Skip to content
DraconiticResearch
Search Sources API
203,948 studies31 sourcesUpdated 21 min ago
Peer-reviewedCC BYBiology letters

Quantifying pollen and spore morphology using a language model.

  • Luke Mander1
  • Peng Sun2
  • Surangi W Punyasena3
  • Carlos Jaramillo4
  • Francisca Oboh-Ikuenobe5
5 affiliations
  1. 1School of Environment, Earth and Ecosystem Sciences, The Open University , Milton Keynes, UK.
  2. 2Institute of Environmental Sciences, Leiden University , Leiden, The Netherlands.
  3. 3Department of Plant Biology, University of Illinois , Urbana, IL, USA.
  4. 4Smithsonian Tropical Research Institute , Panama City, Panama, Panama City, Panama.
  5. 5Department of Earth Sciences and Engineering, Missouri University of Science and Technology , Rolla, MO, USA.
Read full textPDFDOICite

Abstract

In a typical systematic paper, specimen morphology is described with natural language, and taxonomic specialists use glossaries of technical terminology to establish and communicate taxon concepts, using morphology to delimit species. Textual descriptions of specimen morphology are therefore foundational to biological systematics, but they also serve as a primary data source for studies of morphological evolution. Typically, researchers extract attributes of taxon morphology from descriptions and analyse them to quantify how organismal form has evolved. Focussing on fossil pollen and spores as records of plant evolution, we outline a potential approach to quantifying and comparing morphology that involves using a language model (LM) to transform textual descriptions of specimen morphology into numerical embeddings and then analysing the embeddings statistically. Our results show how an LM can be used to quantitatively analyse the morphological information contained within the text of taxonomic descriptions, illustrating that first-order botanical groupings such as pollen versus spores can be distinguished in the text of a single monograph and potentially from multiple texts by different authors. Although our dataset is small, we tentatively suggest that the spore-plant dominated tropical vegetation of the Carboniferous was comparable in morphological diversity to the angiosperm dominated tropical rainforests of the Palaeogene.

Related

  1. SkeleSketch: An Open-Source Tool for Quantifying Microglial Morphology in Fiji/ImageJ
    L. A. Pascoe, V. M. Masegosa, S. Liu +1
    bioRxivPreprintCC BYFull textNeurosciencebioRxiv
  2. Quantifying punctate morphology in mesenchymal stem cells from single cell images provides a definitive quality assessment pipeline for direct correlation to osteogenic lineage differentiation
    U. Chakraborty, S. Purushotham, T. Bhattacharjee +4
    bioRxivPreprintCC BY-NDFull textCell biologybioRxiv
  3. Chaperone protein DnaK-mediated regulation of spore coat assembly in Bacillus subtilis
    Kangyi Mu, Chunrong Ling, Tianlin Cui +4
    ISciencePeer-reviewedCC BY-NC-NDFull textGenetics & genomicsEurope PMCCrossref
  4. The Epistemic Risk of the 31st Spore: If Planets Aren't Fine Tuned, We're Doing Life Detection Wrong
    Harrison B. Smith, Cole Mathis
    arXivPreprintCC BY-NC-SA 4.0Full textGeneral biologyGeneral physicsarXiv
  5. Do Botanical Gardens Pose a Pollen Allergenicity Risk? A Multi-Method Assessment Integrating Species-Specific Values of Potential Allergenicity and Pollen Concentration Monitoring
    Mengxia Li, Qi Tang, Hua Zong +3
    Plants (Basel, Switzerland)Peer-reviewedCC BYFull textPlant biologyEurope PMC

Cite

BibTeXRIS
BibTeX
@article{mander2026quantifying,
  title = {{Quantifying pollen and spore morphology using a language model.}},
  author = {Luke Mander and Peng Sun and Surangi W Punyasena and Carlos Jaramillo and Francisca Oboh-Ikuenobe},
  journal = {Biology letters},
  year = {2026},
  month = oct,
  doi = {10.1098/rsbl.2026.0313},
  url = {https://europepmc.org/article/MED/42869452},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Quantifying pollen and spore morphology using a language model.
AU  - Luke Mander
AU  - Peng Sun
AU  - Surangi W Punyasena
AU  - Carlos Jaramillo
AU  - Francisca Oboh-Ikuenobe
PY  - 2026
DA  - 2026/10/01
JO  - Biology letters
DO  - 10.1098/rsbl.2026.0313
UR  - https://europepmc.org/article/MED/42869452
AB  - In a typical systematic paper, specimen morphology is described with natural language, and taxonomic specialists use glossaries of technical terminology to establish and communicate taxon concepts, using morphology to delimit species. Textual descriptions of specimen morphology are therefore foundational to biological systematics, but they also serve as a primary data source for studies of morphological evolution. Typically, researchers extract attributes of taxon morphology from descriptions and analyse them to quantify how organismal form has evolved. Focussing on fossil pollen and spores as records of plant evolution, we outline a potential approach to quantifying and comparing morphology that involves using a language model (LM) to transform textual descriptions of specimen morphology into numerical embeddings and then analysing the embeddings statistically. Our results show how an LM can be used to quantitatively analyse the morphological information contained within the text of taxonomic descriptions, illustrating that first-order botanical groupings such as pollen versus spores can be distinguished in the text of a single monograph and potentially from multiple texts by different authors. Although our dataset is small, we tentatively suggest that the spore-plant dominated tropical vegetation of the Carboniferous was comparable in morphological diversity to the angiosperm dominated tropical rainforests of the Palaeogene.
SN  - 1744-9561
SN  - 1744-957X
ER  -