fix: updated task definitions (#12)

* fix: updated missing requirements and fixed task 3 description

* fix: added additional references from AM

Author: dmccloskey

docs/tasks.md

@@ -9,8 +9,8 @@ hide:
 > **Date** 2024-10-14 to -15<br>
 > **Location** BioLabs Heidelberg and Online<br>
 
-- General software requirements: [Streamlit](https://streamlit.io/), [Ollama](https://ollama.com/)
-- General database requirements: vector database (our internal stack is preferential towards FAISS, but ChromeDB, Milvus, can be used just as well).
+- Infrastructure: [Amazon Web Services](https://aws.amazon.com/de/) and [Code Ocean](https://codeocean.com/)
+- Application requirements: [Streamlit](https://streamlit.io/), [Ollama](https://ollama.com/), [LangChain](https://www.langchain.com/), and [FAISS](https://github.com/facebookresearch/faiss)
 
 ## AI agents for computational modelling and simulation
 - Special software requirements: https://github.com/copasi/basico
@@ -19,47 +19,47 @@ hide:
 - Other data: [PubMed](https://pubmed.ncbi.nlm.nih.gov/) for original articles
 
 ### Task type 1
-- Description: Simulation of a mathematical model and reporting of the biomarker trajectories and predicted clinical efficacy
-- Input: simulation parameters such as initial concentrations
-- Output: time-course of simulation species
+- **Description**: Simulation of a mathematical model and reporting of the biomarker trajectories and predicted clinical efficacy
+- **Input**: simulation parameters such as initial concentrations
+- **Output**: time-course of simulation species
 
 ### Task type 2
-- Description: Creating a mathematical model from scratch
-- Input: Original article describing the mathematical model and list of equations
-- Output: SBML model with annotated species
+- **Description**: Creating a mathematical model from scratch
+- **Input**: Original article describing the mathematical model and list of equations
+- **Output**: SBML model with annotated species
 
 ## AI agents for omics and foundation models
 - Special software requirements: [scGPT](https://www.nature.com/articles/s41592-024-02201-0)
 - Data for analysis: [cell by gene](https://cellxgene.cziscience.com/)
 - Other tools/analyses: [differential gene set enrichment analysis using GO](https://amigo.geneontology.org/amigo), UMAP
 
 ### Task type 1
-- Description: Integration of multiple scRNA seq datasets, correction for batch effects, annotation of cells, and reporting of the results as a UMAP
-- Input: multiple cellxgene datasets for a particular disease (e.g., Rheumatoid Arthritis)
-- Output: UMAP visualization with cell annotation
+- **Description**: Integration of multiple scRNA seq datasets, correction for batch effects, annotation of cells, and reporting of the results as a UMAP
+- **Input**: multiple cellxgene datasets for a particular disease (e.g., Rheumatoid Arthritis)
+- **Output**: UMAP visualization with cell annotation
 
 ### Task type 2
-- Description: Simulation of gene perturbation and reporting of the predicted differentially expressed genes using pathway enrichment analysis
-- Input: cell x gene dataset for a particular disease, knockout gene list
-- Output: list of differentially expressed genes and pathway enrichment analysis visualization
+- **Description**: Simulation of gene perturbation and reporting of the predicted differentially expressed genes using pathway enrichment analysis
+- **Input**: cell x gene dataset for a particular disease, knockout gene list
+- **Output**: list of differentially expressed genes and pathway enrichment analysis visualization
 
 ## AI agent for Biomedical knowledge graph reasoning and construction
-- Special software requirements: [LLMGraphTransformer](https://api.python.langchain.com/en/latest/graph_transformers/langchain_experimental.graph_transformers.llm.LLMGraphTransformer.html) and [ULTRA](https://github.com/DeepGraphLearning/ULTRA)
-- Biomedical knowledge graph dataset: [PrimeKG](https://github.com/mims-harvard/PrimeKG) specifically the subset used in [STARK](https://github.com/snap-stanford/stark)
+- Special software requirements: [PyTorch Geometric](https://github.com/pyg-team/pytorch_geometric) and [available models through PyG](https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html), [LLMGraphTransformer](https://api.python.langchain.com/en/latest/graph_transformers/langchain_experimental.graph_transformers.llm.LLMGraphTransformer.html), and schema-agnostic graph foundation model (e.g., [ULTRA](https://github.com/DeepGraphLearning/ULTRA))
+- Biomedical knowledge graph dataset: [PrimeKG](https://github.com/mims-harvard/PrimeKG) specifically the subset used in [STARK](https://github.com/snap-stanford/stark) for textual Q&A
 - Other data: [PubMed](https://pubmed.ncbi.nlm.nih.gov/) for original articles
 - Graph database: [NetworkX](https://networkx.org/)
 
 ### Task type 1
-- Description: Knowledge graph Q&A and retrieval of K-hop subgraph explanations
-- Input: Natural language question (see subset used in https://arxiv.org/abs/2404.13207 for PrimeKG)
-- Output: Ranked nodes answers and visualization of k-hop subgraphs
+- **Description**: Knowledge graph Q&A and retrieval of the K-hop subgraph explanations
+- **Input**: Natural language question (see subset used in https://arxiv.org/abs/2404.13207 for PrimeKG)
+- **Output**: Ranked nodes answers and visualization of k-hop subgraphs
 
 ### Task type 2
-- Description: Disease knowledge graph construction from text using a LLM to graph model and link prediction model to fill in gaps
-- Input: List of disease MeSH terms and associated articles from PubMed and list of nodes and edges (same as in PrimeKG)
-- Output: NetworkX representation of the knowledge graph and visualization
+- **Description**: Disease knowledge graph construction from text using a text-to-graph model to construct the initial knowledge graph and a link prediction model to fill in gaps in the reconstructed knowledge graph
+- **Input**: List of disease MeSH terms and associated articles from PubMed and list of nodes and edges (same as in PrimeKG)
+- **Output**: NetworkX representation of the knowledge graph and visualization
 
 ### Task type 3
-- Description: Same as type 1 but including protein embeddings from https://www.uniprot.org/help/embeddings and additional vector similarity search of drug targets embeddings 
-- Input: Natural language question (see subset used in https://arxiv.org/abs/2404.13207 for PrimeKG)
-- Output: Ranked nodes answers and visualization of k-hop subgraphs
+- **Description**: Same as type 1 but including protein embeddings from https://www.uniprot.org/help/embeddings and additional vector similarity search of drug targets embeddings 
+- **Input**: Natural language question (see subset used in https://arxiv.org/abs/2404.13207 for PrimeKG)
+- **Output**: Ranked nodes answers and visualization of k-hop subgraphs