Update polars 0.41.3

Cargo.toml

@@ -39,15 +39,17 @@ path = "src/lib/lib.rs"
 
 [dependencies]
 anyhow = "1.0.75"
+# https://github.com/pola-rs/polars/issues/19157
+hashbrown = { version = "0.14.5", features = ["raw"] }
 clap = { version = "4.4.7", features = ["derive", "wrap_help","cargo"] }
-grangers = { git = "https://github.com/COMBINE-lab/grangers.git", branch="dev", version = "0.4.0" }
-polars = { version = "0.38.2", features = ["lazy","dataframe_arithmetic", "checked_arithmetic","rows","dtype-struct", "dtype-categorical", "list_eval","concat_str", "strings"]}
+grangers = { git = "https://github.com/an-altosian/grangers.git", branch="add_rustdoc", version = "0.4.0" }
+polars = { version = "0.45.1", features = ["lazy","dataframe_arithmetic", "checked_arithmetic","rows","dtype-struct", "dtype-categorical", "list_eval","concat_str", "strings"]}
 peak_alloc = "0.2.0"
 tracing = "0.1.40"
 tracing-subscriber = { version = "0.3.17", features = ["env-filter"] }
-noodles = { version = "0.65.0", features = ["gtf","gff","fasta", "core"] }
+noodles = { version = "0.87.0", features = ["gtf","gff","fasta", "core"] }
 serde = {version = "1.0.190", features = ["derive"]}
 serde_json = "1.0.107"
-itertools = "0.12.1"
+itertools = "0.14.0"
 oomfi = "0.1.2"
 xxhash-rust = { version = "0.8.7", features = ["xxh3"] }

README.md

@@ -1,3 +1,52 @@
 # roers
 
 A rust library for preparing expanded transcriptome references for quantification with [`alevin-fry`](https://alevin-fry.readthedocs.io/en/latest/).
+
+To use outside of simpleaf, follow the following help message:
+
+```bash
+build the (expanded) reference index
+
+Usage: roers make-ref [OPTIONS] <GENOME> <GENES> <OUT_DIR>
+
+Arguments:
+  <GENOME>   The path to a genome fasta file
+  <GENES>    The path to a gene annotation gtf/gff3 file
+  <OUT_DIR>  The path to the output directory (will be created if it doesn't exist)
+
+Options:
+  -a, --aug-type <AUG_TYPE>
+          Comma separated types of augmented sequences to include in the output FASTA file on
+          top of spliced transcripts. Available options are `intronic` (or `i` for short),
+          `gene-body` (or `g`), and `transcript-body` (or `t`)
+      --dedup
+          Indicates whether identical sequences will be deduplicated
+  -p, --filename-prefix <FILENAME_PREFIX>
+          The file name prefix of the generated output files [default: roers_ref]
+      --no-transcript
+          A flag of not including spliced transcripts in the output FASTA file. (usually there
+          should be a good reason to do so)
+      --gff3
+          Denotes that the input annotation is a GFF3 (instead of GTF) file
+  -h, --help
+          Print help
+  -V, --version
+          Print version
+
+Intronic Sequence Options:
+  -r, --read-length <READ_LENGTH>
+          The read length of the single-cell experiment being processed (determines flank size)
+          [default: 91]
+      --flank-trim-length <FLANK_TRIM_LENGTH>
+          Determines the length of sequence subtracted from the read length to obtain the flank
+          length [default: 5]
+      --no-flanking-merge
+          Indicates whether flank lengths will be considered when merging introns
+
+Extra Spliced Sequence File:
+      --extra-spliced <EXTRA_SPLICED>  The path to an extra spliced sequence fasta file
+
+Extra Unspliced Sequence File:
+      --extra-unspliced <EXTRA_UNSPLICED>  The path to an extra unspliced sequence fasta file
+
+```