vector<int> findMinHeightTrees(int n, vector<pair<int, int>>& edges) { vector<vector<int>> adjacency_list(n); vector<summary> summaries(n); for (size_t e = 0; e < edges.size(); e++) { adjacency_list[edges[e].first].push_back(edges[e].second); adjacency_list[edges[e].second].push_back(edges[e].first); } first_pass(-1, 0, adjacency_list, summaries); second_pass(-1, 0, 0, adjacency_list, summaries); vector<int> result; int min_max = 100000; for (int i = 0; i < n; i++) { min_max = min(min_max, summaries[i].get_max()); } for (int i = 0; i < n; i++) { if (summaries[i].get_max() == min_max) { result.push_back(i); } } return result; }
void train_one_round(const Fast5Map& name_map, size_t round) { const PoreModelMap& current_models = PoreModelSet::get_models(opt::trained_model_type); // Initialize the training summary stats for each kmer for each model ModelTrainingMap model_training_data; for(auto current_model_iter = current_models.begin(); current_model_iter != current_models.end(); current_model_iter++) { // one summary entry per kmer in the model std::vector<StateSummary> summaries(current_model_iter->second.get_num_states()); model_training_data[current_model_iter->first] = summaries; } // Open the BAM and iterate over reads // load bam file htsFile* bam_fh = sam_open(opt::bam_file.c_str(), "r"); assert(bam_fh != NULL); // load bam index file std::string index_filename = opt::bam_file + ".bai"; hts_idx_t* bam_idx = bam_index_load(index_filename.c_str()); assert(bam_idx != NULL); // read the bam header bam_hdr_t* hdr = sam_hdr_read(bam_fh); // load reference fai file faidx_t *fai = fai_load(opt::genome_file.c_str()); hts_itr_t* itr; // If processing a region of the genome, only emit events aligned to this window int clip_start = -1; int clip_end = -1; if(opt::region.empty()) { // TODO: is this valid? itr = sam_itr_queryi(bam_idx, HTS_IDX_START, 0, 0); } else { fprintf(stderr, "Region: %s\n", opt::region.c_str()); itr = sam_itr_querys(bam_idx, hdr, opt::region.c_str()); hts_parse_reg(opt::region.c_str(), &clip_start, &clip_end); } #ifndef H5_HAVE_THREADSAFE if(opt::num_threads > 1) { fprintf(stderr, "You enabled multi-threading but you do not have a threadsafe HDF5\n"); fprintf(stderr, "Please recompile nanopolish's built-in libhdf5 or run with -t 1\n"); exit(1); } #endif // Initialize iteration std::vector<bam1_t*> records(opt::batch_size, NULL); for(size_t i = 0; i < records.size(); ++i) { records[i] = bam_init1(); } int result; size_t num_reads_realigned = 0; size_t num_records_buffered = 0; Progress progress("[methyltrain]"); do { assert(num_records_buffered < records.size()); // read a record into the next slot in the buffer result = sam_itr_next(bam_fh, itr, records[num_records_buffered]); num_records_buffered += result >= 0; // realign if we've hit the max buffer size or reached the end of file if(num_records_buffered == records.size() || result < 0) { #pragma omp parallel for for(size_t i = 0; i < num_records_buffered; ++i) { bam1_t* record = records[i]; size_t read_idx = num_reads_realigned + i; if( (record->core.flag & BAM_FUNMAP) == 0) { add_aligned_events(name_map, fai, hdr, record, read_idx, clip_start, clip_end, round, model_training_data); } } num_reads_realigned += num_records_buffered; num_records_buffered = 0; } if(opt::progress) { fprintf(stderr, "Realigned %zu reads in %.1lfs\r", num_reads_realigned, progress.get_elapsed_seconds()); } } while(result >= 0); assert(num_records_buffered == 0); progress.end(); // open the summary file std::stringstream summary_fn; summary_fn << "methyltrain" << opt::out_suffix << ".summary"; FILE* summary_fp = fopen(summary_fn.str().c_str(), "w"); fprintf(summary_fp, "model_short_name\tkmer\tnum_matches\tnum_skips\t" "num_stays\tnum_events_for_training\twas_trained\t" "trained_level_mean\ttrained_level_stdv\n"); // open the tsv file with the raw training data std::stringstream training_fn; training_fn << "methyltrain" << opt::out_suffix << ".round" << round << ".events.tsv"; std::ofstream training_ofs(training_fn.str()); // write out a header for the training data StateTrainingData::write_header(training_ofs); // iterate over models: template, complement_pop1, complement_pop2 for(auto model_training_iter = model_training_data.begin(); model_training_iter != model_training_data.end(); model_training_iter++) { // Initialize the trained model from the input model auto current_model_iter = current_models.find(model_training_iter->first); assert(current_model_iter != current_models.end()); std::string model_name = model_training_iter->first; std::string model_short_name = current_model_iter->second.metadata.get_short_name(); // Initialize the new model from the current model PoreModel updated_model = current_model_iter->second; uint32_t k = updated_model.k; const std::vector<StateSummary>& summaries = model_training_iter->second; // Generate the complete set of kmers std::string gen_kmer(k, 'A'); std::vector<std::string> all_kmers; for(size_t ki = 0; ki < summaries.size(); ++ki) { all_kmers.push_back(gen_kmer); mtrain_alphabet->lexicographic_next(gen_kmer); } assert(gen_kmer == std::string(k, 'A')); assert(all_kmers.front() == std::string(k, 'A')); assert(all_kmers.back() == std::string(k, 'T')); // Update means for each kmer #pragma omp parallel for for(size_t ki = 0; ki < summaries.size(); ++ki) { assert(ki < all_kmers.size()); std::string kmer = all_kmers[ki]; // write the observed values to a tsv file #pragma omp critical { for(size_t ei = 0; ei < summaries[ki].events.size(); ++ei) { summaries[ki].events[ei].write_tsv(training_ofs, model_short_name, kmer); } } bool is_m_kmer = kmer.find('M') != std::string::npos; bool update_kmer = opt::training_target == TT_ALL_KMERS || (is_m_kmer && opt::training_target == TT_METHYLATED_KMERS) || (!is_m_kmer && opt::training_target == TT_UNMETHYLATED_KMERS); bool trained = false; // only train if there are a sufficient number of events for this kmer if(update_kmer && summaries[ki].events.size() >= opt::min_number_of_events_to_train) { // train a mixture model where a minority of k-mers aren't methylated ParamMixture mixture; float incomplete_methylation_rate = 0.05f; std::string um_kmer = mtrain_alphabet->unmethylate(kmer); size_t um_ki = mtrain_alphabet->kmer_rank(um_kmer.c_str(), k); // Initialize the training parameters. If this is a kmer containing // a methylation site we train a two component mixture, otherwise // just fit a gaussian float major_weight = is_m_kmer ? 1 - incomplete_methylation_rate : 1.0f; mixture.log_weights.push_back(log(major_weight)); mixture.params.push_back(current_model_iter->second.get_parameters(ki)); if(is_m_kmer) { // add second unmethylated component mixture.log_weights.push_back(std::log(incomplete_methylation_rate)); mixture.params.push_back(current_model_iter->second.get_parameters(um_ki)); } if(opt::verbose > 1) { fprintf(stderr, "INIT__MIX %s\t%s\t[%.2lf %.2lf %.2lf]\t[%.2lf %.2lf %.2lf]\n", model_training_iter->first.c_str(), kmer.c_str(), std::exp(mixture.log_weights[0]), mixture.params[0].level_mean, mixture.params[0].level_stdv, std::exp(mixture.log_weights[1]), mixture.params[1].level_mean, mixture.params[1].level_stdv); } ParamMixture trained_mixture = train_gaussian_mixture(summaries[ki].events, mixture); if(opt::verbose > 1) { fprintf(stderr, "TRAIN_MIX %s\t%s\t[%.2lf %.2lf %.2lf]\t[%.2lf %.2lf %.2lf]\n", model_training_iter->first.c_str(), kmer.c_str(), std::exp(trained_mixture.log_weights[0]), trained_mixture.params[0].level_mean, trained_mixture.params[0].level_stdv, std::exp(trained_mixture.log_weights[1]), trained_mixture.params[1].level_mean, trained_mixture.params[1].level_stdv); } #pragma omp critical updated_model.states[ki] = trained_mixture.params[0]; if (model_stdv()) { ParamMixture ig_mixture; // weights ig_mixture.log_weights = trained_mixture.log_weights; // states ig_mixture.params.emplace_back(trained_mixture.params[0]); if(is_m_kmer) { ig_mixture.params.emplace_back(current_model_iter->second.get_parameters(um_ki)); } // run training auto trained_ig_mixture = train_invgaussian_mixture(summaries[ki].events, ig_mixture); LOG("methyltrain", debug) << "IG_INIT__MIX " << model_training_iter->first.c_str() << " " << kmer.c_str() << " [" << std::fixed << std::setprecision(5) << ig_mixture.params[0].sd_mean << " " << ig_mixture.params[1].sd_mean << "]" << std::endl << "IG_TRAIN_MIX " << model_training_iter->first.c_str() << " " << kmer.c_str() << " [" << trained_ig_mixture.params[0].sd_mean << " " << trained_ig_mixture.params[1].sd_mean << "]" << std::endl; // update state #pragma omp critical { updated_model.states[ki] = trained_ig_mixture.params[0]; } } trained = true; } #pragma omp critical { fprintf(summary_fp, "%s\t%s\t%d\t%d\t%d\t%zu\t%d\t%.2lf\t%.2lf\n", model_short_name.c_str(), kmer.c_str(), summaries[ki].num_matches, summaries[ki].num_skips, summaries[ki].num_stays, summaries[ki].events.size(), trained, updated_model.states[ki].level_mean, updated_model.states[ki].level_stdv); } // add the updated model into the collection (or replace what is already there) PoreModelSet::insert_model(opt::trained_model_type, updated_model); } } // cleanup records for(size_t i = 0; i < records.size(); ++i) { bam_destroy1(records[i]); } // cleanup sam_itr_destroy(itr); bam_hdr_destroy(hdr); fai_destroy(fai); sam_close(bam_fh); hts_idx_destroy(bam_idx); fclose(summary_fp); }