Papers › Evaluating Protein Transfer Learning with TAPE

Evaluating Protein Transfer Learning with TAPE

19 Jun 2019NeurIPS 2019 12arXiv:1906.08230archive 2025-07-28

Roshan Rao, Nicholas Bhattacharya, Neil Thomas, Yan Duan, Xi Chen, John Canny, Pieter Abbeel, Yun S. Song

Protein modeling is an increasingly popular area of machine learning research. Semi-supervised learning has emerged as an important paradigm in protein modeling due to the high cost of acquiring supervised protein labels, but the current literature is fragmented when it comes to datasets and standardized evaluation techniques. To facilitate progress in this field, we introduce the Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology. We curate tasks into specific training, validation, and test splits to ensure that each task tests biologically relevant generalization that transfers to real-life scenarios. We benchmark a range of approaches to semi-supervised protein representation learning, which span recent work as well as canonical sequence learning techniques. We find that self-supervised pretraining is helpful for almost all models on all tasks, more than doubling performance in some cases. Despite this increase, in several cases features learned by self-supervised pretraining still lag behind features extracted by state-of-the-art non-neural techniques. This gap in performance suggests a huge opportunity for innovative architecture design and improved modeling paradigms that better capture the signal in biological sequences. TAPE will help the machine learning community focus effort on scientifically relevant problems. Toward this end, all data and code used to run these experiments are available at https://github.com/songlab-cal/tape.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 4 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 5 ran (3 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 12 samples from 3 repositories, 11 ran (9 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

songlab-cal/tape officialmentioned in papermentioned on GitHubtfBSD-3-ClauseSyntology: 6 samples, 5 ran (2 instrument-failed) · 1 unverified report
THUDM/ProteinLM mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Modeling Protein Using Large-scale Pretrain Language Model (arXiv:2108.07435; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
googleinterns/protein-embedding-retrieval mentioned on GitHubjaxApache-2.0Syntology: 10 samples, 9 ran (0 instrument-failed) · 1 unverified report
songlab-cal/tape-neurips2019 mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
statisticalbiotechnology/tape mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

18 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
12ran
2unverified

Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

songlab-cal/tape official repository 6 samples, 5 ran (2 instrument-failed) · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
tape/models/modeling_utils.py ran fingerprinted BSD-3-Clause (permissive) · fcba2b0e1052ebf4 · report fixture: signature logits:Tensor/2/float, labels:Tensor/1/int, ignore_index:int/0/int · returned Tensor · level recorded 2026-09-25
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
tape/models/modeling_utils.py ran fingerprinted BSD-3-Clause (permissive) · 5f49c78bf7533113 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25
pad_sequences in 19 papers tape/datasets.py ran BSD-3-Clause (permissive) · 8062e9b3b5efa7dd · report fixture: signature sequences:list/1/ndarray, constant_value:int/0/int, dtype:NoneType/0/? · returned ndarray · level recorded 2026-09-25
prune_linear_layer in 40 papers tape/models/modeling_utils.py ran · our draft was wrong BSD-3-Clause (permissive) · d30d6c3098df2c42 · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Linear · level recorded 2026-09-22
url_to_filename in 73 papers tape/models/file_utils.py ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 5eff22fa0a651276 · report fixture: signature url:str/0/str, etag:str/0/str · returned str · level recorded 2026-09-22
get_etag tape/models/file_utils.py unverified BSD-3-Clause (permissive) · a646bd4aa40ada48 · report
googleinterns/protein-embedding-retrieval community (archive-listed) 10 samples, 9 ran (0 instrument-failed) · 1 unverified
create_params generate_params.py ran Apache-2.0 (permissive) · 4884f9783a5e94c1 · report fixture: signature encoder_lrs:list/1/float, lens_lrs:list/1/float, predictor_lrs:list/1/float, encoder_wds:list/1/float, lens_wds:list/1/float, predictor_wds:list/1/float, reduce_fn_kwargs_paths:list/1/str, lens_train_samples:list/1/int, train_families:int/0/int, epochs:int/0/int, measurements:list/1/int, encoder_fn_name:str/0/str, encoder_fn_kwargs_path:str/0/str, reduce_fn_name:str/0/str, lens_batch_size:int/0/int, knn_batch_size:int/0/int, use_transformer:bool/0/bool, use_bert:bool/0/bool, restore_transformer_dir:NoneType/0/?, model_random_keys:list/1/int, first_test_family:int/0/int, last_test_family:int/0/int, load_gcs_bucket:str/0/str, data_partitions_dirpath:str/0/str, save_gcs_bucket:str/0/str, results_save_dir:str/0/str, lens_shuffle_seed:int/0/int, lens_sample_random_state:int/0/int, knn_shuffle_seed:int/0/int, knn_sample_random_state:int/0/int, load_model:bool/0/bool, load_model_dir:str/0/str, load_model_step:int/0/int, save_model:bool/0/bool, save_model_dir:str/0/str · returned list · level recorded 2026-09-24
cross_entropy_loss in 58 papers contextual_lenses/loss_fns.py ran Apache-2.0 (permissive) · af86e14bcdd0eee9 · report fixture: signature Y:ArrayImpl/1/int, Y_hat:ArrayImpl/2/float, num_classes:int/0/int · returned ArrayImpl · level recorded 2026-09-24
max_pool in 11 papers contextual_lenses/contextual_lenses.py ran Apache-2.0 (permissive) · e572cb38b1df143b · report fixture: signature x:ArrayImpl/3/float, padding_mask:ArrayImpl/3/float, pad_constant:float/0/float · returned ArrayImpl · level recorded 2026-09-24
mean_pool in 13 papers contextual_lenses/contextual_lenses.py ran Apache-2.0 (permissive) · 3ac8c389a631fc4b · report fixture: signature x:ArrayImpl/3/float, padding_mask:ArrayImpl/3/float · returned ArrayImpl · level recorded 2026-09-24
mod_family_accession contextual_lenses/pfam_utils.py ran Apache-2.0 (permissive) · c7f103c56b719278 · report fixture: signature family_accession:str/0/str · returned str · level recorded 2026-09-24
mse_loss in 73 papers
census: 8 implementations from 12 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
contextual_lenses/loss_fns.py ran Apache-2.0 (permissive) · eafa5a8ead83133c · report fixture: signature Y:ArrayImpl/1/float, Y_hat:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-24
one_hot_encoder in 7 papers contextual_lenses/encoders.py ran fingerprinted Apache-2.0 (permissive) · b10d1d06cd24b15f · report fixture: signature batch_inds:ArrayImpl/1/int, num_categories:int/0/int · returned ArrayImpl · level recorded 2026-09-24
path_inclusion_filter_fn contextual_lenses/train_utils.py ran Apache-2.0 (permissive) · 72ec4c60f133c8a3 · report fixture: signature path:str/0/str, param:Tensor/2/float, layer:str/0/str · returned bool · level recorded 2026-09-24
set_model_parameters pfam_experiment.py ran Apache-2.0 (permissive) · d3eb70af2cd44569 · report fixture: signature model:callable/0/?, params:dict/0/? · returned SimpleModel · level recorded 2026-09-24
create_data_iterator contextual_lenses/train_utils.py unverified Apache-2.0 (permissive) · e90485a45ea78dba · report
songlab-cal/tape-neurips2019 community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
filter_text tape/__main__.py ran · our draft was wrong fingerprinted MIT (permissive) · 03beff488122d034 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
statisticalbiotechnology/tape community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
pythonify scripts/tfrecord_to_lmdb.py ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · ae2d936644fd0314 · report fixture: signature tensor:Tensor/1/int · returned ndarray · level recorded 2026-09-22

Tasks

BIG-bench Machine LearningRepresentation LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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