Refactor code for finding experiments in DesignIP class and update ti…

…le_size in pileup_norm.smk rule

seqnado/design.py

@@ -20,7 +20,7 @@ def is_path(path: Optional[Union[str, pathlib.Path]]) -> Optional[pathlib.Path]:
     else:
         p = None
 
-    if p is not None:
+    if p is not None and str(p) != "." and str(p):
         return True
     else:
         return False
@@ -421,17 +421,19 @@ def query(
 
         name_to_query = sample_name + (f"_{ip}" if ip is not None else "")
 
-        for experiment in self.assays.values():
-
-            name_ip = experiment.name
-            name_control = f"{experiment.control_files.r1.sample_base_without_ip}_{experiment.control_files.r1.ip}"
+        # Check if the sample name is in the index of the dataframe
+        df = self.to_dataframe()
+        is_name_in_index = df.index.str.contains(name_to_query)
 
-            if name_to_query == name_ip or name_to_query == name_control:
-                if control is not None:
-                    if experiment.control == control:
-                        return experiment
-                else:
-                    return experiment
+        if is_name_in_index.sum() == 1:
+            return self.assays[df.index[is_name_in_index][0]]
+
+        else:
+            # Check if its the name of a control
+            for assay in self.assays.values():
+                name_control = f"{assay.control_files.r1.sample_base_without_ip}_{assay.control_files.r1.ip}" if assay.control_files is not None else None
+                if name_to_query == name_control:
+                    return assay
 
         raise ValueError(
             f"Could not find experiment with sample name {sample_name} and ip {ip} and control {control}"
@@ -605,7 +607,6 @@ def from_dataframe(cls, df: pd.DataFrame, simplified: bool = True, **kwargs):
                     )
             else:
                 raise NotImplementedError("Not implemented")
-
         return cls(assays=experiments, **kwargs)
 
 

seqnado/workflow/rules/pileup_norm.smk

@@ -76,9 +76,9 @@ rule tile_regions:
         import pyranges as pr
 
         chromsizes = (
-            pd.read_csv(chromsizes, sep="\t", header=None).set_index(0)[1].to_dict()
+            pd.read_csv(input.chromsizes, sep="\t", header=None).set_index(0)[1].to_dict()
         )
-        genome_tiled = pr.gf.tile_genome(chromsizes, tile_size=tile_size)
+        genome_tiled = pr.gf.tile_genome(chromsizes, tile_size=params.tile_size)
         genome_tiled = genome_tiled.df.assign(
             feature="tile", gene_id=lambda df: df.index.astype(str)
         ).pipe(pr.PyRanges)