diff --git a/abutils/tests/test_phylo.py b/abutils/tests/test_phylo.py index 982a7c1..0caf1ab 100644 --- a/abutils/tests/test_phylo.py +++ b/abutils/tests/test_phylo.py @@ -178,6 +178,13 @@ def test_phylogeny_with_list_input(sequences): assert len(phylo.sequences) == 3 +def test_phylogeny_tree_loads_newick(sequences): + phylo = phylogeny(sequences) + phylo.tree_string = "(seq1:0.1,seq2:0.2,seq3:0.3);" + leaves = [o for o in phylo.tree.Objects if o.branchType == "leaf"] + assert sorted(leaf.name for leaf in leaves) == ["seq1", "seq2", "seq3"] + + def test_phylogeny_with_name(fasta_file): name = "test_phylogeny_with_name" phylo = phylogeny(fasta_file.name, name=name) diff --git a/abutils/tools/preprocessing.py b/abutils/tools/preprocessing.py index d162ef4..6fc21c7 100644 --- a/abutils/tools/preprocessing.py +++ b/abutils/tools/preprocessing.py @@ -677,7 +677,7 @@ def _deduplicate_sequences( return ( df.group_by(group_by_cols) .agg( - pl.count().alias("count"), + pl.len().alias("count"), pl.col("sequence_id").first(), ) .sort("sequence") @@ -1030,7 +1030,7 @@ def deduplicate( pool_unique = ( pool_df.group_by("sequence") .agg( - pl.count().alias("count"), + pl.len().alias("count"), pl.col("sequence_id").first(), ) .sort("sequence") diff --git a/requirements.txt b/requirements.txt index e9bc612..c217a25 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,5 +1,6 @@ abstar>=0.7 -baltic +# baltic 1.0 renamed its API (loadNewick -> load_newick, leaf/node/tree are modules) +baltic<1 biopython>=1.78 # celery dnachisel