nextPARS, a novel Illumina-based implementation of in-vitro parallel probing of RNA structures.

Related tags

Deep LearningnextPARS
Overview

nextPARS, a novel Illumina-based implementation of in-vitro parallel probing of RNA structures.

Here you will find the scripts necessary to produce the scores described in our paper from fastq files obtained during the experiment.

Install Prerequisites

First install git:

sudo apt-get update
sudo apt-get install git-all

Then clone this repository

git clone https://github.com/jwill123/nextPARS.git

Now, ensure the necessary python packages are installed, and can be found in the $PYTHONPATH environment variable by running the script packages_for_nextPARS.sh in the nextPARS directory.

cd nextPARS/conf
chmod 775 packages_for_nextPARS.sh
./packages_for_nextPARS.sh

Convert fastq to tab

In order to go from the fastq outputs of the nextPARS experiments to a format that allows us to calculate scores, first map the reads in the fastq files to a reference using the program of your choice. Once you have obtained a bam file, use PARSParser_0.67.b.jar. This program counts the number of reads beginning at each position (which indicates a cut site for the enzyme in the file name) and outputs it in .tab format (count values for each position are separated by semi-colons).

Example usage:

java -jar PARSParser_0.67.b.jar -a bamFile -b bedFile -out outFile -q 20 -m 5

where the required arguments are:

  • -a gives the bam file of interest
  • -b is the bed file for the reference
  • -out is the name given to the output file in .tab format

Also accepts arguments:

  • -q for minimum mapping quality for reads to be included [default = 0]
  • -m for minimum average counts per position for a given transcript [default = 5.0]

Sample Data

There are sample data files found in the folder nextPARS/data, as well as the necessary fasta files in nextPARS/data/SEQS/PROBES, and the reference structures obtained from PDB in nextPARS/data/STRUCTURES/REFERENCE_STRUCTURES There are also 2 folders of sample output files from the PARSParser_0.67.b.jar program that can be used as further examples of the nextPARS score calculations described below. These folders are found in nextPARS/data/PARSParser_outputs. NOTE: these are randomly generated sequences with random enzyme values, so they are just to be used as examples for the usage of the scripts, good results should not be expected with these.

nextPARS Scores

To obtain the scores from nextPARS experiments, use the script get_combined_score.py. Sample data for the 5 PDB control structures can be found in the folder nextPARS/data/

There are a number of different command line options in the script, many of which were experimental or exploratory and are not relevant here. The useful ones in this context are the following:

  • Use the -i option [REQUIRED] to indicate the molecule for which you want scores (all available data files will be included in the calculations -- molecule name must match that in the data file names)

  • Use the -inDir option to indicate the directory containing the .tab files with read counts for each V1 and S1 enzyme cuts

  • Use the -f option to indicate the path to the fasta file for the input molecule

  • Use the -s option to produce an output Structure Preference Profile (SPP) file. Values for each position are separated by semi-colons. Here 0 = paired position, 1 = unpaired position, and NA = position with a score too low to determine its configuration.

  • Use the -o option to output the calculated scores, again with values for each position separated by semi-colons.

  • Use the --nP_only option to output the calculated nextPARS scores before incorporating the RNN classifier, again with values for each position separated by semi-colons.

  • Use the option {-V nextPARS} to produce an output with the scores that is compatible with the structure visualization program VARNA1

  • Use the option {-V spp} to produce an output with the SPP values that is compatible with VARNA.

  • Use the -t option to change the threshold value for scores when determining SPP values [default = 0.8, or -0.8 for negative scores]

  • Use the -c option to change the percentile cap for raw values at the beginning of calculations [default = 95]

  • Use the -v option to print some statistics in the case that there is a reference CT file available ( as with the example molecules, found in nextPARS/data/STRUCTURES/REFERENCE_STRUCTURES ). If not, will still print nextPARS scores and info about the enzyme .tab files included in the calculations.

Example usage:

# to produce an SPP file for the molecule TETp4p6
python get_combined_score.py -i TETp4p6 -s
# to produce a Varna-compatible output with the nextPARS scores for one of the 
# randomly generated example molecules
python get_combined_score.py -i test_37 -inDir nextPARS/data/PARSParser_outputs/test1 \
  -f nextPARS/data/PARSParser_outputs/test1/test1.fasta -V nextPARS

RNN classifier (already incorporated into the nextPARS scores above)

To run the RNN classifier separately, using a different experimental score input (in .tab format), it can be run like so with the predict2.py script:

python predict2.py -f molecule.fasta -p scoreFile.tab -o output.tab

Where the command line options are as follows:

  • the -f option [REQUIRED] is the input fasta file
  • the -p option [REQUIRED] is the input Score tab file
  • the -o option [REQUIRED] is the final Score tab output file.
  • the -w1 option is the weight for the RNN score. [default = 0.5]
  • the -w2 option is the weight for the experimental data score. [default = 0.5]

References:

  1. Darty,K., Denise,A. and Ponty,Y. (2009) VARNA: Interactive drawing and editing of the RNA secondary structure. Bioinforma. Oxf. Engl., 25, 1974–197
Owner
Jesse Willis
Jesse Willis
ColossalAI-Examples - Examples of training models with hybrid parallelism using ColossalAI

ColossalAI-Examples This repository contains examples of training models with Co

HPC-AI Tech 185 Jan 09, 2023
My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot

Deep Q&A Table of Contents Presentation Installation Running Chatbot Web interface Results Pretrained model Improvements Upgrade Presentation This wor

Conchylicultor 2.9k Dec 28, 2022
FaRL for Facial Representation Learning

FaRL for Facial Representation Learning This repo hosts official implementation of our paper General Facial Representation Learning in a Visual-Lingui

Microsoft 19 Jan 05, 2022
Implementation of the Point Transformer layer, in Pytorch

Point Transformer - Pytorch Implementation of the Point Transformer self-attention layer, in Pytorch. The simple circuit above seemed to have allowed

Phil Wang 501 Jan 03, 2023
[BMVC2021] The official implementation of "DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations"

DomainMix [BMVC2021] The official implementation of "DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations" [paper] [de

Wenhao Wang 17 Dec 20, 2022
A Self-Supervised Contrastive Learning Framework for Aspect Detection

AspDecSSCL A Self-Supervised Contrastive Learning Framework for Aspect Detection This repository is a pytorch implementation for the following AAAI'21

Tian Shi 30 Dec 28, 2022
NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR2021)

NExT-QA We reproduce some SOTA VideoQA methods to provide benchmark results for our NExT-QA dataset accepted to CVPR2021 (with 1 'Strong Accept' and 2

Junbin Xiao 50 Nov 24, 2022
OBBDetection is a oriented object detection library, which is based on MMdetection.

OBBDetection news: We are now updating OBBDetection to new vision based on MMdetection v2.10, which has more advanced models and more efficient featur

jbwang1997 401 Jan 02, 2023
Yolo Traffic Light Detection With Python

Yolo-Traffic-Light-Detection This project is based on detecting the Traffic light. Pretained data is used. This application entertained both real time

Ananta Raj Pant 2 Aug 08, 2022
Unified MultiWOZ evaluation scripts for the context-to-response task.

MultiWOZ Context-to-Response Evaluation Standardized and easy to use Inform, Success, BLEU ~ See the paper ~ Easy-to-use scripts for standardized eval

Tomáš Nekvinda 38 Dec 13, 2022
Fastshap: A fast, approximate shap kernel

fastshap: A fast, approximate shap kernel fastshap was designed to be: Fast Calculating shap values can take an extremely long time. fastshap utilizes

Samuel Wilson 22 Sep 24, 2022
Official repository for the paper F, B, Alpha Matting

FBA Matting Official repository for the paper F, B, Alpha Matting. This paper and project is under heavy revision for peer reviewed publication, and s

Marco Forte 404 Jan 05, 2023
UFT - Universal File Transfer With Python

UFT 2.0.0 UFT (Universal File Transfer) is a CLI tool , which can be used to upl

Merwin 1 Feb 18, 2022
Analysing poker data from home games with friends

Poker Game Analysis Analysing poker data from home games with friends. Not a lot of data is collected, so this project is primarily focussed on descri

Stavros Karmaniolos 1 Oct 15, 2022
The source code of the paper "SHGNN: Structure-Aware Heterogeneous Graph Neural Network"

SHGNN: Structure-Aware Heterogeneous Graph Neural Network The source code and dataset of the paper: SHGNN: Structure-Aware Heterogeneous Graph Neural

Wentao Xu 7 Nov 13, 2022
PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".

Sharpness-aware Quantization for Deep Neural Networks This is the official repository for our paper: Sharpness-aware Quantization for Deep Neural Netw

Zhuang AI Group 30 Dec 19, 2022
[ACM MM 2021] Diverse Image Inpainting with Bidirectional and Autoregressive Transformers

Diverse Image Inpainting with Bidirectional and Autoregressive Transformers Installation pip install -r requirements.txt Dataset Preparation Given the

Yingchen Yu 25 Nov 09, 2022
RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation

RIFE - Real Time Video Interpolation arXiv | YouTube | Colab | Tutorial | Demo Table of Contents Introduction Collection Usage Evaluation Training and

hzwer 3k Jan 04, 2023
Official code of paper: MovingFashion: a Benchmark for the Video-to-Shop Challenge

SEAM Match-RCNN Official code of MovingFashion: a Benchmark for the Video-to-Shop Challenge paper Installation Requirements: Pytorch 1.5.1 or more rec

HumaticsLAB 31 Oct 10, 2022
Cl datasets - PyTorch image dataloaders and utility functions to load datasets for supervised continual learning

Continual learning datasets Introduction This repository contains PyTorch image

berjaoui 5 Aug 28, 2022