diff --git a/CommandLines.cpp b/CommandLines.cpp index c3f2d16..e4e080b 100644 --- a/CommandLines.cpp +++ b/CommandLines.cpp @@ -44,8 +44,8 @@ void Print_H(hifiasm_opt_t* asm_opt) fprintf(stderr, " -h show help information\n"); fprintf(stderr, " Trio-partition:\n"); - fprintf(stderr, " -P FILE paternal trio index [NULL]\n"); - fprintf(stderr, " -M FILE Maternal trio index [NULL]\n"); + fprintf(stderr, " -P FILE paternal trio index generated by \"yak count\" [NULL]\n"); + fprintf(stderr, " -M FILE Maternal trio index generated by \"yak count\" [NULL]\n"); fprintf(stderr, " -c INT lower bound of the binned k-mer's frequency [%d]\n", asm_opt->min_cnt); fprintf(stderr, " -d INT upper bound of the binned k-mer's frequency [%d]\n", asm_opt->mid_cnt); diff --git a/hifiasm.1 b/hifiasm.1 index 0e00f30..da39c12 100644 --- a/hifiasm.1 +++ b/hifiasm.1 @@ -1,4 +1,4 @@ -.TH hifiasm 1 "3 Jan 2020" "hifiasm-0.1.0" "Bioinformatics tools" +.TH hifiasm 1 "3 Jan 2020" "hifiasm-0.3.0" "Bioinformatics tools" .SH NAME .PP @@ -181,6 +181,25 @@ Maternal trio index. This index should be generated by with the maternal short reads. For details of yak, please see .I [https://github.com/lh3/yak] +.TP 10 +.BI -c \ INT +Lower bound of the binned k-mer's frequency [2]. When doing trio binning, +a k-mer is said to be differentiating if it occurs >= +.I [-d upper_bound] +times in one sample +but occurs < +.I [-c lower_bound] +times in the other sample. + +.TP 10 +.BI -d \ INT +Upper bound of the binned k-mer's frequency [5]. When doing trio binning, +a k-mer is said to be differentiating if it occurs >= +.I [-d upper_bound] +times in one sample +but occurs < +.I [-c lower_bound] +times in the other sample. @@ -202,6 +221,22 @@ With .I [-z 20], hifiasm will remove 20 bases from both ends of each read. +.SH EXAMPLES FRO TRIO +.TP +.BR ./yak " " count " " \-k31 " " \-b37 " " \-t16 " " \-o " " mat.yak " " mat.fq.gz +Build maternal trio index from mat.fq.gz. + +.TP +.BR ./yak " " count " " \-k31 " " \-b37 " " \-t16 " " \-o " " pat.yak " " pat.fq.gz +Build paternal trio index from pat.fq.gz. + +.TP +.BR ./hifiasm " " \-o " " NA12878.asm " " \-t " " 32 " " \-P " " pat.yak " " \-M " " mat.yak " " NA12878_1.fq.gz " " NA12878_2.fq.gz +In this example, hifiasm will do trio assembly with 32 CPU threads. The paternal assembly can be found at [NA12878.asm.p.r_utg.gfa], +and the maternal assembly can be found at [NA12878.asm.m.r_utg.gfa]. + + + .SH OUTPUTS @@ -216,7 +251,7 @@ During the error correction step, hifiasm outputs the following two files: 2. All-to-all overlaps in paf format [outPrefix.ovlp.paf]. .PP -During the assembly step, hifiasm outputs the following four assembly graphs in GFA format: +During the non-trio assembly step, hifiasm outputs the following four assembly graphs in GFA format: .IP @@ -236,6 +271,21 @@ This graph collapses different haplotypes. 4. Alternate assembly contig graph [outPrefix.a_ctg.gfa]. This graph consists of all assemblies that are discarded in primary assembly contig graph. + +.PP +If you have trio information, hifiasm outputs the following three assembly graphs in GFA format: + +.IP +1. Phased maternal unitig graph [outPrefix.m.r_utg.gfa]. +This graph keeps the phased maternal assembly. + +2. Phased paternal unitig graph [outPrefix.p.r_utg.gfa]. +This graph keeps the phased paternal assembly. + +3. Haplotype-resolved raw unitig graph [outPrefix.r_utg.gfa]. +This graph keeps all haplotype information. + + .PP For each graph, hifiasm also outputs a simplified version without sequences. These simplified graphs can be easily visualized.