dna2vec: Consistent Vector Representations of Variable-Length k-mers

Patrick Ng · arXiv · 2017 · genetics · record ng2017-dna2vec
tag layer · index · concepts · authors · עברית

Where this record's text came from. faceted 2026-08 by reading the locally held text (pdftext); every evidence string verified as an exact substring of that text before merging. limitations is empty because the paper states no limitation of its own work: the Discussion contains only results and a future-work sentence ("we will explore the application of dna2vec with machine learning techniques on biological sequence analysis"), which flags that no downstream task has been demonstrated but is phrased as future work, not as a limitation. The only weaknesses named in the text belong to other approaches (one-hot encoding's dimensionality, Needleman-Wunsch's quadratic cost). Evaluation is intrinsic only (concatenation analogies, alignment-score correlation on sampled 8-mers), with no biological benchmark. 2026-08-14, 2026-08-15 and 2026-08-25 schema-0.3 passes: every quote verified as an exact substring of the staged text and anchored at merge time; concept terms verified present; every edge endpoint an existing node.

How to read this page. The article itself is not reproduced here — this paper is not cleared for redistribution, so what follows is the tag layer alone. The evidence sentences are withheld with the article. The table at the foot lists every tag the record carries; each row names the facet it belongs to, and the whose words column says whether the tag records the paper's own wording or the tagger's sentence about the paper. Every tag links to each other paper in the corpus carrying it. The machine-readable edition of the same thing is the TEI file beside this one, where the tags live in standOff, and the article is at its publisher via the link below. When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.

Other fields define these differently the same word, defined another way in another discipline
representation 47 fields · distributed representation 2 fields · DNA 2 fields · genomics 2 fields

Tags on this paper

Every tag the record carries, each linking to every other paper in the corpus that carries it. A tag appears here whether or not its words occur in the article — the spans below are only the ones a sentence in this paper licenses. Of the 9 concept tags on this paper, 6 are grounded in a quoted sentence.

word embedding k-mer distributed representation genomics DNA sequence one-hot vector dna2vec word2vec Needleman-Wunsch training word2vec (CBOW/skip-gram) on overlapping variable-length DNA k-mers vector embedding DNA similarity nucleotide representation sequence DNA k-mer cosine similarity of dna2vec vectors correlation correlation coefficient system-or-tool-building

Legend

relation to other work	`claim_relations`	how this paper stands to another: agrees, contradicts, extends, qualifies
claim type	`claim_type`	the shape of the claim: existence, mechanism, method, critique, prediction, null
concept edge	`concept_edges`	an asserted relation between two concepts, with the sentence asserting it
concept	`concepts`	an idea the paper works with, quoted where the paper uses it
content tag	`content_tags`	a finding, definition, quantity, statistic or variable named in the paper
control	`controls`	an experiment run to eliminate a rival explanation
limitation	`limitations`	what the paper says its evidence cannot support
mechanism	`mechanisms`	how the reported effect is said to come about
method	`method`	how the paper produced its evidence
phenomenon	`phenomenon`	the effect or regularity under study
sense	`senses`	a distinct use of a term, quoted where the paper fixes it
transfer	`transfers`	a method or concept carried in from another field

The paper

The full text is not reproduced here. This article is not cleared for redistribution, so the page carries the tag layer only. Its evidence sentences are withheld; the grounding status remains with each tag, and the article itself is at https://arxiv.org/abs/1701.06279. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 3 · claim_type 1 · concept_edges 1 · concepts 6 · content_tags 9 · controls 1 · limitations 3 · mechanisms 1 · method 1 · phenomenon 1 · senses 3 · transfers 1

Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; none of 1 relation here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.

facet	tag	field	conf.	whose words
claim_type	method Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_type`		the paper's words
phenomenon	distributed vector representations of DNA k-mers Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`phenomenon`		the paper's words
method	system-or-tool-building Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: system-or-tool-building	`method`		the paper's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: training word2vec (CBOW/skip-gram) on overlapping variable-length DNA k-mers	`mechanisms[0]`		the tagger's words
limitations	The standard encoding asserts that every pair of sequences is equally unlike every other, which is false of the sequences themselves. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: any similarity computed over one-hot k-mer encodings: the distance between any arbitrary pair is equidistant, even though ATGGC should be closer to ATGGG than CACGA	`limitations[0]`	1.0	the tagger's words
limitations	Every similarity result in the paper is measured against one stipulated alignment scoring, including a gap penalty of zero. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the reported correlation between dna2vec cosine similarity and sequence similarity: the Needleman-Wunsch scores use a match score of 1, mismatch of 0 and gap penalty of 0, so the correlation is with that scoring and not with alignment in general	`limitations[1]`	1.0	the tagger's words
limitations	The method's justification is a hypothesis about words, carried over to nucleotides, and the paper marks the inspiration as loose. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the claim that dna2vec vectors carry biological meaning: the training objective is warranted by the distributional hypothesis about words appearing in the same context, which the paper says it is loosely inspired by	`limitations[2]`	1.0	the tagger's words
transfers	the word2vec word-embedding model, applied to DNA k-mers Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`transfers[0]`		the tagger's words
controls	a null distribution built by scoring pairs of RANDOM 8-mers, against which the real scores are read Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: similarity scores that look high simply because any two short sequences share structure - the null is constructed data rather than a reshuffling of the observed data · outcome (stated by the tagger, no quotation): held	`controls[0]`	0.85	the tagger's words
concepts	k-mer Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: k-mer	`concepts[1]`		the paper's words
concepts	distributed representation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: distributed representation	`concepts[2]`		the paper's words
concepts	one-hot vector Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: one-hot vector	`concepts[5]`		the paper's words
concepts	dna2vec Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: dna2vec	`concepts[6]`		the paper's words
concepts	word2vec Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: word2vec	`concepts[7]`		the paper's words
concepts	Needleman-Wunsch Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Needleman-Wunsch	`concepts[8]`		the paper's words
senses	context - AS PHYSICAL ADJACENCY ALONG THE SEQUENCE: the set of k-mers next to the target within a fragment, which is what the word means here, not linguistic co-occurrence Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	1.0	the tagger's words
senses	the distributional hypothesis - AS THE TRANSFERRED WARRANT: a 1954 claim about words in the same context having similar meaning, doing the justificatory work for a model of nucleotides Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	1.0	the tagger's words
senses	k-mer length - AS A RANDOM VARIABLE: the window size is drawn from a discrete uniform distribution for each position, so the same sequence yields different k-mers on different runs Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	1.0	the tagger's words
claim_relations	builds-on → word2vec (from NLP/linguistics) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[0]`		the tagger's words
claim_relations	builds-on → word2vec (Mikolov et al., 2013a) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[1]`		the tagger's words
claim_relations	extends → BioVec (Asgari and Mofrad, 2015) and seq2vec (Kimothi et al., 2016) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[2]`		the tagger's words
concept_edges	EVIDENCE CORRECTED (RE-GROUNDED) · k-mer —operationalised-as→ one-hot vector Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. EVIDENCE CORRECTED: RE-GROUNDED. The old span named only 'one-hot vector'. This sentence names both and states the encoding explicitly - 'of k-mer AS a…'. — strength of the relation: 1 also in: k-mer · one-hot vector	`concept_edges[0]`		the tagger's words
content_tags	100 — dimensionality of the continuous dna2vec vector space Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[0]`		the tagger's words
content_tags	two-layer — depth of the shallow neural network (as in word2vec) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[1]`		the tagger's words
content_tags	dna2vec trains distributed representations of variable-length DNA k-mers, based on the word embedding model word2vec. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[0]`		the tagger's words
content_tags	Summing dna2vec vectors approximates nucleotide concatenation, and cosine similarity of the vectors correlates with Needleman-Wunsch alignment similarity. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[1]`		the tagger's words
content_tags	DNA k-mer Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: DNA k-mer	`content_tags.variables[0]`		the tagger's words
content_tags	cosine similarity of dna2vec vectors Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: cosine similarity of dna2vec vectors	`content_tags.variables[1]`		the tagger's words
content_tags	k-mer Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: k-mer	`content_tags.definitions[0]`		the tagger's words
content_tags	one-hot vector Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: one-hot vector	`content_tags.definitions[1]`		the tagger's words
content_tags	correlation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: correlation	`content_tags.statistics[0]`		the tagger's words

Interpretive choices

Tags that could not be placed in the text:

none — every tag was located in the text

What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.