diff --git a/.gitignore b/.gitignore
index 5a2dce5..c59b0c5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,5 @@
 .gitignore
 /venv
-/.pytest_cache
\ No newline at end of file
+/.pytest_cache
+__pycache__/
+*.pyc
diff --git a/.jules/bolt.md b/.jules/bolt.md
index 8780446..1775206 100644
--- a/.jules/bolt.md
+++ b/.jules/bolt.md
@@ -1,3 +1,7 @@
 ## 2024-05-23 - [Regex Pre-compilation in Loops]
 **Learning:** Pre-compiling regular expressions (`re.compile`) at the module level provides a significant performance boost (measured ~1.8x speedup) when the regex is used inside a tight loop or a pandas `apply` function, compared to compiling it repeatedly or implicitly inside the loop. Vectorized string operations in Pandas are usually faster, but in complex logic cases (multiple prioritized regex groups + fallback logic), a simple pre-compiled regex with `apply` can sometimes be cleaner and sufficiently fast, or even faster if the vectorized approach requires multiple passes or expensive intermediate structures.
 **Action:** Always check for regex usage in loops or `apply` calls. If found, refactor to use module-level pre-compiled patterns. When considering vectorization, benchmark against the optimized loop version, as the overhead of complex vectorization might outweigh the benefits for moderate dataset sizes.
+
+## 2024-10-30 - [Streaming Text Decoding]
+**Learning:** When handling large text-based file uploads (like MGF/mzTab) in Streamlit/Python, using `io.TextIOWrapper(binary_stream, encoding='utf-8')` is significantly more memory-efficient than `io.StringIO(binary_stream.read().decode('utf-8'))`. The latter approach loads the entire binary content into memory, creates a huge string copy, and then creates another buffer, potentially tripling memory usage. The wrapper approach streams the decoding, keeping memory footprint low.
+**Action:** Use `io.TextIOWrapper` for parsing large text files from binary streams (like `streamlit.UploadedFile`) instead of reading and decoding the full content. Verify compatibility with downstream parsers (e.g., `pyteomics` supports it).
diff --git a/__pycache__/data_loading.cpython-312.pyc b/__pycache__/data_loading.cpython-312.pyc
new file mode 100644
index 0000000..77ed2c9
Binary files /dev/null and b/__pycache__/data_loading.cpython-312.pyc differ
diff --git a/__pycache__/processing.cpython-312.pyc b/__pycache__/processing.cpython-312.pyc
new file mode 100644
index 0000000..b9a17d9
Binary files /dev/null and b/__pycache__/processing.cpython-312.pyc differ
diff --git a/app.py b/app.py
index aa7990e..f4c3782 100644
--- a/app.py
+++ b/app.py
@@ -32,9 +32,9 @@ def run_streamlit_app():
     # Process files only when both are uploaded
     if mgf_file and mztab_file:
         # Decode uploaded file contents (Streamlit files are bytes by default)
-        # Use StringIO to create file-like objects for pyteomics parsers
-        spectra = load_mgf(io.StringIO(mgf_file.read().decode('utf-8')))
-        psm_df = load_mztab(io.StringIO(mztab_file.read().decode('utf-8')))
+        # Use TextIOWrapper to create streaming file-like objects, avoiding full memory load
+        spectra = load_mgf(io.TextIOWrapper(mgf_file, encoding='utf-8'))
+        psm_df = load_mztab(io.TextIOWrapper(mztab_file, encoding='utf-8'))
 
         # Create mappings between PSMs and spectra
         mapped = map_psms_to_spectra(spectra, psm_df)
diff --git a/tests/__pycache__/__init__.cpython-312.pyc b/tests/__pycache__/__init__.cpython-312.pyc
new file mode 100644
index 0000000..9804010
Binary files /dev/null and b/tests/__pycache__/__init__.cpython-312.pyc differ
diff --git a/tests/__pycache__/conftest.cpython-312-pytest-9.0.2.pyc b/tests/__pycache__/conftest.cpython-312-pytest-9.0.2.pyc
new file mode 100644
index 0000000..6a2f6b8
Binary files /dev/null and b/tests/__pycache__/conftest.cpython-312-pytest-9.0.2.pyc differ
diff --git a/tests/__pycache__/test_extract_index_from_spectra_ref.cpython-312-pytest-9.0.2.pyc b/tests/__pycache__/test_extract_index_from_spectra_ref.cpython-312-pytest-9.0.2.pyc
new file mode 100644
index 0000000..b380bd8
Binary files /dev/null and b/tests/__pycache__/test_extract_index_from_spectra_ref.cpython-312-pytest-9.0.2.pyc differ
diff --git a/tests/__pycache__/test_integration.cpython-312-pytest-9.0.2.pyc b/tests/__pycache__/test_integration.cpython-312-pytest-9.0.2.pyc
new file mode 100644
index 0000000..7c5342c
Binary files /dev/null and b/tests/__pycache__/test_integration.cpython-312-pytest-9.0.2.pyc differ
diff --git a/tests/__pycache__/test_load_mgf.cpython-312-pytest-9.0.2.pyc b/tests/__pycache__/test_load_mgf.cpython-312-pytest-9.0.2.pyc
new file mode 100644
index 0000000..e434a95
Binary files /dev/null and b/tests/__pycache__/test_load_mgf.cpython-312-pytest-9.0.2.pyc differ
diff --git a/tests/__pycache__/test_load_mztab.cpython-312-pytest-9.0.2.pyc b/tests/__pycache__/test_load_mztab.cpython-312-pytest-9.0.2.pyc
new file mode 100644
index 0000000..aefee96
Binary files /dev/null and b/tests/__pycache__/test_load_mztab.cpython-312-pytest-9.0.2.pyc differ
diff --git a/tests/__pycache__/test_map_psms_to_spectra.cpython-312-pytest-9.0.2.pyc b/tests/__pycache__/test_map_psms_to_spectra.cpython-312-pytest-9.0.2.pyc
new file mode 100644
index 0000000..bc3a5d0
Binary files /dev/null and b/tests/__pycache__/test_map_psms_to_spectra.cpython-312-pytest-9.0.2.pyc differ
diff --git a/tests/__pycache__/test_streaming_io.cpython-312-pytest-9.0.2.pyc b/tests/__pycache__/test_streaming_io.cpython-312-pytest-9.0.2.pyc
new file mode 100644
index 0000000..75b18f1
Binary files /dev/null and b/tests/__pycache__/test_streaming_io.cpython-312-pytest-9.0.2.pyc differ
diff --git a/tests/test_streaming_io.py b/tests/test_streaming_io.py
new file mode 100644
index 0000000..9856fde
--- /dev/null
+++ b/tests/test_streaming_io.py
@@ -0,0 +1,55 @@
+import io
+import pytest
+import pandas as pd
+from data_loading import load_mgf, load_mztab
+
+class TestStreamingIO:
+    """
+    Test suite to ensure that data loading functions support streaming I/O.
+    This validates the optimization of using TextIOWrapper instead of reading
+    entire files into memory.
+    """
+
+    def test_load_mgf_streaming(self):
+        """Test load_mgf with io.TextIOWrapper wrapping a binary stream."""
+        mgf_content = b"""BEGIN IONS
+TITLE=test_spectrum
+PEPMASS=450.25
+1.0 10.0
+2.0 20.0
+END IONS
+"""
+        # Simulate binary stream (like Streamlit's UploadedFile)
+        binary_stream = io.BytesIO(mgf_content)
+
+        # Wrap with TextIOWrapper to simulate streaming text decoding
+        text_stream = io.TextIOWrapper(binary_stream, encoding='utf-8')
+
+        # This should not raise an error
+        spectra = load_mgf(text_stream)
+
+        assert len(spectra) == 1
+        assert spectra[0]['title'] == 'test_spectrum'
+        assert spectra[0]['pepmass'] == (450.25, None)
+        assert len(spectra[0]['mz_array']) == 2
+
+    def test_load_mztab_streaming(self):
+        """Test load_mztab with io.TextIOWrapper wrapping a binary stream."""
+        mztab_content = b"""MTD\tmzTab-version\t1.0.0
+MTD\tmzTab-mode\tSummary
+PSH\tsequence\tPSM_ID\tspectra_ref
+PSM\tPEPTIDE_SEQ\t1\tms_run[1]:index=0
+"""
+        # Simulate binary stream
+        binary_stream = io.BytesIO(mztab_content)
+
+        # Wrap with TextIOWrapper
+        text_stream = io.TextIOWrapper(binary_stream, encoding='utf-8')
+
+        # This should not raise an error
+        df = load_mztab(text_stream)
+
+        assert isinstance(df, pd.DataFrame)
+        assert len(df) == 1
+        assert df.iloc[0]['sequence'] == 'PEPTIDE_SEQ'
+        assert df.iloc[0]['spectra_ref'] == 'ms_run[1]:index=0'