Ready for v5.3.0

Sqanti reads ready for production. vUpdated to version 5.3.0 in all files that include sqanti version

Dockerfile

@@ -1,18 +1,18 @@
-# Base image for SQANTI3/v5.2.2 with Ubuntu 22.04
+# Base image for SQANTI3/v5.3.0 with Ubuntu 22.04
 
 # Using ubuntu 22.04
 # Right now edlib doesn't work with python 3.12 which is the default version
 # of python in Ubuntu 24.04. edlib has had no updates since April 19, 2023
 # so no compatibility is expected for the time being.
 # Dockerfile originally developed by @skchronicles, updated and optimized
-# for version v5.2.2 by @Fabian-RY
+# for version v5.3.0 by @Fabian-RY
 
 FROM ubuntu:22.04
 SHELL ["/bin/bash", "--login" ,"-c"]
 
 # Set the versions of different softwares dependencies and SQANTI3 version
 # To install
-ENV SQANTI3_VERSION="5.2.2"
+ENV SQANTI3_VERSION="5.3.0"
 ENV DESALT_VERSION="1.5.6"
 ENV NAMFINDER_VERSION="0.1.3"
 
@@ -124,7 +124,7 @@ ENV PATH="${PATH}:/opt2/namfinder/${NAMFINDER_VERSION}/namfinder-${NAMFINDER_VER
 WORKDIR /opt2
 
 ########### SQANTI3 (currentily v${NAMFINDER_VERSION}) ############
-# Installs SQANTI3 with the version defined in the ENV variable (currently 5.2.2)
+# Installs SQANTI3 with the version defined in the ENV variable (currently 5.3.0)
 # dependenciesand requirements have already been
 # satisfied, for more info see:
 # https://github.com/ConesaLab/SQANTI3

README.md

@@ -13,7 +13,7 @@ SQANTI3 is the newest version of the [SQANTI tool](https://www.ncbi.nlm.nih.gov/
 SQANTI3 is the first module of the [Functional IsoTranscriptomics (FIT)](https://tappas.org/) framework, which also includes IsoAnnot and tappAS.
 
 ## Installation
-The [latest SQANTI3 release](https://github.com/ConesaLab/SQANTI3/releases/tag/v5.2.2) (31/07/2024) is **version 5.2.2**. See our wiki for [installation instructions](https://github.com/ConesaLab/SQANTI3/wiki/Dependencies-and-installation).
+The [latest SQANTI3 release](https://github.com/ConesaLab/SQANTI3/releases/tag/v5.3.0) (04/12/2024) is **version 5.3.0**. See our wiki for [installation instructions](https://github.com/ConesaLab/SQANTI3/wiki/Dependencies-and-installation).
 
 For informacion about previous releases and features introduced in them, see the [version history](https://github.com/ConesaLab/SQANTI3/wiki/Version-history).
 
@@ -56,3 +56,4 @@ If you are using SQANTI3 in your research, please cite the following paper in ad
 
 - Pardo-Palacios, F.J., Arzalluz-Luque, A. et al. **SQANTI3: curation of long-read transcriptomes for accurate identification of known and novel isoforms**. *Nat Methods* (2024). https://doi.org/10.1038/s41592-024-02229-2
 
+- Keil, N., Monzó, C., McIntyre, L., Conesa, A. **SQANTI-reads: a tool for the quality assessment of long read data in multi-sample lrRNA-seq experiments**. BioRxiv (2024) https://www.biorxiv.org/content/10.1101/2024.08.23.609463v2

SQANTI3.conda_env.yml

@@ -6,6 +6,7 @@ channels:
   - r
   - defaults
 dependencies:
+  - argcomplete=3.4.0
   - bcbio-gff
   - bedtools
   - biopython<=1.81
@@ -15,7 +16,9 @@ dependencies:
   - cython
   - desalt
   - gffread
+  - gtftools=0.9.0
   - gmap
+  - jinja2
   - kallisto=0.48.0
   - minimap2
   - numpy
@@ -61,8 +64,8 @@ dependencies:
   - seqtk
   - star
   - slamem
-  - gtftools
   - seaborn
   - scikit-learn
   - pip:
     - ultra-bioinformatics
+    - pdf2image

example/sqanti_reads_test/sqR_design_file.csv

@@ -0,0 +1,4 @@
+sampleID,file_acc,classification_file,junction_file
+SQ_R1,sqR1,./example/sqanti_reads_test//sqR1/SQ_R1_reads_classification.txt,./example/sqanti_reads_test//sqR1/SQ_R1_junctions.txt
+SQ_R2,sqR2,./example/sqanti_reads_test//sqR2/SQ_R2_reads_classification.txt,./example/sqanti_reads_test//sqR2/SQ_R2_junctions.txt
+SQ_R3,sqR3,./example/sqanti_reads_test//sqR3/SQ_R3_reads_classification.txt,./example/sqanti_reads_test//sqR3/SQ_R3_junctions.txt

sqanti3_filter.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 __author__  = "[email protected]"
-__version__ = '5.2.2'  # Python 3.7 syntax!
+__version__ = '5.3.0.'  # Python 3.7 syntax!
 
 """
 New SQANTI3 filter. It will serve as a wrapper for "rules" filter and "Machine-Learning" filter.

sqanti3_qc.py

@@ -5,7 +5,7 @@
 # Modified by Fran ([email protected]) currently as SQANTI3 version (05/15/2020)
 
 __author__  = "[email protected]"
-__version__ = '5.2.2'  # Python 3.7
+__version__ = '5.3.0'  # Python 3.7
 
 import pdb
 import os, re, sys, subprocess, timeit, glob, copy

sqanti3_rescue.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 __author__  = "[email protected]"
-__version__ = '5.2.2'
+__version__ = '5.3.0'
 
 ###################################################
 ##########     SQANTI3 RESCUE WRAPPER    ##########

sqanti3_wrapper.conf

@@ -0,0 +1,142 @@
+#!/bin/bash
+
+# Conf for SQANTI3 wrapper
+# Includes all variables needed to execute all optional parameters of SQANTI3_QC,
+# SQANTI3_filter and SQANTI3_rescue.
+# Using this wrapper helps to know the execution parameters of a run
+
+sqanti3_qc="python3 sqanti3_qc.py"
+sqanti3_filter="python3 sqanti3_filter.py"
+sqanti3_rescue="python3 sqanti3_rescue.py"
+
+# Somewhat common arguments for QC, Filter and rescue
+# This parameters will (99.9% of the time) be common between the steps
+# They only need to be defined once, and referenced within the script or conf
+reference_gtf="example/gencode.v38.basic_chr22.gtf"
+reference_fasta="example/GRCh38.p13_chr22.fasta"
+cpus="4"
+json_for_rules="utilities/filter/filter_default.json" # json file with rules for filter and rescue rules
+threshold="0.7" 
+
+# Execution control
+# Skip parts at will, however, be careful if you skip QC or filter, but you
+# need one of its ouput later and still does not exist, it will fail.
+
+skip_qc="true" #true to skip the QC
+skip_filter="true" # true to skip the filter
+filter_mode="both" # rules, ml or both
+skip_rescue="false" # true to skip the rescue
+rescue_mode="both" # rules, ml or both
+
+# Sqanti3.qc
+
+QC_input="example/UHR_chr22.gtf" # Input data
+QC_min_ref_length="" # minimum reference transcript length. Default 0 bp
+QC_force_id_ignore="" 
+QC_cage_peak_bed_file="data/ref_TSS_annotation/human.refTSS_v3.1.hg38.bed"
+QC_aligner_choice="" # minimap2, deSALT, gmap or uLTRA
+QC_polyA_motif_list="data/polyA_motifs/mouse_and_human.polyA_motif.txt"
+QC_polyA_peak=""
+QC_phylobed=""
+QC_skipORF="true"
+QC_is_fusion="false"
+QC_orf_input=""
+QC_is_fastq="false" # Requiered to be true if QC_input is a fastq file.
+QC_expression_matrix=""
+QC_gmap_index=""
+QC_chunks=1
+QC_output_prefix="UHR_chr22"
+QC_destination_folder="/tmp/sqanti3_wrapper/QC/"
+QC_coverage="" # Junctions coverage file
+QC_sites=""
+QC_window=""
+QC_genename="" # Column name from GTF to define gene names
+QC_full_length_pacbio_abundance_tsv="example/UHR_abundance.tsv"
+QC_saturation="true"
+QC_report_file="both" # pdf, html or both
+QC_isoAnnotLite=""
+QC_gff3=""
+QC_short_reads_fofn="example/UHR_chr22_short_reads.fofn"
+QC_SR_bam=""
+QC_isoform_hits=""
+QC_ratio_TSS_metric="" # Which metric should be reported in the ratio_TSS column
+
+
+
+# Sqanti3.filter
+
+# Common elements for filter rules and ml
+filter_skip_report="false"
+filter_input_classification="${QC_destination_folder}/${QC_output_prefix}_classification.txt" 
+filter_corrected_gtf="${QC_destination_folder}/${QC_output_prefix}_corrected.gtf"
+filter_isoforms="GMST/GMST_tmp.faa"
+filter_isoannotgff3="example/SQANTI3_QC_output/UHR_chr22.gff3"
+filter_sam=""
+filter_faa="${QC_destination_folder}/${QC_output_prefix}_corrected.faa"
+filter_monoexonic="true"
+filter_skip_report=""
+
+filter_cpus=${cpus}
+
+# Filter rules parameters
+filter_rules_ouput_folder="/tmp/sqanti3_wrapper/sqanti3_filter_rules"
+filter_rules_prefix="${QC_output_prefix}"
+filter_rules_json_file=${json_for_rules}
+
+# Filter ml parameters
+filter_ml_ouput_folder="/tmp/sqanti3_wrapper/sqanti3_filter_ml"
+filter_ml_prefix="${QC_output_prefix}"
+filter_ml_percent_training="0.8"
+filter_ml_TP=""
+filter_ml_TN=""
+filter_ml_threshold=${threshold}
+filter_ml_remove_columns=""
+filter_ml_intermediate_files=""
+filter_ml_max_class_size=""
+filter_ml_intrapriming=""
+
+# Sqanti3.rescue
+
+# Rescue rules parameters
+rescue_rules_filtered_classification="${filter_rules_ouput_folder}/${filter_rules_prefix}_RulesFilter_result_classification.txt"
+rescue_rules_reference_classification="${QC_destination_folder}/${QC_output_prefix}_classification.txt"
+rescue_rules_isoforms="${QC_destination_folder}/${QC_output_prefix}_corrected.fasta"
+rescue_rules_gtf="${filter_rules_ouput_folder}/${filter_rules_prefix}.filtered.gtf"
+rescue_rules_monoexons="all"
+rescue_rules_mode="full"
+rescue_rules_output_prefix="${QC_output_prefix}"
+rescue_rules_output_folder="/tmp/sqanti3_wrapper/sqanti3_rescue_rules"
+
+
+# Rescue ml parameters
+rescue_ml_filtered_classification="${filter_ml_ouput_folder}/${filter_ml_prefix}_MLresult_classification.txt"
+rescue_ml_reference_classification="${QC_destination_folder}/${QC_output_prefix}_classification.txt"
+rescue_ml_isoforms="${QC_destination_folder}/${QC_output_prefix}_corrected.fasta"
+rescue_ml_gtf="${filter_ml_ouput_folder}/${filter_ml_prefix}.filtered.gtf"
+rescue_ml_monoexons="all"
+rescue_ml_mode="full"
+rescue_ml_output_prefix="${QC_output_prefix}"
+rescue_ml_output_folder="/tmp/sqanti3_wrapper/sqanti3_rescue_ml"
+rescue_ml_monoexons="all"
+rescue_ml_mode="full"
+rescue_ml_randomforest_rdata="${filter_ml_ouput_folder}/randomforest.RData"
+
+
+# WARNING ZONE: By default the QC, filter and Rescue use the common 
+# parameters for references and static files but they can be changed
+# if needed (although you probably won't need to'). 
+
+# QC warning zone
+QC_reference_gtf=${reference_gtf}
+QC_reference_fasta=${reference_fasta}
+QC_cpus=${cpus}
+
+# Rescue warning zone
+
+rescue_rules_reference_genome=${reference_fasta}
+rescue_rules_reference_gtf=${reference_gtf}
+rescue_rules_json_file="${json_for_rules}"
+
+rescue_ml_reference_genome=${reference_fasta}
+rescue_ml_reference_gtf=${reference_gtf}
+rescue_ml_threshold=${threshold}