EMAIL=retro-blockbalster@gmail.com
BASE_URL=http://epyc:8001
</pre>

== RDKit Environment ==

The retro reaction script uses RDKit through:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python
</pre>

Test on epyc:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python -c "from rdkit import Chem; print('rdkit works')"
</pre>

RDKit works on epyc.

== Troubleshooting ==

=== Site Cannot Be Reached ===

Check that:

* Backend is running on epyc.
* The SSH/SOCKS tunnel is running.
* SwitchyOmega is set to SOCKS5 localhost port 1080.
* The browser is using http://epyc:8001.

=== Port Already In Use ===

Check port 8001:

<pre>
ss -ltnp | grep 8001
</pre>

Only kill processes owned by you:

<pre>
kill PID_NUMBER
</pre>

=== Email Not Sending ===

Check that:

* `.env` exists.
* Gmail app password is correct.
* SMTP_USER and FROM_EMAIL are the same account.
* The app password belongs to that same account.

File:Ex results with building blocks.png

2026-07-13T22:09:42Z

Bromero:

4 Synthons

File:Example results.png

2026-07-13T22:08:22Z

Bromero:

Enumeration

Retro-Blockblaster

2026-07-13T22:05:43Z

Bromero:

= Retro-Blockbalster (BenZinc26) =

== Introduction ==

[[File:Web-interface.png|thumb]]

As of 7/13/26, Retro-Blockbalster is an internal Irwin Lab web tool for submitting a compound in SMILES format and receiving retro/analoging reaction results (also enumeration)--all info is from Chemistry Commons and uses RDKit.

The current backend runs on Cluster 2 using epyc (port 8001)

== How to Open Website (MUST USE) With SwitchyOmega ==

Start the portal SSH/SOCKS tunnel from your laptop:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 USER@portal3.ucsf.bkslab.org
</pre>

Leave this terminal open.

In Chrome, set SwitchyOmega to:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1080
</pre>

Then open:

<pre>
http://epyc:8001
</pre>

== Where The Website Lives ==

Project directory on epyc:

<pre>
~/Initial-BenZinc26-website
</pre>

Important files:

<pre>
index.html
run_job.py
backend/server_old.py
.env
</pre>

== .env Setup ==

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=...@...com
SMTP_PASSWORD=....(GOOGLE_APP_PASSWORD)
FROM_EMAIL=...@....com
</pre>

== How to Start Backend ==

On epyc:

<pre>
cd ~/Initial-BenZinc26-website
python3 backend/server_old.py
</pre>

The backend currently runs on:

<pre>
http://0.0.0.0:8001
</pre>

Test from epyc:

<pre>
curl http://127.0.0.1:8001
</pre>

== How to Keep Backend Running ==

Use screen:

<pre>
cd ~/Initial-BenZinc26-website
screen -S benzinc26
python3 backend/server_old.py
</pre>

Detach:

<pre>
Ctrl-A
D
</pre>

Reconnect:

<pre>
screen -r benzinc26
</pre>

List screens:

<pre>
screen -ls
</pre>

Stop backend:

<pre>
screen -r benzinc26
Ctrl-C
exit
</pre>

== Test Input ==

A test molecule that returns reaction rows:

<pre>
CN(C)C(=O)NC1=CC=CC=C1
</pre>

Test with curl from epyc:

<pre>
curl -X POST http://127.0.0.1:8001/hello-job \
-H "Content-Type: application/json" \
-d '{"user_input":"CN(C)C(=O)NC1=CC=CC=C1 urea_test","email":"your_email@gmail.com"}'
</pre>

== Environment ==

The backend needs a `.env` file in the project root.

Do not commit `.env` to GitHub.

Example:

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=retro-blockbalster@gmail.com
SMTP_PASSWORD=abcdefghijklmnop
FROM_EMAIL=retro-blockbalster@gmail.com
BASE_URL=http://epyc:8001
</pre>

== RDKit Environment ==

The retro reaction script uses RDKit through:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python
</pre>

Test on epyc:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python -c "from rdkit import Chem; print('rdkit works')"
</pre>

RDKit works on epyc.

== Troubleshooting ==

=== Site Cannot Be Reached ===

Check that:

* Backend is running on epyc.
* The SSH/SOCKS tunnel is running.
* SwitchyOmega is set to SOCKS5 localhost port 1080.
* The browser is using http://epyc:8001.

=== Port Already In Use ===

Check port 8001:

<pre>
ss -ltnp | grep 8001
</pre>

Only kill processes owned by you:

<pre>
kill PID_NUMBER
</pre>

=== Email Not Sending ===

Check that:

* `.env` exists.
* Gmail app password is correct.
* SMTP_USER and FROM_EMAIL are the same account.
* The app password belongs to that same account.

File:Ex. Results .png

2026-07-13T22:04:06Z

Bromero:

Synthons

File:Web-interface.png

2026-07-13T22:03:36Z

Bromero:

Landing page

ADMET Builder

2026-07-13T22:00:23Z

Bromero:

= ADMET Builder (OpenADMET) =

== Introduction ==

As of 7/6/26, '''ADMET Builder''' is an internal Irwin Lab web tool for submitting one or more compounds in SMILES format and receiving OpenADMET prediction results.

The current backend runs on C7 using the `openadmet-models` conda environment.

ADMET Builder returns:

* Molecular formula
* SMILES string
* RDKit-generated 2D structure image
* logD
* Caco-2 A to B permeability
* Caco-2 B to A permeability
* Mouse plasma protein binding
* Human plasma protein binding
* Downloadable CSV output

[[File:ADMET builder.png|thumb]]
[[File:ADMET builder results.png|thumb]]

Created by Benjamin "Ben" Romero (Undergrad Northwestern University '29), Summer 2026. 
Developed in the Irwin Lab at UCSF.

== How to Login ==

Log into C7:

<pre>
ssh USER@epsilon.compbio.ucsf.edu
</pre>

== How to Open Website With SwitchyOmega ==

If using SwitchyOmega, use:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1074
</pre>

Then open:

<pre>
http://169.230.26.173:8501
</pre>

If the SOCKS proxy is not running, start it from a terminal:

<pre>
ssh -f -N -D 1074 USER@epsilon.compbio.ucsf.edu
</pre>

When finished, switch SwitchyOmega back to Direct.

== Where The Website Lives ==

Project directory on C7:

<pre>
~/openadmet/admet-builder
</pre>

Important files:

<pre>
app.py
static/index.html
static/styles.css
static/app.js
.gitignore
</pre>

== Repository ==

GitLab repository:

<pre>
https://gitlab.docking.org/USERNAME/admet-builder
</pre>

Clone using HTTPS:

<pre>
git clone https://gitlab.docking.org/USERNAME/admet-builder.git
cd admet-builder
</pre>

Clone using SSH:

<pre>
git clone git@gitlab.docking.org:USERNAME/admet-builder.git
cd admet-builder
</pre>

== Environment ==

The backend uses the OpenADMET conda environment:

<pre>
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
</pre>

Python dependencies include:

* Flask
* pandas
* RDKit
* OpenADMET models package

The OpenADMET model directory is expected at:

<pre>
~/openadmet/permeability-logd-ppb-chemeleon-baseline/anvil_training
</pre>

== How to Start Backend ==

On C7:

<pre>
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
cd ~/openadmet/admet-builder
python app.py
</pre>

The backend runs on:

<pre>
http://0.0.0.0:8501
</pre>

The browser URL is:

<pre>
http://169.230.26.173:8501
</pre>

Test from C7:

<pre>
curl http://127.0.0.1:8501
</pre>

== How to Keep Backend Running ==

Use screen:

<pre>
screen -S admet-builder
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
cd ~/openadmet/admet-builder
python app.py
</pre>

Detach:

<pre>
Ctrl-A
D
</pre>

Reconnect:

<pre>
screen -r admet-builder
</pre>

List screens:

<pre>
screen -ls
</pre>

Stop backend:

<pre>
screen -r admet-builder
Ctrl-C
exit
</pre>

== Test Input ==

Example SMILES input:

<pre>
CCO
c1ccccc1
CC(=O)Oc1ccccc1C(=O)O
</pre>

Larger test molecule:

<pre>
CC(C)Cc1ccc(cc1)[C@@H](C)C(=O)O
</pre>

== Test API With curl ==

Test the API from C7:

<pre>
curl -X POST http://127.0.0.1:8501/predict-smiles \
-H "Content-Type: application/json" \
-d '{"smiles":["CCO","c1ccccc1","CC(=O)Oc1ccccc1C(=O)O"]}'
</pre>

== Current API Endpoint ==

Main endpoint:

<pre>
POST /predict-smiles
</pre>

Example JSON request:

<pre>
{
"smiles": [
"CCO",
"c1ccccc1",
"CC(=O)Oc1ccccc1C(=O)O"
]
}
</pre>

Example response contains:

<pre>
{
"csv": "...",
"rows": [],
"columns": []
}
</pre>

The frontend uses this response to display the results table and automatically download the CSV.

== How It Works ==

ADMET Builder has three major parts:

{| class="wikitable"
! Layer
! Technology
! Purpose
|-
| Frontend
| HTML, CSS, JavaScript
| User interface, SMILES input, results table, and structure image display
|-
| Backend API
| Flask
| Receives SMILES, runs predictions, and returns results
|-
| Prediction Engine
| OpenADMET
| Generates ADMET predictions from molecular input
|}

Backend flow:

# Receives SMILES strings from the website.
# Converts the SMILES into a temporary CSV file.
# Runs the OpenADMET command-line prediction tool.
# Reads the OpenADMET output CSV.
# Uses RDKit to calculate molecular formulas.
# Uses RDKit to generate 2D molecular structure images.
# Sends results back to the web interface as JSON.
# Provides the same results as a downloadable CSV file.

== Modularity ==

ADMET Builder is modular by design. The frontend, backend, and prediction engine are separated so each part can be reused or replaced.

This means:

* The frontend can be redesigned without changing the model logic.
* The Flask backend can support new endpoints.
* Additional OpenADMET models can be added later.
* Other chemistry tools can be wrapped using the same backend pattern.
* The results table can be adapted for different prediction outputs.
* The SMILES-to-structure display can be reused in other cheminformatics apps.
* The app can serve as a template for future scientific web interfaces.

Because of this structure, ADMET Builder can be used both as a working lab tool and as a starting point for other modular research software.

== Output ==

The output table includes:

{| class="wikitable"
! Column
! Meaning
|-
| Molecule
| Molecular formula calculated from the SMILES string
|-
| SMILES
| Input molecule string
|-
| Structure Image
| RDKit-generated 2D molecular structure
|-
| logD
| Predicted distribution coefficient
|-
| Caco-2 A to B
| Predicted apical-to-basolateral permeability
|-
| Caco-2 B to A
| Predicted basolateral-to-apical permeability
|-
| Mouse PPB
| Predicted mouse plasma protein binding
|-
| Human PPB
| Predicted human plasma protein binding
|}

The CSV download contains the same prediction values in a machine-readable format.

== Troubleshooting ==

=== Site Cannot Be Reached ===

Check that:

* Backend is running on C7.
* The app is running on port 8501.
* SwitchyOmega is set to SOCKS5 localhost port 1074.
* The browser is using:

<pre>
http://169.230.26.173:8501
</pre>

=== SwitchyOmega Proxy Error ===

If Chrome says the proxy failed, the SOCKS proxy may not be running.

Start it from a Mac terminal:

<pre>
ssh -f -N -D 1074 USER@epsilon.compbio.ucsf.edu
</pre>

SwitchyOmega should be:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1074
</pre>

=== Port Already In Use ===

Check port 8501:

<pre>
ss -ltnp | grep 8501
</pre>

Only kill processes owned by you:

<pre>
kill PID_NUMBER
</pre>

=== Missing pandas or Flask ===

This usually means the conda environment is not active.

Run:

<pre>
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
</pre>

=== RDKit Image Error ===

Make sure the app is running inside the `openadmet-models` environment, which includes RDKit.

Test RDKit:

<pre>
python -c "from rdkit import Chem; print('rdkit works')"
</pre>

== Notes ==

ADMET Builder is a research tool. Its predictions are intended for screening, comparison, prioritization, and exploration.

Results should not be treated as experimental measurements.

For office-wide use without SSH/SOCKS tunnels, ADMET Builder should eventually be placed behind an internal hostname or proxy.

== Attribution ==

Created by Benjamin "Ben" Romero (Undergrad Northwestern University '29), Summer 2026. 
Developed in the Irwin Lab at UCSF. 
Released as part of an open-source UCSF research tool; please credit the creator and lab when using or adapting this work.

File:ADMET builder results.png

2026-07-13T21:59:46Z

Bromero:

results

File:ADMET builder.png

2026-07-13T21:58:55Z

Bromero:

ADMET builder

Retro-Blockblaster

2026-07-10T21:29:37Z

Bromero:

= Retro-Blockbalster (BenZinc26) =

== Introduction ==

As of 6/29/26, Retro-Blockbalster is an internal Irwin Lab web tool for submitting a compound in SMILES format and receiving retro/analoging reaction results (also enumeration)--all info is from Chemistry Commons and uses RDKit.

The current backend runs on Cluster 2 using epyc (port 8001)

== How to Login ==

Start the portal SSH/SOCKS tunnel from your laptop:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 USER@portal3.ucsf.bkslab.org
</pre>

Leave this terminal open.

In a second terminal, log into gimel:

<pre>
ssh -p 2222 USER@localhost
</pre>

Then log into epyc:

<pre>
ssh epyc
</pre>

== How to Open Website (MUST USE) With SwitchyOmega ==

In Chrome, set SwitchyOmega to:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1080
</pre>

Then open:

<pre>
http://epyc:8001
</pre>

== Where The Website Lives ==

Project directory on epyc:

<pre>
~/Initial-BenZinc26-website
</pre>

Important files:

<pre>
index.html
run_job.py
backend/server_old.py
.env
</pre>

== .env Setup ==

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=...@...com
SMTP_PASSWORD=....(GOOGLE_APP_PASSWORD)
FROM_EMAIL=...@....com
</pre>

== How to Start Backend ==

On epyc:

<pre>
cd ~/Initial-BenZinc26-website
python3 backend/server_old.py
</pre>

The backend currently runs on:

<pre>
http://0.0.0.0:8001
</pre>

Test from epyc:

<pre>
curl http://127.0.0.1:8001
</pre>

== How to Keep Backend Running ==

Use screen:

<pre>
cd ~/Initial-BenZinc26-website
screen -S benzinc26
python3 backend/server_old.py
</pre>

Detach:

<pre>
Ctrl-A
D
</pre>

Reconnect:

<pre>
screen -r benzinc26
</pre>

List screens:

<pre>
screen -ls
</pre>

Stop backend:

<pre>
screen -r benzinc26
Ctrl-C
exit
</pre>

== Test Input ==

A test molecule that returns reaction rows:

<pre>
CN(C)C(=O)NC1=CC=CC=C1
</pre>

Test with curl from epyc:

<pre>
curl -X POST http://127.0.0.1:8001/hello-job \
-H "Content-Type: application/json" \
-d '{"user_input":"CN(C)C(=O)NC1=CC=CC=C1 urea_test","email":"your_email@gmail.com"}'
</pre>

== Environment ==

The backend needs a `.env` file in the project root.

Do not commit `.env` to GitHub.

Example:

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=retro-blockbalster@gmail.com
SMTP_PASSWORD=abcdefghijklmnop
FROM_EMAIL=retro-blockbalster@gmail.com
BASE_URL=http://epyc:8001
</pre>

== RDKit Environment ==

The retro reaction script uses RDKit through:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python
</pre>

Test on epyc:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python -c "from rdkit import Chem; print('rdkit works')"
</pre>

RDKit works on epyc. RDKit may fail on gimel.

== Final Result ==

Web interface

[[File:Screenshot 2026-06-29 at 1.27.35 PM.png|thumb]]

Finished job

[[File:FinalJobEx.png|thumb]]

== Troubleshooting ==

=== Site Cannot Be Reached ===

Check that:

* Backend is running on epyc.
* The SSH/SOCKS tunnel is running.
* SwitchyOmega is set to SOCKS5 localhost port 1080.
* The browser is using http://epyc:8001.

=== Port Already In Use ===

Check port 8001:

<pre>
ss -ltnp | grep 8001
</pre>

Only kill processes owned by you:

<pre>
kill PID_NUMBER
</pre>

=== Email Not Sending ===

Check that:

* `.env` exists.
* Gmail app password is correct.
* SMTP_USER and FROM_EMAIL are the same account.
* The app password belongs to that same account.

ADMET Builder

2026-07-07T00:23:52Z

Bromero:

= ADMET Builder (OpenADMET) =

== Introduction ==
[[File:ADMET builder webpage.png|thumb]]

As of 7/6/26, '''ADMET Builder''' is an internal Irwin Lab web tool for submitting one or more compounds in SMILES format and receiving OpenADMET prediction results.

The current backend runs on C7 using the `openadmet-models` conda environment.

ADMET Builder returns:

* Molecular formula
* SMILES string
* RDKit-generated 2D structure image
* logD
* Caco-2 A to B permeability
* Caco-2 B to A permeability
* Mouse plasma protein binding
* Human plasma protein binding
* Downloadable CSV output

[[File:Results.png|thumb]]

Created by Benjamin "Ben" Romero (Undergrad Northwestern University '29), Summer 2026. 
Developed in the Irwin Lab at UCSF.

== How to Login ==

Log into C7:

<pre>
ssh USER@epsilon.compbio.ucsf.edu
</pre>

Confirm location:

<pre>
hostname
pwd
</pre>

== How to Open Website With SwitchyOmega ==

If using SwitchyOmega, use:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1074
</pre>

Then open:

<pre>
http://169.230.26.173:8501
</pre>

If the SOCKS proxy is not running, start it from a Mac terminal:

<pre>
ssh -f -N -D 1074 USER@epsilon.compbio.ucsf.edu
</pre>

When finished, switch SwitchyOmega back to Direct.

== Where The Website Lives ==

Project directory on C7:

<pre>
~/openadmet/admet-builder
</pre>

Important files:

<pre>
app.py
static/index.html
static/styles.css
static/app.js
.gitignore
</pre>

== Repository ==

GitLab repository:

<pre>
https://gitlab.docking.org/USERNAME/admet-builder
</pre>

Clone using HTTPS:

<pre>
git clone https://gitlab.docking.org/USERNAME/admet-builder.git
cd admet-builder
</pre>

Clone using SSH:

<pre>
git clone git@gitlab.docking.org:USERNAME/admet-builder.git
cd admet-builder
</pre>

== Environment ==

The backend uses the OpenADMET conda environment:

<pre>
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
</pre>

Python dependencies include:

* Flask
* pandas
* RDKit
* OpenADMET models package

The OpenADMET model directory is expected at:

<pre>
~/openadmet/permeability-logd-ppb-chemeleon-baseline/anvil_training
</pre>

== How to Start Backend ==

On C7:

<pre>
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
cd ~/openadmet/admet-builder
python app.py
</pre>

The backend runs on:

<pre>
http://0.0.0.0:8501
</pre>

The browser URL is:

<pre>
http://169.230.26.173:8501
</pre>

Test from C7:

<pre>
curl http://127.0.0.1:8501
</pre>

== How to Keep Backend Running ==

Use screen:

<pre>
screen -S admet-builder
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
cd ~/openadmet/admet-builder
python app.py
</pre>

Detach:

<pre>
Ctrl-A
D
</pre>

Reconnect:

<pre>
screen -r admet-builder
</pre>

List screens:

<pre>
screen -ls
</pre>

Stop backend:

<pre>
screen -r admet-builder
Ctrl-C
exit
</pre>

== Test Input ==

Example SMILES input:

<pre>
CCO
c1ccccc1
CC(=O)Oc1ccccc1C(=O)O
</pre>

Larger test molecule:

<pre>
CC(C)Cc1ccc(cc1)[C@@H](C)C(=O)O
</pre>

== Test API With curl ==

Test the API from C7:

<pre>
curl -X POST http://127.0.0.1:8501/predict-smiles \
-H "Content-Type: application/json" \
-d '{"smiles":["CCO","c1ccccc1","CC(=O)Oc1ccccc1C(=O)O"]}'
</pre>

== Current API Endpoint ==

Main endpoint:

<pre>
POST /predict-smiles
</pre>

Example JSON request:

<pre>
{
"smiles": [
"CCO",
"c1ccccc1",
"CC(=O)Oc1ccccc1C(=O)O"
]
}
</pre>

Example response contains:

<pre>
{
"csv": "...",
"rows": [],
"columns": []
}
</pre>

The frontend uses this response to display the results table and automatically download the CSV.

== How It Works ==

ADMET Builder has three major parts:

{| class="wikitable"
! Layer
! Technology
! Purpose
|-
| Frontend
| HTML, CSS, JavaScript
| User interface, SMILES input, results table, and structure image display
|-
| Backend API
| Flask
| Receives SMILES, runs predictions, and returns results
|-
| Prediction Engine
| OpenADMET
| Generates ADMET predictions from molecular input
|}

Backend flow:

# Receives SMILES strings from the website.
# Converts the SMILES into a temporary CSV file.
# Runs the OpenADMET command-line prediction tool.
# Reads the OpenADMET output CSV.
# Uses RDKit to calculate molecular formulas.
# Uses RDKit to generate 2D molecular structure images.
# Sends results back to the web interface as JSON.
# Provides the same results as a downloadable CSV file.

== Modularity ==

ADMET Builder is modular by design. The frontend, backend, and prediction engine are separated so each part can be reused or replaced.

This means:

* The frontend can be redesigned without changing the model logic.
* The Flask backend can support new endpoints.
* Additional OpenADMET models can be added later.
* Other chemistry tools can be wrapped using the same backend pattern.
* The results table can be adapted for different prediction outputs.
* The SMILES-to-structure display can be reused in other cheminformatics apps.
* The app can serve as a template for future scientific web interfaces.

Because of this structure, ADMET Builder can be used both as a working lab tool and as a starting point for other modular research software.

== Output ==

The output table includes:

{| class="wikitable"
! Column
! Meaning
|-
| Molecule
| Molecular formula calculated from the SMILES string
|-
| SMILES
| Input molecule string
|-
| Structure Image
| RDKit-generated 2D molecular structure
|-
| logD
| Predicted distribution coefficient
|-
| Caco-2 A to B
| Predicted apical-to-basolateral permeability
|-
| Caco-2 B to A
| Predicted basolateral-to-apical permeability
|-
| Mouse PPB
| Predicted mouse plasma protein binding
|-
| Human PPB
| Predicted human plasma protein binding
|}

The CSV download contains the same prediction values in a machine-readable format.

== Troubleshooting ==

=== Site Cannot Be Reached ===

Check that:

* Backend is running on C7.
* The app is running on port 8501.
* SwitchyOmega is set to SOCKS5 localhost port 1074.
* The browser is using:

<pre>
http://169.230.26.173:8501
</pre>

=== SwitchyOmega Proxy Error ===

If Chrome says the proxy failed, the SOCKS proxy may not be running.

Start it from a Mac terminal:

<pre>
ssh -f -N -D 1074 USER@epsilon.compbio.ucsf.edu
</pre>

SwitchyOmega should be:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1074
</pre>

=== Port Already In Use ===

Check port 8501:

<pre>
ss -ltnp | grep 8501
</pre>

Only kill processes owned by you:

<pre>
kill PID_NUMBER
</pre>

=== Missing pandas or Flask ===

This usually means the conda environment is not active.

Run:

<pre>
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
</pre>

=== RDKit Image Error ===

Make sure the app is running inside the `openadmet-models` environment, which includes RDKit.

Test RDKit:

<pre>
python -c "from rdkit import Chem; print('rdkit works')"
</pre>

== Notes ==

ADMET Builder is a research tool. Its predictions are intended for screening, comparison, prioritization, and exploration.

Results should not be treated as experimental measurements.

For office-wide use without SSH/SOCKS tunnels, ADMET Builder should eventually be placed behind an internal hostname or proxy.

== Attribution ==

Created by Benjamin "Ben" Romero (Undergrad Northwestern University '29), Summer 2026. 
Developed in the Irwin Lab at UCSF. 
Released as part of an open-source UCSF research tool; please credit the creator and lab when using or adapting this work.

File:Results.png

2026-07-07T00:23:43Z

Bromero:

Results

File:ADMET builder webpage.png

2026-07-07T00:22:09Z

Bromero:

interface

ADMET Builder

2026-07-07T00:18:27Z

Bromero:

= ADMET Builder (OpenADMET) =

== Introduction ==

As of 7/6/26, '''ADMET Builder''' is an internal Irwin Lab web tool for submitting one or more compounds in SMILES format and receiving OpenADMET prediction results.

The current backend runs on C7 using the `openadmet-models` conda environment.

ADMET Builder returns:

* Molecular formula
* SMILES string
* RDKit-generated 2D structure image
* logD
* Caco-2 A to B permeability
* Caco-2 B to A permeability
* Mouse plasma protein binding
* Human plasma protein binding
* Downloadable CSV output

Created by Benjamin "Ben" Romero (Undergrad Northwestern University '29), Summer 2026. 
Developed in the Irwin Lab at UCSF.

== How to Login ==

Log into C7:

<pre>
ssh USER@epsilon.compbio.ucsf.edu
</pre>

Confirm location:

<pre>
hostname
pwd
</pre>

== How to Open Website With SwitchyOmega ==

If using SwitchyOmega, use:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1074
</pre>

Then open:

<pre>
http://169.230.26.173:8501
</pre>

If the SOCKS proxy is not running, start it from a Mac terminal:

<pre>
ssh -f -N -D 1074 USER@epsilon.compbio.ucsf.edu
</pre>

When finished, switch SwitchyOmega back to Direct.

== Where The Website Lives ==

Project directory on C7:

<pre>
~/openadmet/admet-builder
</pre>

Important files:

<pre>
app.py
static/index.html
static/styles.css
static/app.js
.gitignore
</pre>

== Repository ==

GitLab repository:

<pre>
https://gitlab.docking.org/USERNAME/admet-builder
</pre>

Clone using HTTPS:

<pre>
git clone https://gitlab.docking.org/USERNAME/admet-builder.git
cd admet-builder
</pre>

Clone using SSH:

<pre>
git clone git@gitlab.docking.org:USERNAME/admet-builder.git
cd admet-builder
</pre>

== Environment ==

The backend uses the OpenADMET conda environment:

<pre>
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
</pre>

Python dependencies include:

* Flask
* pandas
* RDKit
* OpenADMET models package

The OpenADMET model directory is expected at:

<pre>
~/openadmet/permeability-logd-ppb-chemeleon-baseline/anvil_training
</pre>

== How to Start Backend ==

On C7:

<pre>
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
cd ~/openadmet/admet-builder
python app.py
</pre>

The backend runs on:

<pre>
http://0.0.0.0:8501
</pre>

The browser URL is:

<pre>
http://169.230.26.173:8501
</pre>

Test from C7:

<pre>
curl http://127.0.0.1:8501
</pre>

== How to Keep Backend Running ==

Use screen:

<pre>
screen -S admet-builder
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
cd ~/openadmet/admet-builder
python app.py
</pre>

Detach:

<pre>
Ctrl-A
D
</pre>

Reconnect:

<pre>
screen -r admet-builder
</pre>

List screens:

<pre>
screen -ls
</pre>

Stop backend:

<pre>
screen -r admet-builder
Ctrl-C
exit
</pre>

== Test Input ==

Example SMILES input:

<pre>
CCO
c1ccccc1
CC(=O)Oc1ccccc1C(=O)O
</pre>

Larger test molecule:

<pre>
CC(C)Cc1ccc(cc1)[C@@H](C)C(=O)O
</pre>

== Test API With curl ==

Test the API from C7:

<pre>
curl -X POST http://127.0.0.1:8501/predict-smiles \
-H "Content-Type: application/json" \
-d '{"smiles":["CCO","c1ccccc1","CC(=O)Oc1ccccc1C(=O)O"]}'
</pre>

== Current API Endpoint ==

Main endpoint:

<pre>
POST /predict-smiles
</pre>

Example JSON request:

<pre>
{
"smiles": [
"CCO",
"c1ccccc1",
"CC(=O)Oc1ccccc1C(=O)O"
]
}
</pre>

Example response contains:

<pre>
{
"csv": "...",
"rows": [],
"columns": []
}
</pre>

The frontend uses this response to display the results table and automatically download the CSV.

== How It Works ==

ADMET Builder has three major parts:

{| class="wikitable"
! Layer
! Technology
! Purpose
|-
| Frontend
| HTML, CSS, JavaScript
| User interface, SMILES input, results table, and structure image display
|-
| Backend API
| Flask
| Receives SMILES, runs predictions, and returns results
|-
| Prediction Engine
| OpenADMET
| Generates ADMET predictions from molecular input
|}

Backend flow:

# Receives SMILES strings from the website.
# Converts the SMILES into a temporary CSV file.
# Runs the OpenADMET command-line prediction tool.
# Reads the OpenADMET output CSV.
# Uses RDKit to calculate molecular formulas.
# Uses RDKit to generate 2D molecular structure images.
# Sends results back to the web interface as JSON.
# Provides the same results as a downloadable CSV file.

== Modularity ==

ADMET Builder is modular by design. The frontend, backend, and prediction engine are separated so each part can be reused or replaced.

This means:

* The frontend can be redesigned without changing the model logic.
* The Flask backend can support new endpoints.
* Additional OpenADMET models can be added later.
* Other chemistry tools can be wrapped using the same backend pattern.
* The results table can be adapted for different prediction outputs.
* The SMILES-to-structure display can be reused in other cheminformatics apps.
* The app can serve as a template for future scientific web interfaces.

Because of this structure, ADMET Builder can be used both as a working lab tool and as a starting point for other modular research software.

== Output ==

The output table includes:

{| class="wikitable"
! Column
! Meaning
|-
| Molecule
| Molecular formula calculated from the SMILES string
|-
| SMILES
| Input molecule string
|-
| Structure Image
| RDKit-generated 2D molecular structure
|-
| logD
| Predicted distribution coefficient
|-
| Caco-2 A to B
| Predicted apical-to-basolateral permeability
|-
| Caco-2 B to A
| Predicted basolateral-to-apical permeability
|-
| Mouse PPB
| Predicted mouse plasma protein binding
|-
| Human PPB
| Predicted human plasma protein binding
|}

The CSV download contains the same prediction values in a machine-readable format.

== Troubleshooting ==

=== Site Cannot Be Reached ===

Check that:

* Backend is running on C7.
* The app is running on port 8501.
* SwitchyOmega is set to SOCKS5 localhost port 1074.
* The browser is using:

<pre>
http://169.230.26.173:8501
</pre>

=== SwitchyOmega Proxy Error ===

If Chrome says the proxy failed, the SOCKS proxy may not be running.

Start it from a Mac terminal:

<pre>
ssh -f -N -D 1074 USER@epsilon.compbio.ucsf.edu
</pre>

SwitchyOmega should be:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1074
</pre>

=== Port Already In Use ===

Check port 8501:

<pre>
ss -ltnp | grep 8501
</pre>

Only kill processes owned by you:

<pre>
kill PID_NUMBER
</pre>

=== Missing pandas or Flask ===

This usually means the conda environment is not active.

Run:

<pre>
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
</pre>

=== RDKit Image Error ===

Make sure the app is running inside the `openadmet-models` environment, which includes RDKit.

Test RDKit:

<pre>
python -c "from rdkit import Chem; print('rdkit works')"
</pre>

== Notes ==

ADMET Builder is a research tool. Its predictions are intended for screening, comparison, prioritization, and exploration.

Results should not be treated as experimental measurements.

For office-wide use without SSH/SOCKS tunnels, ADMET Builder should eventually be placed behind an internal hostname or proxy.

== Attribution ==

Created by Benjamin "Ben" Romero (Undergrad Northwestern University '29), Summer 2026. 
Developed in the Irwin Lab at UCSF. 
Released as part of an open-source UCSF research tool; please credit the creator and lab when using or adapting this work.

ADMET Builder

2026-07-07T00:13:48Z

Bromero: ADMET Builder is a lightweight very modular web interface for running OpenADMET predictions from typed SMILES strings. It was created to make ADMET prediction easier to use for chemists, students, and researchers who may not want to run command-line tools directly.

# ADMET Builder

ADMET Builder is a lightweight web interface for running OpenADMET predictions from typed SMILES strings. It was created to make ADMET prediction easier to use for chemists, students, and researchers who may not want to run command-line tools directly.

---

## What It Does

ADMET Builder lets a user paste one or more SMILES strings into a web interface and run ADMET predictions.

The app returns:

- A clean results table in the browser
- A downloadable CSV file
- Molecular formulas calculated from SMILES
- RDKit-generated 2D structure images
- Click-to-enlarge structure viewing

The current OpenADMET model predicts:

- logD
- Caco-2 A to B permeability
- Caco-2 B to A permeability
- Mouse plasma protein binding
- Human plasma protein binding

---

## How It Works

ADMET Builder has three main parts:

| Layer | Technology | Purpose |
|---|---|---|
| Frontend | HTML, CSS, JavaScript | User interface, SMILES input, results table, structure display |
| Backend API | Flask | Receives SMILES, runs predictions, returns results |
| Prediction Engine | OpenADMET | Generates ADMET predictions from molecular input |

The browser sends SMILES strings to the backend using:

```text
POST /predict-smiles
```

The Flask backend then:

1. Receives the SMILES strings.
2. Converts them into a temporary CSV file.
3. Runs the OpenADMET command-line prediction tool.
4. Reads the prediction output.
5. Generates molecular formulas and structure images using RDKit.
6. Sends results back to the web interface as JSON.
7. Provides the same results as a downloadable CSV file.

---

## Why It Is Modular

ADMET Builder is intentionally modular. The frontend, backend, and prediction engine are separated so each part can be changed or reused.

This means:

- The frontend can be redesigned without changing the model logic.
- The Flask backend can support new endpoints.
- Additional OpenADMET models can be added later.
- Other chemistry tools can be wrapped using the same backend pattern.
- The results table can be adapted for different prediction outputs.
- The SMILES-to-structure display can be reused in other cheminformatics apps.
- The app can serve as a template for future scientific web interfaces.

Because of this structure, ADMET Builder can be used not only as a lab tool, but also as a starting point for other modular research software.

---

## Getting The Code

Clone the repository using HTTPS:

```bash
git clone https://gitlab.docking.org/bromero/admet-builder.git
cd admet-builder
```

Or clone using SSH:

```bash
git clone git@gitlab.docking.org:bromero/admet-builder.git
cd admet-builder
```

---

## Requirements

ADMET Builder expects OpenADMET to already be installed in a working conda environment.

The C7 setup uses:

```bash
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
```

Python dependencies include:

- Flask
- pandas
- RDKit
- OpenADMET models package

The app also expects the OpenADMET model directory to be available at:

```text
~/openadmet/permeability-logd-ppb-chemeleon-baseline/anvil_training
```

---

## Running The App

From the repository folder:

```bash
cd ~/openadmet/admet-builder
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
python app.py
```

The app runs on:

```text
http://169.230.26.173:8501
```

---

## Running In Screen

For persistent use on C7, run ADMET Builder inside `screen`.

Start a screen session:

```bash
screen -S admet-builder
```

Inside screen, run:

```bash
module load anaconda3/2025.06.0
source "$(conda info --base)/etc/profile.d/conda.sh"
conda activate openadmet-models
cd ~/openadmet/admet-builder
python app.py
```

Detach from screen while keeping the app running:

```text
Ctrl+A
D
```

Reconnect later:

```bash
screen -r admet-builder
```

List running screen sessions:

```bash
screen -ls
```

Stop the app from inside screen:

```text
Ctrl+C
```

---

## Using The Website

1. Open ADMET Builder in the browser.
2. Paste one SMILES string per line.
3. Click `RUN ADMET`.
4. View the results in the table.
5. A CSV file downloads automatically.
6. Click a molecular structure image to enlarge it.

Example input:

```text
CCO
c1ccccc1
CC(=O)Oc1ccccc1C(=O)O
```

---

## Output

The output table includes:

| Column | Meaning |
|---|---|
| Molecule | Molecular formula calculated from the SMILES string |
| SMILES | Input molecule string |
| Structure Image | RDKit-generated 2D molecular structure |
| logD | Predicted distribution coefficient |
| Caco-2 A to B | Predicted apical-to-basolateral permeability |
| Caco-2 B to A | Predicted basolateral-to-apical permeability |
| Mouse PPB | Predicted mouse plasma protein binding |
| Human PPB | Predicted human plasma protein binding |

The CSV download contains the same prediction values in a machine-readable format.

---

## Access Through SwitchyOmega

If using SwitchyOmega, the proxy should be:

```text
SOCKS5
localhost
1074
```

The website itself is opened at:

```text
http://169.230.26.173:8501
```

The ports mean different things:

| Port | Purpose |
|---|---|
| 1074 | Local SOCKS5 proxy used by SwitchyOmega |
| 8501 | ADMET Builder web app running on C7 |

If the SOCKS proxy is not running, start it from a Mac terminal:

```bash
ssh -f -N -D 1074 bromero@epsilon.compbio.ucsf.edu
```

---

## Repository Structure

```text
admet-builder/
├── app.py
├── static/
│ ├── index.html
│ ├── styles.css
│ └── app.js
└── .gitignore
```

### `app.py`

The Flask backend. It receives SMILES input, runs OpenADMET, generates formulas and structure images, and returns results.

### `static/index.html`

The main web page structure.

### `static/styles.css`

The UCSF-style visual design and table layout.

### `static/app.js`

The browser-side logic. It sends SMILES to the backend, renders the results table, downloads CSV output, and handles structure image enlargement.

---

## Current API Endpoint

```text
POST /predict-smiles
```

Example JSON request:

```json
{
"smiles": [
"CCO",
"c1ccccc1",
"CC(=O)Oc1ccccc1C(=O)O"
]
}
```

Example response includes:

```json
{
"csv": "...",
"rows": [],
"columns": []
}
```

The frontend uses this response to display results and download the CSV.

---

## Notes

ADMET Builder is a research tool. Its predictions are intended for screening, comparison, prioritization, and exploration.

Results should not be treated as experimental measurements.

---

## Attribution

Created by Benjamin "Ben" Romero (Undergrad Northwestern University '29), Summer 2026.
Developed in the Irwin Lab at UCSF.
Released as part of an open-source UCSF research tool; please credit the creator and lab when using or adapting this work.

Retro-Blockblaster

2026-06-29T20:49:04Z

Bromero: /* Environment */

= Retro-Blockbalster (BenZinc26) =

== Introduction ==

As of 6/29/26, Retro-Blockbalster is an internal Irwin Lab web tool for submitting a compound in SMILES format and receiving retro/analoging reaction results.

The current backend runs on Cluster 2 using epyc.

== How to Login ==

=== Off Site ===

Start the portal SSH/SOCKS tunnel from your laptop:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 USER@portal3.ucsf.bkslab.org
</pre>

Leave this terminal open.

In a second terminal, log into gimel:

<pre>
ssh -p 2222 USER@localhost
</pre>

Then log into epyc:

<pre>
ssh epyc
</pre>

Confirm location:

<pre>
hostname
</pre>

=== On Site ===

If on the UCSF/lab network, direct login may work:

<pre>
ssh -o HostKeyAlgorithms=+ssh-rsa bromero@gimel.compbio.ucsf.edu
ssh epyc
</pre>

== How to Open Website (MUST USE) With SwitchyOmega ==

Start the portal SSH/SOCKS tunnel:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 USER@portal3.ucsf.bkslab.org
</pre>

In Chrome, set SwitchyOmega to:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1080
</pre>

Then open:

<pre>
http://epyc:8001
</pre>

When finished, switch SwitchyOmega back to Direct.

== Where The Website Lives ==

Project directory on epyc:

<pre>
~/Initial-BenZinc26-website
</pre>

Important files:

<pre>
index.html
run_job.py
backend/server_old.py
.env
</pre>

== .env Setup ==

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=...@...com
SMTP_PASSWORD=....(GOOGLE_APP_PASSWORD)
FROM_EMAIL=...@....com
</pre>

== How to Start Backend ==

On epyc:

<pre>
cd ~/Initial-BenZinc26-website
python3 backend/server_old.py
</pre>

The backend currently runs on:

<pre>
http://0.0.0.0:8001
</pre>

Test from epyc:

<pre>
curl http://127.0.0.1:8001
</pre>

== How to Keep Backend Running ==

Use screen:

<pre>
cd ~/Initial-BenZinc26-website
screen -S benzinc26
python3 backend/server_old.py
</pre>

Detach:

<pre>
Ctrl-A
D
</pre>

Reconnect:

<pre>
screen -r benzinc26
</pre>

List screens:

<pre>
screen -ls
</pre>

Stop backend:

<pre>
screen -r benzinc26
Ctrl-C
exit
</pre>

== Test Input ==

A test molecule that returns reaction rows:

<pre>
CN(C)C(=O)NC1=CC=CC=C1
</pre>

Test with curl from epyc:

<pre>
curl -X POST http://127.0.0.1:8001/hello-job \
-H "Content-Type: application/json" \
-d '{"user_input":"CN(C)C(=O)NC1=CC=CC=C1 urea_test","email":"your_email@gmail.com"}'
</pre>

== Environment ==

The backend needs a `.env` file in the project root.

Do not commit `.env` to GitHub.

Example:

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=retro-blockbalster@gmail.com
SMTP_PASSWORD=abcdefghijklmnop
FROM_EMAIL=retro-blockbalster@gmail.com
BASE_URL=http://epyc:8001
</pre>

== RDKit Environment ==

The retro reaction script uses RDKit through:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python
</pre>

Test on epyc:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python -c "from rdkit import Chem; print('rdkit works')"
</pre>

RDKit works on epyc. RDKit may fail on gimel.

== Final Result ==

Web interface

[[File:Screenshot 2026-06-29 at 1.27.35 PM.png|thumb]]

Finished job

[[File:FinalJobEx.png|thumb]]

== Troubleshooting ==

=== Site Cannot Be Reached ===

Check that:

* Backend is running on epyc.
* The SSH/SOCKS tunnel is running.
* SwitchyOmega is set to SOCKS5 localhost port 1080.
* The browser is using http://epyc:8001.

=== Port Already In Use ===

Check port 8001:

<pre>
ss -ltnp | grep 8001
</pre>

Only kill processes owned by you:

<pre>
kill PID_NUMBER
</pre>

=== Email Not Sending ===

Check that:

* `.env` exists.
* Gmail app password is correct.
* SMTP_USER and FROM_EMAIL are the same account.
* The app password belongs to that same account.

== Notes ==

For office-wide use without SSH/SOCKS tunnels, Retro-Blockblaster will eventually be placed behind an internal hostname or proxy.

Retro-Blockblaster

2026-06-29T20:47:49Z

Bromero: /* Environment */

= Retro-Blockbalster (BenZinc26) =

== Introduction ==

As of 6/29/26, Retro-Blockbalster is an internal Irwin Lab web tool for submitting a compound in SMILES format and receiving retro/analoging reaction results.

The current backend runs on Cluster 2 using epyc.

== How to Login ==

=== Off Site ===

Start the portal SSH/SOCKS tunnel from your laptop:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 USER@portal3.ucsf.bkslab.org
</pre>

Leave this terminal open.

In a second terminal, log into gimel:

<pre>
ssh -p 2222 USER@localhost
</pre>

Then log into epyc:

<pre>
ssh epyc
</pre>

Confirm location:

<pre>
hostname
</pre>

=== On Site ===

If on the UCSF/lab network, direct login may work:

<pre>
ssh -o HostKeyAlgorithms=+ssh-rsa bromero@gimel.compbio.ucsf.edu
ssh epyc
</pre>

== How to Open Website (MUST USE) With SwitchyOmega ==

Start the portal SSH/SOCKS tunnel:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 USER@portal3.ucsf.bkslab.org
</pre>

In Chrome, set SwitchyOmega to:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1080
</pre>

Then open:

<pre>
http://epyc:8001
</pre>

When finished, switch SwitchyOmega back to Direct.

== Where The Website Lives ==

Project directory on epyc:

<pre>
~/Initial-BenZinc26-website
</pre>

Important files:

<pre>
index.html
run_job.py
backend/server_old.py
.env
</pre>

== .env Setup ==

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=...@...com
SMTP_PASSWORD=....(GOOGLE_APP_PASSWORD)
FROM_EMAIL=...@....com
</pre>

== How to Start Backend ==

On epyc:

<pre>
cd ~/Initial-BenZinc26-website
python3 backend/server_old.py
</pre>

The backend currently runs on:

<pre>
http://0.0.0.0:8001
</pre>

Test from epyc:

<pre>
curl http://127.0.0.1:8001
</pre>

== How to Keep Backend Running ==

Use screen:

<pre>
cd ~/Initial-BenZinc26-website
screen -S benzinc26
python3 backend/server_old.py
</pre>

Detach:

<pre>
Ctrl-A
D
</pre>

Reconnect:

<pre>
screen -r benzinc26
</pre>

List screens:

<pre>
screen -ls
</pre>

Stop backend:

<pre>
screen -r benzinc26
Ctrl-C
exit
</pre>

== Test Input ==

A test molecule that returns reaction rows:

<pre>
CN(C)C(=O)NC1=CC=CC=C1
</pre>

Test with curl from epyc:

<pre>
curl -X POST http://127.0.0.1:8001/hello-job \
-H "Content-Type: application/json" \
-d '{"user_input":"CN(C)C(=O)NC1=CC=CC=C1 urea_test","email":"your_email@gmail.com"}'
</pre>

== Environment ==

The backend needs a `.env` file in the project root.

Do not commit `.env` to GitHub.

Example:

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=retro-blockbalster@gmail.com
SMTP_PASSWORD=GOOGLE_APP_PASSWORD
FROM_EMAIL=retro-blockbalster@gmail.com
BASE_URL=http://epyc:8001
</pre>

== RDKit Environment ==

The retro reaction script uses RDKit through:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python
</pre>

Test on epyc:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python -c "from rdkit import Chem; print('rdkit works')"
</pre>

RDKit works on epyc. RDKit may fail on gimel.

== Final Result ==

Web interface

[[File:Screenshot 2026-06-29 at 1.27.35 PM.png|thumb]]

Finished job

[[File:FinalJobEx.png|thumb]]

== Troubleshooting ==

=== Site Cannot Be Reached ===

Check that:

* Backend is running on epyc.
* The SSH/SOCKS tunnel is running.
* SwitchyOmega is set to SOCKS5 localhost port 1080.
* The browser is using http://epyc:8001.

=== Port Already In Use ===

Check port 8001:

<pre>
ss -ltnp | grep 8001
</pre>

Only kill processes owned by you:

<pre>
kill PID_NUMBER
</pre>

=== Email Not Sending ===

Check that:

* `.env` exists.
* Gmail app password is correct.
* SMTP_USER and FROM_EMAIL are the same account.
* The app password belongs to that same account.

== Notes ==

For office-wide use without SSH/SOCKS tunnels, Retro-Blockblaster will eventually be placed behind an internal hostname or proxy.

Retro-Blockblaster

2026-06-29T20:46:56Z

Bromero: /* How to Open Website (MUST USE) With SwitchyOmega */

= Retro-Blockbalster (BenZinc26) =

== Introduction ==

As of 6/29/26, Retro-Blockbalster is an internal Irwin Lab web tool for submitting a compound in SMILES format and receiving retro/analoging reaction results.

The current backend runs on Cluster 2 using epyc.

== How to Login ==

=== Off Site ===

Start the portal SSH/SOCKS tunnel from your laptop:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 USER@portal3.ucsf.bkslab.org
</pre>

Leave this terminal open.

In a second terminal, log into gimel:

<pre>
ssh -p 2222 USER@localhost
</pre>

Then log into epyc:

<pre>
ssh epyc
</pre>

Confirm location:

<pre>
hostname
</pre>

=== On Site ===

If on the UCSF/lab network, direct login may work:

<pre>
ssh -o HostKeyAlgorithms=+ssh-rsa bromero@gimel.compbio.ucsf.edu
ssh epyc
</pre>

== How to Open Website (MUST USE) With SwitchyOmega ==

Start the portal SSH/SOCKS tunnel:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 USER@portal3.ucsf.bkslab.org
</pre>

In Chrome, set SwitchyOmega to:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1080
</pre>

Then open:

<pre>
http://epyc:8001
</pre>

When finished, switch SwitchyOmega back to Direct.

== Where The Website Lives ==

Project directory on epyc:

<pre>
~/Initial-BenZinc26-website
</pre>

Important files:

<pre>
index.html
run_job.py
backend/server_old.py
.env
</pre>

== .env Setup ==

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=...@...com
SMTP_PASSWORD=....(GOOGLE_APP_PASSWORD)
FROM_EMAIL=...@....com
</pre>

== How to Start Backend ==

On epyc:

<pre>
cd ~/Initial-BenZinc26-website
python3 backend/server_old.py
</pre>

The backend currently runs on:

<pre>
http://0.0.0.0:8001
</pre>

Test from epyc:

<pre>
curl http://127.0.0.1:8001
</pre>

== How to Keep Backend Running ==

Use screen:

<pre>
cd ~/Initial-BenZinc26-website
screen -S benzinc26
python3 backend/server_old.py
</pre>

Detach:

<pre>
Ctrl-A
D
</pre>

Reconnect:

<pre>
screen -r benzinc26
</pre>

List screens:

<pre>
screen -ls
</pre>

Stop backend:

<pre>
screen -r benzinc26
Ctrl-C
exit
</pre>

== Test Input ==

A test molecule that returns reaction rows:

<pre>
CN(C)C(=O)NC1=CC=CC=C1
</pre>

Test with curl from epyc:

<pre>
curl -X POST http://127.0.0.1:8001/hello-job \
-H "Content-Type: application/json" \
-d '{"user_input":"CN(C)C(=O)NC1=CC=CC=C1 urea_test","email":"your_email@gmail.com"}'
</pre>

== Environment ==

The backend needs a `.env` file in the project root.

Do not commit `.env` to GitHub.

Example:

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=benzinc26@gmail.com
SMTP_PASSWORD=GOOGLE_APP_PASSWORD
FROM_EMAIL=benzinc26@gmail.com
BASE_URL=http://epyc:8001
</pre>

== RDKit Environment ==

The retro reaction script uses RDKit through:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python
</pre>

Test on epyc:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python -c "from rdkit import Chem; print('rdkit works')"
</pre>

RDKit works on epyc. RDKit may fail on gimel.

== Final Result ==

Web interface

[[File:Screenshot 2026-06-29 at 1.27.35 PM.png|thumb]]

Finished job

[[File:FinalJobEx.png|thumb]]

== Troubleshooting ==

=== Site Cannot Be Reached ===

Check that:

* Backend is running on epyc.
* The SSH/SOCKS tunnel is running.
* SwitchyOmega is set to SOCKS5 localhost port 1080.
* The browser is using http://epyc:8001.

=== Port Already In Use ===

Check port 8001:

<pre>
ss -ltnp | grep 8001
</pre>

Only kill processes owned by you:

<pre>
kill PID_NUMBER
</pre>

=== Email Not Sending ===

Check that:

* `.env` exists.
* Gmail app password is correct.
* SMTP_USER and FROM_EMAIL are the same account.
* The app password belongs to that same account.

== Notes ==

For office-wide use without SSH/SOCKS tunnels, Retro-Blockblaster will eventually be placed behind an internal hostname or proxy.

Retro-Blockblaster

2026-06-29T20:46:38Z

Bromero: /* Off Site */

= Retro-Blockbalster (BenZinc26) =

== Introduction ==

As of 6/29/26, Retro-Blockbalster is an internal Irwin Lab web tool for submitting a compound in SMILES format and receiving retro/analoging reaction results.

The current backend runs on Cluster 2 using epyc.

== How to Login ==

=== Off Site ===

Start the portal SSH/SOCKS tunnel from your laptop:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 USER@portal3.ucsf.bkslab.org
</pre>

Leave this terminal open.

In a second terminal, log into gimel:

<pre>
ssh -p 2222 USER@localhost
</pre>

Then log into epyc:

<pre>
ssh epyc
</pre>

Confirm location:

<pre>
hostname
</pre>

=== On Site ===

If on the UCSF/lab network, direct login may work:

<pre>
ssh -o HostKeyAlgorithms=+ssh-rsa bromero@gimel.compbio.ucsf.edu
ssh epyc
</pre>

== How to Open Website (MUST USE) With SwitchyOmega ==

Start the portal SSH/SOCKS tunnel:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 bromero@portal3.ucsf.bkslab.org
</pre>

In Chrome, set SwitchyOmega to:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1080
</pre>

Then open:

<pre>
http://epyc:8001
</pre>

When finished, switch SwitchyOmega back to Direct.

== Where The Website Lives ==

Project directory on epyc:

<pre>
~/Initial-BenZinc26-website
</pre>

Important files:

<pre>
index.html
run_job.py
backend/server_old.py
.env
</pre>

== .env Setup ==

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=...@...com
SMTP_PASSWORD=....(GOOGLE_APP_PASSWORD)
FROM_EMAIL=...@....com
</pre>

== How to Start Backend ==

On epyc:

<pre>
cd ~/Initial-BenZinc26-website
python3 backend/server_old.py
</pre>

The backend currently runs on:

<pre>
http://0.0.0.0:8001
</pre>

Test from epyc:

<pre>
curl http://127.0.0.1:8001
</pre>

== How to Keep Backend Running ==

Use screen:

<pre>
cd ~/Initial-BenZinc26-website
screen -S benzinc26
python3 backend/server_old.py
</pre>

Detach:

<pre>
Ctrl-A
D
</pre>

Reconnect:

<pre>
screen -r benzinc26
</pre>

List screens:

<pre>
screen -ls
</pre>

Stop backend:

<pre>
screen -r benzinc26
Ctrl-C
exit
</pre>

== Test Input ==

A test molecule that returns reaction rows:

<pre>
CN(C)C(=O)NC1=CC=CC=C1
</pre>

Test with curl from epyc:

<pre>
curl -X POST http://127.0.0.1:8001/hello-job \
-H "Content-Type: application/json" \
-d '{"user_input":"CN(C)C(=O)NC1=CC=CC=C1 urea_test","email":"your_email@gmail.com"}'
</pre>

== Environment ==

The backend needs a `.env` file in the project root.

Do not commit `.env` to GitHub.

Example:

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=benzinc26@gmail.com
SMTP_PASSWORD=GOOGLE_APP_PASSWORD
FROM_EMAIL=benzinc26@gmail.com
BASE_URL=http://epyc:8001
</pre>

== RDKit Environment ==

The retro reaction script uses RDKit through:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python
</pre>

Test on epyc:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python -c "from rdkit import Chem; print('rdkit works')"
</pre>

RDKit works on epyc. RDKit may fail on gimel.

== Final Result ==

Web interface

[[File:Screenshot 2026-06-29 at 1.27.35 PM.png|thumb]]

Finished job

[[File:FinalJobEx.png|thumb]]

== Troubleshooting ==

=== Site Cannot Be Reached ===

Check that:

* Backend is running on epyc.
* The SSH/SOCKS tunnel is running.
* SwitchyOmega is set to SOCKS5 localhost port 1080.
* The browser is using http://epyc:8001.

=== Port Already In Use ===

Check port 8001:

<pre>
ss -ltnp | grep 8001
</pre>

Only kill processes owned by you:

<pre>
kill PID_NUMBER
</pre>

=== Email Not Sending ===

Check that:

* `.env` exists.
* Gmail app password is correct.
* SMTP_USER and FROM_EMAIL are the same account.
* The app password belongs to that same account.

== Notes ==

For office-wide use without SSH/SOCKS tunnels, Retro-Blockblaster will eventually be placed behind an internal hostname or proxy.

Retro-Blockblaster

2026-06-29T20:39:33Z

Bromero: Retro-Blockblaster is an internal UCSF Irwin Lab web tool for submitting compounds in SMILES format and identifying possible Chemistry Commons retro/analoging reactions. The site runs on Cluster 2 using epyc, processes jobs with an RDKit-enabled environment, generates downloadable result files, and emails users when their job is complete.

= Retro-Blockbalster (BenZinc26) =

== Introduction ==

As of 6/29/26, Retro-Blockbalster is an internal Irwin Lab web tool for submitting a compound in SMILES format and receiving retro/analoging reaction results.

The current backend runs on Cluster 2 using epyc.

== How to Login ==

=== Off Site ===

Start the portal SSH/SOCKS tunnel from your laptop:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 bromero@portal3.ucsf.bkslab.org
</pre>

Leave this terminal open.

In a second terminal, log into gimel:

<pre>
ssh -p 2222 bromero@localhost
</pre>

Then log into epyc:

<pre>
ssh epyc
</pre>

Confirm location:

<pre>
hostname
</pre>

=== On Site ===

If on the UCSF/lab network, direct login may work:

<pre>
ssh -o HostKeyAlgorithms=+ssh-rsa bromero@gimel.compbio.ucsf.edu
ssh epyc
</pre>

== How to Open Website (MUST USE) With SwitchyOmega ==

Start the portal SSH/SOCKS tunnel:

<pre>
ssh -vNL localhost:2222:gimel:22 -D1080 bromero@portal3.ucsf.bkslab.org
</pre>

In Chrome, set SwitchyOmega to:

<pre>
Protocol: SOCKS5
Host: localhost
Port: 1080
</pre>

Then open:

<pre>
http://epyc:8001
</pre>

When finished, switch SwitchyOmega back to Direct.

== Where The Website Lives ==

Project directory on epyc:

<pre>
~/Initial-BenZinc26-website
</pre>

Important files:

<pre>
index.html
run_job.py
backend/server_old.py
.env
</pre>

== .env Setup ==

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=...@...com
SMTP_PASSWORD=....(GOOGLE_APP_PASSWORD)
FROM_EMAIL=...@....com
</pre>

== How to Start Backend ==

On epyc:

<pre>
cd ~/Initial-BenZinc26-website
python3 backend/server_old.py
</pre>

The backend currently runs on:

<pre>
http://0.0.0.0:8001
</pre>

Test from epyc:

<pre>
curl http://127.0.0.1:8001
</pre>

== How to Keep Backend Running ==

Use screen:

<pre>
cd ~/Initial-BenZinc26-website
screen -S benzinc26
python3 backend/server_old.py
</pre>

Detach:

<pre>
Ctrl-A
D
</pre>

Reconnect:

<pre>
screen -r benzinc26
</pre>

List screens:

<pre>
screen -ls
</pre>

Stop backend:

<pre>
screen -r benzinc26
Ctrl-C
exit
</pre>

== Test Input ==

A test molecule that returns reaction rows:

<pre>
CN(C)C(=O)NC1=CC=CC=C1
</pre>

Test with curl from epyc:

<pre>
curl -X POST http://127.0.0.1:8001/hello-job \
-H "Content-Type: application/json" \
-d '{"user_input":"CN(C)C(=O)NC1=CC=CC=C1 urea_test","email":"your_email@gmail.com"}'
</pre>

== Environment ==

The backend needs a `.env` file in the project root.

Do not commit `.env` to GitHub.

Example:

<pre>
SMTP_HOST=smtp.gmail.com
SMTP_PORT=587
SMTP_USER=benzinc26@gmail.com
SMTP_PASSWORD=GOOGLE_APP_PASSWORD
FROM_EMAIL=benzinc26@gmail.com
BASE_URL=http://epyc:8001
</pre>

== RDKit Environment ==

The retro reaction script uses RDKit through:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python
</pre>

Test on epyc:

<pre>
/nfs/exj/Fe/scripts/common_db/arthor-env/bin/python -c "from rdkit import Chem; print('rdkit works')"
</pre>

RDKit works on epyc. RDKit may fail on gimel.

== Final Result ==

Web interface

[[File:Screenshot 2026-06-29 at 1.27.35 PM.png|thumb]]

Finished job

[[File:FinalJobEx.png|thumb]]

== Troubleshooting ==

=== Site Cannot Be Reached ===

Check that:

* Backend is running on epyc.
* The SSH/SOCKS tunnel is running.
* SwitchyOmega is set to SOCKS5 localhost port 1080.
* The browser is using http://epyc:8001.

=== Port Already In Use ===

Check port 8001:

<pre>
ss -ltnp | grep 8001
</pre>

Only kill processes owned by you:

<pre>
kill PID_NUMBER
</pre>

=== Email Not Sending ===

Check that:

* `.env` exists.
* Gmail app password is correct.
* SMTP_USER and FROM_EMAIL are the same account.
* The app password belongs to that same account.

== Notes ==

For office-wide use without SSH/SOCKS tunnels, Retro-Blockblaster will eventually be placed behind an internal hostname or proxy.

File:FinalJobEx.png

2026-06-29T20:36:56Z

Bromero:

Complete Job

File:Screenshot 2026-06-29 at 1.27.35 PM.png

2026-06-29T20:28:40Z

Bromero:

Website Screen