diff --git a/src/__init__.py b/src/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/src/constants.py b/src/constants.py
new file mode 100644
index 0000000..8da64ef
--- /dev/null
+++ b/src/constants.py
@@ -0,0 +1 @@
+ALLOWED_BASES = "ACGT-"
diff --git a/src/model.py b/src/model.py
new file mode 100644
index 0000000..9a0aef8
--- /dev/null
+++ b/src/model.py
@@ -0,0 +1,6 @@
+from tensorflow_io import genome
+
+
+def parse_data(filepath):
+    HVR = genome.read_fastq(filename=filepath)
+    return HVR.sequences, HVR.raw_quality