Merge pull request #94 from lilab-bcb/boli

Added transpose option and fixed a bug in read_csv

ext_modules/io_funcs.pyx

@@ -4,7 +4,7 @@ import numpy as np
 
 from libc.stdlib cimport malloc, free, atoi
 from libc.stdio cimport fopen, fclose, getline, FILE, fscanf, sscanf, fprintf, fread, fseek, SEEK_CUR, SEEK_SET#, printf
-from libc.string cimport strncmp, strlen, strtok, strcmp, memcpy, memset
+from libc.string cimport strncmp, strlen, strtok, strchr, strcmp, memcpy, memset
 from libc.math cimport pow
 
 cimport cython
@@ -144,7 +144,13 @@ cpdef tuple read_csv(char* csv_file, char* delimiters):
     assert getline(&line, &size, fi) >= 0
     pch = strtok(line, delimiters)
     assert pch != NULL
-    row_key = pch
+
+    if strchr(delimiters, line[0]) != NULL:
+        row_key = ""
+        N = 1
+        colnames.append(pch)
+    else:
+        row_key = pch
 
     pch = strtok(NULL, delimiters)
     while pch != NULL:

pegasusio/readwrite.py

@@ -98,6 +98,7 @@ def read_input(
     select_data: Set[str] = None,
     select_genome: Set[str] = None,
     select_modality: Set[str] = None,
+    transpose: bool = False,
 ) -> MultimodalData:
     """Load data into memory.
     This function is used to load input data into memory. Inputs can be in 'zarr', 'h5ad', 'loom', '10x', 'mtx', 'csv', 'tsv', 'fcs' (for flow/mass cytometry data) or 'nanostring' (Nanostring GeoMx spatial data) formats.
@@ -122,6 +123,8 @@ def read_input(
         Only select data with genomes in select_genome. Select_data, select_genome and select_modality are mutually exclusive.
     select_modality: `Set[str]`, optional (default: None)
         Only select data with modalities in select_modality. Select_data, select_genome and select_modality are mutually exclusive.
+    transpose: `bool`, optional (default: False)
+        Only applicable if input type is 'csv' or 'tsv'. Need to turn it on if gene names are columns names.
 
     Returns
     -------
@@ -172,7 +175,7 @@ def read_input(
             if is_vdj_file(input_file, file_type):
                 data = load_10x_vdj_file(input_file, genome = genome, modality = modality)
             else:
-                data = load_csv_file(input_file, sep = "," if file_type == "csv" else "\t", genome = genome, modality = modality)
+                data = load_csv_file(input_file, sep = "," if file_type == "csv" else "\t", genome = genome, modality = modality, transpose = transpose)
 
     data.subset_data(select_data, select_genome, select_modality)
     data.kick_start()

pegasusio/text_utils.py

@@ -314,6 +314,7 @@ def load_csv_file(
     sep: str = ",",
     genome: str = None,
     modality: str = None,
+    transpose: bool = False,
 ) -> MultimodalData:
     """Load count matrix from a CSV-style file, such as CSV file or DGE style tsv file.
 
@@ -328,6 +329,8 @@ def load_csv_file(
         The genome reference. If None, use "unknown" instead.
     modality: `str`, optional (default None)
         Modality. If None, use "rna" instead.
+    transpose: `bool`, optional (default False)
+        If transpose the matrix. Transposation is needed if gene names are in the columns.
 
     Returns
     -------
@@ -382,15 +385,20 @@ def load_csv_file(
                ((barcode_metadata["barcodekey"].values != np.array(rownames)).sum() == 0) and ((feature_metadata["featureid"].values != np.array(colnames)).sum() == 0)
         mat = csr_matrix((data, (row_ind, col_ind)), shape = shape)
     else:
-        mat = csr_matrix((data, (col_ind, row_ind)), shape = (shape[1], shape[0]))
-        if barcode_metadata is None:
-            barcode_metadata = {"barcodekey": colnames}
+        if transpose:
+            mat = csr_matrix((data, (row_ind, col_ind)), shape = (shape[0], shape[1]))
+            barcode_metadata = {"barcodekey": rownames}
+            feature_metadata = {"featurekey": colnames}
         else:
-            assert (barcode_metadata.shape[0] == shape[1]) and ((barcode_metadata["barcodekey"].values != np.array(colnames)).sum() == 0)
-        if feature_metadata is None:
-            feature_metadata = {"featurekey": rownames}
-        else:
-            assert (feature_metadata.shape[0] == shape[0]) and ((feature_metadata["featurekey"].values != np.array(rownames)).sum() == 0)
+            mat = csr_matrix((data, (col_ind, row_ind)), shape = (shape[1], shape[0]))
+            if barcode_metadata is None:
+                barcode_metadata = {"barcodekey": colnames}
+            else:
+                assert (barcode_metadata.shape[0] == shape[1]) and ((barcode_metadata["barcodekey"].values != np.array(colnames)).sum() == 0)
+            if feature_metadata is None:
+                feature_metadata = {"featurekey": rownames}
+            else:
+                assert (feature_metadata.shape[0] == shape[0]) and ((feature_metadata["featurekey"].values != np.array(rownames)).sum() == 0)
 
     genome = genome if genome is not None else "unknown"
     modality = modality if modality is not None else "rna"