mindsponge.metrics

API Name	Description	Supported Platforms
`mindsponge.metrics.BalancedMSE`	Balanced MSE error Compute Balanced MSE error between the prediction and the ground truth to solve unbalanced labels in regression task.	`Ascend` `GPU`
`mindsponge.metrics.BinaryFocal`	Focal error for Binary classifications.	`Ascend` `GPU`
`mindsponge.metrics.MultiClassFocal`	Focal error for multi-class classifications.	`Ascend` `GPU`
`mindsponge.metrics.backbone`	Backbone FAPE Loss using frame_aligned_point_error_map function.	`Ascend` `GPU`
`mindsponge.metrics.between_residue_bond`	Flat-bottom loss to penalize structural violations between residues.	`Ascend` `GPU`
`mindsponge.metrics.between_residue_clash`	This is a loss penalizing any steric clashes due to non bonded atoms in different peptides coming too close.	`Ascend` `GPU`
`mindsponge.metrics.compute_renamed_ground_truth`	Find optimal renaming of ground truth based on the predicted positions.	`Ascend` `GPU`
`mindsponge.metrics.frame_aligned_point_error`	Measure point error under different alignments which computes error between two structures with B points under A alignments derived from the given pairs of frames.	`Ascend` `GPU`
`mindsponge.metrics.frame_aligned_point_error_map`	Measure point error under different alignments which computes error between two structures with B points under A alignments derived from the given pairs of frames.	`Ascend` `GPU`
`mindsponge.metrics.get_structural_violations`	Computes several checks for structural violations.	`Ascend` `GPU`
`mindsponge.metrics.local_distance_difference_test`	Compute true and predicted distance matrices for \(C\alpha\).	`Ascend` `GPU`
`mindsponge.metrics.sidechain`	sidechain FAPE Loss which take all local frames (side-chain, backbone) into consideration.	`Ascend` `GPU`
`mindsponge.metrics.supervised_chi`	Computes loss for direct chi angle supervision.	`Ascend` `GPU`
`mindsponge.metrics.within_residue_violations`	Loss to penalize steric clashes within residues.	`Ascend` `GPU`