The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

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.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.