CFM-ID 3.0: Significantly Improved ESI-MS/MS Prediction and Compound Identification
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Metabolite identification for untargeted metabolomics is often hampered by the lack of experimentally collected reference spectra from tandem mass spectrometry (MS/MS). To circumvent this problem, Competitive Fragmentation Modeling-ID (CFM-ID) was developed to accurately predict electrospray ionization-MS/MS (ESI-MS/MS) spectra from chemical structures and to aid in compound identification via MS/MS spectral matching. While earlier versions of CFM-ID performed very well, CFM-ID's performance for predicting the MS/MS spectra of certain classes of compounds, including many lipids, was quite poor. Furthermore, CFM-ID's compound identification capabilities were limited because it did not use experimentally available MS/MS spectra nor did it exploit metadata in its spectral matching algorithm. Here, we describe significant improvements to CFM-ID's performance and speed. These include (1) the implementation of a rule-based fragmentation approach for lipid MS/MS spectral prediction, which greatly improves the speed and accuracy of CFM-ID; (2) the inclusion of experimental MS/MS spectra and other metadata to enhance CFM-ID's compound identification abilities; (3) the development of new scoring functions that improves CFM-ID's accuracy by 21.1%; and (4) the implementation of a chemical classification algorithm that correctly classifies unknown chemicals (based on their MS/MS spectra) in >80% of the cases. This improved version called CFM-ID 3.0 is freely available as a web server. Its source code is also accessible online.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it