added new categories (#1478)

* added new categories

* added try-except

* bugfix list to dictionary

* added output consistency field and blackened code

* Update columns_information.py

.github/scripts/airtableops.py

@@ -121,7 +121,7 @@ def __init__(self, model_id, config_json=None):
         self.model_id = model_id
 
     def read_information(self):
-        print ("Cannot read directly from README file. Using AirTable instead")
+        print("Cannot read directly from README file. Using AirTable instead")
         am = AirtableMetadata(model_id=self.model_id)
         bi = am.read_information()
         print(bi.as_dict())

.github/scripts/summarize_publication_with_llm.py

@@ -9,6 +9,7 @@
 import json
 from typing import List
 from pydantic import BaseModel
+
 # from dotenv import load_dotenv
 
 # load_dotenv()
@@ -187,6 +188,7 @@
 Reformat, if necessary, the following publication report:
 """
 
+
 class Summary(BaseModel):
     title: str
     authors: str
@@ -278,9 +280,10 @@ def download(self):
             return self.download_from_file_path()
         return None
 
+
 class PublicationSummarizer:
     def __init__(self, publication_pdf, output_file, format="json"):
-        self.tmp_dir = tempfile.mkdtemp(prefix="ersilia-") # TODO Unused
+        self.tmp_dir = tempfile.mkdtemp(prefix="ersilia-")  # TODO Unused
         self.model_name = MODEL_NAME
         self.publication_pdf = publication_pdf
         self.output_file = output_file
@@ -336,9 +339,11 @@ def postprocess_response(self, text_response, output_file):
             text_response = response.choices[0].message.content
             with open(output_file, "w") as f:
                 f.write(text_response)
-        
+
         else:
-            raise ValueError("Invalid format. Please choose either 'json' or 'markdown'.")
+            raise ValueError(
+                "Invalid format. Please choose either 'json' or 'markdown'."
+            )
 
     def run(self):
         text = self.extract_text_from_pdf(self.publication_pdf)
@@ -358,6 +363,7 @@ def serialize_json_to_md(json_file, md_file):
             else:
                 f.write(str(value) + "\n")
 
+
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description="Process arguments.")
     parser.add_argument(
@@ -394,7 +400,7 @@ def serialize_json_to_md(json_file, md_file):
         type=str,
         default="json",
         required=False,
-        help="File format in which to save the summary, defaults to JSON"
+        help="File format in which to save the summary, defaults to JSON",
     )
     args = parser.parse_args()
     model_id = args.model_id

README.md

@@ -20,77 +20,89 @@
 
 ## Project Description
 
-The [Ersilia Model Hub](https://ersilia.io) is a unified platform of pre-trained AI/ML models dedicated to 🦠 infectious and neglected disease research. Our mission is to offer an open-source, 🛠 low-code solution that provides seamless access to AI/ML models for 💊 drug discovery. Models housed in our hub come from two sources:
+The [Ersilia Model Hub](https://ersilia.io) is a unified platform of pre-trained AI/ML models for 🦠 infectious and neglected disease research. Our mission is to offer an open-source, 🛠 low-code solution that provides seamless access to AI/ML models for 💊 drug discovery. Models housed in our hub come from two sources:
 
-1. 📚 Published models from literature (with due third-party acknowledgement)
-2. 🛠 Custom models developed by the **Ersilia team** or our valued contributors.
+- Published models from literature (with due third-party acknowledgement)
+- Custom models developed by the Ersilia team or our valued contributors
 
-* Read more about the project in the [Ersilia Book](https://ersilia.gitbook.io/ersilia-book/)
-* Browse available models in the [Ersilia Model Hub](https://ersilia.io/model-hub/)
+You can read more about the project in the [Ersilia Book](https://ersilia.gitbook.io/ersilia-book/) and browse available models in the [Ersilia Model Hub](https://ersilia.io/model-hub/).
 
 ## Quick Start Guide
 
-Please check the package requirements in the [Installation Guide](https://ersilia.gitbook.io/ersilia-book/quick-start/installation). The next steps are a quickstart guide to installing Ersilia.
+Please check the package requirements in the [Installation Guide](https://ersilia.gitbook.io/ersilia-book/quick-start/installation). The following steps are a quick start guide to using Ersilia.
 
-1. Create a conda environment and activate it
+First, create a conda environment and activate it:
 
-    ```bash
-    conda create -n ersilia python=3.10
-    conda activate ersilia
-    ```
+```bash
+conda create -n ersilia python=3.10
+conda activate ersilia
+```
 
-1. Clone this repository and install with pip
+Then, clone this repository and install with `pip`:
 
-    ```bash
-    git clone https://github.com/ersilia-os/ersilia.git
-    cd ersilia
-    pip install -e .
-    ```
+```bash
+git clone https://github.com/ersilia-os/ersilia.git
+cd ersilia
+pip install -e .
+```
 
-1. Once the Ersilia Model Hub is installed, you can use the CLI to run predictions. First, select a model from the [Ersilia Model Hub](https://ersilia.io/model-hub/) and **fetch** it:
+Alternatively, you can directly install from PyPi:
+```bash
+pip install ersilia
+```
 
-    ```bash
-    ersilia fetch retrosynthetic-accessibility
-    ```
+Once the Ersilia package is installed, you can use the CLI to run predictions. First, select a model from the [Ersilia Model Hub](https://ersilia.io/model-hub/) and fetch it:
 
-1. Generate a few (5) example molecules, to be used as input. The **example** command will generate the adequate input for the model in use
+```bash
+ersilia fetch eos4e40
+```
 
-    ```bash
-    ersilia example retrosynthetic-accessibility -n 5 -f my_molecules.csv
-    ```
+Note that you can use the model identifier (eos4e40) or its human-readable slug (antibiotic-activity).
 
-1. Then, **serve** your model:
+Now you can serve the model:
 
-    ```bash
-    ersilia serve retrosynthetic-accessibility
-    ```
+```bash
+ersilia serve eos4e40
+```
 
-1. And **run** the model:
+To view some information of the model, type the following:
 
-    ```bash
-    ersilia run -i my_molecules.csv -o my_predictions.csv
-    ```
+```bash
+ersilia info
+```
 
-1. Finally, **close** the service when you are done.
+The simplest way to run a model is by passing a CSV file as input. If you don't have one, you can generate it easily. In this case, we take 5 molecules as an example:
 
-    ```bash
-    ersilia close
-    ```
+```bash
+ersilia example -n 5 -f my_input.csv
+```
 
-1. If you no longer want to use the model, you can **delete** it.
+Now you can run the model:
 
-    ```bash
-    ersilia delete retrosynthetic-accessibility
-    ```
+```bash
+ersilia run -i my_input.csv -o my_output.csv
+```
+
+To stop the service, you can simply close the model:
+
+```bash
+ersilia close
+```
+
+Finally, if you don't want to use the model anymore, delete it as follows:
+
+```bash
+ersilia delete eos4e40
+```
 
 Please see the [Ersilia Book](https://ersilia.gitbook.io/ersilia-book/) for more examples and detailed explanations.
 
 ## Contribute
 
 The Ersilia Model Hub is a Free, Open Source Software and we highly value new contributors. There are several ways in which you can contribute to the project:
 
-* A good place to start is checking open [issues](https://github.com/ersilia-os/ersilia/issues).
-* If you have identified a bug in the code, please open a new issue using the bug template.
+* A good place to start is checking open [issues](https://github.com/ersilia-os/ersilia/issues)
+* If you have identified a bug in the code, please open a new issue using the bug template
 * Share any feedback with the community using [GitHub Discussions](https://github.com/ersilia-os/ersilia/discussions) for the project
 * Check our [Contributing Guide](https://github.com/ersilia-os/ersilia/blob/master/CONTRIBUTING.md) for more details
 
@@ -100,7 +112,7 @@ The Ersilia Open Source Initiative adheres to the [Contributor Covenant](https:/
 
 If you want to incorporate a new model in the platform, open a new issue using the [model request template](https://github.com/ersilia-os/ersilia/issues/new?assignees=&labels=new-model&template=model_request.yml&title=%F0%9F%A6%A0+Model+Request%3A+%3Cname%3E) or contact us using the following [form](https://www.ersilia.io/request-model).
 
-After submitting your model request via an issue (suggested), a maintainer will review your request. If they `/approve` your request, a new model respository will be created for you to fork and use! There is a [demo repository](https://github.com/ersilia-os/eos-demo) explaining the steps one-by-one.
+After submitting your model request via an issue (suggested), an Ersilia maintainer will review your request. If they approve your request, a new model respository will be created for you to fork and use! There is a [demo repository](https://github.com/ersilia-os/eos-demo) explaining the steps one-by-one.
 
 ## License and Citation
 
@@ -113,6 +125,7 @@ Please note that Ersilia distinguises between software contributors and software
 - Carolina Caballero
 
 ### Cited by
+
 The Ersilia Model Hub is used in a number of scientific projects. Read more about how we are implementing it in:
 - [Turon, Hlozek et al, Nat Commun, 2023](https://www.nature.com/articles/s41467-023-41512-2)
 - [Van Heerden et al, ACS Omega, 2023](https://pubs.acs.org/doi/10.1021/acsomega.3c05664)
@@ -125,4 +138,5 @@ The [Ersilia Open Source Initiative](https://ersilia.io) is a Non Profit Organiz
 [Help us](https://www.ersilia.io/donate) achieve our mission!
 
 ### Funding
-The Ersilia Model Hub is the flagship product of Ersilia. It has been funded thanks to a combination of funding sources. Full disclosure can be found in our [website](https://ersilia.io/supporters). Highlighted supporters include Splunk Pledge, the Mozilla Builders Accelerator and the AI2050 Program by Schmidt Futures. 
+
+The Ersilia Model Hub is the flagship product of Ersilia. It has been funded thanks to a combination of funding sources. Full disclosure can be found in our [website](https://ersilia.io/supporters). Highlighted supporters include the Mozilla Builders Accelerator, Fast Forward, Splunk Pledge and the AI2050 Program by Schmidt Sciences. 

docs/conf.py

@@ -13,7 +13,7 @@
     "sphinx.ext.mathjax",
     "sphinx.ext.viewcode",
     "sphinx.ext.napoleon",
-    'sphinx.ext.autosummary'
+    "sphinx.ext.autosummary",
 ]
 
 autosummary_generate = True
@@ -26,15 +26,12 @@
 exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 
 html_theme = "furo"
-html_theme_options = {
-    "collapse_navigation": True, 
-    "navigation_depth": 4        
-}
+html_theme_options = {"collapse_navigation": True, "navigation_depth": 4}
 
 html_static_path = []
 htmlhelp_basename = "ersilia_doc"
 
-pygments_style = 'sphinx'
+pygments_style = "sphinx"
 
 latex_documents = [
     (master_doc, "ersilia.tex", "Ersilia Documentation", author, "manual"),

ersilia/cli/cmd.py

@@ -59,4 +59,4 @@ def setup(self):
 
     def test(self):
         m = importlib.import_module("ersilia.cli.commands.test")
-        m.test_cmd()
+        m.test_cmd()

ersilia/cli/commands/catalog.py

@@ -25,6 +25,7 @@ def catalog_cmd():
     Display model card for a specific model ID and show catalog in json format:
     $ ersilia catalog --card <model_id> --as-json
     """
+
     # Example usage: ersilia catalog
     @ersilia_cli.command(help="List a catalog of models")
     @click.option(

ersilia/cli/commands/close.py

@@ -6,6 +6,7 @@
 from ...core.session import Session
 from ...utils.session import deregister_model_session
 
+
 def close_cmd():
     """
     Closes the current session.
@@ -24,6 +25,7 @@ def close_cmd():
         Close the current session:
         $ ersilia close
     """
+
     # Example usage: ersilia close {MODEL}
     @ersilia_cli.command(short_help="Close model", help="Close model")
     def close():

ersilia/cli/commands/delete.py

@@ -31,6 +31,7 @@ def delete_cmd():
         Delete all models:
         $ ersilia delete --all
     """
+
     def _delete(md, model_id):
         md.delete(model_id)
 
@@ -46,9 +47,7 @@ def _delete_model_by_id(model_id):
             )
         else:
             echo(
-                f":person_tipping_hand: {reason}".format(
-                    model_id
-                ),
+                f":person_tipping_hand: {reason}".format(model_id),
                 fg="yellow",
             )
 

ersilia/cli/commands/example.py

@@ -29,7 +29,8 @@ def example(model, n_samples, file_name, simple, predefined):
             model_id = session.current_model_id()
         if not model_id:
             echo(
-                "No model found. Please specify a model or serve a model in the current shell.", fg="red"
+                "No model found. Please specify a model or serve a model in the current shell.",
+                fg="red",
             )
             return
         eg = ExampleGenerator(model_id=model_id)
@@ -41,4 +42,4 @@ def example(model, n_samples, file_name, simple, predefined):
                 )
             )
         else:
-            eg.example(n_samples, file_name, simple, try_predefined=predefined)
+            eg.example(n_samples, file_name, simple, try_predefined=predefined)

ersilia/cli/commands/fetch.py

@@ -30,6 +30,7 @@ def fetch_cmd():
         Fetch a model from a local directory:
         $ ersilia fetch <model_id> --from_dir <path>
     """
+
     def _fetch(mf, model_id):
         res = asyncio.run(mf.fetch(model_id))
         return res
@@ -78,7 +79,7 @@ def _fetch(mf, model_id):
         "--hosted_url",
         default=None,
         type=click.STRING,
-        help="URL of the hosted model service"
+        help="URL of the hosted model service",
     )
     @click.option(
         "--with_bentoml",
@@ -136,6 +137,9 @@ def fetch(
                 fg="green",
             )
         else:
-            echo(f":thumbs_down: Model {model_id} failed to fetch! {fetch_result.reason}", fg="red")
+            echo(
+                f":thumbs_down: Model {model_id} failed to fetch! {fetch_result.reason}",
+                fg="red",
+            )
 
     return fetch

ersilia/cli/commands/info.py

@@ -25,6 +25,7 @@ def info_cmd():
         Get information about active session as json:
         $ ersilia info  --as_json
     """
+
     @ersilia_cli.command(
         short_help="Get model information", help="Get model information"
     )

ersilia/cli/commands/publish.py

@@ -28,6 +28,7 @@ def publish_cmd():
         Rebase a model:
         $ ersilia publish rebase <model_id>
     """
+
     def _publish(mf, model_id):
         mf.publish(model_id)
 

ersilia/cli/commands/run.py

@@ -32,6 +32,7 @@ def run_cmd():
         Run a model with batch size:
         $ ersilia run -i <input_data> -b 50
     """
+
     # Example usage: ersilia run -i {INPUT} [-o {OUTPUT} -b {BATCH_SIZE}]
     @ersilia_cli.command(short_help="Run a served model", help="Run a served model")
     @click.option("-i", "--input", "input", required=True, type=click.STRING)

ersilia/cli/commands/serve.py

@@ -29,6 +29,7 @@ def serve_cmd():
         Serve a model and track the session:
         $ ersilia serve <model_id> --track
     """
+
     # Example usage: ersilia serve {MODEL}
     @ersilia_cli.command(short_help="Serve model", help="Serve model")
     @click.argument("model", type=click.STRING)
@@ -77,7 +78,7 @@ def serve(model, output_source, lake, port, track):
         if mdl.url is None:
             echo("No URL found. Service unsuccessful.", fg="red")
             return
-        
+
         register_model_session(mdl.model_id, mdl.session._session_dir)
         echo(
             ":rocket: Serving model {0}: {1}".format(mdl.model_id, mdl.slug), fg="green"

ersilia/cli/commands/setup.py

@@ -25,6 +25,7 @@ def setup_cmd():
         Set up the environment with base installation:
         $ ersilia setup --base
     """
+
     # Example usage: ersilia setup
     @ersilia_cli.command(
         short_help="Setup ersilia",