Closed
Conversation
… O(P^2) computation In summary statistics mode, XtX %*% beta was computed 3 separate times per iteration per outcome: in residual update, profile loglikelihood, and correlation update (get_correlation). This commit caches the product once after the beta update and reuses it, reducing the dominant O(P^2) cost by 3x. Also precomputes per-outcome constants (scaling_factor, beta_scaling) during model initialization to avoid repeated conditional evaluation per iteration. Benchmark results (micro-benchmark on XtX %*% beta): P=1000, L=2, M=100: 0.43s -> 0.14s (3x speedup) P=2000, L=5, M=200: 9.75s -> 3.25s (3x speedup) P=5000, L=10, M=500: 324s -> 108s (3x speedup, saves 216s) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…f LD When the number of variants P is large, the P×P LD matrix may be too large to fit in memory. Users can now pass X_ref (N_ref × P reference panel) directly instead of precomputing LD = cor(X_ref). When N_ref < P, ColocBoost computes LD products on the fly via t(X_ref) %*% (X_ref %*% v) / (N_ref - 1), avoiding the P×P memory cost. When N_ref >= P, LD is precomputed internally. Key design: - get_genotype_matrix(): returns $X or $X_ref from a data entry (mutually exclusive per entry: individual-level has $X, summary stats has $XtX or $X_ref) - compute_xtx_product(v, XtX, X_ref): unified XtX %*% v from either source - LD lookup functions (get_LD_jk, get_LD_jk1_jk2, get_LD_jk_each) reuse existing X path via get_genotype_matrix — no X_ref-specific code needed - dict_sumstatLD works for both LD and X_ref mapping Also: - Replace all Rfast:: calls with proper @importFrom (correls, standardise, upper_tri, med) and remove redundant local aliases - Add vignette section 3.4 with X_ref usage example - 23 new tests covering numerical equivalence, edge cases, error handling Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Codecov Report❌ Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #133 +/- ##
==========================================
+ Coverage 84.05% 84.72% +0.66%
==========================================
Files 14 14
Lines 4828 4889 +61
==========================================
+ Hits 4058 4142 +84
+ Misses 770 747 -23 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.