smftools 0.2.3__py3-none-any.whl → 0.2.5__py3-none-any.whl

smftools/informatics/modkit_functions.py

@@ -1,10 +1,19 @@
-import os
 import subprocess
-import glob
-import zipfile
-from pathlib import Path
 
-def extract_mods(thresholds, mod_tsv_dir, split_dir, bam_suffix, skip_unclassified=True, modkit_summary=False, threads=None):
+from smftools.logging_utils import get_logger
+
+logger = get_logger(__name__)
+
+
+def extract_mods(
+    thresholds,
+    mod_tsv_dir,
+    split_dir,
+    bam_suffix,
+    skip_unclassified=True,
+    modkit_summary=False,
+    threads=None,
+):
     """
     Takes all of the aligned, sorted, split modified BAM files and runs Nanopore Modkit Extract to load the modification data into zipped TSV files
 
@@ -23,10 +32,12 @@ def extract_mods(thresholds, mod_tsv_dir, split_dir, bam_suffix, skip_unclassifi
 
     """
     filter_threshold, m6A_threshold, m5C_threshold, hm5C_threshold = thresholds
-    bam_files = sorted(p for p in split_dir.iterdir() if bam_suffix in p.name and '.bai' not in p.name)
+    bam_files = sorted(
+        p for p in split_dir.iterdir() if bam_suffix in p.name and ".bai" not in p.name
+    )
     if skip_unclassified:
         bam_files = [p for p in bam_files if "unclassified" not in p.name]
-    print(f"Running modkit extract for the following bam files: {bam_files}")
+    logger.info(f"Running modkit extract for the following bam files: {bam_files}")
 
     if threads:
         threads = str(threads)
@@ -34,14 +45,14 @@ def extract_mods(thresholds, mod_tsv_dir, split_dir, bam_suffix, skip_unclassifi
         pass
 
     for input_file in bam_files:
-        print(input_file)
+        logger.debug(input_file)
         # Construct the output TSV file path
         output_tsv = mod_tsv_dir / (input_file.stem + "_extract.tsv")
-        output_tsv_gz = output_tsv.parent / (output_tsv.name + '.gz')
+        output_tsv_gz = output_tsv.parent / (output_tsv.name + ".gz")
         if output_tsv_gz.exists():
-            print(f"{output_tsv_gz} already exists, skipping modkit extract")
+            logger.debug(f"{output_tsv_gz} already exists, skipping modkit extract")
         else:
-            print(f"Extracting modification data from {input_file}")
+            logger.info(f"Extracting modification data from {input_file}")
             if modkit_summary:
                 # Run modkit summary
                 subprocess.run(["modkit", "summary", str(input_file)])
@@ -50,28 +61,43 @@ def extract_mods(thresholds, mod_tsv_dir, split_dir, bam_suffix, skip_unclassifi
             # Run modkit extract
             if threads:
                 extract_command = [
-                    "modkit", "extract",
-                    "calls", "--mapped-only",
-                    "--filter-threshold", f'{filter_threshold}',
-                    "--mod-thresholds", f"m:{m5C_threshold}",
-                    "--mod-thresholds", f"a:{m6A_threshold}",
-                    "--mod-thresholds", f"h:{hm5C_threshold}",
-                    "-t", threads,
-                    str(input_file), str(output_tsv)
-                    ]
+                    "modkit",
+                    "extract",
+                    "calls",
+                    "--mapped-only",
+                    "--filter-threshold",
+                    f"{filter_threshold}",
+                    "--mod-thresholds",
+                    f"m:{m5C_threshold}",
+                    "--mod-thresholds",
+                    f"a:{m6A_threshold}",
+                    "--mod-thresholds",
+                    f"h:{hm5C_threshold}",
+                    "-t",
+                    threads,
+                    str(input_file),
+                    str(output_tsv),
+                ]
             else:
                 extract_command = [
-                    "modkit", "extract",
-                    "calls", "--mapped-only",
-                    "--filter-threshold", f'{filter_threshold}',
-                    "--mod-thresholds", f"m:{m5C_threshold}",
-                    "--mod-thresholds", f"a:{m6A_threshold}",
-                    "--mod-thresholds", f"h:{hm5C_threshold}",
-                    str(input_file), str(output_tsv)
-                    ]                    
+                    "modkit",
+                    "extract",
+                    "calls",
+                    "--mapped-only",
+                    "--filter-threshold",
+                    f"{filter_threshold}",
+                    "--mod-thresholds",
+                    f"m:{m5C_threshold}",
+                    "--mod-thresholds",
+                    f"a:{m6A_threshold}",
+                    "--mod-thresholds",
+                    f"h:{hm5C_threshold}",
+                    str(input_file),
+                    str(output_tsv),
+                ]
             subprocess.run(extract_command)
             # Zip the output TSV
-            print(f'zipping {output_tsv}')
+            logger.info(f"zipping {output_tsv}")
             if threads:
                 zip_command = ["pigz", "-f", "-p", threads, str(output_tsv)]
             else:
@@ -79,30 +105,39 @@ def extract_mods(thresholds, mod_tsv_dir, split_dir, bam_suffix, skip_unclassifi
             subprocess.run(zip_command, check=True)
     return
 
+
 def make_modbed(aligned_sorted_output, thresholds, mod_bed_dir):
     """
     Generating position methylation summaries for each barcoded sample starting from the overall BAM file that was direct output of dorado aligner.
     Parameters:
         aligned_sorted_output (str): A string representing the file path to the aligned_sorted non-split BAM file.
-    
+
     Returns:
         None
     """
-    import os
     import subprocess
-    
+
     filter_threshold, m6A_threshold, m5C_threshold, hm5C_threshold = thresholds
     command = [
-        "modkit", "pileup", str(aligned_sorted_output), str(mod_bed_dir),
-        "--partition-tag", "BC",
+        "modkit",
+        "pileup",
+        str(aligned_sorted_output),
+        str(mod_bed_dir),
+        "--partition-tag",
+        "BC",
         "--only-tabs",
-        "--filter-threshold", f'{filter_threshold}',
-        "--mod-thresholds", f"m:{m5C_threshold}",
-        "--mod-thresholds", f"a:{m6A_threshold}",
-        "--mod-thresholds", f"h:{hm5C_threshold}"
+        "--filter-threshold",
+        f"{filter_threshold}",
+        "--mod-thresholds",
+        f"m:{m5C_threshold}",
+        "--mod-thresholds",
+        f"a:{m6A_threshold}",
+        "--mod-thresholds",
+        f"h:{hm5C_threshold}",
     ]
     subprocess.run(command)
 
+
 def modQC(aligned_sorted_output, thresholds):
     """
     Output the percentile of bases falling at a call threshold (threshold is a probability between 0-1) for the overall BAM file.
@@ -120,10 +155,16 @@ def modQC(aligned_sorted_output, thresholds):
     filter_threshold, m6A_threshold, m5C_threshold, hm5C_threshold = thresholds
     subprocess.run(["modkit", "sample-probs", str(aligned_sorted_output)])
     command = [
-        "modkit", "summary", str(aligned_sorted_output),
-        "--filter-threshold", f"{filter_threshold}",
-        "--mod-thresholds", f"m:{m5C_threshold}",
-        "--mod-thresholds", f"a:{m6A_threshold}",
-        "--mod-thresholds", f"h:{hm5C_threshold}"
+        "modkit",
+        "summary",
+        str(aligned_sorted_output),
+        "--filter-threshold",
+        f"{filter_threshold}",
+        "--mod-thresholds",
+        f"m:{m5C_threshold}",
+        "--mod-thresholds",
+        f"a:{m6A_threshold}",
+        "--mod-thresholds",
+        f"h:{hm5C_threshold}",
     ]
-    subprocess.run(command)
+    subprocess.run(command)

smftools/informatics/ohe.py

@@ -1,10 +1,15 @@
-import numpy as np
+import concurrent.futures
+import os
+
 import anndata as ad
+import numpy as np
 
-import os
-import concurrent.futures
+from smftools.logging_utils import get_logger
+
+logger = get_logger(__name__)
 
-def one_hot_encode(sequence, device='auto'):
+
+def one_hot_encode(sequence, device="auto"):
     """
     One-hot encodes a DNA sequence.
 
@@ -14,7 +19,7 @@ def one_hot_encode(sequence, device='auto'):
     Returns:
         ndarray: Flattened one-hot encoded representation of the input sequence.
     """
-    mapping = np.array(['A', 'C', 'G', 'T', 'N'])
+    mapping = np.array(["A", "C", "G", "T", "N"])
 
     # Ensure input is a list of characters
     if not isinstance(sequence, list):
@@ -22,14 +27,14 @@ def one_hot_encode(sequence, device='auto'):
 
     # Handle empty sequences
     if len(sequence) == 0:
-        print("Warning: Empty sequence encountered in one_hot_encode()")
+        logger.warning("Empty sequence encountered in one_hot_encode()")
         return np.zeros(len(mapping))  # Return empty encoding instead of failing
 
     # Convert sequence to NumPy array
-    seq_array = np.array(sequence, dtype='<U1')
+    seq_array = np.array(sequence, dtype="<U1")
 
     # Replace invalid bases with 'N'
-    seq_array = np.where(np.isin(seq_array, mapping), seq_array, 'N')
+    seq_array = np.where(np.isin(seq_array, mapping), seq_array, "N")
 
     # Create one-hot encoding matrix
     one_hot_matrix = (seq_array[:, None] == mapping).astype(int)
@@ -37,6 +42,7 @@ def one_hot_encode(sequence, device='auto'):
     # Flatten and return
     return one_hot_matrix.flatten()
 
+
 def one_hot_decode(ohe_array):
     """
     Takes a flattened one hot encoded array and returns the sequence string from that array.
@@ -47,20 +53,21 @@ def one_hot_decode(ohe_array):
         sequence (str): Sequence string of the one hot encoded array
     """
     # Define the mapping of one-hot encoded indices to DNA bases
-    mapping = ['A', 'C', 'G', 'T', 'N']
-    
+    mapping = ["A", "C", "G", "T", "N"]
+
     # Reshape the flattened array into a 2D matrix with 5 columns (one for each base)
     one_hot_matrix = ohe_array.reshape(-1, 5)
-    
+
     # Get the index of the maximum value (which will be 1) in each row
     decoded_indices = np.argmax(one_hot_matrix, axis=1)
-    
+
     # Map the indices back to the corresponding bases
     sequence_list = [mapping[i] for i in decoded_indices]
-    sequence = ''.join(sequence_list)
-    
+    sequence = "".join(sequence_list)
+
     return sequence
 
+
 def ohe_layers_decode(adata, obs_names):
     """
     Takes an anndata object and a list of observation names. Returns a list of sequence strings for the reads of interest.
@@ -72,7 +79,7 @@ def ohe_layers_decode(adata, obs_names):
         sequences (list of str): List of strings of the one hot encoded array
     """
     # Define the mapping of one-hot encoded indices to DNA bases
-    mapping = ['A', 'C', 'G', 'T', 'N']
+    mapping = ["A", "C", "G", "T", "N"]
 
     ohe_layers = [f"{base}_binary_encoding" for base in mapping]
     sequences = []
@@ -85,9 +92,10 @@ def ohe_layers_decode(adata, obs_names):
         ohe_array = np.array(ohe_list)
         sequence = one_hot_decode(ohe_array)
         sequences.append(sequence)
-        
+
     return sequences
 
+
 def _encode_sequence(args):
     """Parallel helper function for one-hot encoding."""
     read_name, seq, device = args
@@ -97,18 +105,29 @@ def _encode_sequence(args):
     except Exception:
         return None  # Skip invalid sequences
 
+
 def _encode_and_save_batch(batch_data, tmp_dir, prefix, record, batch_number):
     """Encodes a batch and writes to disk immediately."""
     batch = {read_name: matrix for read_name, matrix in batch_data if matrix is not None}
 
     if batch:
-        save_name = os.path.join(tmp_dir, f'tmp_{prefix}_{record}_{batch_number}.h5ad')
+        save_name = os.path.join(tmp_dir, f"tmp_{prefix}_{record}_{batch_number}.h5ad")
         tmp_ad = ad.AnnData(X=np.zeros((1, 1)), uns=batch)  # Placeholder X
         tmp_ad.write_h5ad(save_name)
         return save_name
     return None
 
-def ohe_batching(base_identities, tmp_dir, record, prefix='', batch_size=100000, progress_bar=None, device='auto', threads=None):
+
+def ohe_batching(
+    base_identities,
+    tmp_dir,
+    record,
+    prefix="",
+    batch_size=100000,
+    progress_bar=None,
+    device="auto",
+    threads=None,
+):
     """
     Efficient version of ohe_batching: one-hot encodes sequences in parallel and writes batches immediately.
 
@@ -131,7 +150,9 @@ def ohe_batching(base_identities, tmp_dir, record, prefix='', batch_size=100000,
     file_names = []
 
     # Step 1: Prepare Data for Parallel Encoding
-    encoding_args = [(read_name, seq, device) for read_name, seq in base_identities.items() if seq is not None]
+    encoding_args = [
+        (read_name, seq, device) for read_name, seq in base_identities.items() if seq is not None
+    ]
 
     # Step 2: Parallel One-Hot Encoding using threads (to avoid nested processes)
     with concurrent.futures.ThreadPoolExecutor(max_workers=threads) as executor:
@@ -141,7 +162,9 @@ def ohe_batching(base_identities, tmp_dir, record, prefix='', batch_size=100000,
 
                 if len(batch_data) >= batch_size:
                     # Step 3: Process and Write Batch Immediately
-                    file_name = _encode_and_save_batch(batch_data.copy(), tmp_dir, prefix, record, batch_number)
+                    file_name = _encode_and_save_batch(
+                        batch_data.copy(), tmp_dir, prefix, record, batch_number
+                    )
                     if file_name:
                         file_names.append(file_name)
 
@@ -157,4 +180,4 @@ def ohe_batching(base_identities, tmp_dir, record, prefix='', batch_size=100000,
         if file_name:
             file_names.append(file_name)
 
-    return file_names
+    return file_names

smftools/informatics/pod5_functions.py

@@ -1,26 +1,29 @@
-from ..config import LoadExperimentConfig
-from ..readwrite import make_dirs
+from __future__ import annotations
 
 import os
 import subprocess
 from pathlib import Path
+from typing import Iterable
 
 import pod5 as p5
 
-from typing import Union, List
+from smftools.logging_utils import get_logger
 
-def basecall_pod5s(config_path):
-    """
-    Basecall from pod5s given a config file.
+from ..config import LoadExperimentConfig
+from ..informatics.basecalling import canoncall, modcall
+from ..readwrite import make_dirs
 
-    Parameters:
-        config_path (str): File path to the basecall configuration file
+logger = get_logger(__name__)
 
-    Returns:
-        None
+
+def basecall_pod5s(config_path: str | Path) -> None:
+    """Basecall POD5 inputs using a configuration file.
+
+    Args:
+        config_path: Path to the basecall configuration file.
     """
     # Default params
-    bam_suffix = '.bam' # If different, change from here.
+    bam_suffix = ".bam"  # If different, change from here.
 
     # Load experiment config parameters into global variables
     experiment_config = LoadExperimentConfig(config_path)
@@ -30,66 +33,89 @@ def basecall_pod5s(config_path):
     default_value = None
 
     # General config variable init
-    input_data_path = Path(var_dict.get('input_data_path', default_value)) # Path to a directory of POD5s/FAST5s or to a BAM/FASTQ file. Necessary.
-    output_directory = Path(var_dict.get('output_directory', default_value)) # Path to the output directory to make for the analysis. Necessary.
-    model = var_dict.get('model', default_value) # needed for dorado basecaller
-    model_dir = Path(var_dict.get('model_dir', default_value)) # model directory
-    barcode_kit = var_dict.get('barcode_kit', default_value) # needed for dorado basecaller
-    barcode_both_ends = var_dict.get('barcode_both_ends', default_value) # dorado demultiplexing
-    trim = var_dict.get('trim', default_value) # dorado adapter and barcode removal
-    device = var_dict.get('device', 'auto')
+    input_data_path = Path(
+        var_dict.get("input_data_path", default_value)
+    )  # Path to a directory of POD5s/FAST5s or to a BAM/FASTQ file. Necessary.
+    output_directory = Path(
+        var_dict.get("output_directory", default_value)
+    )  # Path to the output directory to make for the analysis. Necessary.
+    model = var_dict.get("model", default_value)  # needed for dorado basecaller
+    model_dir = Path(var_dict.get("model_dir", default_value))  # model directory
+    barcode_kit = var_dict.get("barcode_kit", default_value)  # needed for dorado basecaller
+    barcode_both_ends = var_dict.get("barcode_both_ends", default_value)  # dorado demultiplexing
+    trim = var_dict.get("trim", default_value)  # dorado adapter and barcode removal
+    device = var_dict.get("device", "auto")
 
     # Modified basecalling specific variable init
-    filter_threshold = var_dict.get('filter_threshold', default_value)
-    m6A_threshold = var_dict.get('m6A_threshold', default_value)
-    m5C_threshold = var_dict.get('m5C_threshold', default_value)
-    hm5C_threshold = var_dict.get('hm5C_threshold', default_value)
+    filter_threshold = var_dict.get("filter_threshold", default_value)
+    m6A_threshold = var_dict.get("m6A_threshold", default_value)
+    m5C_threshold = var_dict.get("m5C_threshold", default_value)
+    hm5C_threshold = var_dict.get("hm5C_threshold", default_value)
     thresholds = [filter_threshold, m6A_threshold, m5C_threshold, hm5C_threshold]
-    mod_list = var_dict.get('mod_list', default_value)
-    
+    mod_list = var_dict.get("mod_list", default_value)
+
     # Make initial output directory
     make_dirs([output_directory])
 
     # Get the input filetype
     if input_data_path.is_file():
         input_data_filetype = input_data_path.suffixes[0]
-        input_is_pod5 = input_data_filetype in ['.pod5','.p5']
-        input_is_fast5 = input_data_filetype in ['.fast5','.f5']
+        input_is_pod5 = input_data_filetype in [".pod5", ".p5"]
+        input_is_fast5 = input_data_filetype in [".fast5", ".f5"]
 
     elif input_data_path.is_dir():
         # Get the file names in the input data dir
         input_files = input_data_path.iterdir()
-        input_is_pod5 = sum([True for file in input_files if '.pod5' in file or '.p5' in file])
-        input_is_fast5 = sum([True for file in input_files if '.fast5' in file or '.f5' in file])
+        input_is_pod5 = sum([True for file in input_files if ".pod5" in file or ".p5" in file])
+        input_is_fast5 = sum([True for file in input_files if ".fast5" in file or ".f5" in file])
 
     # If the input files are not pod5 files, and they are fast5 files, convert the files to a pod5 file before proceeding.
     if input_is_fast5 and not input_is_pod5:
         # take the input directory of fast5 files and write out a single pod5 file into the output directory.
-        output_pod5 = output_directory / 'FAST5s_to_POD5.pod5'
-        print(f'Input directory contains fast5 files, converting them and concatenating into a single pod5 file in the {output_pod5}')
+        output_pod5 = output_directory / "FAST5s_to_POD5.pod5"
+        logger.info(
+            f"Input directory contains fast5 files, converting them and concatenating into a single pod5 file in the {output_pod5}"
+        )
         fast5_to_pod5(input_data_path, output_pod5)
         # Reassign the pod5_dir variable to point to the new pod5 file.
         input_data_path = output_pod5
 
     model_basename = model.name
-    model_basename = model_basename.replace('.', '_')
+    model_basename = model_basename.replace(".", "_")
 
     if mod_list:
         mod_string = "_".join(mod_list)
         bam = output_directory / f"{model_basename}_{mod_string}_calls"
-        modcall(model, input_data_path, barcode_kit, mod_list, bam, bam_suffix, barcode_both_ends, trim, device)
+        modcall(
+            model,
+            input_data_path,
+            barcode_kit,
+            mod_list,
+            bam,
+            bam_suffix,
+            barcode_both_ends,
+            trim,
+            device,
+        )
     else:
         bam = output_directory / f"{model_basename}_canonical_basecalls"
-        canoncall(model, input_data_path, barcode_kit, bam, bam_suffix, barcode_both_ends, trim, device)
+        canoncall(
+            model, input_data_path, barcode_kit, bam, bam_suffix, barcode_both_ends, trim, device
+        )
 
 
 def fast5_to_pod5(
-    fast5_dir: Union[str, Path, List[Union[str, Path]]],
-    output_pod5: Union[str, Path] = "FAST5s_to_POD5.pod5"
+    fast5_dir: str | Path | Iterable[str | Path],
+    output_pod5: str | Path = "FAST5s_to_POD5.pod5",
 ) -> None:
-    """
-    Convert Nanopore FAST5 files (single file, list of files, or directory)
-    into a single .pod5 output using the 'pod5 convert fast5' CLI tool.
+    """Convert FAST5 inputs into a single POD5 file.
+
+    Args:
+        fast5_dir: FAST5 file path, directory, or iterable of file paths to convert.
+        output_pod5: Output POD5 file path.
+
+    Raises:
+        FileNotFoundError: If no FAST5 files are found or the input path is invalid.
     """
 
     output_pod5 = str(output_pod5)  # ensure string
@@ -122,45 +148,51 @@ def fast5_to_pod5(
 
     raise FileNotFoundError(f"Input path invalid: {fast5_dir}")
 
-def subsample_pod5(pod5_path, read_name_path, output_directory):
-    """
-    Takes a POD5 file and a text file containing read names of interest and writes out a subsampled POD5 for just those reads.
-    This is a useful function when you have a list of read names that mapped to a region of interest that you want to reanalyze from the pod5 level.
 
-    Parameters:
-        pod5_path (str): File path to the POD5 file (or directory of multiple pod5 files) to subsample.
-        read_name_path (str | int): File path to a text file of read names. One read name per line. If an int value is passed, a random subset of that many reads will occur
-        output_directory (str): A file path to the directory to output the file.
+def subsample_pod5(
+    pod5_path: str | Path,
+    read_name_path: str | int,
+    output_directory: str | Path,
+) -> None:
+    """Write a subsampled POD5 containing selected reads.
 
-    Returns:
-        None
+    Args:
+        pod5_path: POD5 file path or directory of POD5 files to subsample.
+        read_name_path: Path to a text file of read names (one per line) or an integer
+            specifying a random subset size.
+        output_directory: Directory to write the subsampled POD5 file.
     """
 
     if os.path.isdir(pod5_path):
         pod5_path_is_dir = True
-        input_pod5_base = 'input_pod5s.pod5'
+        input_pod5_base = "input_pod5s.pod5"
         files = os.listdir(pod5_path)
-        pod5_files = [os.path.join(pod5_path, file) for file in files if '.pod5' in file]
+        pod5_files = [os.path.join(pod5_path, file) for file in files if ".pod5" in file]
         pod5_files.sort()
-        print(f'Found input pod5s: {pod5_files}')
-    
+        logger.info(f"Found input pod5s: {pod5_files}")
+
     elif os.path.exists(pod5_path):
         pod5_path_is_dir = False
         input_pod5_base = os.path.basename(pod5_path)
 
     else:
-        print('Error: pod5_path passed does not exist')
+        logger.error("pod5_path passed does not exist")
         return None
 
-    if type(read_name_path) == str:
+    if type(read_name_path) is str:
         input_read_name_base = os.path.basename(read_name_path)
-        output_base = input_pod5_base.split('.pod5')[0] + '_' + input_read_name_base.split('.txt')[0] + '_subsampled.pod5'
+        output_base = (
+            input_pod5_base.split(".pod5")[0]
+            + "_"
+            + input_read_name_base.split(".txt")[0]
+            + "_subsampled.pod5"
+        )
 
         # extract read names into a list of strings
-        with open(read_name_path, 'r') as file:
+        with open(read_name_path, "r") as file:
             read_names = [line.strip() for line in file]
 
-        print(f'Looking for read_ids: {read_names}')
+        logger.info(f"Looking for read_ids: {read_names}")
         read_records = []
 
         if pod5_path_is_dir:
@@ -168,22 +200,25 @@ def subsample_pod5(pod5_path, read_name_path, output_directory):
                 with p5.Reader(input_pod5) as reader:
                     try:
                         for read_record in reader.reads(selection=read_names, missing_ok=True):
-                            read_records.append(read_record.to_read())      
-                            print(f'Found read in {input_pod5}: {read_record.read_id}')      
-                    except:
-                        print('Skipping pod5, could not find reads')    
-        else:    
+                            read_records.append(read_record.to_read())
+                            logger.info(f"Found read in {input_pod5}: {read_record.read_id}")
+                    except Exception:
+                        logger.warning("Skipping pod5, could not find reads")
+        else:
             with p5.Reader(pod5_path) as reader:
                 try:
                     for read_record in reader.reads(selection=read_names):
                         read_records.append(read_record.to_read())
-                        print(f'Found read in {input_pod5}: {read_record}')  
-                except:
-                    print('Could not find reads')   
+                        logger.info(f"Found read in {input_pod5}: {read_record}")
+                except Exception:
+                    logger.warning("Could not find reads")
 
-    elif type(read_name_path) == int:
+    elif type(read_name_path) is int:
         import random
-        output_base = input_pod5_base.split('.pod5')[0] + f'_{read_name_path}_randomly_subsampled.pod5'
+
+        output_base = (
+            input_pod5_base.split(".pod5")[0] + f"_{read_name_path}_randomly_subsampled.pod5"
+        )
         all_read_records = []
 
         if pod5_path_is_dir:
@@ -191,7 +226,7 @@ def subsample_pod5(pod5_path, read_name_path, output_directory):
             random.shuffle(pod5_files)
             for input_pod5 in pod5_files:
                 # iterate over the input pod5s
-                print(f'Opening pod5 file {input_pod5}')
+                logger.info(f"Opening pod5 file {input_pod5}")
                 with p5.Reader(pod5_path) as reader:
                     for read_record in reader.reads():
                         all_read_records.append(read_record.to_read())
@@ -202,9 +237,11 @@ def subsample_pod5(pod5_path, read_name_path, output_directory):
             if read_name_path <= len(all_read_records):
                 read_records = random.sample(all_read_records, read_name_path)
             else:
-                print('Trying to sample more reads than are contained in the input pod5s, taking all reads')
+                logger.info(
+                    "Trying to sample more reads than are contained in the input pod5s, taking all reads"
+                )
                 read_records = all_read_records
-                    
+
         else:
             with p5.Reader(pod5_path) as reader:
                 for read_record in reader.reads():
@@ -214,11 +251,13 @@ def subsample_pod5(pod5_path, read_name_path, output_directory):
                 # if the subsampling amount is less than the record amount in the file, randomly subsample the reads
                 read_records = random.sample(all_read_records, read_name_path)
             else:
-                print('Trying to sample more reads than are contained in the input pod5s, taking all reads')
+                logger.info(
+                    "Trying to sample more reads than are contained in the input pod5s, taking all reads"
+                )
                 read_records = all_read_records
 
     output_pod5 = os.path.join(output_directory, output_base)
 
     # Write the subsampled POD5
     with p5.Writer(output_pod5) as writer:
-        writer.add_reads(read_records)
+        writer.add_reads(read_records)