Error : peptides have non standard amino acids

[rohan-bareja-turnstone]

Hello,

While running mhcflurry, I get this error (shown in the last few lines)
2022-08-11 01:32:37,063 - isovar.effect_prediction:112 - INFO - Keeping 0 effects with predictable AA sequences for Variant(contig='X', start=155238667, ref='TG', alt='', reference_name='GRCh37'): []
2022-08-11 01:32:37,063 - tbiomerge.cli:188 - INFO - No nmer generated for variant Variant(contig='X', start=155238667, ref='TG', alt='', reference_name='GRCh37') due to no effects with mutant proteins
2022-08-11 01:32:37,063 - isovar.effect_prediction:61 - INFO - Predicted total 1 effects for variant Variant(contig='Y', start=13489095, ref='G', alt='A', reference_name='GRCh37')
2022-08-11 01:32:37,063 - isovar.effect_prediction:88 - INFO - Keeping 1/1 effects which have associated coding transcripts for Variant(contig='Y', start=13489095, ref='G', alt='A', reference_name='GRCh37'): <EffectCollection with 1 elements>
-- NoncodingTranscript(variant=Variant(contig='Y', start=13489095, ref='G', alt='A', reference_name='GRCh37'), transcript_name=DUX4L19-001, transcript_id=ENST00000557448)
2022-08-11 01:32:37,063 - isovar.effect_prediction:112 - INFO - Keeping 0 effects with predictable AA sequences for Variant(contig='Y', start=13489095, ref='G', alt='A', reference_name='GRCh37'): []
2022-08-11 01:32:37,063 - tbiomerge.cli:188 - INFO - No nmer generated for variant Variant(contig='Y', start=13489095, ref='G', alt='A', reference_name='GRCh37') due to no effects with mutant proteins
2022-08-11 01:32:41.404500: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory
2022-08-11 01:32:41.404547: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2022-08-11 01:32:42.964046: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 AVX512F FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2022-08-11 01:32:42.968616: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory
2022-08-11 01:32:42.968655: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
2022-08-11 01:32:42.968681: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (afbe7440a752): /proc/driver/nvidia/version does not exist
2022-08-11 01:32:43.359550: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:354] MLIR V1 optimization pass is not enabled
Forcing tensorflow backend.
{'LGRHGSPSTPDRIVVVQWDQGTRTN': 'LGRHGSPSTPDRIVVVQWDQGTRTN', 'VAEKSPVRVRPPHVLDGPGPAGMAA': 'VAEKSPVRVRPPHVLDGPGPAGMAA', 'GKRKKKEGSNDEQSENEEDLEEKSE': 'GKRKKKEGSNDEQSENEEDLEEKSE', 'GRDFSHDDTLDVTTQVELLIKQATS': 'GRDFSHDDTLDVTTQVELLIKQATS', 'GSIPIDQAGLFLIAIEISLDVDADR': 'GSIPIDQAGLFLIAIEISLDVDADR', 'YDCELVPRRVAIVIEKTKDGQILPV': 'YDCELVPRRVAIVIEKTKDGQILPV', 'MGRIVDYFTIQNHSNVDHYSKLLFP', 'VRQQQEKARLPKNQRSEGKTRMAMY': 'VRQQQEKARLPKNQRSEGKTRMAMY', 'NLRSKLRPAKSQVKSLLDGEGPQAV': 'NLRSKLRPAKSQVKSLLDGEGPQAV', 'VGQNVGWYVGVCWDDVDRGKNNVTL': 'VGQNVGWYVGVCWDDVDRGKNNVTL', 'YNPEFFYENVKILSITLNKDSQFQI': 'YNPEFFYENVKILSITLNKDSQFQI', 'SKSRSASSEEASQSPTARQIPPEAR': 'SKSRSASSEEASQSPTARQIPPEAR', 'LHSEKKIHRDIKGANVLLSEQGDVK': 'LHSEKKIHRDIKGANVLLSEQGDVK', 'MPNREPAGMGLNTFGDSTHAAAAAA': 'MPNREPAGMGLNTFGDSTHAAAAAA', 'PNLQLLYLNNNLIKSLPVYIFSGAP': 'PNLQLLYLNNNLIKSLPVYIFSGAP', 'SFDVRPSQGYRRQRGRGQHRRGGVA': 'SFDVRPSQGYRRQRGRGQHRRGGVA', 'GGSSSSSQASCGRESSGSELALATP': 'GGSSSSSQASCGRESSGSELALATP', 'YQNHNKTLQLLKAGEEDDGEYRCLA': 'YQNHNKTLQLLKAGEEDDGEYRCLA', 'PRGPHGGAASAQYGRCPCGARRPDS': 'PRGPHGGAASAQYGRCPCGARRPDS', 'LLFCHISSHQHDDMEAYVKVDSCPE': 'LLFCHISSHQHDDMEAYVKVDSCPE', 'WHSETKNSLMQDSDAASARAWPKMH': 'WHSETKNSLMQDSDAASARAWPKMH', 'RAMCMKNLKLTIMIIIVSIVFIYII': 'RAMCMKNLKLTIMIIIVSIVFIYII'}
Traceback (most recent call last):
File "/home/user/miniconda/envs/mp/bin/tbiomerge", line 8, in
sys.exit(run_cli())
File "/home/user/miniconda/envs/mp/lib/python3.8/site-packages/tbiomerge/cli.py", line 347, in run_cli
nmer_collector.calculate_binding_predictions()
File "/home/user/miniconda/envs/mp/lib/python3.8/site-packages/tbiomerge/nmer.py", line 330, in calculate_binding_predictions
binding_predictions = predictor.predict_subsequences(
File "/home/user/miniconda/envs/mp/lib/python3.8/site-packages/mhctools/base_predictor.py", line 212, in predict_subsequences
binding_predictions = self.predict_peptides(peptide_list)
File "/home/user/miniconda/envs/mp/lib/python3.8/site-packages/mhctools/mhcflurry.py", line 91, in predict_peptides
predictions_df = self.predictor.predict_to_dataframe(
File "/home/user/miniconda/envs/mp/lib/python3.8/site-packages/mhcflurry/class1_affinity_predictor.py", line 1225, in predict_to_dataframe
raise ValueError(msg)
ValueError: 12 peptides have nonstandard amino acids: ['AAELCMTU' 'AAELCMTUS' 'AAELCMTUSS' 'AELCMTUS' 'AELCMTUSS' 'ELCMTUSS'
'LWAAELCMTU' 'LWAAELCMTUS' 'PLWAAELCMTU' 'WAAELCMTU' 'WAAELCMTUS'
'WAAELCMTUSS']

Is there any way to solve this. I am using tensorflow 2.2.2 version.
I searched the error comes from this script : https://github.com/openvax/mhcflurry/blob/master/mhcflurry/class1_affinity_predictor.py

[HA1-biocopy]

I'm having the same issue, in my case, ther are peptides with stop codon (*); I was hoping that it will return NaNs

[floralo40]

The non-standard amino acid error was resolved for me when I added the --no-throw flag on. The Python version equivalent is the argument 'throw = False'.

Reference:
#199