<p><span>[KEYNOTE] Computational Tools for the Identification of Unknowns (Video) </span></p>
Bibliographic record
Abstract
In untargeted MS studies involving metabolomics the proportion of unknown or unidentifiable compounds (i.e. features) detected can often be >90%. Given that the proper identification of a true unknown can take many months or years of work, it is little wonder that few investigators are willing to undertake the task of rigorously identifying these unknowns. While experimental techniques such as suspect screening can lead to the occasional “lucky” hit, a more rapid and robust approach is needed for unknown identification. In this presentation I will introduce the concept of in silico metabolomics. This is a computational approach to unknown identification that combines the extensive knowledge of known compounds with the existing knowledge of how compounds are chemically or biologically transformed. In silico metabolomics fundamentally requires a large collection of known structures. Over the past 10 years we have created a number of compound databases that catalogue the known compounds, including human metabolites (HMDB), food constituents (FooDB), drugs (DrugBank), plant products (PhytoBank) and contaminants (ContaminantDB). We have also developed a software package called BioTransformer, that uses expert-knowledge combined with machine learning to accurately predict the biological and chemical transformations that known compounds may undergo in humans and in the environment. This software has been used to create a database called BioTranformerDB consisting of several million “biologically feasible” structures. By exploiting several in-house tools for accurate MS/MS and NMR spectral prediction we have been able to calculate the MS/MS and NMR spectra for all of the compounds in BioTransformerDB. Using these newly developed software tools and resources for in silico metabolomics, I will show how unknown compounds may be identified from untargeted MS studies. Video from the Keynote Speaker Dr. David S. Wishart can be found: https://www.youtube.com/watch?v=CAU_cWPtNHQ&feature=youtu.be
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.395 | 0.199 |
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".