diff --git a/environment.yaml b/environment.yaml
new file mode 100644
index 0000000..b17c34f
--- /dev/null
+++ b/environment.yaml
@@ -0,0 +1,526 @@
+name: base
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - _anaconda_depends=2023.09=py311_openblas_1
+  - abseil-cpp=20211102.0=hc377ac9_0
+  - aiobotocore=2.5.0=py311hca03da5_0
+  - aiofiles=22.1.0=py311hca03da5_0
+  - aiohttp=3.8.5=py311h80987f9_0
+  - aioitertools=0.7.1=pyhd3eb1b0_0
+  - aiosignal=1.2.0=pyhd3eb1b0_0
+  - aiosqlite=0.18.0=py311hca03da5_0
+  - alabaster=0.7.12=pyhd3eb1b0_0
+  - anaconda-anon-usage=0.4.2=py311hd6b623d_0
+  - anaconda-catalogs=0.2.0=py311hca03da5_0
+  - anaconda-client=1.12.1=py311hca03da5_0
+  - anaconda-cloud-auth=0.1.3=py311hca03da5_0
+  - anaconda-navigator=2.5.1=py311hca03da5_0
+  - anaconda-project=0.11.1=py311hca03da5_0
+  - anyio=3.5.0=py311hca03da5_0
+  - aom=3.6.0=h313beb8_0
+  - appdirs=1.4.4=pyhd3eb1b0_0
+  - applaunchservices=0.3.0=py311hca03da5_0
+  - appnope=0.1.2=py311hca03da5_1001
+  - appscript=1.1.2=py311h80987f9_0
+  - argon2-cffi=21.3.0=pyhd3eb1b0_0
+  - argon2-cffi-bindings=21.2.0=py311h80987f9_0
+  - arrow=1.2.3=py311hca03da5_1
+  - arrow-cpp=11.0.0=hc7aafb3_2
+  - astroid=2.14.2=py311hca03da5_0
+  - astropy=5.1=py311ha0d4635_0
+  - asttokens=2.0.5=pyhd3eb1b0_0
+  - async-timeout=4.0.2=py311hca03da5_0
+  - atomicwrites=1.4.0=py_0
+  - attrs=22.1.0=py311hca03da5_0
+  - automat=20.2.0=py_0
+  - autopep8=1.6.0=pyhd3eb1b0_1
+  - aws-c-common=0.6.8=h80987f9_1
+  - aws-c-event-stream=0.1.6=h313beb8_6
+  - aws-checksums=0.1.11=h80987f9_2
+  - aws-sdk-cpp=1.8.185=ha71a6ea_1
+  - babel=2.11.0=py311hca03da5_0
+  - backcall=0.2.0=pyhd3eb1b0_0
+  - backports=1.1=pyhd3eb1b0_0
+  - backports.functools_lru_cache=1.6.4=pyhd3eb1b0_0
+  - backports.tempfile=1.0=pyhd3eb1b0_1
+  - backports.weakref=1.0.post1=py_1
+  - bcrypt=3.2.0=py311h80987f9_1
+  - beautifulsoup4=4.12.2=py311hca03da5_0
+  - binaryornot=0.4.4=pyhd3eb1b0_1
+  - black=23.3.0=py311hca03da5_0
+  - blas=1.0=openblas
+  - bleach=4.1.0=pyhd3eb1b0_0
+  - blosc=1.21.3=h313beb8_0
+  - bokeh=3.2.1=py311hb6e6a13_0
+  - boltons=23.0.0=py311hca03da5_0
+  - boost-cpp=1.73.0=h1a28f6b_12
+  - botocore=1.29.76=py311hca03da5_0
+  - bottleneck=1.3.5=py311ha0d4635_0
+  - brotli=1.0.9=h1a28f6b_7
+  - brotli-bin=1.0.9=h1a28f6b_7
+  - brotlipy=0.7.0=py311h80987f9_1002
+  - brunsli=0.1=hc377ac9_1
+  - bzip2=1.0.8=h620ffc9_4
+  - c-ares=1.19.1=h80987f9_0
+  - c-blosc2=2.8.0=h313beb8_0
+  - ca-certificates=2025.1.31=hf0a4a13_0
+  - cctools=949.0.1=hc179dcd_25
+  - cctools_osx-arm64=949.0.1=h332cad3_25
+  - certifi=2025.1.31=pyhd8ed1ab_0
+  - cffi=1.15.1=py311h80987f9_3
+  - cfitsio=3.470=h7f6438f_7
+  - chardet=4.0.0=py311hca03da5_1003
+  - charls=2.2.0=hc377ac9_0
+  - charset-normalizer=2.0.4=pyhd3eb1b0_0
+  - click=8.0.4=py311hca03da5_0
+  - cloudpickle=2.2.1=py311hca03da5_0
+  - clyent=1.2.2=py311hca03da5_1
+  - colorama=0.4.6=py311hca03da5_0
+  - colorcet=3.0.1=py311hca03da5_0
+  - comm=0.1.2=py311hca03da5_0
+  - conda=23.7.4=py311hca03da5_0
+  - conda-build=3.26.1=py311hca03da5_0
+  - conda-content-trust=0.2.0=py311hca03da5_0
+  - conda-index=0.3.0=py311hca03da5_0
+  - conda-libmamba-solver=23.7.0=py311hca03da5_0
+  - conda-pack=0.6.0=pyhd3eb1b0_0
+  - conda-package-handling=2.2.0=py311hca03da5_0
+  - conda-package-streaming=0.9.0=py311hca03da5_0
+  - conda-repo-cli=1.0.75=py311hca03da5_0
+  - conda-token=0.4.0=pyhd3eb1b0_0
+  - conda-verify=3.4.2=py_1
+  - constantly=15.1.0=py311hca03da5_0
+  - contourpy=1.0.5=py311h48ca7d4_0
+  - cookiecutter=1.7.3=pyhd3eb1b0_0
+  - cryptography=41.0.3=py311hd4332d6_0
+  - cssselect=1.1.0=pyhd3eb1b0_0
+  - curl=8.2.1=h02f6b3c_0
+  - cycler=0.11.0=pyhd3eb1b0_0
+  - cyrus-sasl=2.1.28=h9131b1a_1
+  - cytoolz=0.12.0=py311h80987f9_0
+  - dask=2023.6.0=py311hca03da5_0
+  - dask-core=2023.6.0=py311hca03da5_0
+  - datasets=2.12.0=py311hca03da5_0
+  - datashader=0.15.2=py311hca03da5_0
+  - datashape=0.5.4=py311hca03da5_1
+  - dav1d=1.2.1=h80987f9_0
+  - debugpy=1.6.7=py311h313beb8_0
+  - decorator=5.1.1=pyhd3eb1b0_0
+  - defusedxml=0.7.1=pyhd3eb1b0_0
+  - diff-match-patch=20200713=pyhd3eb1b0_0
+  - dill=0.3.6=py311hca03da5_0
+  - distributed=2023.6.0=py311hca03da5_0
+  - docstring-to-markdown=0.11=py311hca03da5_0
+  - docutils=0.18.1=py311hca03da5_3
+  - entrypoints=0.4=py311hca03da5_0
+  - et_xmlfile=1.1.0=py311hca03da5_0
+  - executing=0.8.3=pyhd3eb1b0_0
+  - filelock=3.9.0=py311hca03da5_0
+  - flake8=6.0.0=py311hca03da5_0
+  - flask=2.2.2=py311hca03da5_0
+  - fmt=9.1.0=h48ca7d4_0
+  - fonttools=4.25.0=pyhd3eb1b0_0
+  - freetype=2.12.1=h1192e45_0
+  - frozenlist=1.3.3=py311h80987f9_0
+  - fsspec=2023.4.0=py311hca03da5_0
+  - future=0.18.3=py311hca03da5_0
+  - gensim=4.3.0=py311h6956b77_0
+  - gettext=0.21.0=h13f89a0_1
+  - gflags=2.2.2=hc377ac9_0
+  - giflib=5.2.1=h80987f9_3
+  - glib=2.69.1=h514c7bf_2
+  - glob2=0.7=pyhd3eb1b0_0
+  - glog=0.5.0=hc377ac9_0
+  - gmp=6.2.1=hc377ac9_3
+  - gmpy2=2.1.2=py311h40f64dc_0
+  - greenlet=2.0.1=py311h313beb8_0
+  - grpc-cpp=1.48.2=hc60591f_1
+  - gst-plugins-base=1.14.1=h313beb8_1
+  - gstreamer=1.14.1=h80987f9_1
+  - h5py=3.9.0=py311hba6ad2f_0
+  - hdf5=1.12.1=h05c076b_3
+  - heapdict=1.0.1=pyhd3eb1b0_0
+  - holoviews=1.17.1=py311hca03da5_0
+  - huggingface_hub=0.15.1=py311hca03da5_0
+  - hvplot=0.8.4=py311hca03da5_0
+  - hyperlink=21.0.0=pyhd3eb1b0_0
+  - icu=68.1=hc377ac9_0
+  - idna=3.4=py311hca03da5_0
+  - imagecodecs=2023.1.23=py311h5e7c512_0
+  - imageio=2.31.1=py311hca03da5_0
+  - imagesize=1.4.1=py311hca03da5_0
+  - imbalanced-learn=0.10.1=py311hca03da5_1
+  - importlib-metadata=6.0.0=py311hca03da5_0
+  - importlib_metadata=6.0.0=hd3eb1b0_0
+  - incremental=21.3.0=pyhd3eb1b0_0
+  - inflection=0.5.1=py311hca03da5_0
+  - iniconfig=1.1.1=pyhd3eb1b0_0
+  - intake=0.6.8=py311hca03da5_0
+  - intervaltree=3.1.0=pyhd3eb1b0_0
+  - ipykernel=6.25.0=py311hb6e6a13_0
+  - ipython=8.15.0=py311hca03da5_0
+  - ipython_genutils=0.2.0=pyhd3eb1b0_1
+  - ipywidgets=8.0.4=py311hca03da5_0
+  - isort=5.9.3=pyhd3eb1b0_0
+  - itemadapter=0.3.0=pyhd3eb1b0_0
+  - itemloaders=1.0.4=pyhd3eb1b0_1
+  - itsdangerous=2.0.1=pyhd3eb1b0_0
+  - jaraco.classes=3.2.1=pyhd3eb1b0_0
+  - jedi=0.18.1=py311hca03da5_1
+  - jellyfish=1.0.1=py311h15d1925_0
+  - jinja2=3.1.2=py311hca03da5_0
+  - jinja2-time=0.2.0=pyhd3eb1b0_3
+  - jmespath=0.10.0=pyhd3eb1b0_0
+  - joblib=1.2.0=py311hca03da5_0
+  - jpeg=9e=h80987f9_1
+  - jq=1.6=h1a28f6b_1
+  - json5=0.9.6=pyhd3eb1b0_0
+  - jsonpatch=1.32=pyhd3eb1b0_0
+  - jsonpointer=2.1=pyhd3eb1b0_0
+  - jsonschema=4.17.3=py311hca03da5_0
+  - jupyter=1.0.0=py311hca03da5_8
+  - jupyter_client=7.4.9=py311hca03da5_0
+  - jupyter_console=6.6.3=py311hca03da5_0
+  - jupyter_core=5.3.0=py311hca03da5_0
+  - jupyter_events=0.6.3=py311hca03da5_0
+  - jupyter_server=1.23.4=py311hca03da5_0
+  - jupyter_server_fileid=0.9.0=py311hca03da5_0
+  - jupyter_server_ydoc=0.8.0=py311hca03da5_1
+  - jupyter_ydoc=0.2.4=py311hca03da5_0
+  - jupyterlab=3.6.3=py311hca03da5_0
+  - jupyterlab_pygments=0.1.2=py_0
+  - jupyterlab_server=2.22.0=py311hca03da5_0
+  - jupyterlab_widgets=3.0.5=py311hca03da5_0
+  - jxrlib=1.1=h1a28f6b_2
+  - kaleido-core=0.2.1=h80987f9_0
+  - keyring=23.13.1=py311hca03da5_0
+  - kiwisolver=1.4.4=py311h313beb8_0
+  - krb5=1.20.1=hf3e1bf2_1
+  - krona=2.8.1=pl5321hdfd78af_1
+  - lazy-object-proxy=1.6.0=py311h80987f9_0
+  - lazy_loader=0.2=py311hca03da5_0
+  - lcms2=2.12=hba8e193_0
+  - ld64=530=hb29bf3f_25
+  - ld64_osx-arm64=530=h001ce53_25
+  - ldid=2.1.5=h20b2a84_3
+  - lerc=3.0=hc377ac9_0
+  - libaec=1.0.4=hc377ac9_1
+  - libarchive=3.6.2=h62fee54_2
+  - libavif=0.11.1=h80987f9_0
+  - libboost=1.73.0=h49e8a49_12
+  - libbrotlicommon=1.0.9=h1a28f6b_7
+  - libbrotlidec=1.0.9=h1a28f6b_7
+  - libbrotlienc=1.0.9=h1a28f6b_7
+  - libclang=14.0.6=default_h1b80db6_1
+  - libclang13=14.0.6=default_h24352ff_1
+  - libcurl=8.2.1=h3e2b118_0
+  - libcxx=14.0.6=h848a8c0_0
+  - libdeflate=1.17=h80987f9_0
+  - libedit=3.1.20221030=h80987f9_0
+  - libev=4.33=h1a28f6b_1
+  - libevent=2.1.12=h02f6b3c_1
+  - libffi=3.4.4=hca03da5_0
+  - libgfortran=5.0.0=11_3_0_hca03da5_28
+  - libgfortran5=11.3.0=h009349e_28
+  - libiconv=1.16=h1a28f6b_2
+  - liblief=0.12.3=h313beb8_0
+  - libllvm14=14.0.6=h7ec7a93_3
+  - libmamba=1.5.1=h15e39b3_0
+  - libmambapy=1.5.1=py311h1c5506f_0
+  - libnghttp2=1.52.0=h62f6fdd_1
+  - libopenblas=0.3.21=h269037a_0
+  - libpng=1.6.39=h80987f9_0
+  - libpq=12.15=h02f6b3c_1
+  - libprotobuf=3.20.3=h514c7bf_0
+  - libsodium=1.0.18=h1a28f6b_0
+  - libsolv=0.7.24=h514c7bf_0
+  - libspatialindex=1.9.3=hc377ac9_0
+  - libssh2=1.10.0=h02f6b3c_2
+  - libthrift=0.15.0=h73c2103_2
+  - libtiff=4.5.1=h313beb8_0
+  - libwebp=1.3.2=ha3663a8_0
+  - libwebp-base=1.3.2=h80987f9_0
+  - libxml2=2.10.4=h372ba2a_0
+  - libxslt=1.1.37=habca612_0
+  - libzopfli=1.0.3=hc377ac9_0
+  - linkify-it-py=2.0.0=py311hca03da5_0
+  - llvm-openmp=14.0.6=hc6e5704_0
+  - llvmlite=0.40.0=py311h514c7bf_0
+  - locket=1.0.0=py311hca03da5_0
+  - lxml=4.9.3=py311h50ffb84_0
+  - lz4=4.3.2=py311h80987f9_0
+  - lz4-c=1.9.4=h313beb8_0
+  - lzo=2.10=h1a28f6b_2
+  - markdown=3.4.1=py311hca03da5_0
+  - markdown-it-py=2.2.0=py311hca03da5_1
+  - markupsafe=2.1.1=py311h80987f9_0
+  - mathjax=2.7.5=hca03da5_0
+  - matplotlib=3.7.2=py311hca03da5_0
+  - matplotlib-base=3.7.2=py311h7aedaa7_0
+  - matplotlib-inline=0.1.6=py311hca03da5_0
+  - mccabe=0.7.0=pyhd3eb1b0_0
+  - mdit-py-plugins=0.3.0=py311hca03da5_0
+  - mdurl=0.1.0=py311hca03da5_0
+  - mistune=0.8.4=py311h80987f9_1000
+  - more-itertools=8.12.0=pyhd3eb1b0_0
+  - mpc=1.1.0=h8c48613_1
+  - mpfr=4.0.2=h695f6f0_1
+  - mpmath=1.3.0=py311hca03da5_0
+  - msgpack-python=1.0.3=py311h48ca7d4_0
+  - multidict=6.0.2=py311h80987f9_0
+  - multipledispatch=0.6.0=py311hca03da5_0
+  - multiprocess=0.70.14=py311hca03da5_0
+  - munkres=1.1.4=py_0
+  - mypy_extensions=1.0.0=py311hca03da5_0
+  - mysql=5.7.24=ha71a6ea_2
+  - navigator-updater=0.4.0=py311hca03da5_1
+  - nbclassic=0.5.5=py311hca03da5_0
+  - nbclient=0.5.13=py311hca03da5_0
+  - nbconvert=6.5.4=py311hca03da5_0
+  - nbformat=5.9.2=py311hca03da5_0
+  - ncurses=6.4=h313beb8_0
+  - nest-asyncio=1.5.6=py311hca03da5_0
+  - networkx=3.1=py311hca03da5_0
+  - nltk=3.8.1=py311hca03da5_0
+  - notebook=6.5.4=py311hca03da5_1
+  - notebook-shim=0.2.2=py311hca03da5_0
+  - numba=0.57.1=py311h7aedaa7_0
+  - numexpr=2.8.4=py311h6dc990b_1
+  - numpy=1.24.3=py311hb57d4eb_0
+  - numpy-base=1.24.3=py311h1d85a46_0
+  - numpydoc=1.5.0=py311hca03da5_0
+  - oniguruma=6.9.7.1=h1a28f6b_0
+  - openjpeg=2.3.0=h7a6adac_2
+  - openpyxl=3.0.10=py311h80987f9_0
+  - openssl=3.4.1=h81ee809_0
+  - orc=1.7.4=hdca1487_1
+  - pandas=2.0.3=py311h7aedaa7_0
+  - pandoc=3.6.2=hce30654_0
+  - pandocfilters=1.5.0=pyhd3eb1b0_0
+  - panel=1.2.3=py311hca03da5_0
+  - param=1.13.0=py311hca03da5_0
+  - parsel=1.6.0=py311hca03da5_0
+  - parso=0.8.3=pyhd3eb1b0_0
+  - partd=1.4.0=py311hca03da5_0
+  - patch=2.7.6=h1a28f6b_1001
+  - pathlib=1.0.1=pyhd3eb1b0_1
+  - pathspec=0.10.3=py311hca03da5_0
+  - patsy=0.5.3=py311hca03da5_0
+  - pcre=8.45=hc377ac9_0
+  - pcre2=10.42=hb066dcc_0
+  - pep8=1.7.1=py311hca03da5_1
+  - perl=5.32.1=7_h4614cfb_perl5
+  - pexpect=4.8.0=pyhd3eb1b0_3
+  - pickleshare=0.7.5=pyhd3eb1b0_1003
+  - pillow=10.4.0=py311h80987f9_0
+  - pip=23.2.1=py311hca03da5_0
+  - pkce=1.0.3=py311hca03da5_0
+  - pkginfo=1.9.6=py311hca03da5_0
+  - platformdirs=3.10.0=py311hca03da5_0
+  - plotly=5.9.0=py311hca03da5_0
+  - pluggy=1.0.0=py311hca03da5_1
+  - ply=3.11=py311hca03da5_0
+  - poyo=0.5.0=pyhd3eb1b0_0
+  - prometheus_client=0.14.1=py311hca03da5_0
+  - prompt-toolkit=3.0.36=py311hca03da5_0
+  - prompt_toolkit=3.0.36=hd3eb1b0_0
+  - protego=0.1.16=py_0
+  - psutil=5.9.0=py311h80987f9_0
+  - ptyprocess=0.7.0=pyhd3eb1b0_2
+  - pure_eval=0.2.2=pyhd3eb1b0_0
+  - py-cpuinfo=8.0.0=pyhd3eb1b0_1
+  - py-lief=0.12.3=py311h313beb8_0
+  - pyarrow=11.0.0=py311h7575258_1
+  - pyasn1=0.4.8=pyhd3eb1b0_0
+  - pyasn1-modules=0.2.8=py_0
+  - pybind11-abi=4=hd3eb1b0_1
+  - pycodestyle=2.10.0=py311hca03da5_0
+  - pycosat=0.6.4=py311h80987f9_0
+  - pycparser=2.21=pyhd3eb1b0_0
+  - pyct=0.5.0=py311hca03da5_0
+  - pycurl=7.45.2=py311h02f6b3c_1
+  - pydantic=1.10.8=py311h80987f9_0
+  - pydispatcher=2.0.5=py311hca03da5_2
+  - pydocstyle=6.3.0=py311hca03da5_0
+  - pyerfa=2.0.0=py311h80987f9_0
+  - pyflakes=3.0.1=py311hca03da5_0
+  - pygments=2.15.1=py311hca03da5_1
+  - pyjwt=2.4.0=py311hca03da5_0
+  - pylint=2.16.2=py311hca03da5_0
+  - pylint-venv=2.3.0=py311hca03da5_0
+  - pyls-spyder=0.4.0=pyhd3eb1b0_0
+  - pyobjc-core=9.0=py311h3eb5a62_1
+  - pyobjc-framework-cocoa=9.0=py311hb094c41_0
+  - pyobjc-framework-coreservices=9.0=py311hdd8dd1f_0
+  - pyobjc-framework-fsevents=9.0=py311hca03da5_0
+  - pyodbc=4.0.34=py311h313beb8_0
+  - pyopenssl=23.2.0=py311hca03da5_0
+  - pyparsing=3.0.9=py311hca03da5_0
+  - pyqt=5.15.7=py311h313beb8_0
+  - pyqt5-sip=12.11.0=py311h313beb8_0
+  - pyqtwebengine=5.15.7=py311h313beb8_0
+  - pyrsistent=0.18.0=py311h80987f9_0
+  - pysocks=1.7.1=py311hca03da5_0
+  - pytables=3.8.0=py311he080bb3_3
+  - pytest=7.4.0=py311hca03da5_0
+  - python=3.11.5=hb885b13_0
+  - python-dateutil=2.8.2=pyhd3eb1b0_0
+  - python-dotenv=0.21.0=py311hca03da5_0
+  - python-fastjsonschema=2.16.2=py311hca03da5_0
+  - python-json-logger=2.0.7=py311hca03da5_0
+  - python-kaleido=0.2.1=py311hca03da5_0
+  - python-libarchive-c=2.9=pyhd3eb1b0_1
+  - python-lmdb=1.4.1=py311h313beb8_0
+  - python-lsp-black=1.2.1=py311hca03da5_0
+  - python-lsp-jsonrpc=1.0.0=pyhd3eb1b0_0
+  - python-lsp-server=1.7.2=py311hca03da5_0
+  - python-slugify=5.0.2=pyhd3eb1b0_0
+  - python-snappy=0.6.1=py311h313beb8_0
+  - python-tzdata=2023.3=pyhd3eb1b0_0
+  - python-xxhash=2.0.2=py311h80987f9_1
+  - python.app=3=py311h80987f9_0
+  - pytoolconfig=1.2.5=py311hca03da5_1
+  - pytz=2023.3.post1=py311hca03da5_0
+  - pyviz_comms=2.3.0=py311hca03da5_0
+  - pywavelets=1.4.1=py311h80987f9_0
+  - pyyaml=6.0=py311h80987f9_1
+  - pyzmq=23.2.0=py311h313beb8_0
+  - qdarkstyle=3.0.2=pyhd3eb1b0_0
+  - qstylizer=0.2.2=py311hca03da5_0
+  - qt-main=5.15.2=h9b4df51_9
+  - qt-webengine=5.15.9=h2903aaf_7
+  - qtawesome=1.2.2=py311hca03da5_0
+  - qtconsole=5.4.2=py311hca03da5_0
+  - qtpy=2.2.0=py311hca03da5_0
+  - qtwebkit=5.212=h19f419d_5
+  - queuelib=1.5.0=py311hca03da5_0
+  - re2=2022.04.01=hc377ac9_0
+  - readline=8.2=h1a28f6b_0
+  - regex=2022.7.9=py311h80987f9_0
+  - reproc=14.2.4=hc377ac9_1
+  - reproc-cpp=14.2.4=hc377ac9_1
+  - requests=2.31.0=py311hca03da5_0
+  - requests-file=1.5.1=pyhd3eb1b0_0
+  - requests-toolbelt=1.0.0=py311hca03da5_0
+  - responses=0.13.3=pyhd3eb1b0_0
+  - rfc3339-validator=0.1.4=py311hca03da5_0
+  - rfc3986-validator=0.1.1=py311hca03da5_0
+  - rope=1.7.0=py311hca03da5_0
+  - rtree=1.0.1=py311hca03da5_0
+  - ruamel.yaml=0.17.21=py311h80987f9_0
+  - ruamel_yaml=0.17.21=py311h80987f9_0
+  - s3fs=2023.4.0=py311hca03da5_0
+  - safetensors=0.3.2=py311hf0e4da2_0
+  - scikit-image=0.20.0=py311h313beb8_0
+  - scikit-learn=1.3.0=py311h7aedaa7_0
+  - scipy=1.11.1=py311hc76d9b0_0
+  - scrapy=2.8.0=py311hca03da5_0
+  - send2trash=1.8.0=pyhd3eb1b0_1
+  - service_identity=18.1.0=pyhd3eb1b0_1
+  - setuptools=68.0.0=py311hca03da5_0
+  - sip=6.6.2=py311h313beb8_0
+  - six=1.16.0=pyhd3eb1b0_1
+  - smart_open=5.2.1=py311hca03da5_0
+  - snappy=1.1.9=hc377ac9_0
+  - sniffio=1.2.0=py311hca03da5_1
+  - snowballstemmer=2.2.0=pyhd3eb1b0_0
+  - sortedcontainers=2.4.0=pyhd3eb1b0_0
+  - soupsieve=2.4=py311hca03da5_0
+  - sphinx=5.0.2=py311hca03da5_0
+  - sphinxcontrib-applehelp=1.0.2=pyhd3eb1b0_0
+  - sphinxcontrib-devhelp=1.0.2=pyhd3eb1b0_0
+  - sphinxcontrib-htmlhelp=2.0.0=pyhd3eb1b0_0
+  - sphinxcontrib-jsmath=1.0.1=pyhd3eb1b0_0
+  - sphinxcontrib-qthelp=1.0.3=pyhd3eb1b0_0
+  - sphinxcontrib-serializinghtml=1.1.5=pyhd3eb1b0_0
+  - spyder=5.4.3=py311hca03da5_1
+  - spyder-kernels=2.4.4=py311hca03da5_0
+  - sqlalchemy=1.4.39=py311h80987f9_0
+  - sqlite=3.41.2=h80987f9_0
+  - stack_data=0.2.0=pyhd3eb1b0_0
+  - statsmodels=0.14.0=py311hb9f6ed7_0
+  - tabulate=0.8.10=py311hca03da5_0
+  - tapi=1100.0.11=h8754e6a_1
+  - tbb=2021.8.0=h48ca7d4_0
+  - tblib=1.7.0=pyhd3eb1b0_0
+  - tenacity=8.2.2=py311hca03da5_0
+  - terminado=0.17.1=py311hca03da5_0
+  - text-unidecode=1.3=pyhd3eb1b0_0
+  - textdistance=4.2.1=pyhd3eb1b0_0
+  - threadpoolctl=2.2.0=pyh0d69192_0
+  - three-merge=0.1.1=pyhd3eb1b0_0
+  - tifffile=2023.4.12=py311hca03da5_0
+  - tinycss2=1.2.1=py311hca03da5_0
+  - tk=8.6.12=hb8d0fd4_0
+  - tldextract=3.2.0=pyhd3eb1b0_0
+  - tokenizers=0.13.2=py311h3dd52b7_1
+  - toml=0.10.2=pyhd3eb1b0_0
+  - tomlkit=0.11.1=py311hca03da5_0
+  - toolz=0.12.0=py311hca03da5_0
+  - tornado=6.3.2=py311h80987f9_0
+  - tqdm=4.65.0=py311hb6e6a13_0
+  - traitlets=5.7.1=py311hca03da5_0
+  - transformers=4.32.1=py311hca03da5_0
+  - twisted=22.10.0=py311h80987f9_0
+  - tzdata=2023c=h04d1e81_0
+  - uc-micro-py=1.0.1=py311hca03da5_0
+  - ujson=5.4.0=py311h313beb8_0
+  - unidecode=1.2.0=pyhd3eb1b0_0
+  - unixodbc=2.3.11=h1a28f6b_0
+  - urllib3=1.26.16=py311hca03da5_0
+  - utf8proc=2.6.1=h1a28f6b_0
+  - w3lib=1.21.0=pyhd3eb1b0_0
+  - watchdog=2.1.6=py311h80987f9_0
+  - wcwidth=0.2.5=pyhd3eb1b0_0
+  - webencodings=0.5.1=py311hca03da5_1
+  - websocket-client=0.58.0=py311hca03da5_4
+  - werkzeug=2.2.3=py311hca03da5_0
+  - whatthepatch=1.0.2=py311hca03da5_0
+  - wheel=0.38.4=py311hca03da5_0
+  - widgetsnbextension=4.0.5=py311hca03da5_0
+  - wrapt=1.14.1=py311h80987f9_0
+  - wurlitzer=3.0.2=py311hca03da5_0
+  - xarray=2023.6.0=py311hca03da5_0
+  - xlwings=0.29.1=py311hca03da5_0
+  - xxhash=0.8.0=h1a28f6b_3
+  - xyzservices=2022.9.0=py311hca03da5_1
+  - xz=5.4.2=h80987f9_0
+  - y-py=0.5.9=py311ha6e5c4f_0
+  - yaml=0.2.5=h1a28f6b_0
+  - yaml-cpp=0.7.0=hc377ac9_1
+  - yapf=0.31.0=pyhd3eb1b0_0
+  - yarl=1.8.1=py311h80987f9_0
+  - ypy-websocket=0.8.2=py311hca03da5_0
+  - zeromq=4.3.4=hc377ac9_0
+  - zfp=1.0.0=h313beb8_0
+  - zict=2.2.0=py311hca03da5_0
+  - zipp=3.11.0=py311hca03da5_0
+  - zlib=1.2.13=h5a0b063_0
+  - zlib-ng=2.0.7=h80987f9_0
+  - zope=1.0=py311hca03da5_1
+  - zope.interface=5.4.0=py311h80987f9_0
+  - zstandard=0.19.0=py311h80987f9_0
+  - zstd=1.5.5=hd90d995_0
+  - pip:
+      - anndata==0.11.4
+      - array-api-compat==1.11.2
+      - biopython==1.81
+      - ete3==3.1.3
+      - legacy-api-wrap==1.4.1
+      - natsort==8.4.0
+      - orffinder==1.8
+      - packaging==24.2
+      - pynndescent==0.5.13
+      - scanpy==1.11.1
+      - seaborn==0.13.2
+      - session-info2==0.1.2
+      - sympy==1.13.1
+      - torch==2.6.0
+      - torchaudio==2.6.0
+      - torchvision==0.21.0
+      - typing-extensions==4.13.2
+      - umap-learn==0.5.7
+prefix: /Users/markkachanovskii/anaconda3
diff --git a/filter.log b/filter.log
new file mode 100644
index 0000000..9daa09a
--- /dev/null
+++ b/filter.log
@@ -0,0 +1,24 @@
+2025-04-19 15:36:38,181 - INFO - Starting filtering of fastq file: /private/var/folders/8y/lpd58rc57495mk0nf4dsz2d80000gn/T/pytest-of-markkachanovskii/pytest-30/test_output_exists0/example_fastq.fastq
+2025-04-19 15:36:38,181 - INFO - Parameters: GC=(0, 100), Length=(0, 4294967296), Quality=0
+2025-04-19 15:36:38,193 - INFO - Filtered 4 sequences
+2025-04-19 15:36:38,194 - INFO - Starting filtering of fastq file: /private/var/folders/8y/lpd58rc57495mk0nf4dsz2d80000gn/T/pytest-of-markkachanovskii/pytest-30/test_quality_threshold_output0/example_fastq.fastq
+2025-04-19 15:36:38,195 - INFO - Parameters: GC=(0, 100), Length=(0, 4294967296), Quality=38
+2025-04-19 15:36:38,196 - INFO - Filtered 3 sequences
+2025-04-19 15:36:38,200 - INFO - Starting filtering of fastq file: /private/var/folders/8y/lpd58rc57495mk0nf4dsz2d80000gn/T/pytest-of-markkachanovskii/pytest-30/test_gc_bounds_filtering0/example_fastq.fastq
+2025-04-19 15:36:38,200 - INFO - Parameters: GC=(50.1, 100), Length=(0, 4294967296), Quality=0
+2025-04-19 15:36:38,200 - INFO - Filtered 3 sequences
+2025-04-19 15:36:38,201 - INFO - Starting filtering of fastq file: /private/var/folders/8y/lpd58rc57495mk0nf4dsz2d80000gn/T/pytest-of-markkachanovskii/pytest-30/test_length_bounds_filtering0/example_fastq.fastq
+2025-04-19 15:36:38,201 - INFO - Parameters: GC=(0, 100), Length=(5, 15), Quality=0
+2025-04-19 15:36:38,201 - INFO - Filtered 1 sequences
+2025-04-19 15:36:38,202 - INFO - Starting filtering of fastq file: /private/var/folders/8y/lpd58rc57495mk0nf4dsz2d80000gn/T/pytest-of-markkachanovskii/pytest-30/test_empty_result0/example_fastq.fastq
+2025-04-19 15:36:38,202 - INFO - Parameters: GC=(0, 100), Length=(0, 4294967296), Quality=100
+2025-04-19 15:36:38,202 - INFO - No sequences was found the filtering criteria.
+2025-04-19 15:36:38,203 - INFO - Starting filtering of fastq file: non_existent.fastq
+2025-04-19 15:36:38,203 - INFO - Parameters: GC=(0, 100), Length=(0, 4294967296), Quality=0
+2025-04-19 15:36:38,203 - ERROR - Fastq file 'non_existent.fastq' was not found
+2025-04-19 15:36:38,203 - INFO - Starting filtering of fastq file: /private/var/folders/8y/lpd58rc57495mk0nf4dsz2d80000gn/T/pytest-of-markkachanovskii/pytest-30/test_logging_output0/example_fastq.fastq
+2025-04-19 15:36:38,204 - INFO - Parameters: GC=(0, 100), Length=(0, 4294967296), Quality=0
+2025-04-19 15:36:38,204 - INFO - Filtered 4 sequences
+2025-04-19 15:36:38,204 - INFO - Starting filtering of fastq file: /private/var/folders/8y/lpd58rc57495mk0nf4dsz2d80000gn/T/pytest-of-markkachanovskii/pytest-30/test_invalid_fastq_format0/invalid_fastq.fastq
+2025-04-19 15:36:38,204 - INFO - Parameters: GC=(0, 100), Length=(0, 4294967296), Quality=0
+2025-04-19 15:36:38,204 - ERROR - Invalid format in /private/var/folders/8y/lpd58rc57495mk0nf4dsz2d80000gn/T/pytest-of-markkachanovskii/pytest-30/test_invalid_fastq_format0/invalid_fastq.fastq: Lengths of sequence and quality values differs for seq1 (4 and 2).
diff --git a/filter_fastq.py b/filter_fastq.py
index 20ee98e..c8c0a80 100644
--- a/filter_fastq.py
+++ b/filter_fastq.py
@@ -1,45 +1,108 @@
+import argparse
+import logging
 from Bio import SeqIO
-from Bio.SeqUtils import GC
+from Bio.SeqUtils import gc_fraction
 import numpy as np
 from typing import Dict, Tuple
 
-def filter_fastq(fastq_file: str, gc_bounds: Tuple[float, float] = (0, 100), 
+logger = logging.getLogger(__name__) # логгирование
+logger.setLevel(logging.INFO)
+if not logger.handlers:
+    file_handler = logging.FileHandler("filter.log")
+    file_handler.setLevel(logging.INFO)
+    stream_handler = logging.StreamHandler()
+    stream_handler.setLevel(logging.INFO)
+    formatter = logging.Formatter("%(asctime)s - %(levelname)s - %(message)s")
+    file_handler.setFormatter(formatter)
+    stream_handler.setFormatter(formatter)
+    logger.addHandler(file_handler)
+    logger.addHandler(stream_handler)
+    
+def filter_fastq(fastq_file: str, gc_bounds: Tuple[float, float] = (0, 100),
                  length_bounds: Tuple[int, int] = (0, 2**32), quality_threshold: float = 0) -> Dict[str, Tuple[str, str]]:
     """
-    Filter FastQ sequences based on GC content, length, and average quality.
+    Filter sequences based on GC content, length, and average quality.
 
     Args:
-        fastq_file: Path to the FastQ file.
-        gc_bounds: GC content range in percentage. Defaults to (0, 100).
-        length_bounds: Sequence length range. Defaults to (0, 2**32).
+        fastq_file: Path to the fastq file.
+        gc_bounds: GC content range in percentage (min-max). Defaults to (0, 100).
+        length_bounds: Sequence length range (min-max). Defaults to (0, 2**32).
         quality_threshold: Minimum average quality threshold (Phred scale). Defaults to 0.
 
     Returns:
         A dictionary with filtered sequences in the format {name: (sequence, quality)}.
-        Returns a string message if no sequences meet the criteria.
+        Returns a string message if no sequences meet the criteria or if the file is invalid.
+
+    Raises:
+        FileNotFoundError: If the fastq file does not exist.
     """
     filtered_seqs: Dict[str, Tuple[str, str]] = {}
 
+    logger.info(f"Starting filtering of fastq file: {fastq_file}")
+    logger.info(f"Parameters: GC={gc_bounds}, Length={length_bounds}, Quality={quality_threshold}")
+
     try:
         with open(fastq_file, 'r'):
             pass
     except FileNotFoundError:
-        raise FileNotFoundError(f"FastQ file '{fastq_file}' not found")
+        logger.error(f"Fastq file '{fastq_file}' was not found")
+        raise FileNotFoundError(f"Fastq file '{fastq_file}' was not found")
 
-    for record in SeqIO.parse(fastq_file, "fastq"):
-        sequence = str(record.seq)
-        gc_content = GC(record.seq)
-        seq_length = len(sequence)
-        quality_scores = record.letter_annotations["phred_quality"]
-        avg_quality = np.mean(quality_scores) if quality_scores else 0.0
+    try:
+        for record in SeqIO.parse(fastq_file, "fastq"):
+            sequence = str(record.seq)
+            gc_content = gc_fraction(record.seq) * 100
+            seq_length = len(sequence)
+            quality_scores = record.letter_annotations["phred_quality"]
+            avg_quality = np.mean(quality_scores) if quality_scores else 0.0
 
-        if (gc_bounds[0] <= gc_content <= gc_bounds[1] and
-            length_bounds[0] <= seq_length <= length_bounds[1] and
-            avg_quality >= quality_threshold):
-            quality_str = "".join(chr(q + 33) for q in quality_scores)
-            filtered_seqs[record.id] = (sequence, quality_str)
+            if (gc_bounds[0] <= gc_content <= gc_bounds[1] and
+                length_bounds[0] <= seq_length <= length_bounds[1] and
+                avg_quality >= quality_threshold):
+                quality_str = "".join(chr(q + 33) for q in quality_scores)
+                filtered_seqs[record.id] = (sequence, quality_str)
+    except ValueError as e:
+        logger.error(f"Invalid format in {fastq_file}: {str(e)}")
+        return "Invalid format. Please check the file."
 
     if not filtered_seqs:
-        return "Удовлетворяющих последовательностей не найдено. Попробуйте другие аргументы."
-    
+        logger.info("No sequences was found the filtering criteria.")
+        return "No sequences was found the filtering criteria. Try another parameters."
+
+    logger.info(f"Filtered {len(filtered_seqs)} sequences")
     return filtered_seqs
+
+def parse_arguments() -> argparse.Namespace:
+    """
+    Parse command-line arguments.
+    """
+    parser = argparse.ArgumentParser(description="Filter fastq sequences by GC content, length, and quality.")
+    parser.add_argument("fastq_file", type=str, help="Path to the input fastq file")
+    parser.add_argument("--gc-bounds", type=float, nargs=2, default=(0, 100),
+                        help="GC content range (min-max, percentage), default: 0-100")
+    parser.add_argument("--length-bounds", type=int, nargs=2, default=(0, 2**32),
+                        help="Sequence length range (min-max), default: 0-2^32")
+    parser.add_argument("--quality-threshold", type=float, default=0,
+                        help="Minimum average Phred quality score, default: 0")
+    return parser.parse_args()
+
+def main():
+    """
+    Main function to run the fastq filter.
+    """
+    args = parse_arguments()
+    result = filter_fastq(
+        fastq_file=args.fastq_file,
+        gc_bounds=tuple(args.gc_bounds),
+        length_bounds=tuple(args.length_bounds),
+        quality_threshold=args.quality_threshold
+    )
+    if isinstance(result, str):
+        print(result)
+    else:
+        print(f"{len(result)} sequences were filtered:")
+        for seq_id, (seq, qual) in result.items():
+            print(f">{seq_id}\n{seq}\nQuality: {qual}")
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file
diff --git a/test_filter_fastq.py b/test_filter_fastq.py
new file mode 100644
index 0000000..3ec00bb
--- /dev/null
+++ b/test_filter_fastq.py
@@ -0,0 +1,112 @@
+import os
+import pytest
+import numpy as np
+from filter_fastq import filter_fastq
+
+class TestFilterFastq:
+    """
+    Test suite for the filter_fastq function in filter_fastq module.
+    Tests cover functionality, error handling, logging, and edge cases.
+    """
+    
+    @pytest.fixture
+    def input_file_path(self, tmp_path):
+        """
+        Fixture to create a temporary FastQ file for testing.
+        """
+        content = (
+            "@seq1\nGACCTTTCCGCAAGCTGTCGC\n+\nIIIIIIIIIIIIIIIIIIIII\n"
+            "@seq2\nCATGGTGGCG\n+\nIIIIIIIIII\n"
+            "@seq3\nC\n+\nI\n"
+            "@seq4\nATCG\n+\n!!!!\n"
+        )
+        file_path = tmp_path / "example_fastq.fastq"
+        file_path.write_text(content)
+        return str(file_path)
+
+    @pytest.fixture
+    def log_file_path(self, tmp_path):
+        """
+        Fixture to clean up the log file after the test.
+        """
+        yield str(tmp_path / "filter.log")
+        #if os.path.exists("filter.log"):
+            #os.remove("filter.log")
+
+    def test_output_exists(self, input_file_path):
+        """
+        Test that filter_fastq returns a non-empty dictionary with default parameters.
+        """
+        result = filter_fastq(input_file_path)
+        assert isinstance(result, dict), "Result should be a dictionary"
+        assert len(result) > 0, "Result dictionary should not be empty"
+
+    def test_quality_threshold_output(self, input_file_path):
+        """
+        Test the correctness of output sequences with quality_threshold=38.
+        """
+        target_seqs = ['GACCTTTCCGCAAGCTGTCGC', 'CATGGTGGCG', 'C']
+        result = filter_fastq(input_file_path, quality_threshold=38)
+        assert isinstance(result, dict), "Result should be a dictionary"
+        result_seqs = [seq for seq, _ in result.values()]
+        assert result_seqs == target_seqs, f"Expected sequences {target_seqs}, but got {result_seqs}"
+
+    def test_gc_bounds_filtering(self, input_file_path):
+        """
+        Test filtering by GC content (gc_bounds=(50.1, 100)).
+        """
+        target_seqs = ['GACCTTTCCGCAAGCTGTCGC', 'CATGGTGGCG', 'C']
+        result = filter_fastq(input_file_path, gc_bounds=(50.1, 100))
+        assert isinstance(result, dict), "Result should be a dictionary"
+        result_seqs = [seq for seq, _ in result.values()]
+        assert result_seqs == target_seqs, f"Expected sequences {target_seqs}, but got {result_seqs}"
+
+    def test_length_bounds_filtering(self, input_file_path):
+        """
+        Test filtering by sequence length (length_bounds=(5, 15)).
+        """
+        target_seqs = ['CATGGTGGCG']
+        result = filter_fastq(input_file_path, length_bounds=(5, 15))
+        assert isinstance(result, dict), "Result should be a dictionary"
+        result_seqs = [seq for seq, _ in result.values()]
+        assert result_seqs == target_seqs, f"Expected sequences {target_seqs}, but got {result_seqs}"
+
+    def test_empty_result(self, input_file_path):
+        """
+        Test that filter_fastq returns a string when no sequences pass the filter.
+        """
+        result = filter_fastq(input_file_path, quality_threshold=100)
+        assert isinstance(result, str), "Result should be a string"
+        assert "No sequences was found" in result, "Result should indicate no sequences found"
+
+    def test_file_not_found_error(self):
+        """
+        Test that filter_fastq raises FileNotFoundError for a non-existent file.
+        """
+        with pytest.raises(FileNotFoundError, match="Fastq file 'non_existent.fastq' was not found"):
+            filter_fastq("non_existent.fastq")
+
+    def test_logging_output(self, input_file_path, log_file_path):
+        """
+        Test that filter_fastq creates a log file and writes expected messages.
+        """
+        result = filter_fastq(input_file_path)
+        log_file = "filter.log"
+        assert os.path.exists(log_file), "Log file 'filter.log' should be created"
+        with open(log_file, 'r') as f:
+            log_content = f.read()
+            assert "Starting filtering of fastq file" in log_content, "Log should contain start message"
+            assert f"Filtered {len(result)} sequences" in log_content, "Log should contain result message"
+
+    def test_invalid_fastq_format(self, tmp_path):
+        """
+        Test that filter_fastq handles invalid FastQ format gracefully.
+        """
+        invalid_content = (
+            "@seq1\nATCG\n+\n!!\n"
+        )
+        file_path = tmp_path / "invalid_fastq.fastq"
+        file_path.write_text(invalid_content)
+        result = filter_fastq(str(file_path))
+        assert isinstance(result, str), "Result should be a string"
+        assert "Invalid format" in result, "Result should indicate invalid format"
\ No newline at end of file