WSSmod 0.1.0

First release.

Module scores

• calculate_WSS() computes Weighted Sum Score module-level summaries from proteomic data, using STRING network connectivity and biomarker-association weighting to align and aggregate protein-level signal into module scores. Supports dedup_by and min_module_size options for controlling how genes assigned to multiple modules are deduplicated and how small modules are filtered.
• load_prebuilt_wss(), list_prebuilt_wss(), and load_prebuilt_terms() provide access to a bundled reference module/weighting table ("core_AD_plasma_biomarkers") and its module term labels.
• calculate_WSS() accepts a data frame as result (converted to a data.table) and rejects other classes with an informative error.
• calculate_WSS() stops with a clear error that names the affected proteins when a protein used by a module has a missing value. This also covers the case where every module has one, which previously returned NA scores without any message.
• The documentation now states that a module with none of its proteins in the matrix is reported with all-NA scores and a module_sd of 0.

Prediction from core biomarkers

• predict_WSS() predicts all 75 module scores for the "core_AD_plasma_biomarkers" reference set from Age, Gender, and 8 core plasma biomarkers, using a bundled joinet two-layer elastic net model, without requiring the full proteomic panel.
• normalize_wss_biomarkers() builds the rank-normalized biomarker inputs predict_WSS() requires from raw biomarker values, via either method = "project" (projecting onto a bundled, anonymized baseline reference distribution, using project_rank_norm() – supports a single new patient) or method = "self" (rank-normalizing within your own cohort).
• project_rank_norm() and load_prebuilt_biomarker_reference() expose the underlying projection utility and reference distribution directly.

Documentation

• Added a citation (citation("WSSmod")) and links to the accompanying preprint.
• New vignette, “Calculating Weighted Sum Scores”, covering input normalization, the bundled and custom module tables, and scoring new samples against a reference cohort.
• New vignette, “Predicting Weighted Sum Scores from plasma biomarkers”, covering the biomarker inputs, the two normalization methods, and reading the predicted module scores.
• New vignette, “Exploring the bundled datasets”, describing each bundled file, its loader and what it can be used for.
• A package-level help page (?WSSmod) gives an overview of the functions and bundled data.
• calculate_WSS() now documents what input scale it expects.

Example data

• wss_example_expression and wss_example_biomarkers are small, fully simulated datasets (no participant data) for trying out calculate_WSS(), normalize_wss_biomarkers() and predict_WSS().

The bundled model and reference data were verified end-to-end against the original analysis’s held-out follow-up cohort, reproducing published predictions to floating-point precision.