Expose scGPT fine-tuning epochs and batch size

CHANGELOG.md

@@ -39,6 +39,8 @@
 
 ## Minor changes
 
+* Expose `methods/scgpt_finetuned`'s epochs and batch size as arguments, preserving defaults of 15 and 64.
+    Batch size also applies to validation and embedding (issue #111).
 * Un-pin the scPRINT version and update parameters (PR #51)
 * Update scPRINT to better handle large datasets, including a new default model (PR #54)
 * Credit contributors missing from the authors list, and fix Martin Kim's orcid (PR #100).

_viash.yaml

@@ -141,6 +141,10 @@ authors:
     info:
       github: cmclean
       orcid: 0000-0001-9928-8216
+  - name: Daesun Ryu
+    roles: [contributor]
+    info:
+      github: Daesun-Ryu
 config_mods: |
   .runners[.type == "nextflow"].config.labels := { lowmem : "memory = 20.Gb", midmem : "memory = 50.Gb", highmem : "memory = 100.Gb", lowcpu : "cpus = 5", midcpu : "cpus = 15", highcpu : "cpus = 30", lowtime : "time = 1.h", midtime : "time = 4.h", hightime : "time = 8.h", veryhightime : "time = 24.h" }
 

src/methods/scgpt_finetuned/config.vsh.yaml

@@ -38,6 +38,20 @@ arguments:
     type: integer
     default: 3000
     description: Number of highly variable genes to use.
+  - name: --epochs
+    type: integer
+    default: 15
+    min: 1
+    description: Number of fine-tuning epochs.
+    info:
+      test_default: 2
+  - name: --batch_size
+    type: integer
+    default: 64
+    min: 1
+    description: Batch size for fine-tuning, validation and embedding.
+    info:
+      test_default: 4
 
 resources:
   - type: python_script

src/methods/scgpt_finetuned/script.py

@@ -24,6 +24,8 @@
     "model_name": "scGPT_human",
     "model": "scGPT_human",
     "n_hvg": 3000,
+    "epochs": 15,
+    "batch_size": 64,
 }
 meta = {"name": "scgpt"}
 ## VIASH END
@@ -221,9 +223,9 @@
     "ecs_thres": 0.8,  # Elastic cell similarity objective, 0.0 to 1.0, 0.0 to disable
     "dab_weight": 1.0,  # DAR objective weight for batch correction
     "mask_ratio": 0.4,
-    "epochs": 15,
+    "epochs": par["epochs"],
     "lr": 1e-4,
-    "batch_size": 64,
+    "batch_size": par["batch_size"],
     "dropout": 0.2,
     "schedule_ratio": 0.9,  # Learning rate decay
     "log_interval": 100,
@@ -364,7 +366,7 @@
     adata,
     best_model_dir.name,
     gene_col="feature_name",
-    batch_size=64,
+    batch_size=par["batch_size"],
     use_fast_transformer=False,  # Disable fast-attn as not installed
     device=device,
     return_new_adata=True,