Papers › Bio-xLSTM: Generative modeling, representation and in-context learning of biological...

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences

6 Nov 2024arXiv:2411.04165archive 2025-07-28

Niklas Schmidinger, Lisa Schneckenreiter, Philipp Seidl, Johannes Schimunek, Pieter-Jan Hoedt, Johannes Brandstetter, Andreas Mayr, Sohvi Luukkonen, Sepp Hochreiter, Günter Klambauer

Language models for biological and chemical sequences enable crucial applications such as drug discovery, protein engineering, and precision medicine. Currently, these language models are predominantly based on Transformer architectures. While Transformers have yielded impressive results, their quadratic runtime dependency on the sequence length complicates their use for long genomic sequences and in-context learning on proteins and chemical sequences. Recently, the recurrent xLSTM architecture has been shown to perform favorably compared to Transformers and modern state-space model (SSM) architectures in the natural language domain. Similar to SSMs, xLSTMs have a linear runtime dependency on the sequence length and allow for constant-memory decoding at inference time, which makes them prime candidates for modeling long-range dependencies in biological and chemical sequences. In this work, we tailor xLSTM towards these domains and propose a suite of architectural variants called Bio-xLSTM. Extensive experiments in three large domains, genomics, proteins, and chemistry, were performed to assess xLSTM's ability to model biological and chemical sequences. The results show that models based on Bio-xLSTM a) can serve as proficient generative models for DNA, protein, and chemical sequences, b) learn rich representations for those modalities, and c) can perform in-context learning for proteins and small molecules.

PaperPDFCodeCode 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 29 code samples harvested from 3 repositories linked to this paper: 27 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 15 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 15 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 29 samples from 3 repositories, 27 ran (12 with no instrument failure; 15 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.

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. 1 of the 27 samples that ran has no recorded date.

ml-jku/chem-xlstm officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 17 samples, 15 ran (10 instrument-failed) · 2 unverified report
ml-jku/dna-xlstm officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 9 samples, 9 ran (5 instrument-failed) · 0 unverified report
ml-jku/prot-xlstm officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (0 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.

Code Syntology ran Syntology

29 samples harvested: 27 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 1 violated, 8 with no contract checked; 15 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · violated contract
15ran · our draft was wrong
8ran
2unverified

Licence: 1 of the 29 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 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”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

ml-jku/chem-xlstm official repository 17 samples, 15 ran (10 instrument-failed) · 2 unverified
cauchy_naive in 7 papers chemxlstm/module_library/cauchy.py ran Apache-2.0 (permissive) · bf0be6c26af1d44e · report fixture: signature v:Tensor/2/complex, z:Tensor/2/complex, w:Tensor/2/complex, conj:bool/0/bool · returned Tensor · level recorded 2026-09-25
combination in 8 papers chemxlstm/module_library/dplr.py ran · our draft was wrong Apache-2.0 (permissive) · 5688929ec94f213a · report fixture: signature measures:str/0/str, N:int/0/int, R:int/0/int, S:int/0/int · returned tuple · level recorded 2026-09-25
dplr in 7 papers chemxlstm/module_library/dplr.py ran · our draft was wrong Apache-2.0 (permissive) · 7c3fe064733e56b3 · report fixture: signature scaling:str/0/str, N:int/0/int, rank:int/0/int, H:int/0/int, dtype:dtype/0/?, real_scale:float/0/float, imag_scale:float/0/float, random_real:bool/0/bool, random_imag:bool/0/bool, normalize:bool/0/bool, diagonal:bool/0/bool, random_B:bool/0/bool · returned tuple · level recorded 2026-09-25
krylov chemxlstm/module_library/krylov.py ran · our draft was wrong Apache-2.0 (permissive) · 1f3623588b61ca31 · report fixture: signature L:int/0/int, A:Tensor/2/float, b:Tensor/1/float, c:Tensor/1/float, return_power:bool/0/bool · returned tuple · level recorded 2026-09-22
krylov_sequential chemxlstm/module_library/krylov.py ran Apache-2.0 (permissive) · b060864a3e29a600 · report fixture: signature L:int/0/int, A:Tensor/3/float, b:Tensor/2/float, c:Tensor/2/float · returned Tensor · level recorded 2026-09-25
learn_label_encoding chemxlstm/fasta_utils.py ran · our draft was wrong Apache-2.0 (permissive) · 1fb8af0f651b45c7 · report fixture: signature tokenized_inputs:list/1/list · returned dict · level recorded 2026-09-25
load_file in 52 papers chemxlstm/evaluate_cond_gen.py ran · our draft was wrong Apache-2.0 (permissive) · 4208c567af7da5a8 · report fixture: signature file_path:str/0/str · returned list · level recorded 2026-09-25
load_model in 479 papers chemxlstm/evaluate_cond_gen.py ran Apache-2.0 (permissive) · df4c6239424d356d · report fixture: returned xLSTMforNTP · level recorded 2026-09-25
load_smiles_from_zip chemxlstm/metrics.py ran · our draft was wrong Apache-2.0 (permissive) · 8a748a919db6ec4d · report fixture: signature zip_path:str/0/str · returned list · level recorded 2026-09-25
power in 16 papers chemxlstm/module_library/krylov.py ran · our draft was wrong Apache-2.0 (permissive) · 5df4043c60e49613 · report fixture: signature L:int/0/int, A:Tensor/3/float, v:Tensor/3/float · returned tuple · level recorded 2026-09-25
rank_correction in 7 papers chemxlstm/module_library/hippo.py ran · honoured contract Apache-2.0 (permissive) · 433b3d872e02032c · report fixture: signature measure:str/0/str, N:int/0/int, rank:int/0/int, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-25
read_fastas chemxlstm/fasta_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 6e10ab4b4709a633 · report fixture: signature path_to_data:str/0/str · returned list · level recorded 2026-09-25
segment_fasta chemxlstm/fasta_utils.py ran fingerprinted Apache-2.0 (permissive) · c0dc66eb84a1479a · report fixture: signature fasta:str/0/str, replace_rare_aas:bool/0/bool · returned list · level recorded 2026-09-25
ssm in 8 papers chemxlstm/module_library/dplr.py ran · our draft was wrong Apache-2.0 (permissive) · a59eccfb252a06f0 · report fixture: signature measure:str/0/str, N:int/0/int, R:int/0/int, H:int/0/int, scaling:str/0/str, dtype:dtype/0/?, real_scale:float/0/float, imag_scale:float/0/float, random_real:bool/0/bool, random_imag:bool/0/bool, normalize:bool/0/bool, diagonal:bool/0/bool, random_B:bool/0/bool · returned tuple · level recorded 2026-09-25
transition in 16 papers chemxlstm/module_library/hippo.py ran · our draft was wrong Apache-2.0 (permissive) · 34b2aa570368722c · report fixture: signature measure:str/0/str, N:int/0/int, alpha:float/0/float, beta:float/0/float · returned tuple · level recorded 2026-09-25
create_dataloader in 35 papers chemxlstm/dataloaders.py unverified Apache-2.0 (permissive) · b52fb76a05e95adb · report
embed_c2r chemxlstm/module_library/hippo.py unverified Apache-2.0 (permissive) · e6845c8558af2604 · report
ml-jku/dna-xlstm official repository 9 samples, 9 ran (5 instrument-failed) · 0 unverified
bias_linspace_init_ models/dna_xlstm/xlstm/components/init.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 705d17e5f5c0489b · report fixture: signature param:Tensor/1/float, start:float/0/float, end:float/0/float · returned Tensor · level recorded 2026-09-22
conditional_decorator models/dna_xlstm/xlstm/components/util.py ran · our draft was wrong Apache-2.0 (permissive) · 683dd071b7bcb7c7 · report fixture: signature condition:bool/0/bool, decorator:callable/0/? · returned function · level recorded 2026-09-25
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
models/dna_xlstm/xlstm/xlstm_block_stack.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded
get_act_fn in 7 papers models/dna_xlstm/xlstm/components/feedforward.py ran · our draft was wrong Apache-2.0 (permissive) · ed05db9cecbe4f40 · report fixture: signature act_fn_name:str/0/str · returned builtin_function_or_method · level recorded 2026-09-25
get_mlstm_inner_dim models/dna_xlstm/xlstm/xlstm_block_stack.py ran · honoured contract Apache-2.0 (permissive) · 3b07afcb40c29e2a · report fixture: signature m_config:MLSTMConfig/0/? · returned int · level recorded 2026-09-25
precompute_freqs_cis in 112 papers models/dna_xlstm/xlstm/xlstm_block_stack.py ran Apache-2.0 (permissive) · 2bf924786015498d · report fixture: signature dim:int/0/int, end:int/0/int, theta:float/0/float · returned tuple · level recorded 2026-09-25
round_to_multiple models/dna_xlstm/xlstm/components/util.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 3a70ec6e0ac819b2 · report fixture: signature n:int/0/int, m:int/0/int · returned int · level recorded 2026-09-25
small_init_init_ models/dna_xlstm/xlstm/components/init.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · cfe16cc8552a2332 · report fixture: signature param:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-25
wang_init_ models/dna_xlstm/xlstm/components/init.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 431c81ae48403967 · report fixture: signature param:Tensor/2/float, dim:int/0/int, num_blocks:int/0/int · returned Tensor · level recorded 2026-09-25
ml-jku/prot-xlstm official repository 3 samples, 3 ran (0 instrument-failed) · 0 unverified
apply_rotary_emb in 121 papers protxlstm/xlstm/components/rotary_position.py ran Apache-2.0 (permissive) · ac829870c326eb73 · report fixture: signature xq:Tensor/3/float, xk:Tensor/3/float, freqs_cos:Tensor/2/float, freqs_sin:Tensor/2/float · returned tuple · level recorded 2026-09-25
compute_freqs_cis protxlstm/xlstm/components/rotary_position.py ran Apache-2.0 (permissive) · 2a573b08e6c410c8 · report fixture: signature t:Tensor/1/float, head_dim:int/0/int, theta:float/0/float · returned tuple · level recorded 2026-09-25
conv1d_step protxlstm/xlstm/components/conv.py ran Apache-2.0 (permissive) · 25766cf2cb87920f · report fixture: signature x:Tensor/3/float, conv_state:Tensor/3/float, conv1d_weight:Tensor/2/float, conv1d_bias:Tensor/1/float · returned tuple · level recorded 2026-09-25

Tasks

Drug DiscoveryIn-Context Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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