Merge main

.github/workflows/ci-cogent3-dev.yml

@@ -21,7 +21,7 @@ jobs:
             python-version: "3.12"
 
       - name: Install uv
-        uses: astral-sh/setup-uv@v3
+        uses: astral-sh/setup-uv@v5
         with:
             enable-cache: true
 

paper/paper.bib

@@ -1,176 +1,239 @@
 
-@article{parks.2018.natbiotechnol,
-	author = {Parks, Donovan H. and Chuvochina, Maria and Waite, David W. and Rinke, Christian and Skarshewski, Adam and Chaumeil, Pierre-Alain and Hugenholtz, Philip},
-	journal = {Nature Biotechnology},
-	month = nov,
-	number = {10},
-	pages = {996--1004},
-	title = {A standardized bacterial taxonomy based on genome phylogeny substantially revises the tree of life},
-	volume = {36},
-	year = {2018}}
+@article{balaban.2019.plosone,
+	author = {Balaban, Metin and Moshiri, Niema and Mai, Uyen and Jia, Xingfan and Mirarab, Siavash},
+	doi = {10.1371/journal.pone.0221068},
+	editor = {Bozdag, Serdar},
+	issn = {1932-6203},
+	journal = {PLOS ONE},
+	language = {en},
+	month = aug,
+	number = {8},
+	pages = {e0221068},
+	shorttitle = {{TreeCluster}},
+	title = {{TreeCluster}: {Clustering} biological sequences using phylogenetic trees},
+	url = {https://dx.plos.org/10.1371/journal.pone.0221068},
+	urldate = {2024-08-14},
+	volume = {14},
+	year = {2019}}
 
-@book{sokal.1995,
-	address = {New York},
-	author = {Sokal, R R and Rohlf, F J},
-	edition = {3},
-	publisher = {W. H. Freeman and Company},
-	title = {Biometry},
-	year = {1995}}
+@article{widmann.2006.molcellproteomics,
+	author = {Widmann, Jeremy and Hamady, Micah and Knight, Rob},
+	doi = {10.1074/mcp.T600022-MCP200},
+	journal = {Mol Cell Proteomics},
+	language = {eng},
+	number = {8},
+	pages = {1520--1532},
+	pmid = {16769708},
+	title = {{DivergentSet}, a tool for picking non-redundant sequences from large sequence collections.},
+	volume = {5},
+	year = {2006}}
+
+@article{schneider.1990.nucleicacidsres,
+	author = {Schneider, T D and Stephens, R M},
+	doi = {10.1093/NAR/18.20.6097},
+	issn = {0305-1048},
+	journal = {Nucleic acids research},
+	month = oct,
+	number = {20},
+	pages = {6097--100},
+	pmid = {2172928},
+	title = {Sequence logos: a new way to display consensus sequences.},
+	url = {http://www.ncbi.nlm.nih.gov/pubmed/2172928},
+	urldate = {2016-11-08},
+	volume = {18},
+	year = {1990}}
 
 @article{lin.1991.ieeetrans.inf.theory,
 	author = {Lin, J.},
+	doi = {10.1109/18.61115},
+	issn = {1557-9654},
 	journal = {IEEE Transactions on Information Theory},
 	month = jan,
 	number = {1},
 	pages = {145--151},
 	title = {Divergence measures based on the {Shannon} entropy},
+	url = {https://ieeexplore.ieee.org/document/61115},
+	urldate = {2024-08-21},
 	volume = {37},
 	year = {1991}}
 
-@article{widmann.2006.molcellproteomics,
-	author = {Widmann, Jeremy and Hamady, Micah and Knight, Rob},
-	journal = {Mol Cell Proteomics},
-	number = {8},
-	pages = {1520--1532},
-	title = {{DivergentSet}, a tool for picking non-redundant sequences from large sequence collections.},
-	volume = {5},
-	year = {2006}}
+@article{lake.1994.procnatlacadsciua,
+	author = {Lake, J A},
+	journal = {Proc Natl Acad Sci U S A},
+	language = {eng},
+	number = {4},
+	pages = {1455--1459},
+	pmid = {8108430},
+	title = {Reconstructing evolutionary trees from {DNA} and protein sequences: paralinear distances.},
+	url = {https://pubmed.ncbi.nlm.nih.gov/8108430},
+	volume = {91},
+	year = {1994}}
 
 @article{harrison.2024.nucleicacidsresearch,
 	author = {Harrison, Peter W and Amode, M Ridwan and Austine-Orimoloye, Olanrewaju and Azov, Andrey G and Barba, Matthieu and Barnes, If and Becker, Arne and Bennett, Ruth and Berry, Andrew and Bhai, Jyothish and Bhurji, Simarpreet Kaur and Boddu, Sanjay and Branco Lins, Paulo R and Brooks, Lucy and Ramaraju, Shashank Budhanuru and Campbell, Lahcen I and Martinez, Manuel Carbajo and Charkhchi, Mehrnaz and Chougule, Kapeel and Cockburn, Alexander and Davidson, Claire and De Silva, Nishadi H and Dodiya, Kamalkumar and Donaldson, Sarah and El Houdaigui, Bilal and Naboulsi, Tamara El and Fatima, Reham and Giron, Carlos Garcia and Genez, Thiago and Grigoriadis, Dionysios and Ghattaoraya, Gurpreet S and Martinez, Jose Gonzalez and Gurbich, Tatiana A and Hardy, Matthew and Hollis, Zoe and Hourlier, Thibaut and Hunt, Toby and Kay, Mike and Kaykala, Vinay and Le, Tuan and Lemos, Diana and Lodha, Disha and Marques-Coelho, Diego and Maslen, Gareth and Merino, Gabriela Alejandra and Mirabueno, Louisse Paola and Mushtaq, Aleena and Hossain, Syed Nakib and Ogeh, Denye N and Sakthivel, Manoj Pandian and Parker, Anne and Perry, Malcolm and Pili{\v z}ota, Ivana and Poppleton, Daniel and Prosovetskaia, Irina and Raj, Shriya and P{\'e}rez-Silva, Jos{\'e} G and Salam, Ahamed Imran Abdul and Saraf, Shradha and Saraiva-Agostinho, Nuno and Sheppard, Dan and Sinha, Swati and Sipos, Botond and Sitnik, Vasily and Stark, William and Steed, Emily and Suner, Marie-Marthe and Surapaneni, Likhitha and Sutinen, Ky{\"o}sti and Tricomi, Francesca Floriana and Urbina-G{\'o}mez, David and Veidenberg, Andres and Walsh, Thomas A and Ware, Doreen and Wass, Elizabeth and Willhoft, Natalie L and Allen, Jamie and Alvarez-Jarreta, Jorge and Chakiachvili, Marc and Flint, Bethany and Giorgetti, Stefano and Haggerty, Leanne and Ilsley, Garth R and Keatley, Jon and Loveland, Jane E and Moore, Benjamin and Mudge, Jonathan M and Naamati, Guy and Tate, John and Trevanion, Stephen J and Winterbottom, Andrea and Frankish, Adam and Hunt, Sarah E and Cunningham, Fiona and Dyer, Sarah and Finn, Robert D and Martin, Fergal J and Yates, Andrew D},
+	doi = {10.1093/nar/gkad1049},
+	issn = {0305-1048},
 	journal = {Nucleic Acids Research},
 	month = jan,
 	number = {D1},
 	pages = {D891--D899},
 	title = {Ensembl 2024},
+	url = {https://doi.org/10.1093/nar/gkad1049},
+	urldate = {2024-08-22},
 	volume = {52},
 	year = {2024}}
 
-@inproceedings{numba,
-	address = {New York, NY, USA},
-	author = {Lam, Siu Kwan and Pitrou, Antoine and Seibert, Stanley},
-	booktitle = {Proceedings of the {Second} {Workshop} on the {LLVM} {Compiler} {Infrastructure} in {HPC}},
-	month = nov,
-	pages = {1--6},
-	publisher = {Association for Computing Machinery},
-	series = {{LLVM} '15},
-	title = {Numba: a {LLVM}-based {Python} {JIT} compiler},
-	year = {2015}}
-
 @article{zhu.2019.nat.commun,
 	author = {Zhu, Qiyun and Mai, Uyen and Pfeiffer, Wayne and Janssen, Stefan and Asnicar, Francesco and Sanders, Jon G. and Belda-Ferre, Pedro and Al-Ghalith, Gabriel A. and Kopylova, Evguenia and McDonald, Daniel and Kosciolek, Tomasz and Yin, John B. and Huang, Shi and Salam, Nimaichand and Jiao, Jian-Yu and Wu, Zijun and Xu, Zhenjiang Z. and Cantrell, Kalen and Yang, Yimeng and Sayyari, Erfan and Rabiee, Maryam and Morton, James T. and Podell, Sheila and Knights, Dan and Li, Wen-Jun and Huttenhower, Curtis and Segata, Nicola and Smarr, Larry and Mirarab, Siavash and Knight, Rob},
+	doi = {10.1038/s41467-019-13443-4},
 	journal = {Nature Communications},
 	number = {1},
 	pages = {5477},
+	pmid = {31792218},
 	title = {Phylogenomics of 10,575 genomes reveals evolutionary proximity between domains {Bacteria} and {Archaea}},
+	url = {https://doi.org/10.1038/s41467-019-13443-4},
 	volume = {10},
 	year = {2019}}
 
+@book{sokal.1995,
+	address = {New York},
+	author = {Sokal, R R and Rohlf, F J},
+	edition = {3},
+	publisher = {W. H. Freeman and Company},
+	title = {Biometry},
+	year = {1995}}
+
 @article{knight.2007.genomebiol,
 	author = {Knight, R and Maxwell, P and Birmingham, A and Carnes, J and Caporaso, J G and Easton, B C and Eaton, M and Hamady, M and Lindsay, H and Liu, Z and Lozupone, C and McDonald, D and Robeson, M and Sammut, R and Smit, S and Wakefield, M J and Widmann, J and Wikman, S and Wilson, S and Ying, H and Huttley, G A},
+	doi = {10.1186/gb-2007-8-8-r171},
 	journal = {Genome Biol},
+	language = {ENG},
 	number = {8},
 	pages = {R171},
+	pmid = {17708774},
 	title = {{PyCogent}: a toolkit for making sense from sequence.},
+	url = {https://www.ncbi.nlm.nih.gov/pubmed/17708774},
 	volume = {8},
 	year = {2007}}
 
-@article{lake.1994.procnatlacadsciua,
-	author = {Lake, J A},
-	journal = {Proc Natl Acad Sci U S A},
-	number = {4},
-	pages = {1455--1459},
-	title = {Reconstructing evolutionary trees from {DNA} and protein sequences: paralinear distances.},
-	volume = {91},
-	year = {1994}}
-
 @article{cleveland.1979.j.am.stat.assoc,
 	author = {Cleveland, William S.},
+	doi = {10.1080/01621459.1979.10481038},
+	issn = {0162-1459},
 	journal = {Journal of the American Statistical Association},
 	month = dec,
 	number = {368},
 	pages = {829--836},
 	title = {Robust {Locally} {Weighted} {Regression} and {Smoothing} {Scatterplots}},
+	url = {https://www.tandfonline.com/doi/abs/10.1080/01621459.1979.10481038},
+	urldate = {2024-08-26},
 	volume = {74},
 	year = {1979}}
 
-@article{schneider.1990.nucleicacidsres,
-	author = {Schneider, T D and Stephens, R M},
-	journal = {Nucleic acids research},
-	month = oct,
-	number = {20},
-	pages = {6097--100},
-	title = {Sequence logos: a new way to display consensus sequences.},
-	volume = {18},
-	year = {1990}}
-
-@article{ondov.2016.mash,
-  title={Mash: fast genome and metagenome distance estimation using MinHash},
-  author={Ondov, Brian D and Treangen, Todd J and Melsted, P{\'a}ll and Mallonee, Adam B and Bergman, Nicholas H and Koren, Sergey and Phillippy, Adam M},
-  journal={Genome biology},
-  volume={17},
-  pages={1--14},
-  year={2016},
-  publisher={Springer}
-}
-
-
-@article{minh.2020.iq,
-  title={IQ-TREE 2: new models and efficient methods for phylogenetic inference in the genomic era},
-  author={Minh, Bui Quang and Schmidt, Heiko A and Chernomor, Olga and Schrempf, Dominik and Woodhams, Michael D and Von Haeseler, Arndt and Lanfear, Robert},
-  journal={Molecular biology and evolution},
-  volume={37},
-  number={5},
-  pages={1530--1534},
-  year={2020},
-  publisher={Oxford University Press}
-}
-
-@article{murtagh.2012.algorithms,
-  title={Algorithms for hierarchical clustering: an overview},
-  author={Murtagh, Fionn and Contreras, Pedro},
-  journal={Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery},
-  volume={2},
-  number={1},
-  pages={86--97},
-  year={2012},
-  publisher={Wiley Online Library}
-}
-
-@article{tavare.1986.some,
-  title={Some probabilistic and statistical problems on the analysis of DNA sequence.},
-  author={Tavar{\'e}, Simon},
-  journal={Lecture of Mathematics for Life Science},
-  volume={17},
-  pages={57},
-  year={1986}
-}
+@article{saitou.1987.mol.biol.evol,
+	author = {Saitou, N and Nei, M},
+	journal = {Mol. Biol. Evol.},
+	number = {4},
+	pages = {406--425},
+	title = {The neighbor-joining method: a new method for reconstructing phylogenetic trees},
+	url = {https://www.ncbi.nlm.nih.gov/pubmed/3447015},
+	volume = {4},
+	year = {1987}}
 
 @article{choi.2017.ismej,
 	author = {Choi, Jinlyung and Yang, Fan and Stepanauskas, Ramunas and Cardenas, Erick and Garoutte, Aaron and Williams, Ryan and Flater, Jared and Tiedje, James M. and Hofmockel, Kirsten S. and Gelder, Brian and Howe, Adina},
+	doi = {10.1038/ismej.2016.168},
+	issn = {1751-7370},
 	journal = {The ISME journal},
+	language = {eng},
 	month = apr,
 	number = {4},
 	pages = {829--834},
+	pmcid = {PMC5364351},
+	pmid = {27935589},
 	title = {Strategies to improve reference databases for soil microbiomes},
 	volume = {11},
 	year = {2017}}
 
-@article{saitou.1987.mol.biol.evol,
-	author = {Saitou, N and Nei, M},
-	journal = {Mol. Biol. Evol.},
-	number = {4},
-	pages = {406--425},
-	title = {The neighbor-joining method: a new method for reconstructing phylogenetic trees},
-	volume = {4},
-	year = {1987}}
+@article{parks.2018.natbiotechnol,
+	author = {Parks, Donovan H. and Chuvochina, Maria and Waite, David W. and Rinke, Christian and Skarshewski, Adam and Chaumeil, Pierre-Alain and Hugenholtz, Philip},
+	doi = {10.1038/nbt.4229},
+	issn = {1546-1696},
+	journal = {Nature Biotechnology},
+	language = {en},
+	month = nov,
+	number = {10},
+	pages = {996--1004},
+	title = {A standardized bacterial taxonomy based on genome phylogeny substantially revises the tree of life},
+	url = {https://www.nature.com/articles/nbt.4229},
+	urldate = {2024-08-27},
+	volume = {36},
+	year = {2018}}
 
-@article{balaban.2019.plosone,
-	author = {Balaban, Metin and Moshiri, Niema and Mai, Uyen and Jia, Xingfan and Mirarab, Siavash},
-	journal = {PLOS ONE},
-	month = aug,
-	number = {8},
-	pages = {e0221068},
-	title = {{TreeCluster}: {Clustering} biological sequences using phylogenetic trees},
-	volume = {14},
-	year = {2019}}
+@inproceedings{numba,
+	address = {New York, NY, USA},
+	author = {Lam, Siu Kwan and Pitrou, Antoine and Seibert, Stanley},
+	booktitle = {Proceedings of the {Second} {Workshop} on the {LLVM} {Compiler} {Infrastructure} in {HPC}},
+	doi = {10.1145/2833157.2833162},
+	isbn = {978-1-4503-4005-2},
+	month = nov,
+	pages = {1--6},
+	publisher = {Association for Computing Machinery},
+	series = {{LLVM} '15},
+	shorttitle = {Numba},
+	title = {Numba: a {LLVM}-based {Python} {JIT} compiler},
+	url = {https://dl.acm.org/doi/10.1145/2833157.2833162},
+	urldate = {2024-09-22},
+	year = {2015}}
+
+@article{minh.2020.iq,
+	author = {Minh, Bui Quang and Schmidt, Heiko A and Chernomor, Olga and Schrempf, Dominik and Woodhams, Michael D and von Haeseler, Arndt and Lanfear, Robert},
+	doi = {10.1093/molbev/msaa015},
+	issn = {0737-4038},
+	journal = {Molecular Biology and Evolution},
+	month = may,
+	number = {5},
+	pages = {1530--1534},
+	shorttitle = {{IQ}-{TREE} 2},
+	title = {{IQ}-{TREE} 2: {New} {Models} and {Efficient} {Methods} for {Phylogenetic} {Inference} in the {Genomic} {Era}},
+	url = {https://doi.org/10.1093/molbev/msaa015},
+	urldate = {2024-10-16},
+	volume = {37},
+	year = {2020}}
+
+@article{murtagh.2012.algorithms,
+	author = {Murtagh, Fionn and Contreras, Pedro},
+	doi = {10.1002/widm.53},
+	issn = {1942-4795},
+	journal = {WIREs Data Mining and Knowledge Discovery},
+	language = {en},
+	number = {1},
+	pages = {86--97},
+	shorttitle = {Algorithms for hierarchical clustering},
+	title = {Algorithms for hierarchical clustering: an overview},
+	url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/widm.53},
+	urldate = {2025-01-12},
+	volume = {2},
+	year = {2012}}
+
+@article{ondov.2016.mash,
+	author = {Ondov, Brian D. and Treangen, Todd J. and Melsted, P?ll and Mallonee, Adam B. and Bergman, Nicholas H. and Koren, Sergey and Phillippy, Adam M.},
+	doi = {10.1186/s13059-016-0997-x},
+	issn = {1474-760X},
+	journal = {Genome Biology},
+	month = dec,
+	number = {1},
+	pages = {132},
+	title = {Mash: fast genome and metagenome distance estimation using {MinHash}},
+	url = {http://genomebiology.biomedcentral.com/articles/10.1186/s13059-016-0997-x},
+	urldate = {2017-07-04},
+	volume = {17},
+	year = {2016}}
+
+@article{tavare.1986.some,
+	author = {Tavare, S},
+	journal = {Lec. Math. Life Sci.},
+	pages = {57--86},
+	title = {Some probabilistic and statistical problems in the analysis of {DNA} sequences.},
+	volume = {17},
+	year = {1986}}

pyproject.toml

@@ -50,7 +50,7 @@ test = [
     "pytest",
     "pytest-cov",
     "pytest-xdist",
-    "ruff==0.7.3",
+    "ruff==0.8.4",
 ]
 dev = [
     "cogapp",
@@ -60,7 +60,7 @@ dev = [
     "pytest",
     "pytest-cov",
     "pytest-xdist",
-    "ruff==0.7.3",
+    "ruff==0.8.4",
 ]
 doc  = ["click",
         "ipykernel",
@@ -75,7 +75,7 @@ doc  = ["click",
         "nbformat",
         "nbsphinx",
         "numpydoc",
-        "piqtree2",
+        "piqtree",
         "pandas",
         "plotly",
         "requests",

src/diverse_seq/__init__.py

@@ -4,4 +4,4 @@
 # found by h5py
 import hdf5plugin  # noqa
 
-__version__ = "2024.11.8a3"
+__version__ = "2024.12.26a1"