12 #include "my_assert.h"
14 #include "SingleRead.h"
15 #include "SingleReadQ.h"
16 #include "PairedEndRead.h"
17 #include "PairedEndReadQ.h"
20 #include "SingleModel.h"
21 #include "SingleQModel.h"
22 #include "PairedEndModel.h"
23 #include "PairedEndQModel.h"
26 #include "Transcript.h"
27 #include "Transcripts.h"
29 #include "WriteResults.h"
42 Transcripts transcripts;
45 vector<double> theta, counts;
49 char outReadF[2][STRLEN];
52 char refF[STRLEN], tiF[STRLEN];
56 void genOutReadStreams(int type, char *outFN) {
60 sprintf(outReadF[0], "%s.fa", outFN);
64 sprintf(outReadF[0], "%s.fq", outFN);
68 for (int i = 0; i < n_os; i++)
69 sprintf(outReadF[i], "%s_%d.fa", outFN, i + 1);
73 for (int i = 0; i < n_os; i++)
74 sprintf(outReadF[i], "%s_%d.fq", outFN, i + 1);
78 for (int i = 0; i < n_os; i++)
79 os[i] = new ofstream(outReadF[i]);
82 template<class ReadType, class ModelType>
83 void simulate(char* modelF, char* resultsF) {
84 ModelType model(&refs);
91 calcExpectedEffectiveLengths<ModelType>(M, refs, model, eel);
93 //generate theta vector
94 ifstream fin(resultsF);
98 getline(fin, line); // read the first line, which is just column names
99 for (int i = 1; i <= M; i++) {
102 for (int j = 0; j < OFFSITE; j++) pos = line.find_first_of('\t', pos) + 1;
103 size_t pos2 = line.find_first_of('\t', pos);
104 if (pos2 == string::npos) pos2 = line.length();
105 tpm = atof(line.substr(pos, pos2 - pos).c_str());
106 theta[i] = tpm * eel[i]; // during simulation, there is no check for effL < 0. The reason is for that case, eel[i] here = 0 and therefore no chance to sample from it
109 assert(denom > EPSILON);
111 for (int i = 1; i <= M; i++) theta[i] = theta[i] / denom * (1.0 - theta[0]);
113 READ_INT_TYPE resimulation_count = 0;
116 model.startSimulation(&sampler, theta);
117 for (READ_INT_TYPE i = 0; i < N; i++) {
118 while (!model.simulate(i, read, sid)) { ++resimulation_count; }
119 read.write(n_os, os);
121 if ((i + 1) % 1000000 == 0 && verbose) cout<<"GEN "<< i + 1<< endl;
123 model.finishSimulation();
125 cout<< "Total number of resimulation is "<< resimulation_count<< endl;
128 void releaseOutReadStreams() {
129 for (int i = 0; i < n_os; i++) {
130 ((ofstream*)os[i])->close();
135 int main(int argc, char* argv[]) {
139 if (argc != 7 && argc != 8) {
140 printf("Usage: rsem-simulate-reads reference_name estimated_model_file estimated_isoform_results theta0 N output_name [-q]\n\n");
141 printf("Parameters:\n\n");
142 printf("reference_name: The name of RSEM references, which should be already generated by 'rsem-prepare-reference'\n");
143 printf("estimated_model_file: This file describes how the RNA-Seq reads will be sequenced given the expression levels. It determines what kind of reads will be simulated (single-end/paired-end, w/o quality score) and includes parameters for fragment length distribution, read start position distribution, sequencing error models, etc. Normally, this file should be learned from real data using 'rsem-calculate-expression'. The file can be found under the 'sample_name.stat' folder with the name of 'sample_name.model'\n");
144 printf("estimated_isoform_results: This file contains expression levels for all isoforms recorded in the reference. It can be learned using 'rsem-calculate-expression' from real data. The corresponding file users want to use is 'sample_name.isoforms.results'. If simulating from user-designed expression profile is desired, start from a learned 'sample_name.isoforms.results' file and only modify the 'TPM' column. The simulator only reads the TPM column. But keeping the file format the same is required. If the RSEM references built are aware of allele-specific transcripts, 'sample_name.alleles.results' should be used instead.\n");
145 printf("theta0: This parameter determines the fraction of reads that are coming from background \"noise\" (instead of from a transcript). It can also be estimated using 'rsem-calculate-expression' from real data. Users can find it as the first value of the third line of the file 'sample_name.stat/sample_name.theta'.\n");
146 printf("N: The total number of reads to be simulated. If 'rsem-calculate-expression' is executed on a real data set, the total number of reads can be found as the 4th number of the first line of the file 'sample_name.stat/sample_name.cnt'.\n");
147 printf("output_name: Prefix for all output files.\n");
148 printf("-q: Set it will stop outputting intermediate information.\n\n");
149 printf("Outputs:\n\n");
150 printf("output_name.sim.isoforms.results, output_name.sim.genes.results: Expression levels estimated by counting where each simulated read comes from.\n\n");
151 printf("output_name.fa if single-end without quality score;\noutput_name.fq if single-end with quality score;\noutput_name_1.fa & output_name_2.fa if paired-end without quality score;\noutput_name_1.fq & output_name_2.fq if paired-end with quality score.\n\n");
152 printf("Format of the header line: Each simulated read's header line encodes where it comes from. The header line has the format:\n\n");
153 printf("\t{>/@}_rid_dir_sid_pos[_insertL]\n\n");
154 printf("{>/@}: Either '>' or '@' must appear. '>' appears if FASTA files are generated and '@' appears if FASTQ files are generated\n");
155 printf("rid: Simulated read's index, numbered from 0\n");
156 printf("dir: The direction of the simulated read. 0 refers to forward strand ('+') and 1 refers to reverse strand ('-')\n");
157 printf("sid: Represent which transcript this read is simulated from. It ranges between 0 and M, where M is the total number of transcripts. If sid=0, the read is simulated from the background noise. Otherwise, the read is simulated from a transcript with index sid. Transcript sid's transcript name can be found in the 'transcript_id' column of the 'sample_name.isoforms.results' file (at line sid + 1, line 1 is for column names)\n");
158 printf("pos: The start position of the simulated read in strand dir of transcript sid. It is numbered from 0\n");
159 printf("insertL: Only appear for paired-end reads. It gives the insert length of the simulated read.\n\n");
160 printf("Example:\n\n");
161 printf("Suppose we want to simulate 50 millon single-end reads with quality scores and use the parameters learned from [Example](#example). In addition, we set theta0 as 0.2 and output_name as 'simulated_reads'. The command is:\n\n");
162 printf("\trsem-simulate-reads /ref/mouse_125 mmliver_single_quals.stat/mmliver_single_quals.model mmliver_single_quals.isoforms.results 0.2 50000000 simulated_reads\n");
166 if (argc == 8 && !strcmp(argv[7], "-q")) quiet = true;
169 strcpy(refName, argv[1]);
170 alleleS = isAlleleSpecific(refName);
171 OFFSITE = (alleleS ? 6: 5);
174 sprintf(refF, "%s.seq", argv[1]);
177 sprintf(tiF, "%s.ti", argv[1]);
178 transcripts.readFrom(tiF);
180 //read model type from modelF
181 fi = fopen(argv[2], "r");
182 if (fi == NULL) { fprintf(stderr, "Cannot open %s! It may not exist.\n", argv[2]); exit(-1); }
183 assert(fscanf(fi, "%d", &model_type) == 1);
186 theta.assign(M + 1, 0.0);
187 theta[0] = atof(argv[4]);
190 genOutReadStreams(model_type, argv[6]);
192 counts.assign(M + 1, 0.0);
195 case 0: simulate<SingleRead, SingleModel>(argv[2], argv[3]); break;
196 case 1: simulate<SingleReadQ, SingleQModel>(argv[2], argv[3]); break;
197 case 2: simulate<PairedEndRead, PairedEndModel>(argv[2], argv[3]); break;
198 case 3: simulate<PairedEndReadQ, PairedEndQModel>(argv[2], argv[3]); break;
201 writeResultsSimulation(M, refName, argv[6], transcripts, eel, counts);
202 releaseOutReadStreams();