`add_orf_prediction` fails with KeyError when Fasta file has lowercase characters

[kbseah]

I encountered a KeyError when trying to add ORFs to an isotools.Transcriptome object using the add_orf_prediction method.

The long error message copied below is returned.

I think that the error is caused by lowercase characters for bases (atcg) in the genome Fasta file, as the function tries to calculate the Kozak score by looking up values in the Kozak matrix, which has only uppercase characters for row names.

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
File [/data/CaiyuLab/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/pandas/core/indexes/base.py:3812](http://localhost:8889/lab/tree/pbisoseq-smk/nb/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/pandas/core/indexes/base.py#line=3811), in Index.get_loc(self, key)
   3811 try:
-> 3812     return self._engine.get_loc(casted_key)
   3813 except KeyError as err:

File pandas[/_libs/index.pyx:167](http://localhost:8889/_libs/index.pyx#line=166), in pandas._libs.index.IndexEngine.get_loc()

File pandas[/_libs/index.pyx:196](http://localhost:8889/_libs/index.pyx#line=195), in pandas._libs.index.IndexEngine.get_loc()

File pandas[/_libs/hashtable_class_helper.pxi:7088](http://localhost:8889/_libs/hashtable_class_helper.pxi#line=7087), in pandas._libs.hashtable.PyObjectHashTable.get_item()

File pandas[/_libs/hashtable_class_helper.pxi:7096](http://localhost:8889/_libs/hashtable_class_helper.pxi#line=7095), in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 'a'

The above exception was the direct cause of the following exception:

KeyError                                  Traceback (most recent call last)
Cell In[8], line 1
----> 1 isoseq.add_orf_prediction(
      2     "../ref/merged.strelka.variants.GT_AA.consensus.fasta"
      3 )

File [/data/CaiyuLab/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/isotools/_transcriptome_filter.py:139](http://localhost:8889/lab/tree/pbisoseq-smk/nb/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/isotools/_transcriptome_filter.py#line=138), in add_orf_prediction(self, genome_fn, progress_bar, filter_transcripts, filter_ref_transcripts, min_len, max_5utr_len, min_kozak, prefer_annotated_init, kozak_matrix, fickett_score, hexamer_file)
    137 if gene.chrom in genome_fh.references:
    138     if filter_transcripts is not None:
--> 139         gene.add_orfs(
    140             genome_fh,
    141             reference=False,
    142             prefer_annotated_init=prefer_annotated_init,
    143             minlen=min_len,
    144             min_kozak=min_kozak,
    145             max_5utr_len=max_5utr_len,
    146             tr_filter=filter_transcripts,
    147             kozak_matrix=kozak_matrix,
    148             get_fickett=fickett_score,
    149             coding_hexamers=coding,
    150             noncoding_hexamers=noncoding,
    151         )
    152     if filter_ref_transcripts is not None:
    153         gene.add_orfs(
    154             genome_fh,
    155             reference=True,
   (...)    164             noncoding_hexamers=noncoding,
    165         )

File [/data/CaiyuLab/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/isotools/gene.py:779](http://localhost:8889/lab/tree/pbisoseq-smk/nb/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/isotools/gene.py#line=778), in Gene.add_orfs(self, genome_fh, tr_filter, reference, minlen, min_kozak, max_5utr_len, prefer_annotated_init, start_codons, stop_codons, kozak_matrix, get_fickett, coding_hexamers, noncoding_hexamers)
    777 if kozak_matrix is not None:
    778     if kozak is None:
--> 779         orf_dict["kozak"] = kozak_score(tr_seq, start, kozak_matrix)
    780     else:
    781         orf_dict["kozak"] = kozak

File [/data/CaiyuLab/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/isotools/_utils.py:220](http://localhost:8889/lab/tree/pbisoseq-smk/nb/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/isotools/_utils.py#line=219), in kozak_score(sequence, pos, pwm)
    219 def kozak_score(sequence, pos, pwm=DEFAULT_KOZAK_PWM):
--> 220     return sum(
    221         pwm.loc[sequence[pos + i], i]
    222         for i in pwm.columns
    223         if pos + i >= 0 and pos + i < len(sequence)
    224     )

File [/data/CaiyuLab/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/isotools/_utils.py:221](http://localhost:8889/lab/tree/pbisoseq-smk/nb/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/isotools/_utils.py#line=220), in <genexpr>(.0)
    219 def kozak_score(sequence, pos, pwm=DEFAULT_KOZAK_PWM):
    220     return sum(
--> 221         pwm.loc[sequence[pos + i], i]
    222         for i in pwm.columns
    223         if pos + i >= 0 and pos + i < len(sequence)
    224     )

File [/data/CaiyuLab/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/pandas/core/indexing.py:1183](http://localhost:8889/lab/tree/pbisoseq-smk/nb/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/pandas/core/indexing.py#line=1182), in _LocationIndexer.__getitem__(self, key)
   1181     key = tuple(com.apply_if_callable(x, self.obj) for x in key)
   1182     if self._is_scalar_access(key):
-> 1183         return self.obj._get_value(*key, takeable=self._takeable)
   1184     return self._getitem_tuple(key)
   1185 else:
   1186     # we by definition only have the 0th axis

File [/data/CaiyuLab/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/pandas/core/frame.py:4226](http://localhost:8889/lab/tree/pbisoseq-smk/nb/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/pandas/core/frame.py#line=4225), in DataFrame._get_value(self, index, col, takeable)
   4220 engine = self.index._engine
   4222 if not isinstance(self.index, MultiIndex):
   4223     # CategoricalIndex: Trying to use the engine fastpath may give incorrect
   4224     #  results if our categories are integers that dont match our codes
   4225     # IntervalIndex: IntervalTree has no get_loc
-> 4226     row = self.index.get_loc(index)
   4227     return series._values[row]
   4229 # For MultiIndex going through engine effectively restricts us to
   4230 #  same-length tuples; see test_get_set_value_no_partial_indexing

File [/data/CaiyuLab/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/pandas/core/indexes/base.py:3819](http://localhost:8889/lab/tree/pbisoseq-smk/nb/pbisoseq-smk/nb/nb-env/lib/python3.12/site-packages/pandas/core/indexes/base.py#line=3818), in Index.get_loc(self, key)
   3814     if isinstance(casted_key, slice) or (
   3815         isinstance(casted_key, abc.Iterable)
   3816         and any(isinstance(x, slice) for x in casted_key)
   3817     ):
   3818         raise InvalidIndexError(key)
-> 3819     raise KeyError(key) from err
   3820 except TypeError:
   3821     # If we have a listlike key, _check_indexing_error will raise
   3822     #  InvalidIndexError. Otherwise we fall through and re-raise
   3823     #  the TypeError.
   3824     self._check_indexing_error(key)

KeyError: 'a'