PeptDeepRTInference Class Reference

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

Collaboration diagram for PeptDeepRTInference:

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_

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 raw uppercase, unmodified peptide strings (e.g., "PEPTIDEK")

Returns

A vector of predicted RT values corresponding to the input peptides

Exceptions

Exception::IllegalArgument

if peptides is empty or contains an invalid/modified sequence.

Member Data Documentation

batch_size_

size_t batch_size_

private

model_

ONNXPredictorBase model_

private