Claim and evidence Close ×
The bioRxiv preprint "De novo protein design by deep network hallucination" (Anishchenko, Chidyausiku, Ovchinnikov, Pellock and Baker, v1 of 23 July 2020) states that deep networks trained to predict native protein structures can be inverted to design new proteins and should contribute to the de novo design of proteins with new functions. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 2 sources
Date 2020-07-23 · publication Records dated 2020 → Role Articulation Register (kind of text) Nonfiction Scope of the passage An expectation for new functions, from a demonstration of new folded proteins. Scope and limits The record documents what this text states, in its register; it is not evidence that the proposition is true and implies no influence on or from any other text. Read in the v1 abstract served by the bioRxiv API and in the abstract of the Nature version. The contribution to new functions is stated as an expectation (“should contribute”); the abstract reports new folds, not new functions. The research pack headlined it as earliest located; no text holds that role until the criterion is adjudicated (maintainer decision of 2026-10-30). The abstract describes the design and laboratory procedure; only its concluding sentences are cited and no method detail is paraphrased.
The evidence 02 primary source Supports the claim
De novo protein design by deep network hallucination (bioRxiv v1) ↗ bioRxiv (details API) · 2020-07-23
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “such networks and methods should contribute, alongside traditional physically based models, to the de novo design of proteins with new functions.” Location in source v1 abstract (bioRxiv details API, abstract field), last sentence
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-30
Source details and check notes Authors Anishchenko I; Chidyausiku TM; Ovchinnikov S; Pellock SJ; Baker D Version Retrieved for the candidate pack on 2026-10-30 (SHA-256 275259bdb35bb6a61c57c69729653085d6fb43943f49a28e111f28d31260e7cd). bioRxiv details API record (JSON) for v1 of 2020-07-23, with the v1 abstract; the bioRxiv HTML page was not fetched (rate-limited route). Canonical address Open the canonical source ↗ Accessed 2026-10-30 Language English (en) Attribution Anishchenko I, Chidyausiku TM, Ovchinnikov S, Pellock SJ, Baker D, “De novo protein design by deep network hallucination (bioRxiv v1)”, 2020-07-23. Reuse No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution. Check notes Candidate pack passage, AI in biology (research/ai-in-biology). The quotation (21 words) matched the text retrieved for the candidate pack on 2026-10-30. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. Abstract text relayed by the bioRxiv details API's abstract field: the authors' own text, so primary; the journal expression was not read. The authors' stated expectation, in the preprint wording. A cross-family machine check (2026-10-30, item A57) answered the record’s question blind from fresh retrievals and agreed in part; its corrections were applied at admission. No human editorial review. primary source Supports the claim
De novo protein design by deep network hallucination ↗ Nature · 2021-12-01
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Source excerpt “deep networks trained to predict native protein structures from their sequences can be inverted to design new proteins” Location in source Abstract (Nature article page), last sentence
How it was read Retrieved directly from the publisher
Machine-checked · 2026-10-30
Source details and check notes Authors Ivan Anishchenko; Samuel J. Pellock; Tamuka M. Chidyausiku; David Baker Version Retrieved for the candidate pack on 2026-10-30 (SHA-256 eef0974270764f95a79e8713c0238700eab405f815b6a5bd6df6d276b0f55e8c). Nature article page as served on 2026-10-30; abstract and metadata. The author list is partial: it gives the authors the retrieved expression names and leaves out those it abbreviates. Canonical address Open the canonical source ↗ Accessed 2026-10-30 Language English (en) Attribution Ivan Anishchenko, Samuel J. Pellock, Tamuka M. Chidyausiku, David Baker, “De novo protein design by deep network hallucination”, 2021-12-01. Reuse No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution. Check notes Candidate pack passage, AI in biology (research/ai-in-biology). The quotation (18 words) matched the text retrieved for the candidate pack on 2026-10-30. Matching ignored differences of whitespace, case, quotation marks, dashes and Unicode compatibility forms, so the source’s typography can differ. The same conclusion in the journal version of 1 December 2021. A cross-family machine check (2026-10-30, item A57) answered the record’s question blind from fresh retrievals and agreed in part; its corrections were applied at admission. No human editorial review. Status and meaning Editorial status. Not reviewed by an editor . An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.
Relation. A passage of the document meets the proposition’s criterion. The record documents what the text states, in its register (fiction and satire are labelled); it is not evidence that the proposition is true and implies no influence on or from another text.
Date. Date of bioRxiv v1, from the bioRxiv details API. The journal version (Nature, published online 1 December 2021) carries the same concluding statement in edited wording.
Record ID aib-arg-p4-anishchenko-2020