Exploring Large Protein Sequence Space through Homology- and Representation-based Hierarchical Clustering
Bibliographic record
Abstract
Exploration of protein sequence space can offer insight into protein sequence-function relationships, benefitting both basic science and industrial applications. The use of sequence similarity networks is a standard method for exploring large sequence datasets, but is currently limited when scaling to very large datasets and when viewing more than one level (hierarchy) of homology. Here, we present a sequence analysis pipeline with a number of innovations that address some limitations of traditional sequence similarity networks. First, we develop a hierarchical visualization approach that captures the full range of homologies across protein superfamilies. Second, we leverage representations embedded by protein language models as an alternative homology metric to the Basic Local Alignment Search Tool, showing that they produce comparable results when identifying isofunctional protein families. Finally, we demonstrate that unbiased representative sampling of sequences from genetic neighborhoods can be achieved through the use of HMMs or vector representations. The utility of these methods is exemplified by updating the sequence-function analysis of the FMN/F420-binding split barrel superfamily and the nuclear transport factor 2-like superfamily. We also improve the phylogenetic analysis of the FMN/F420-binding split barrel superfamily with more even and diverse sequence sampling across the superfamily. We provide our sequence exploration pipeline as publicly available code (ProteinClusterTools) and show it to be scalable to large datasets (∼445 k sequences) using desktop computers.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.006 | 0.006 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".