PeptDeepCCSInference Class Reference

Inference engine for PeptDeep collisional cross section prediction. More...

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

Collaboration diagram for PeptDeepCCSInference:

Public Member Functions
	PeptDeepCCSInference (const std::string &model_path, int intra_op_threads=4, size_t batch_size=500)
	Constructor initializes the ONNX session with the specified model graph.
	~PeptDeepCCSInference ()
	Destructor.
std::vector< float >	predictCCS (const std::vector< std::string > &peptides, const std::vector< float > &charges)
	Predicts CCS values for a batch of unmodified peptide sequences.

Private Attributes
ONNXPredictorBase	model_
size_t	batch_size_

Detailed Description

Inference engine for PeptDeep collisional cross section prediction.

Constructor & Destructor Documentation

PeptDeepCCSInference()

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

explicit

Constructor initializes the ONNX session with the specified model graph.

Parameters

model_path	Absolute or relative path to the PeptDeep CCS ONNX model file.
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).

~PeptDeepCCSInference()

~PeptDeepCCSInference

(

)

Destructor.

Member Function Documentation

predictCCS()

std::vector< float > predictCCS	(	const std::vector< std::string > &	peptides,
		const std::vector< float > &	charges
	)

Predicts CCS values for a batch of unmodified peptide sequences.

Parameters

peptides	A vector of raw uppercase peptide strings.
charges	A vector of precursor charge states. Must match peptides size.

Returns

A vector of predicted CCS values corresponding to the input peptides.

Exceptions

Exception::IllegalArgument

if peptides is empty, charges.size() != peptides.size(), or a sequence is invalid/modified.

Member Data Documentation

batch_size_

size_t batch_size_

private

model_

ONNXPredictorBase model_

private