about summary refs log tree commit diff
path: root/src/lmm.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'src/lmm.cpp')
-rw-r--r--src/lmm.cpp120
1 files changed, 113 insertions, 7 deletions
diff --git a/src/lmm.cpp b/src/lmm.cpp
index 9fe6bbb..9c66cc4 100644
--- a/src/lmm.cpp
+++ b/src/lmm.cpp
@@ -20,6 +20,7 @@
 
 #include <fstream>
 #include <iostream>
+#include <limits>
 #include <sstream>
 
 #include <assert.h>
@@ -70,6 +71,10 @@ void LMM::CopyFromParam(PARAM &cPar) {
 
   l_min = cPar.l_min;
   l_max = cPar.l_max;
+  maf_level = cPar.maf_level;
+  miss_level = cPar.miss_level;
+  hwe_level = cPar.hwe_level;
+  r2_level = cPar.r2_level;
   n_region = cPar.n_region;
   l_mle_null = cPar.l_mle_null;
   logl_mle_H0 = cPar.logl_mle_H0;
@@ -2239,7 +2244,23 @@ void LMM::mdb_calc_gwa(const gsl_matrix *U, const gsl_vector *eval,
   auto cursor = lmdb::cursor::open(rtxn, geno_mdb);
   cout << "## number of total individuals = " << ni_total << endl;
   cout << "## number of analyzed individuals = " << ni_test << endl;
-  cout << "## number of analyzed SNPs/var = " << num_markers << endl;
+  cout << "## number of total SNPs/var = " << num_markers << endl;
+
+  // -r2 needs (W'W)^-1, which the readers of gemma_io.cpp precompute once per
+  // read; here it is once per scan. W is the covariate matrix (intercept + -c
+  // columns) with ni_test rows, exactly what the readers get.
+  gsl_matrix *WtW = gsl_matrix_safe_alloc(W->size2, W->size2);
+  gsl_matrix *WtWi = gsl_matrix_safe_alloc(W->size2, W->size2);
+  gsl_permutation *pmt = gsl_permutation_alloc(W->size2);
+  gsl_vector *Wtx = gsl_vector_safe_alloc(W->size2);
+  gsl_vector *WtWiWtx = gsl_vector_safe_alloc(W->size2);
+  gsl_vector *x_r2 = gsl_vector_safe_alloc(ni_test);
+  gsl_blas_dgemm(CblasTrans, CblasNoTrans, 1.0, W, W, 0.0, WtW);
+  int sig = 0;
+  LUDecomp(WtW, pmt, &sig);
+  LUInvert(WtW, pmt, WtWi);
+
+  size_t n_analyzed = 0; // markers that survive the filters, for the log line
 
   std::function<SnpNameValues2(size_t)>  fetch_snp = [&](size_t num) {
 
@@ -2262,7 +2283,14 @@ void LMM::mdb_calc_gwa(const gsl_matrix *U, const gsl_vector *eval,
         const uint8_t* gs_bbuf = reinterpret_cast<const uint8_t*>(value.data());
         gs.reserve(size);
         for (size_t i = 0; i < size; ++i) {
-          double g = static_cast<double>(gs_bbuf[i])/127.0;
+          // 255 is the Gb missing sentinel (gemma-wrapper's geno2mdb and
+          // genenetwork4's make-mdb.sh both write it). Read as 255/127.0 it
+          // becomes 2.0079 -- a valid-looking genotype that silently poisons af
+          // and the analysis -- so it has to arrive as NaN, which is what
+          // mdb_analyze already knows how to drop and mean-substitute.
+          double g = (gs_bbuf[i] == 255)
+                       ? std::numeric_limits<double>::quiet_NaN()
+                       : static_cast<double>(gs_bbuf[i])/127.0;
           gs.push_back(g);
         }
       } else {
@@ -2306,11 +2334,79 @@ void LMM::mdb_calc_gwa(const gsl_matrix *U, const gsl_vector *eval,
       // 1       rs13476251      174792257
       // cout << static_cast<int>(chr) << ":" << pos2 << " line " << rest2 << ":" << marker << endl ;
 
-      // compute maf and n_miss (NAs)
-      size_t n_miss = 0; // count NAs: FIXME
-      double maf = compute_maf(ni_total, ni_test, n_miss, gs.data(), indicator_idv);
+      // Same marker statistics and the same filters as gemma_io.cpp's
+      // ReadFile_geno/ReadFile_bimbam_geno, in the same order, so that an lmdb
+      // scan answers the question a BIMBAM scan answers.  Before this, every
+      // marker in the store was analysed: -maf 0.05 on HLC still returned all
+      // 27940 markers of chromosome 1 where GEMMA returns 20246, and af/n_miss
+      // came out nan/0 for any marker with a missing call.
+      size_t n_miss = 0, n_0 = 0, n_1 = 0, n_2 = 0, observed = 0;
+      double geno_total = 0.0;
+      bool first = true, polymorphic = false;
+      double geno_first = 0.0;
+      for (size_t i = 0; i < ni_total; ++i) {
+        if (indicator_idv[i] == 0)
+          continue;
+        double geno = gs[i];
+        if (std::isnan(geno)) {
+          n_miss++;
+          continue;
+        }
+        // The allele-count bins are GEMMA's own (gemma_io.cpp:765-773).
+        if (geno >= 0 && geno <= 0.5)
+          n_0++;
+        if (geno > 0.5 && geno < 1.5)
+          n_1++;
+        if (geno >= 1.5 && geno <= 2.0)
+          n_2++;
+        if (first) {
+          geno_first = geno;
+          first = false;
+        } else if (geno != geno_first) {
+          polymorphic = true;
+        }
+        geno_total += geno;
+        observed++;
+      }
 
-      markerinfo = MarkerInfo { .name=marker,.chr=chr,.pos=pos,.line_no=num,.n_miss=n_miss,.maf=maf };
+      double maf = observed ? geno_total / (2.0 * (double)observed) : 0.0;
+      markerinfo = MarkerInfo { .name=marker,.chr=chr,.pos=pos,.line_no=num,
+                                .n_miss=n_miss,.maf=maf };
+
+      // -miss
+      if ((double)n_miss / (double)ni_test > miss_level)
+        return make_tuple(SKIP, markerinfo, gs);
+      // -maf (maf_level == -1 disables it, as in GEMMA)
+      if ((maf < maf_level || maf > (1.0 - maf_level)) && maf_level != -1)
+        return make_tuple(SKIP, markerinfo, gs);
+      // monomorphic: every observed genotype equal
+      if (!polymorphic)
+        return make_tuple(SKIP, markerinfo, gs);
+      // -hwe
+      if (hwe_level != 0 && maf_level != -1) {
+        if (CalcHWE(n_0, n_2, n_1) < hwe_level)
+          return make_tuple(SKIP, markerinfo, gs);
+      }
+      // -r2: correlation with the covariates, computed on the mean-substituted
+      // genotypes exactly as the readers do (missing -> maf*2).
+      if (W->size2 != 1) {
+        size_t pos2 = 0;
+        for (size_t i = 0; i < ni_total; ++i) {
+          if (indicator_idv[i] == 0)
+            continue;
+          double geno = gs[i];
+          gsl_vector_set(x_r2, pos2, std::isnan(geno) ? maf * 2.0 : geno);
+          pos2++;
+        }
+        double v_x = 0.0, v_w = 0.0;
+        gsl_blas_dgemv(CblasTrans, 1.0, W, x_r2, 0.0, Wtx);
+        gsl_blas_dgemv(CblasNoTrans, 1.0, WtWi, Wtx, 0.0, WtWiWtx);
+        gsl_blas_ddot(x_r2, x_r2, &v_x);
+        gsl_blas_ddot(Wtx, WtWiWtx, &v_w);
+        if (v_x > 0.0 && v_w / v_x > r2_level)
+          return make_tuple(SKIP, markerinfo, gs);
+      }
+      n_analyzed++;
 
       // cout << "!!!!" << size << marker << ": af" << maf << " " << gs[0] << "," << gs[1] << "," << gs[2] << "," << gs[3] << endl;
     }
@@ -2318,7 +2414,17 @@ void LMM::mdb_calc_gwa(const gsl_matrix *U, const gsl_vector *eval,
   };
   LMM::mdb_analyze(fetch_snp,U,eval,UtW,Uty,W,y,num_markers);
 
-  ns_total = ns_test = num_markers; // track global number of snps in original gemma (goes to cPar)
+  gsl_matrix_free(WtW);
+  gsl_matrix_free(WtWi);
+  gsl_permutation_free(pmt);
+  gsl_vector_free(Wtx);
+  gsl_vector_free(WtWiWtx);
+  gsl_vector_free(x_r2);
+
+  cout << "## number of analyzed SNPs/var = " << n_analyzed << endl;
+
+  ns_total = num_markers;
+  ns_test = n_analyzed; // what actually reaches the output (goes to cPar)
 }