Domain adaptation aims to build up an adaptive model for the learning tasks on target domain by using the data from source domain. Existing domain adaptation methods focused on reducing the gap between the data distributions of source domain and target domain but neglected the uncertainty of source domain data for the cross-domain learning. Actually, there exit the data in source domain that are uncertain with respect to the learning task on target domain. The uncertainty will cause negative transfer impacts and lead to the untrustworthy domain adaptation. Aiming at the problem, we propose a measure based on evidence theory to represent the uncertainty of source domain data for cross-domain classification and utilize the uncertainty measure to construct a trusted deep adaptation neural network (TDAN) to implement the trustworthy domain adaptation. Specifically, we design an evidential mass function to represent the uncertainty of source domain data with respect to the classification task on target domain, and formulate the loss function of the trusted deep adaptation network with Dirichlet distribution to involve the uncertainty. Experiments on real-world cross-domain learning tasks validate the trusted deep adaptation network can handle the uncertain data in source domain and produce trustworthy learning results of domain adaptation.

Domain adaptation aims to build up a learning model for target domain by leveraging transferable knowledge from different but related source domains. Existing domain adaptation methods generally transfer the knowledge from source domain to target domain through measuring the consistency between the different domains. Under this strategy, if the data of source domain is not sufficient to guarantee the consistency, the transferable knowledge will be very limited. On the other hand, we often have priors about target domain which facilitate knowledge transfer but are neglected in the extant domain adaptation methods. To tackle the problems, we integrate the priors of target domain into transfer process and propose a domain adaptation method based on evidence evidence theory. We represent the priors with evidential belief function and reformulate the domain adaptation objective based on likelihood principle, in which the priors are used to adjust transferred knowledge to suit for target domain. Based on this, we propose an improved coordinate ascent algorithm to optimize likelihood objective of domain adaption. Experimental results on both text and image datasets validate that the proposed method is effective to improve the knowledge transferability in domain adaptation, especially when the source domain is limited.

For refining and designing protein structures, it is essential to have an efficient protein folding and docking framework that generates a protein 3D structure based on given constraints. In this study, we introduce OPUS-Fold3 as a gradient-based, all-atom protein folding and docking framework, which accurately generates 3D protein structures in compliance with specified constraints, such as a potential function as long as it can be expressed as a function of positions of heavy atoms. Our tests show that, for example, OPUS-Fold3 achieves performance comparable to pyRosetta in backbone folding and significantly better in side-chain modeling. Developed using Python and TensorFlow 2.4, OPUS-Fold3 is user-friendly for any source-code level modifications and can be seamlessly combined with other deep learning models, thus facilitating collaboration between the biology and AI communities. The source code of OPUS-Fold3 can be downloaded from http://github.com/OPUS-MaLab/opus_fold3. It is freely available for academic usage.

Accurate protein side-chain modeling is crucial for protein folding and protein design. In the past decades, many successful methods have been proposed to address this issue. However, most of them depend on the discrete samples from the rotamer library, which may have limitations on their accuracies and usages. In this study, we report an open-source toolkit for protein side-chain modeling, named OPUS-Rota4. It consists of three modules: OPUS-RotaNN2, which predicts protein side-chain dihedral angles; OPUS-RotaCM, which measures the distance and orientation information between the side chain of different residue pairs and OPUS-Fold2, which applies the constraints derived from the first two modules to guide side-chain modeling. OPUS-Rota4 adopts the dihedral angles predicted by OPUS-RotaNN2 as its initial states, and uses OPUS-Fold2 to refine the side-chain conformation with the side-chain contact map constraints derived from OPUS-RotaCM. Therefore, we convert the side-chain modeling problem into a side-chain contact map prediction problem. OPUS-Fold2 is written in Python and TensorFlow2.4, which is user-friendly to include other differentiable energy terms. OPUS-Rota4 also provides a platform in which the side-chain conformation can be dynamically adjusted under the influence of other processes. We apply OPUS-Rota4 on 15 FM predictions submitted by AlphaFold2 on CASP14, the results show that the side chains modeled by OPUS-Rota4 are closer to their native counterparts than those predicted by AlphaFold2 (e.g. the residue-wise RMSD for all residues and core residues are 0.588 and 0.472 for AlphaFold2, and 0.535 and 0.407 for OPUS-Rota4).

In the version of this article initially published, we accidentally misused a script for side-chain accuracy calculation in which the symmetry of residues Asp (χ2), Phe (χ2), Tyr (χ2) and Glu (χ3) were not considered. It led to errors in the calculation for the performance metrics of MAE (χ2), MAE (χ3) and ACC in Tables 1–4, 6, S3 and S5, and RMSD in Tables 5 and S4 in the original article. This corrigendum provides corrections to those errors. Since the miscalculation was on all side-chain accuracy calculations, its impacts on the comparison of all side-chain modeling methods are minimal. Consequently, the majority of the conclusions remain valid. However, due to the fact that AlphaFold2 renamed the symmetric ground truth atoms (specifically, OD1 and OD2 in Asp, CD1 and CD2 in Phe, CD1 and CD2 in Tyr, and OE1 and OE2 in Glu) in its training process [1], the miscalculation underestimated the side-chain prediction accuracy of AlphaFold2. The only change to our original conclusions comes from correcting the miscalculation on AlphaFold2.

Protein side chains are vitally important to many biological processes such as protein-protein interaction. In this study, we evaluate the performance of our previous released side-chain modeling method OPUS-Mut, together with some other methods, on three oligomer datasets, CASP14 (11), CAMEO-Homo (65) and CAMEO-Hetero (21). The results show that OPUS-Mut outperforms other methods measured by all residues or by the interfacial residues. We also demonstrate our method on evaluating protein-protein docking pose on a dataset Oligomer-Dock (75) created using the top 10 predictions from ZDOCK 3.0.2. Our scoring function correctly identifies the native pose as the top-1 in 45 out of 75 targets. Different from traditional scoring functions, our method is based on the overall side-chain packing favorableness in accordance with the local packing environment. It emphasizes the significance of side chains and provides a new and effective scoring term for studying protein-protein interaction.

MOTIVATION: The development of an open-source platform to predict protein 1D features and 3D structure is an important task. In this paper, we report an open-source toolkit for protein 3D structure modeling, named OPUS-X. It contains three modules: OPUS-TASS2, which predicts protein torsion angles, secondary structure and solvent accessibility; OPUS-Contact, which measures the distance and orientation information between different residue pairs; and OPUS-Fold2, which uses the constraints derived from the first two modules to guide folding. RESULTS: OPUS-TASS2 is an upgraded version of our previous method OPUS-TASS. OPUS-TASS2 integrates protein global structure information and significantly outperforms OPUS-TASS. OPUS-Contact combines multiple raw co-evolutionary features with protein 1D features predicted by OPUS-TASS2, and delivers better results than the open-source state-of-the-art method trRosetta. OPUS-Fold2 is a complementary version of our previous method OPUS-Fold. OPUS-Fold2 is a gradient-based protein folding framework based on the differentiable energy terms in opposed to OPUS-Fold that is a sampling-based method used to deal with the non-differentiable terms. OPUS-Fold2 exhibits comparable performance to the Rosetta folding protocol in trRosetta when using identical inputs. OPUS-Fold2 is written in Python and TensorFlow2.4, which is user-friendly to any source-code-level modification. AVAILABILITYAND IMPLEMENTATION: The code and pre-trained models of OPUS-X can be downloaded from https://github.com/OPUS-MaLab/opus_x. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Predictions of protein backbone torsion angles (ϕ and ψ) and secondary structure from sequence are crucial subproblems in protein structure prediction. With the development of deep learning approaches, their accuracies have been significantly improved. To capture the long-range interactions, most studies integrate bidirectional recurrent neural networks into their models. In this study, we introduce and modify a recently proposed architecture named Transformer to capture the interactions between the two residues theoretically with arbitrary distance. Moreover, we take advantage of multitask learning to improve the generalization of neural network by introducing related tasks into the training process. Similar to many previous studies, OPUS-TASS uses an ensemble of models and achieves better results. RESULTS: OPUS-TASS uses the same training and validation sets as SPOT-1D. We compare the performance of OPUS-TASS and SPOT-1D on TEST2016 (1213 proteins) and TEST2018 (250 proteins) proposed in the SPOT-1D paper, CASP12 (55 proteins), CASP13 (32 proteins) and CASP-FM (56 proteins) proposed in the SAINT paper, and a recently released PDB structure collection from CAMEO (93 proteins) named as CAMEO93. On these six test sets, OPUS-TASS achieves consistent improvements in both backbone torsion angles prediction and secondary structure prediction. On CAMEO93, SPOT-1D achieves the mean absolute errors of 16.89 and 23.02 for ϕ and ψ predictions, respectively, and the accuracies for 3- and 8-state secondary structure predictions are 87.72 and 77.15%, respectively. In comparison, OPUS-TASS achieves 16.56 and 22.56 for ϕ and ψ predictions, and 89.06 and 78.87% for 3- and 8-state secondary structure predictions, respectively. In particular, after using our torsion angles refinement method OPUS-Refine as the post-processing procedure for OPUS-TASS, the mean absolute errors for final ϕ and ψ predictions are further decreased to 16.28 and 21.98, respectively. AVAILABILITY AND IMPLEMENTATION: The training and the inference codes of OPUS-TASS and its data are available at https://github.com/thuxugang/opus_tass. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Histopathology image analysis plays a critical role in cancer diagnosis and treatment. To automatically segment the cancerous regions, fully supervised segmentation algorithms require labor-intensive and time-consuming labeling at the pixel level. In this research, we propose CAMEL, a weakly supervised learning framework for histopathology image segmentation using only image-level labels. Using multiple instance learning (MIL)-based label enrichment, CAMEL splits the image into latticed instances and automatically generates instance-level labels. After label enrichment, the instance-level labels are further assigned to the corresponding pixels, producing the approximate pixel-level labels and making fully supervised training of segmentation models possible. CAMEL achieves comparable performance with the fully supervised approaches in both instance-level classification and pixel-level segmentation on CAMELYON16 and a colorectal adenoma dataset. Moreover, the generality of the automatic labeling methodology may benefit future weakly supervised learning studies for histopathology image analysis.