菜单
Use when you have a trained formula ranking model (such as MIST-CF) and want to measure the specific performance gain from incorporating multiple positive-mode adduct types (e.g., [M+H]+, [M+Na]+, [M+K]+, [M+NH4]+) instead of restricting predictions to [M+H]+ only.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | adduct-assignment-accuracy-assessment |
| description | Use when you have a trained formula ranking model (such as MIST-CF) and want to measure the specific performance gain from incorporating multiple positive-mode adduct types (e.g., [M+H]+, [M+Na]+, [M+K]+, [M+NH4]+) instead of restricting predictions to [M+H]+ only. |
| license | CC-BY-4.0 |
| metadata | {"edam_operation":"http://edamontology.org/operation_3927","edam_topics":["http://edamontology.org/topic_3520","http://edamontology.org/topic_0081"],"tools":["MIST","MIST-CF","SIRIUS"],"techniques":["LC-MS"],"license_tier":"open"} |
| derived_from | [{"doi":"10.1021/acs.jcim.3c01082","title":"mistcf"}] |
| evidence_spans | ["an extension of MIST for annotating MS1 precursor masses from MS/MS data","MIST-CF ranks chemical formula and adduct assignments for an unknown mass spectrum using an end-to-end energy based modeling approach"] |
| claims | [] |
| provenance | {"collection":"https://w3id.org/holobiomicslab/asb-skill/collection/metabolomics/v2","assembled_by":"scripts/collect_metabolomics_collection.py","sources":[{"build":"coll_mistcf","doi":"10.1021/acs.jcim.3c01082","title":"mistcf"}],"dedup_kept_from":"coll_mistcf"} |
| schema_version | 0.2.0 |
| attribution | {"generator":"AgenticScienceBuilder","original_doi":"10.1021/acs.jcim.3c01082","all_source_dois":["10.1021/acs.jcim.3c01082"],"zenodo_doi":"10.5281/zenodo.20794027","curators":[],"promoter":"Louis-Félix Nothias","sponsor":"CNRS & Université Côte d'Azur"} |
Quantify the contribution of multi-adduct support to chemical formula ranking accuracy by comparing model performance in [M+H]+-only mode versus full multi-adduct mode. This skill isolates the performance delta attributable to adduct type diversity in MS/MS-based formula inference.
Apply this skill when you have a trained formula ranking model (such as MIST-CF) and want to measure the specific performance gain from incorporating multiple positive-mode adduct types (e.g., [M+H]+, [M+Na]+, [M+K]+, [M+NH4]+) instead of restricting predictions to [M+H]+ only. Use it after model development but before deployment to quantify whether multi-adduct support is worth the added complexity.
Load a published benchmark dataset with MS/MS spectra that include ground-truth formula and adduct assignments. Run the model inference twice: once in [M+H]+-only mode (where the model ranks formulas without considering alternative adduct types) and once in full multi-adduct mode (using the complete energy-based modeling approach to rank formula–adduct pairs across all supported positive-mode adducts). For each mode, record ranked predictions and compute top-1 and top-k ranking accuracy metrics (the fraction of spectra where the correct formula–adduct pair is ranked at position 1 or within the top k). Calculate the performance delta as multi-adduct accuracy minus [M+H]+-only accuracy, disaggregated by rank threshold and optionally by dataset subset (e.g., compound class, instrument type). Document the magnitude and statistical significance of the improvement to justify the additional modeling complexity.
SIRIUS decomp dynamic programming algorithm to generate candidate formulas for a given precursor mass)Use when when you have a neural network or machine learning model with multiple tunable hyperparameters (layer size, regularization strength, dropout) or design choices (e.
Use when when building a visualization library that must support multiple plotting backends (e.g., matplotlib, bokeh, plotly) and multiple data types (e.g., chromatograms, spectra, peak maps) without duplicating core logic or configuration handling across backend–plot-type combinations.
Use when after peaks have been assigned to heteroatom classes (e.g., CHO, CHON, CHOS, CHOP) and you need to compare molecular composition across samples, classes, or time series.
Use when after running inference on a trained structure prediction model with one or more input modalities (1H NMR, 13C NMR, or combined), you have generated predicted molecular formulas and connectivity graphs that need to be compared against known ground truth structures.
Use when after computing a histogram of all pairwise mass differences from an MSI dataset, use this skill when you have observed mass difference peaks that may correspond to known adducts (e.g., [M+H]+, [M+Na]+, [M−H2O]+).
Use when when you have derivatized metabolite structures (SMILES or mol format) and need to predict their ionization products in MS imaging, particularly when the derivatizing matrix produces non-standard adducts (e.