Feature/timsim gui

imspy/imspy/timstof/dbsearch/imspy_dda.py

@@ -25,6 +25,7 @@
 
 from sklearn.svm import SVC
 from sagepy.rescore.rescore import rescore_psms
+from sagepy.core.fdr import sage_fdr_psm
 
 from imspy.timstof.dbsearch.utility import sanitize_mz, sanitize_charge, get_searchable_spec, split_fasta, \
     write_psms_binary, \
@@ -405,7 +406,7 @@ def main():
                 paths.append(os.path.join(root, file))
 
     # Get the write folder path
-    write_folder_path = str(Path(args.path).parent)
+    write_folder_path = str(Path(args.path))
 
     # create imspy folder if it does not exist
     if not os.path.exists(write_folder_path + "/imspy"):
@@ -527,10 +528,10 @@ def main():
                                           load_tokenizer_from_resources("tokenizer-ptm"), verbose=True)
 
     # go over RAW data one file at a time
-    for p, path in enumerate(paths):
+    for file_id, path in enumerate(paths):
         if args.verbose:
             print(f"processing {path} ...")
-            print(f"processing {p + 1} of {len(paths)} ...")
+            print(f"processing {file_id + 1} of {len(paths)} ...")
 
         ds_name = os.path.basename(path).split(".")[0]
         dataset = TimsDatasetDDA(str(path), in_memory=params['in_memory'], use_bruker_sdk=params['bruker_sdk'])
@@ -789,6 +790,10 @@ def main():
         for rt, p in zip(rt_pred, psm):
             p.retention_time_predicted = rt
 
+        # add file id to PSMs
+        for p in psm:
+            p.sage_feature_file_id = file_id
+
         # serialize PSMs to bincode binary
         bts = compress_psms(psm)
 
@@ -832,6 +837,12 @@ def main():
         num_threads=params['num_threads'],
     )
 
+    # if we have only one fasta file, we can use sage core fdr calculation
+    if len(fastas) == 1:
+        if args.verbose:
+            print("calculating q-values using SAGE internal functions...")
+        sage_fdr_psm(psms, indexed_db, use_hyper_score=False)
+
     # serialize all PSMs to JSON binary
     bts = compress_psms(psms)
 

imspy/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "imspy"
-version = "0.3.5"
+version = "0.3.6"
 description = ""
 authors = [
     { name = "theGreatHerrLebert", email = "[email protected]" }
@@ -19,7 +19,7 @@ dependencies = [
     "wandb>=0.12.1",
     "mokapot>=0.10.0",
     "sagepy>=0.3.0",
-    "imspy-connector>=0.3.5",
+    "imspy-connector>=0.3.6",
     "scipy>=1.7.1",
     "tqdm>=4.66",
     "pyarrow>=13.0",

imspy_connector/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "imspy-connector"
-version = "0.3.5"
+version = "0.3.6"
 edition = "2021"
 
 [lib]

mscore/Cargo.toml

@@ -4,14 +4,14 @@ version = "0.2.0"
 edition = "2021"
 
 [dependencies]
-statrs = "0.16.0"
-itertools = "0.13.0"
+statrs = "0.18.0"
+itertools = "0.14.0"
 rayon = "1.10.0"
-nalgebra = "0.32.5"
-serde = { version = "1.0.198", features = ["derive"] }
-regex = "1.10.4"
+nalgebra = "0.33.2"
+serde = { version = "1.0.217", features = ["derive"] }
+regex = "1.11.1"
 rand = "0.8.5"
-ordered-float = "4.5.0"
+ordered-float = "4.6.0"
 bincode = "2.0.0-rc.3"
 
 [lib]

rustdf/Cargo.toml

@@ -10,14 +10,14 @@ path = "src/lib.rs"
 debug = true
 
 [dependencies]
-clap = { version = "4.5.4", features = ["derive"] }
-libloading = "0.8.3"
-rusqlite = { version = "0.31.0", features = ["bundled"] }
+clap = { version = "4.5.24", features = ["derive"] }
+libloading = "0.8.6"
+rusqlite = { version = "0.32.1", features = ["bundled"] }
 lzf = "1.0.0"
-zstd = "0.13.1"
+zstd = "0.13.2"
 byteorder = "1.5.0"
 mscore = {path = "../mscore"}
 rayon = "1.10.0"
-serde = { version = "1.0.197", features = ["derive"] }
-serde_json = "1.0.115"
+serde = { version = "1.0.217", features = ["derive"] }
+serde_json = "1.0.135"
 rand = "0.8.5"