Predicts peptide retention times with the PeptDeep RT model (peptdeep_rt_dynamic.onnx) More...

#include <OpenMS/ML/PEPTDEEP/PeptDeepRTInference.h>

Public Member Functions
	PeptDeepRTInference (const std::string &model_path, int intra_op_threads=4, size_t batch_size=500)
	Constructor initializes the ONNX environment and loads the model.

	~PeptDeepRTInference ()
	Destructor.

std::vector< float >	predictRT (const std::vector< std::string > &peptides)
	Predicts Retention Times for a list of peptide sequences.

Private Attributes
ONNXPredictorBase	model_

size_t	batch_size_

Detailed Description

Predicts peptide retention times with the PeptDeep RT model (peptdeep_rt_dynamic.onnx)

Runs the model through ONNXPredictorBase and returns one predicted retention time per peptide sequence, processing at most batch_size peptides per model run. Available in builds with WITH_ONNX.

Constructor & Destructor Documentation

◆ PeptDeepRTInference()

PeptDeepRTInference	(	const std::string &	model_path,
		int	intra_op_threads = `4`,
		size_t	batch_size = `500`
	)

explicit

Constructor initializes the ONNX environment and loads the model.

Parameters

model_path	Absolute path to peptdeep_rt_dynamic.onnx
intra_op_threads	Number of ONNX execution threads (default 4).
batch_size	Maximum number of peptides to process in a single ONNX run (default 500).

◆ ~PeptDeepRTInference()

~PeptDeepRTInference ( )

Destructor.

Member Function Documentation

◆ predictRT()

std::vector< float > predictRT ( const std::vector< std::string > & peptides )

Predicts Retention Times for a list of peptide sequences.

Parameters

peptides A vector of peptide strings. Supports OpenMS AASequence modification notation (e.g., "PEPTIDEK", "M(Oxidation)PEP").

Returns: A vector of predicted RT values corresponding to the input peptides.

Exceptions

Exception::IllegalArgument if peptides is empty, size constraints fail, or a sequence is chemically invalid.

Member Data Documentation

◆ batch_size_

size_t batch_size_

private

◆ model_

ONNXPredictorBase model_