Fix tests

Author: jkanche

README.md

@@ -24,6 +24,9 @@ pip install genomicranges[optional]
 
 ### From Bioinformatic file formats
 
+> [!NOTE]  
+> When reading genomic formats, `ends` are expected to be inclusive to be consistent with Bioconductor representations (& gff). If they are not, we recommend subtracting 1 from the `ends`.
+
 #### From `biobear`
 
 Although the parsing capabilities in this package are limited, the [biobear](https://github.com/wheretrue/biobear) library is designed for reading and searching various bioinformatics file formats, including FASTA, FASTQ, VCF, BAM, and GFF, or from an object store like S3. Users can esily convert these representations to `GenomicRanges` (or [read more here](https://www.wheretrue.dev/docs/exon/biobear/genomicranges-integration)):
@@ -44,8 +47,8 @@ print(len(gg), len(df))
 ```
 
     ## output
-    ## 77 77
-
+    ## 77 77> [!NOTE]  
+> `ends` are expected to be inclusive to be consistent with Bioconductor representations. If they are not, we recommend subtracting 1 from the `ends`.
 
 #### UCSC or GTF file
 

src/genomicranges/GenomicRanges.py

@@ -1056,6 +1056,7 @@ def from_pandas(cls, input) -> "GenomicRanges":
         Args:
             input:
                 Input data. Must contain columns 'seqnames', 'starts' and 'widths' or "ends".
+                'ends' are expected to be inclusive.
 
         Returns:
             A ``GenomicRanges`` object.
@@ -1136,6 +1137,7 @@ def from_polars(cls, input) -> "GenomicRanges":
         Args:
             input:
                 Input polars DataFrame. Must contain columns 'seqnames', 'starts' and 'widths' or "ends".
+                'ends' are expected to be inclusive.
 
         Returns:
             A ``GenomicRanges`` object.
@@ -2080,30 +2082,40 @@ def intersect(self, other: "GenomicRanges", ignore_strand: bool = False) -> "Gen
         diff = x.setdiff(y_gaps)
         return diff
 
-    def intersect_ncls(self, other: "GenomicRanges") -> "GenomicRanges":
+    def intersect_ncls(
+        self, other: "GenomicRanges", delete_index: bool = True, num_threads: int = 1
+    ) -> "GenomicRanges":
         """Find intersecting genomic intervals with `other` (uses NCLS index).
 
         Args:
             other:
                 The other ``GenomicRanges`` object.
 
+            delete_index:
+                Defaults to True, to delete the cached ncls index.
+                Set to False, to reuse the index across multiple queries.
+
+            num_threads:
+                Number of threads to use.
+                Defaults to 1.
+
         Returns:
             A new ``GenomicRanges`` object with intersecting ranges.
         """
         if not isinstance(other, GenomicRanges):
             raise TypeError("'other' is not a `GenomicRanges` object.")
 
-        if not ut.package_utils.is_package_installed("ncls"):
-            raise ImportError("package: 'ncls' is not installed.")
-
-        from ncls import NCLS
+        self_end = self.get_end()
+        other_end = other.get_end()
 
-        self_end = self.end
-        other_end = other.end
+        other._ranges._build_ncls_index()
+        res = other._ranges.find_overlaps(self._ranges, num_threads=num_threads)
 
-        other_ncls = NCLS(other.start, other_end, np.arange(len(other)))
-        _self_indexes, _other_indexes = other_ncls.all_overlaps_both(self.start, self_end, np.arange(len(self)))
+        if delete_index:
+            other._ranges._delete_ncls_index()
 
+        _other_indexes = res["self_hits"]
+        _self_indexes = res["query_hits"]
         other_chrms = np.array([other._seqinfo._seqnames[other._seqnames[i]] for i in _other_indexes])
         self_chrms = np.array([self._seqinfo._seqnames[self._seqnames[i]] for i in _self_indexes])