Add more information to benchmarks (method, metric and general info) (#…

…365) * Update jsons * add method meta * add task info * Add metric info * remove results temp * remove results temp * Update image url * change nextflow component image link * add doi bibtex extractor * return bobs * create library.bib and print refs * Update data * Transform to functions * add reference changes to method description * fix dataset references * remove echo * WIP for old result files * WIP fix meta data methods and links for old data * fix metric and method meta info * restore other tasks * Fix dataset refernce for old data * set echo to false * remove bat_int library.bib * fix image link is missing * Fix meta labels * fix typo * fix task meta info * fix empty ref links * add dataset meta info * Make file_size human readable * regenerate perturbation index * Update spatialle variable genes data * update gitignore * update metdo data svg * fix wrting library file * WIP fix write to library file * Wip fix write to library file * WIP transform old results * Add second library file to svg * WIP transform results * Update jsons * add method meta * add task info * Add metric info * remove results temp * remove results temp * Update image url * change nextflow component image link * add doi bibtex extractor * return bobs * create library.bib and print refs * Update data * Transform to functions * add reference changes to method description * fix dataset references * remove echo * WIP for old result files * WIP fix meta data methods and links for old data * fix metric and method meta info * restore other tasks * Fix dataset refernce for old data * set echo to false * remove bat_int library.bib * fix image link is missing * Fix meta labels * fix typo * fix task meta info * fix empty ref links * add dataset meta info * Make file_size human readable * regenerate perturbation index * Update spatialle variable genes data * update gitignore * update metdo data svg * fix wrting library file * WIP fix write to library file * Wip fix write to library file * WIP transform old results * Add second library file to svg * WIP transform results * Update jsons * remove results temp * remove results temp * create library.bib and print refs * Transform to functions * add reference changes to method description * fix dataset references * remove echo * WIP fix meta data methods and links for old data * fix metric and method meta info * restore other tasks * set echo to false * remove bat_int library.bib * fix empty ref links * regenerate perturbation index * Update spatialle variable genes data * WIP fix write to library file * Add second library file to svg * WIP transform results * Fix dataset information Link * WIP add authors to task_info.yaml * finalise script task_info transform * update task_info jsons * Update method and metric json files * Add info to control methods * uniformize bibliography * touch library.bib --------- Co-authored-by: Robrecht Cannoodt <[email protected]>
openproblems-bio · Nov 26, 2024 · d3b719d · d3b719d
1 parent 89ee628
commit d3b719d
Show file tree

Hide file tree

Showing 63 changed files with 5,966 additions and 5,742 deletions.
diff --git a/.gitignore b/.gitignore
@@ -8,6 +8,8 @@
 /.quarto/
 /_site
 /_freeze
+# local created libraries
+/results/*/library.bib
 
 # Temporary files generated by quarto preview
 /site_libs

diff --git a/results/_generate_task_pages.py b/results/_generate_task_pages.py
@@ -10,7 +10,7 @@
 for task_info_file in task_info_files:
     print(f"Reading {task_info_file}", flush=True)
     task_info = json.loads(task_info_file.read_text())
-    task_id = task_info.get("task_id", "task_id_missing")
+    task_id = task_info.get("task_id", "task_id_missing").replace("task_", "")
     task_name = task_info.get("task_name", "<Name missing>")
     task_summary = task_info.get("task_summary", "<Summary missing>")
 
@@ -24,6 +24,9 @@
 engine: knitr
 fig-cap-location: bottom
 citation-location: document
+bibliography: 
+  - library.bib
+  - ../../library.bib
 toc: false
 ---
 

diff --git a/results/_include/_baseline_descriptions.qmd b/results/_include/_baseline_descriptions.qmd
@@ -1,13 +1,58 @@
 ```{r baseline_descriptions}
 #| echo: false
 baselines <- method_info %>% filter(is_baseline)
-lines <- pmap_chr(baselines, function(method_name, method_summary, method_description, reference, code_url, ...) {
+lines <- pmap_chr(baselines, function(method_name, method_summary, method_description, reference, code_url, implementation_url, ...) {
+  rest <- list(...)
+  image <- pluck(rest, "image", .default = NULL)
+  documentation_url <- pluck(rest, "documentation_url", .default = NULL)
+  code_version <- pluck(rest, "code_version", .default = NULL)
+  references_doi <- pluck(rest, "references_doi", .default = NULL)
+  references_bibtex <- pluck(rest, "references_bibtex", .default = NULL)
+
+  if ("paper_reference" %in% names(rest)) {
+    ref <- split_cite_fun(rest$paper_reference)
+  } else {
+    bibs <- c()
+    if (!is.null(references_doi) && !is.na(references_doi)) {
+      bibs <- get_bibtex_from_doi(references_doi)
+    }
+    if (!is.null(references_bibtex) && !is.na(references_bibtex)) {
+      bibs <- c(bibs, references_bibtex)
+    }
+    # Write new entries to library.bib
+    write_library(bibs)
+    # Get bibtex references
+    if (!is.null(bibs)) {
+      ref <- get_bibtex_entries(bibs)
+    } else {
+      ref <- ""
+    }
+  }
+
+  if (ref != "") ref <- paste0(" ", ref)
+
   summ <- (method_summary %|% "Missing 'method_summary'") %>% str_replace_all("\\n", " ") %>% str_replace_all("\\. *$", "")
 
+  method_meta <- tribble(
+    ~icon, ~value,
+    "bi bi-book", if (!is.null(documentation_url)) paste0("[Documentation](", documentation_url, ")") else NULL,
+    "bi bi-globe", if (!is.null(code_url)) paste0("[Repository](", code_url, ")") else NULL,
+    "bi bi-file-earmark-code", if (!is.null(implementation_url)) paste0("[Source Code](", implementation_url, ")") else NULL,
+    "bi bi-box-seam", if (!is.null(image)) paste0("[Container](", image, ")") else NULL,
+    "bi bi-tag", if (!is.null(code_version) && !is.na(code_version)) code_version else NULL,
+    ) %>% filter(!sapply(value, is.null))
+  
+  meta_list <- paste(
+      paste0("<i class=\"", method_meta$icon, "\"></i> ", method_meta$value),
+      collapse = " · "
+    )
+
   strip_margin(glue::glue("
     |### {method_name}
     |
-    |{summ}
+    |{meta_list}
+    |
+    |{summ} {ref}
     |
     |{method_description %|% ''}
     |"

diff --git a/results/_include/_dataset_descriptions.qmd b/results/_include/_dataset_descriptions.qmd
@@ -1,23 +1,61 @@
 ```{r dataset_description}
 #| echo: false
-lines <- pmap_chr(dataset_info, function(dataset_name, dataset_summary, dataset_description, data_reference, ...) {
-  ref <- split_cite_fun(data_reference)
+lines <- pmap_chr(dataset_info, function(dataset_id, dataset_name, dataset_summary, dataset_description, data_reference, ...) {
+
   rest <- list(...)
-  source_dataset_id <- if ("source_dataset_id" %in% names(rest)) rest$source_dataset_id else NULL
-  dataset_link <- if (!is.null(source_dataset_id) && dir.exists(paste0("../../datasets/", source_dataset_id))) {
-    glue::glue("[{dataset_name}](/datasets/{source_dataset_id})")
-  } else if ("scPerturb" %in% dataset_name) {
-    dataset_name
-  } else if (dir.exists(paste0("../../datasets/", rest$dataset_id))) {
-    glue::glue("[{dataset_name}](/datasets/{rest$dataset_id})")
+  source_dataset_id <- pluck(rest, "source_dataset_id", .default = NULL)
+  data_url <- pluck(rest, "data_url", .default = NULL)
+  date_created <- pluck(rest, "date_created", .default = NULL)
+  file_size <- pluck(rest, "file_size", .default = NULL)
+
+  if (grep("^[a-zA-Z0-9]+[0-9]{4}[a-z]+$",data_reference) && !grepl("^@",data_reference)) {
+    ref <- split_cite_fun(data_reference)
   } else {
-    dataset_name
+    bibs <- convert_to_bibtex(data_reference)
+    # Write new entries to library.bib
+    write_library(bibs)
+    ref <- get_bibtex_entries(bibs)
   }
+
   if (ref != "") ref <- paste0(" ", ref)
+  
+  dataset_link <- if (!is.null(source_dataset_id) && dir.exists(paste0("../../datasets/", source_dataset_id))) {
+    glue::glue("../../datasets/{source_dataset_id}")
+  } else if (dir.exists(paste0("../../datasets/", dataset_id))) {
+    glue::glue("../../datasets/{dataset_id}")
+  } else {
+    NULL
+  }
+
+  # Make file_size human readable
+  if (!is.null(file_size)) {
+    file_size_str <- format(
+    structure(file_size, class = "object_size"),
+    units = "auto",
+    standard = "IEC",
+    digits = 2
+    )
+  }
+
+  dataset_meta <- tribble(
+    ~icon, ~value,
+    "bi bi-link-45deg", if(!is.null(dataset_link)) paste0("[Source dataset](", dataset_link, ")") else NULL,
+    "bi bi-box-arrow-up-right", if(!is.null(data_url)) paste0("[Data source](", data_url, ")") else NULL,
+    "bi bi-calendar", if(!is.null(date_created)) paste0(date_created) else NULL,
+    "bi bi-file-earmark-text", if(!is.null(file_size)) file_size_str else NULL,
+    ) %>% filter(!sapply(value, is.null))
+  
+  meta_list <- paste(
+      paste0("<i class=\"", dataset_meta$icon, "\"></i> ", dataset_meta$value),
+      collapse = " · "
+    )
+  
   summ <- (dataset_summary %|% "Missing 'dataset_summary'") %>% str_replace_all("\\n", " ") %>% str_replace_all("\\. *$", "")
   
   strip_margin(glue::glue("
-  |### {dataset_link}
+  |### {dataset_name}
+  |
+  |{meta_list}
   |
   |{summ}{ref}.
   |

diff --git a/results/_include/_load_data.qmd b/results/_include/_load_data.qmd
@@ -8,6 +8,11 @@ library(tidyverse)
 library(funkyheatmap)
 library(kableExtra)
 
+# touch library.bib in data dir
+if (!file.exists("library.bib")) {
+  file.create("library.bib")
+}
+
 # read task info
 task_info <- jsonlite::read_json(paste0(params$data_dir, "/task_info.json"))
 
@@ -52,6 +57,89 @@ split_cite_fun <- function(keys) {
   paste0("[@", paste(refs, collapse = "; @"), "]")
 }
 
+
+convert_to_bibtex <- function(refs) {
+
+  bibtexhandle <- curl::new_handle()
+  curl::handle_setheaders(bibtexhandle, "accept" = "application/x-bibtex")
+
+  bibs <- map(refs, function(ref) {
+    if (grepl("^@", ref)) {
+      # text is already a bibtex, update citation key
+      ref
+    } else {
+      url <- paste0("https://doi.org/", ref)
+      res <- curl::curl_fetch_memory(url, handle = bibtexhandle)
+      if (res$status_code != 200) {
+        cli::cli_alert_warning(paste0("Error processing doi '", ref, "'"))
+        ""
+      } else {
+        rawToChar(res$content)
+      }
+    }
+  })
+  return(unlist(bibs))
+}
+
+
+get_bibtex_from_doi <- function(dois) {
+  if (is.null(dois)) return("")
+
+  dois <- dois[!is.na(dois)]
+  if (length(dois) == 0) return("")
+
+  bibtexhandle <- curl::new_handle()
+  curl::handle_setheaders(bibtexhandle, "accept" = "application/x-bibtex")
+
+  refs <- unlist(dois)
+  bibs <- map (refs,function(ref) {
+    url <- paste0("https://doi.org/", ref)
+    res <- curl::curl_fetch_memory(url, handle = bibtexhandle)
+    if (res$status_code != 200) {
+      cli::cli_alert_warning(paste0("Error processing doi '", text, "'"))
+      ""
+    } else {
+      rawToChar(res$content)
+    }
+  })
+
+  return(unlist(bibs))
+}
+
+write_library <- function(library) {
+  # Read existing entries from library.bib
+  existing_bibs <- if (file.exists("library.bib")) {
+    readLines("library.bib")
+  } else {
+    c()
+  }
+
+  # Filter out bibs that already exist in library.bib
+  new_bibs <- library[!library %in% existing_bibs]
+
+  # Write new entries to library.bib
+  if (length(new_bibs) > 0) {
+    write(new_bibs, "library.bib", append=TRUE)
+  }
+}
+
+get_bibtex_entries <- function(bibs) {
+  ref <-sapply(bibs, function(bib) {
+    matches <- regmatches(bib, regexpr("@.*?\\{(.*?),", bib))
+    if (length(matches) > 0) {
+      sub("@.*?\\{(.*?),", "\\1", matches)
+    } else {
+      NA
+    }
+  })
+  ref <- na.omit(ref)
+  ref_string <- paste0("[@", ref, "]", collapse = " ")
+  return(ref_string)
+}
+
+
+
+
 aggregate_scores <- function(scaled_score) {
   mean(pmin(1, pmax(0, scaled_score)) %|% 0)
 }

diff --git a/results/_include/_method_descriptions.qmd b/results/_include/_method_descriptions.qmd
@@ -1,31 +1,57 @@
 ```{r method_description}
 #| echo: false
 # show each method just once
-lines <- pmap_chr(method_info %>% filter(!is_baseline), function(method_name, method_summary, method_description, paper_reference, code_url, code_version, ...) {
-
-  links <- c()
-  if (!is.na(code_url)) {
-    links <- c(links, glue::glue(" [Docs]({code_url})"))
-  }
-  version_label <- 
-    if (!is.na(code_version) && code_version != "missing-version") {
-      glue::glue(" Software version {code_version}.")
-    } else {
-      ""
+lines <- pmap_chr(method_info %>% filter(!is_baseline), function(method_name, method_summary, method_description, code_url, implementation_url, ...) {
+  rest <- list(...)
+  image <- pluck(rest, "image", .default = NULL)
+  documentation_url <- pluck(rest, "documentation_url", .default = NULL)
+  code_version <- pluck(rest, "code_version", .default = NULL)
+  references_doi <- pluck(rest, "references_doi", .default = NULL)
+  references_bibtex <- pluck(rest, "references_bibtex", .default = NULL)
+  if ("paper_reference" %in% names(rest)) {
+    ref <- split_cite_fun(rest$paper_reference)
+  } else {
+    bibs <- c()
+    if (!is.null(references_doi) && !is.na(references_doi)) {
+      bibs <- get_bibtex_from_doi(references_doi)
     }
-  ref <- split_cite_fun(paper_reference)
-  if (ref != "") ref <- paste0(" ", ref)
-  links_label <-
-    if (length(links) > 0) {
-      glue::glue(" Links: {paste(links, collapse = ', ')}.")
+    if (!is.null(references_bibtex) && !is.na(references_bibtex)) {
+      bibs <- c(bibs, references_bibtex)
+    }
+    # Write new entries to library.bib
+    write_library(bibs)
+    # Get bibtex references
+    if (!is.null(bibs)) {
+      ref <- get_bibtex_entries(bibs)
     } else {
-      ""
+      ref <- ""
     }
+  }
+
+  if (ref != "") ref <- paste0(" ", ref)
+  
   summ <- (method_summary %|% "Missing 'method_summary'") %>% str_replace_all("\\n", " ") %>% str_replace_all("\\. *$", "")
+
+  method_meta <- tribble(
+    ~icon, ~value,
+    "bi bi-book", if (!is.null(documentation_url)) paste0("[Documentation](", documentation_url, ")") else NULL,
+    "bi bi-globe", if (!is.null(code_url)) paste0("[Repository](", code_url, ")") else NULL,
+    "bi bi-file-earmark-code", if (!is.null(implementation_url)) paste0("[Source Code](", implementation_url, ")") else NULL,
+    "bi bi-box-seam", if (!is.null(image)) paste0("[Container](", image, ")") else NULL,
+    "bi bi-tag", if (!is.null(code_version) && !is.na(code_version)) code_version else NULL,
+    ) %>% filter(!sapply(value, is.null))
+  
+  meta_list <- paste(
+      paste0("<i class=\"", method_meta$icon, "\"></i> ", method_meta$value),
+      collapse = " · "
+    )
+
   strip_margin(glue::glue("
     |### {method_name}
     |
-    |{summ}{ref}.{version_label}{links_label}
+    |{meta_list}
+    |
+    |{summ}{ref}
     |
     |{method_description %|% ''}
     |"

diff --git a/results/_include/_metric_descriptions.qmd b/results/_include/_metric_descriptions.qmd
@@ -1,12 +1,53 @@
-```{r}
+```{r metric_descriptions}
 #| echo: false
-lines <- pmap_chr(metric_info, function(metric_name, metric_summary, metric_description, paper_reference, ...) {
-  ref <- split_cite_fun(paper_reference)
+lines <- pmap_chr(metric_info, function(metric_name, metric_summary, metric_description, implementation_url, code_version, ...) {
+  rest <- list(...)
+  image <- pluck(rest, "image", .default = NULL)
+  code_version <- pluck(rest, "code_version", .default = NULL)
+  references_doi <- pluck(rest, "references_doi", .default = NULL)
+  references_bibtex <- pluck(rest, "references_bibtex", .default = NULL)
+  if ("paper_reference" %in% names(rest)) {
+    ref <- split_cite_fun(rest$paper_reference)
+  } else {
+    bibs <- c()
+    if (!is.null(references_doi) && !is.na(references_doi)) {
+      bibs <- get_bibtex_from_doi(references_doi)
+    }
+    if (!is.null(references_bibtex) && !is.na(references_bibtex)) {
+      bibs <- c(bibs, references_bibtex)
+    }
+    # Write new entries to library.bib
+    write_library(bibs)
+
+    # Get bibtex references
+    if (!is.null(bibs)) {
+      ref <- get_bibtex_entries(bibs)
+    } else {
+      ref <- ""
+    }
+  }
+
   if (ref != "") ref <- paste0(" ", ref)
+
   summ <- (metric_summary %|% "Missing 'metric_summary'") %>% str_replace_all("\\n", " ") %>% str_replace_all("\\. *$", "")
+
+  metric_meta <- tribble(
+    ~icon, ~value,
+    "bi bi-file-earmark-code", if (!is.null(implementation_url)) paste0("[Source code](", implementation_url, ")") else NULL,
+    "bi bi-box-seam", if (!is.null(image)) paste0("[Container](", image, ")") else NULL,
+    "bi bi-tag", if (!is.null(code_version) && !is.na(code_version)) code_version else NULL,
+    ) %>% filter(!sapply(value, is.null))
+
+  meta_list <- paste(
+      paste0("<i class=\"", metric_meta$icon, "\"></i> ", metric_meta$value),
+      collapse = " · "
+    )
+
   strip_margin(glue::glue("
   |### {metric_name}
   |
+  |{meta_list}
+  |
   |{summ}{ref}.
   |
   |{metric_description %|% ''}