Papers › Pre-Training of Deep Bidirectional Protein Sequence Representations with Structural Information

Pre-Training of Deep Bidirectional Protein Sequence Representations with Structural Information

25 Nov 2019arXiv:1912.05625archive 2025-07-28

Seonwoo Min, Seunghyun Park, Siwon Kim, Hyun-Soo Choi, Byunghan Lee, Sungroh Yoon

Bridging the exponentially growing gap between the numbers of unlabeled and labeled protein sequences, several studies adopted semi-supervised learning for protein sequence modeling. In these studies, models were pre-trained with a substantial amount of unlabeled data, and the representations were transferred to various downstream tasks. Most pre-training methods solely rely on language modeling and often exhibit limited performance. In this paper, we introduce a novel pre-training scheme called PLUS, which stands for Protein sequence representations Learned Using Structural information. PLUS consists of masked language modeling and a complementary protein-specific pre-training task, namely same-family prediction. PLUS can be used to pre-train various model architectures. In this work, we use PLUS to pre-train a bidirectional recurrent neural network and refer to the resulting model as PLUS-RNN. Our experiment results demonstrate that PLUS-RNN outperforms other models of similar size solely pre-trained with the language modeling in six out of seven widely used protein biology tasks. Furthermore, we present the results from our qualitative interpretation analyses to illustrate the strengths of PLUS-RNN. PLUS provides a novel way to exploit evolutionary relationships among unlabeled proteins and is broadly applicable across a variety of protein biology tasks. We expect that the gap between the numbers of unlabeled and labeled proteins will continue to grow exponentially, and the proposed pre-training method will play a larger role.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

mswzeus/PLUS officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingMasked Language ModelingOnly Connect Walls Dataset Task 1 (Grouping)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (LARGE) Wasserstein Distance (WD) 88.3 ± .5 #17 of 22 Archive leaderboard report
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (LARGE) # Correct Groups 33 ± 2 #17 of 22 Archive leaderboard report
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (LARGE) # Solved Walls 0 ± 0 #17 of 22 Archive leaderboard report
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (LARGE) Adjusted Mutual Information (AMI) 10.3 ± .3 #17 of 22 Archive leaderboard report
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (LARGE) Adjusted Rand Index (ARI) 8.2 ± .3 #17 of 22 Archive leaderboard report
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (LARGE) Fowlkes Mallows Score (FMS) 26.5 ± .2 #17 of 22 Archive leaderboard report
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (BASE) Wasserstein Distance (WD) 89.5 ± .4 #18 of 22 Archive leaderboard report
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (BASE) # Correct Groups 22 ± 2 #18 of 22 Archive leaderboard report
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (BASE) # Solved Walls 0 ± 0 #18 of 22 Archive leaderboard report
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (BASE) Adjusted Mutual Information (AMI) 8.1 ± .4 #18 of 22 Archive leaderboard report
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (BASE) Adjusted Rand Index (ARI) 6.4 ± .3 #18 of 22 Archive leaderboard report
Only Connect Walls Dataset Task 1 (Grouping) OCW BERT (BASE) Fowlkes Mallows Score (FMS) 25.1 ± .2 #18 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections