Merge pull request #4 from DormanLab/v1.99

v2.0

README.md

@@ -3,6 +3,8 @@ AmpliCI
 
 AmpliCI, Amplicon Clustering Inference, denoises Illumina amplicon data by approximate model-based clustering.
 
+AmpliCI v2.0 now includes a new module to denoise UMI-tagged Illumina amplicon sequences. See details in the [page](https://github.com/xiyupeng/AmpliCI-UMI).
+
 # Table of Contents
 1. [Prerequisites](#prerequisites)
 1. [Installation](#installation)
@@ -368,10 +370,12 @@ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/your/full/path/to/library
 
 - Peng, X. and Dorman, K. (2020) ‘AmpliCI: A High-resolution Model-Based Approach for Denoising Illumina Amplicon Data’, Bioinformatics. doi: [10.1093/bioinformatics/btaa648](https://academic.oup.com/bioinformatics/article/doi/10.1093/bioinformatics/btaa648/5875058).
 
+- Peng, X. and Dorman, K. (2022) 'Accurate estimation of molecular counts from amplicon sequence data with unique molecular identifiers',[BioRxiv](https://www.biorxiv.org/content/10.1101/2022.06.12.495839v1). 
+
 # Contact <a name = "contact" />
 
 If you have any problems with AmpliCI, please contact:
 
-Xiyu Peng ([email protected])
+Xiyu Peng ([email protected])
 
 Karin Dorman ([email protected])

example_wfile.c

@@ -37,7 +37,7 @@ int main()
     unsigned char *seeds = NULL;
     unsigned int *seeds_length = NULL;
     size_t sample_size = 0;
-    unsigned int max_read_length;
+    unsigned int max_read_length = 0;
     double * abundance = NULL;
     double * ll = NULL;
 

script/ana.bash

@@ -0,0 +1,16 @@
+#!/bin/bash
+
+
+## bc data
+./run_AmpliCI --umi --fastq ../test/sim2.bc.fq --outfile ../test/sim2.bc
+
+## Estimate error profile with partitions
+grep "assign" ../test/sim2.bc.out | awk '{$1="";print}' > ../test/partition.txt
+./run_AmpliCI --fastq ../test/sim2.trim.fq  --outfile ../test/error.out --partition ../test/partition.txt -exclude --abundance 2 --error
+
+## merged data
+./run_AmpliCI --fastq ../test/sim2.fq --outfile ../test/sim2.merge --profile ../test/error.out --trim 9 
+cat ../test/sim2.merge.fa |  seqkit subseq -r 10:250 | seqkit rmdup -s | seqkit seq -w 0 > ../test/sim2.merge.trim_dedup.fa
+
+## run main algorithm
+./run_AmpliCI --fastq ../test/sim2.fq --umifile ../test/sim2.bc.fa --haplotype ../test/sim2.merge.trim_dedup.fa --umilen 9 --outfile ../test/test --profile ../test/error.out -rho 46

script/ana_hiv.bash

@@ -0,0 +1,19 @@
+#!/bin/bash
+
+## changing pho
+PHO=20.01
+FILENAME=SRR2241783_2
+
+## barcode data
+./run_AmpliCI --umi --fastq ../test/$FILENAME.trim.noN.bc.fastq --outfile ../test/$FILENAME.bc
+
+## Estimate error profile with partitions
+grep "assign" ../test/$FILENAME.bc.out | awk '{$1="";print}' > ../test/partition.txt
+./run_AmpliCI --fastq ../test/$FILENAME.trim.noN.fastq --outfile ../test/error.out --partition ../test/partition.txt  --exclude --abundance 2 --error
+
+## merged data
+./run_AmpliCI --fastq ../test/SRR2241783_2.merge.noN.fastq --outfile ../test/$FILENAME.merge --profile ../test/error.out -trim 9
+cat ../test/$FILENAME.merge.fa |  seqkit subseq -r 10:250 | seqkit rmdup -s | seqkit seq -w 0 > ../test/$FILENAME.merge.trim_dedup.fa
+
+## run main algorithm
+./run_AmpliCI --fastq ../test/SRR2241783_2.merge.noN.fastq --umifile ../test/$FILENAME.bc.fa --haplotype ../test/$FILENAME.merge.trim_dedup.fa --umilen 9 --outfile ../test/test_MPLE_${PHO}_band0_amplici_merge_epar_modified_collision_exc2 --profile ../test/error.out -rho $PHO