Python scripts aim to use a Random Forest machine learning algorithm to predict the water affinity of Metal-Organic Frameworks

Overview

MOF-Water-Affinity-Prediction-

The following Python scripts aim to use a Random Forest machine learning algorithm to predict the water affinity of Metal-Organic Frameworks (MOFs). The training set is extracted from the Cambridge Structural Database and the CoRE_MOF 2019 dataset.

Prediction Model

The prediction model is used to determine whether a given MOF is hydrophobic or hydrophilic. It uses a Random Forest model from the XGBoost library through a scikit-learn interface. The model reads in a .csv file of training data and then predicts the water affinity of a user inputted MOF. The user can specify what input parameters are to be used in the model.

Overfitting/Underfitting

This script was created to investigate how the prediction model’s accuracy and precision vary with the number and combination of inputs. This script allows a user to compare how the different combinations of inputs affect the score and the standard deviation of the model’s results.

It operates by reading in a .csv file of training data containing 13 input parameters. It then generates a list of all the possible combinations of input parameters according to the lengths specified by the user. For example, if the user wants all the combinations of length 3, 4, and 10 possible, the program will generate a list of all combinations of those lengths, and then use each combination as input for the model. Basically, each combination will undergo the same process as in the prediction model above, and then its results will be added into a .csv file for later analysis. Finally, a plot is created with filters for visualization.

.cif to .csv Converter

In order to create a training set for the prediction model, a csv must be created with all the available datapoints. This includes the MOFs and their crystallographic data. The data needed is collected from three different sources: WebCSD, CoRE_MOF 2019 dataset, and the MOF’s .cif files. Furthermore, additional calculations need to be performed from the information collected from the .cif files.

The code works by reading a .txt file, folder, or both, containing the refcodes and .cif files given to the MOF by the Cambrdige Structural Database. It then searches for these refcodes in the CoRE_MOF 2019 dataset, and retrieves the crystallographic data attached to them. Additionally, it uses the .cif files of the MOFs to calculate the atomic mass percentage of the metals contained in the MOF. These calculations are stored in columns 14-17, but are treated as one input parameter in the models in an attempt to relate them to each other. It also states the MOFs in the training set as hydrophobic and hydrophilic based on previously collected information from the literature. Finally, it produces a .csv file ready for use in the prediction model.

.cif folders

Three different folders are used to store .cif files.

  1. cif: these are hydrophobic MOFs received from Dr. Z. Qiao.
  2. manual hydrophobic: these are hydrophobic MOFs collected from the literature
  3. manual hydrophilic: these are hydrophilic MOFs collected from the literature

To add additional .cif files:

Add additional .cif files into either the manual hydrophobic folder or the manual hydrophilic folder. Make sure the file names represent the CCDC refcodes (including or excluding the CoRE_MOF 2019 name extensions). Finally, add these refcodes into the .txt file available in each folder so that the .cif files can be read by the cif Reader program.

This project is licensed under the terms of the GNU General Public License v3.0

An ETL Pipeline of a large data set from a fictitious music streaming service named Sparkify.

An ETL Pipeline of a large data set from a fictitious music streaming service named Sparkify. The ETL process flows from AWS's S3 into staging tables in AWS Redshift.

1 Feb 11, 2022
🧪 Panel-Chemistry - exploratory data analysis and build powerful data and viz tools within the domain of Chemistry using Python and HoloViz Panel.

🧪📈 🐍. The purpose of the panel-chemistry project is to make it really easy for you to do DATA ANALYSIS and build powerful DATA AND VIZ APPLICATIONS within the domain of Chemistry using using Python a

Marc Skov Madsen 97 Dec 08, 2022
Catalogue data - A Python Scripts to prepare catalogue data

catalogue_data Scripts to prepare catalogue data. Setup Clone this repo. Install

BigScience Workshop 3 Mar 03, 2022
Create HTML profiling reports from pandas DataFrame objects

Pandas Profiling Documentation | Slack | Stack Overflow Generates profile reports from a pandas DataFrame. The pandas df.describe() function is great

10k Jan 01, 2023
Analyze the Gravitational wave data stored at LIGO/VIRGO observatories

Gravitational-Wave-Analysis This project showcases how to analyze the Gravitational wave data stored at LIGO/VIRGO observatories, using Python program

1 Jan 23, 2022
Retentioneering 581 Jan 07, 2023
PyTorch implementation for NCL (Neighborhood-enrighed Contrastive Learning)

NCL (Neighborhood-enrighed Contrastive Learning) This is the official PyTorch implementation for the paper: Zihan Lin*, Changxin Tian*, Yupeng Hou* Wa

RUCAIBox 73 Jan 03, 2023
LynxKite: a complete graph data science platform for very large graphs and other datasets.

LynxKite is a complete graph data science platform for very large graphs and other datasets. It seamlessly combines the benefits of a friendly graphical interface and a powerful Python API.

124 Dec 14, 2022
A collection of learning outcomes data analysis using Python and SQL, from DQLab.

Data Analyst with PYTHON Data Analyst berperan dalam menghasilkan analisa data serta mempresentasikan insight untuk membantu proses pengambilan keputu

6 Oct 11, 2022
A library to create multi-page Streamlit applications with ease.

A library to create multi-page Streamlit applications with ease.

Jackson Storm 107 Jan 04, 2023
NumPy and Pandas interface to Big Data

Blaze translates a subset of modified NumPy and Pandas-like syntax to databases and other computing systems. Blaze allows Python users a familiar inte

Blaze 3.1k Jan 05, 2023
Cleaning and analysing aggregated UK political polling data.

Analysing aggregated UK polling data The tweet collection & storage pipeline used in email-service is used to also collect tweets from @britainelects.

Ajay Pethani 0 Dec 22, 2021
Python data processing, analysis, visualization, and data operations

Python This is a Python data processing, analysis, visualization and data operations of the source code warehouse, book ISBN: 9787115527592 Descriptio

FangWei 1 Jan 16, 2022
Python Project on Pro Data Analysis Track

Udacity-BikeShare-Project: Python Project on Pro Data Analysis Track Basic Data Exploration with pandas on Bikeshare Data Basic Udacity project using

Belal Mohammed 0 Nov 10, 2021
Spaghetti: an open-source Python library for the analysis of network-based spatial data

pysal/spaghetti SPAtial GrapHs: nETworks, Topology, & Inference Spaghetti is an open-source Python library for the analysis of network-based spatial d

Python Spatial Analysis Library 203 Jan 03, 2023
A Pythonic introduction to methods for scaling your data science and machine learning work to larger datasets and larger models, using the tools and APIs you know and love from the PyData stack (such as numpy, pandas, and scikit-learn).

This tutorial's purpose is to introduce Pythonistas to methods for scaling their data science and machine learning work to larger datasets and larger models, using the tools and APIs they know and lo

Coiled 102 Nov 10, 2022
scikit-survival is a Python module for survival analysis built on top of scikit-learn.

scikit-survival scikit-survival is a Python module for survival analysis built on top of scikit-learn. It allows doing survival analysis while utilizi

Sebastian Pölsterl 876 Jan 04, 2023
This creates a ohlc timeseries from downloaded CSV files from NSE India website and makes a SQLite database for your research.

NSE-timeseries-form-CSV-file-creator-and-SQL-appender- This creates a ohlc timeseries from downloaded CSV files from National Stock Exchange India (NS

PILLAI, Amal 1 Oct 02, 2022
Aggregating gridded data (xarray) to polygons

A package to aggregate gridded data in xarray to polygons in geopandas using area-weighting from the relative area overlaps between pixels and polygons. Check out the binder link above for a sample c

Kevin Schwarzwald 42 Nov 09, 2022
Zipline, a Pythonic Algorithmic Trading Library

Zipline is a Pythonic algorithmic trading library. It is an event-driven system for backtesting. Zipline is currently used in production as the backte

Quantopian, Inc. 15.7k Jan 07, 2023