Merge pull request #28 from monarch-initiative/update_docs

cleaned up docs and adapted to the two use cases

docs/index.md

@@ -1,28 +1,34 @@
 # Phenopacket2Prompt
 
 
-phenopacket2promot is a Java 17 application that creates prompts intended for use with GPT starting from
-GA4GH phenopackets.
-
+*phenopacket2prompt* is a [Java](https://www.java.com/){:target="_blank"} application that creates prompts for Large
+Language Models (LLMs) on the basis of clinical data that has been encoded using 
+the [Global Alliance for Genomics and Health (GA4GH)](https://www.ga4gh.org/){:target="_blank"}
+[Phenopacket Schema](https://pubmed.ncbi.nlm.nih.gov/35705716/){:target="_blank"}.
 
+Optionally, the prompts can be generated in Czech, Dutch German, Italian, and Spanish.
 
+## Running phenopacket2prompt
 
+There are currently two use cases: 
+1. The creation of prompts (in several languages!), starting from phenopackets, intended for use with a Large Language Model (LLM) which is asked for a differential diagnosis.  
+2. The creation of phenopackets from case reports via text mining using the [fenominal](https://pubmed.ncbi.nlm.nih.gov/38001031/){:target="_blank"}
+3. library.
 
+### Running with Phenopackets
 
+For this use case, follow the instructions in [Set-up](setup.md) and [Batch](batch.md).
 
-## Running phenopacket2prompt
+### Running with case reports
 
-
-Assuming the hp.json file has been downloaded as described above and all of the case report text files
+Assuming the hp.json file has been downloaded as described in [Set-up](setup.md) and all the case report text files
 are available in a directory at ``some/path/gptdocs``, run
 
 
 ```shell title="running the app"
-java -jar phenopacket2prompt.jar gpt -g some/path/gptdocs
+java -jar target/phenopacket2prompt.jar gpt -g some/path/gptdocs
 ```
 
-
-
 This command will create a new directory called ``gptOut`` (this can be adjusted using the -o option).
 It will contain four subdirectories
 
@@ -32,11 +38,8 @@ It will contain four subdirectories
 4. txt_with_differential. Text that starts with the presentation by the first discussant up to and including the differential. This was used to check parsing but was not used in our analysis.
 
 
-
-
-
 ### Feedback
 
-
-The best place to leave feedback, ask questions, and report bugs is the [phenopacket2prompt Issue Tracker](https://github.com/monarch-initiative/phenopacket2prompt/issues).
+The best place to leave feedback, ask questions, and report bugs is the 
+[phenopacket2prompt Issue Tracker](https://github.com/monarch-initiative/phenopacket2prompt/issues){:target="_blank"}.
 

docs/languages.md

@@ -1,7 +1,10 @@
 # Languages
 
-phenopacket2prompt creates phenopackets in various languages using a template system. 
-(TODO explain HPO translations).
+*phenopacket2prompt* creates prompts for Large Lanugage Models starting from HPO terms and other data contained in a
+GA4GH phenopacket. 
+
+Additionally, the HPO translation files (See [Gargano et al., 2024](https://pubmed.ncbi.nlm.nih.gov/37953324/){:template="_blank"})
+are leveraged to create prompts in several languages other than English.
 
 
 ## The template

docs/setup.md

@@ -1,42 +1,36 @@
 # Set-up
 
-phenopacket2prompt requires at least Java 17. To build it from scratch, maven is also required.
-
-## Download command
-Before running the batch command, run the download command to get the necessary files
-
-```
-java -jar target/phenopacket2prompt.jar download
-```
-
-
+*phenopacket2prompt* requires at least Java 17. To build it from scratch, [Apache Maven](https://maven.apache.org/){:target="_blank"} is also required.
 
 ## Installation
 
 
 Most users should download the prebuilt executable file from the
-[Releases](https://github.com/monarch-initiative/phenopacket2prompt/releases) page of the GutHub repository.
+[Releases](https://github.com/monarch-initiative/phenopacket2prompt/releases){:target="_blank"} page of the GutHub repository.
 
 It is also possible to build the application from source using standard Maven and Java tools.
 
 ```shell title="building the app"
 git clone https://github.com/monarch-initiative/phenopacket2prompt.git
 cd phenopacket2prompt
 maven package
-java -jar target/phenopacket2prompt.jar
+java -jar target/phenopacket2prompt.jar [OPTIONS]
 ```
 
 ## Setup
 
 
 First download the latest copy of the [Human Phenotype Ontology](https://hpo.jax.org/app/) hp.json file. This file is
 used for text mining of clinical signs and symptoms. For more information about the HPO, see
-[Koehler et al. (2021)](https://pubmed.ncbi.nlm.nih.gov/33264411/). Adjust the path to the `phenopacket2prompt.jar`
-file as necessary.
+[Koehler et al. (2021)](https://pubmed.ncbi.nlm.nih.gov/33264411/). 
+
+## Download command
+Before running the [batch](batch.md) command, run the download command to get the necessary files. Adjust the path to the `phenopacket2prompt.jar`
+file as necessary, the default is `target/phenopacket2prompt`.
 
 
 
 ```shell title="download"
-java -jar phenopacket2prompt.jar download
+java -jar target/phenopacket2prompt.jar download
 ```