Initial commit

.Rbuildignore

@@ -0,0 +1,2 @@
+^CellTypeGPT\.Rproj$
+^\.Rproj\.user$

.gitignore

@@ -0,0 +1 @@
+.Rproj.user

CellTypeGPT.Rproj

@@ -0,0 +1,22 @@
+Version: 1.0
+
+RestoreWorkspace: No
+SaveWorkspace: No
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX
+
+AutoAppendNewline: Yes
+StripTrailingWhitespace: Yes
+LineEndingConversion: Posix
+
+BuildType: Package
+PackageUseDevtools: Yes
+PackageInstallArgs: --no-multiarch --with-keep.source
+PackageRoxygenize: rd,collate,namespace

DESCRIPTION

@@ -0,0 +1,14 @@
+Package: CellTypeGPT
+Title: What the Package Does (One Line, Title Case)
+Version: 0.0.0.9000
+Authors@R: 
+    person("First", "Last", , "[email protected]", role = c("aut", "cre"),
+           comment = c(ORCID = "YOUR-ORCID-ID"))
+Description: What the package does (one paragraph).
+License: `use_mit_license()`, `use_gpl3_license()` or friends to pick a
+    license
+Encoding: UTF-8
+Roxygen: list(markdown = TRUE)
+RoxygenNote: 7.3.2
+Imports:
+    httr2

NAMESPACE

@@ -0,0 +1,3 @@
+# Generated by roxygen2: do not edit by hand
+
+export(CellTypeGPT)

R/CellTypeGPT.R

@@ -0,0 +1,77 @@
+
+
+#' Annotate Cell Types using Custom GPT
+#'
+#' This function annotates cell types based on input gene markers.
+#'
+#' @param input A list or data frame containing gene markers.
+#' @param tissuename A character string specifying the tissue name.
+#' @param model A character string specifying the model to use.
+#' @param topgenenumber An integer specifying the number of top genes to consider.
+#' @param baseurl A character string specifying the base URL for the API. Default is "https://api.default.com/v1/chat/completions".
+#' @return A character vector of annotated cell types.
+#' @export
+#' @name CellTypeGPT
+
+library(httr2)
+
+
+annotate_cell_types <- function(input, tissuename = NULL, model = 'gpt-4o', topgenenumber = 10, api_base) {
+  OPENAI_API_KEY <- Sys.getenv("OPENAI_API_KEY")
+
+  if (OPENAI_API_KEY == "") {
+    stop("OpenAI API key not found. Please set your API key in the environment.")
+  }
+
+
+  if (class(input) == 'list') {
+    input <- sapply(input, paste, collapse = ',')
+  } else {
+    input <- input[input$avg_log2FC > 0, , drop = FALSE]
+    input <- tapply(input$gene, list(input$cluster), function(i) paste0(i[1:topgenenumber], collapse = ','))
+  }
+
+  cutnum <- ceiling(length(input) / 30)
+  if (cutnum > 1) {
+    cid <- as.numeric(cut(1:length(input), cutnum))	
+  } else {
+    cid <- rep(1, length(input))
+  }
+
+  allres <- sapply(1:cutnum, function(i) {
+    id <- which(cid == i)
+    flag <- 0
+    while (flag == 0) {
+
+      req <- request(api_base) %>%
+        req_method("POST") %>%
+        req_headers(
+          "Authorization" = paste("Bearer", OPENAI_API_KEY),
+          "Content-Type" = "application/json"
+        ) %>%
+        req_body_json(list(
+          model = model,
+          messages = list(list(
+            role = "user",
+            content = paste0('You are an expert in cell biology. Identify cell types of ', tissuename, ' cells using the following markers separately for each\n row. Only provide the cell type name. Do not show numbers or additional text before the name.\n Some can be a mixture of multiple cell types.\n', paste(input[id], collapse = '\n'))
+          ))
+        ))
+
+
+      resp <- req_perform(req)
+
+      content <- resp_body_json(resp)
+      res <- strsplit(content$choices[[1]]$message$content, '\n')[[1]]
+
+      if (length(res) == length(id)) {
+        flag <- 1
+      }
+    }
+    names(res) <- names(input)[id]
+    res
+  }, simplify = FALSE)
+
+  print('Note: It is always recommended to check the results returned by GPT in case of\n AI hallucination, before going to downstream analysis.')
+  return(gsub(',$', '', unlist(allres)))
+}
+