Generalizing biomedical relation classification with neural adversarial domain adaptation

Rios, Anthony; Kavuluru, Ramakanth; Lu, Zhiyong

doi:10.1093/bioinformatics/bty190

Cited by 39 publications

(35 citation statements)

References 32 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table 6, among ML without KB methods, Rios et al [11] achieve the best F1-score 36 Therefore, KSM keeps the balance between the precision and the recall, and achieves a state-of-the-art F1-score.…”

Section: Comparison With Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Improving neural protein-protein interaction extraction with knowledge selection

Zhou

Yao

et al. 2019

Computational Biology and Chemistry

View full text Add to dashboard Cite

Protein-protein interaction (PPI) extraction from published scientific literature provides additional support for precision medicine efforts. Meanwhile, knowledge bases (KBs) contain huge amounts of structured information of protein entities and their relations, which can be encoded in entity and relation embeddings to help PPI extraction. However, the prior knowledge of protein-protein pairs must be selectively used so that it is suitable for different contexts. This paper proposes a Knowledge Selection Model (KSM) to fuse the selected prior knowledge and context information for PPI extraction. Firstly, two Transformers encode the context sequence of a protein pair according to each protein embedding, respectively. Then, the two outputs are fed to a mutual attention to capture the important context features towards the protein pair. Next, the context features are used to distill the relation embedding by a knowledge selector. Finally, the selected relation embedding and the context features are concatenated for PPI extraction. Experiments on the BioCreative VI PPI dataset show that KSM achieves a new state-ofthe-art performance (38.08% F1-score) by adding knowledge selection.

show abstract

Section: Comparison With Related Workmentioning

confidence: 99%

“…As for Bi-oCreative VI PPI extraction task, Tran and Kavuluru [7] employ CNN to extract local semantic features and get an F1-score 36.33%. Rios et al [11] use CNN as a base model, and then improve the model with unlabeled data via an adversarial process. They finally improve F1-score to 36.77%.…”

Section: Related Workmentioning

confidence: 99%

Improving neural protein-protein interaction extraction with knowledge selection

Zhou

Yao

et al. 2019

Computational Biology and Chemistry

View full text Add to dashboard Cite

show abstract

“…For AIMed and BioInfer, cross-corpus evaluations have been performed in many previous works (Airola et al, 2008;Tikk et al, 2010;Peng and Lu, 2017;Hsieh et al, 2017;Rios et al, 2018;Garg et al, 2019). These datasets have annotations on pairs of interacting proteins (PPI) in a sentence while ignoring the interaction type.…”

Section: Dataset Detailsmentioning

confidence: 99%

Nearly-Unsupervised Hashcode Representations for Biomedical Relation Extraction

Garg

Galstyan²,

Steeg³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Recently, kernelized locality sensitive hashcodes have been successfully employed as representations of natural language text, especially showing high relevance to biomedical relation extraction tasks. In this paper, we propose to optimize the hashcode representations in a nearly unsupervised manner, in which we only use data points, but not their class labels, for learning. The optimized hashcode representations are then fed to a supervised classifier following the prior work. This nearly unsupervised approach allows fine-grained optimization of each hash function, which is particularly suitable for building hashcode representations generalizing from a training set to a test set. We empirically evaluate the proposed approach for biomedical relation extraction tasks, obtaining significant accuracy improvements w.r.t. stateof-the-art supervised and semi-supervised approaches.

show abstract

“…Our approach is related to that of [13] and the more recent work of [16], who propose domain adaptation techniques based on learning domain-invariant features, where the first one utilizes MMD while the second one utilizes adversarial training. It is also closely related to [15], where domain-invariant representation is learned for music style transfer.…”

Section: Related Workmentioning

confidence: 99%

Batch Effect Removal via Batch-Free Encoding

Shaham

2018

Preprint

View full text Add to dashboard Cite

Biological measurements often contain systematic errors, also known as "batch effects", which may invalidate downstream analysis when not handled correctly. The problem of removing batch effects is of major importance in the biological community. Despite recent advances in this direction via deep learning techniques, most current methods may not fully preserve the true biological patterns the data contains. In this work we propose a deep learning approach for batch effect removal. The crux of our approach is learning a batch-free encoding of the data, representing its intrinsic biological properties, but not batch effects. In addition, we also encode the systematic factors through a decoding mechanism and require accurate reconstruction of the data. Altogether, this allows us to fully preserve the true biological patterns represented in the data. Experimental results are reported on data obtained from two high throughput technologies, mass cytometry and single-cell RNA-seq. Beyond good performance on training data, we also observe that our system performs well on test data obtained from new patients, which was not available at training time. Our method is easy to handle, a publicly available code can be found at https://github.com/ushaham/BatchEffectRemoval2018.

show abstract

Generalizing biomedical relation classification with neural adversarial domain adaptation

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 39 publications

References 32 publications

Improving neural protein-protein interaction extraction with knowledge selection

Improving neural protein-protein interaction extraction with knowledge selection

Nearly-Unsupervised Hashcode Representations for Biomedical Relation Extraction

Batch Effect Removal via Batch-Free Encoding

Contact Info

Product

Resources

About