Back to Programs

Science and medicine

Open Chemistry

Advancing Open Source & Open Science for Chemistry

c++graphicsjavascriptopenglpython

Participation history

9 GSoC years

2024

1 project

Official year page

Improved Rendering with Tessellation Shaders

In avogadrolibs repo, there are ambient occlusion / shading but nothing for fog or blur effects. Moreover, we currently lack real-time structure...

2023

8 projects

Official year page

Improve and enhance 3DMol.js

The 3DMol.js library size is quite large, but can be optimized by using const instead of var, array destructuring, global constants, and the...

Developing Large-Scale Calculation Management Tools for CalcUS

CalcUS aims to democratize access to computational chemistry by providing a user-friendly web interface to simplify running and analyzing quantum...

Active Learning based Bayesian Geometry Optimizer

The goal of this project is to develop an Active Learning based Bayesian Geometry Optimizer(ALBGO) using PyTorch and BoTorch for optimizing the...

Porting SeqToSeq and DTNN Model to PyTorch

PyTorch is becoming increasingly popular as the preferred backend for developing algorithms, thanks to its sustainability. DeepChem has decided to...

MXMNet Model Implementation for DeepChem

The DeepChem project aims to create high-quality, open-source tools to democratize the use of deep learning in drug discovery, materials science,...

Implementation of GAMESS .dat and NBO Parsers

The goal of this GSoC project is to address outstanding issues on GitHub for supporting additional programs and formats that are not currently...

Julia Bindings for Cclib

The Cclib library is a popular tool used in computational chemistry for parsing and interpreting output files from software packages such as...

Addition of support for NWChem to the ccinput package

The necessity of having an application for the automated generation of input files for computational chemistry codes is evident. The ccinput is an...

2022

9 projects

Official year page

Enhancing Avogadro for Biomolecular Modeling

Last year there was some work regarding Avogadro's usability as a tool for bioinformatics. My proposal is working along the same line, giving...

Deepchem - Pytorch Lightning

Pytorch Lightning provides framework and functionalities for building and training PyTorch models. If integrated with deepchem, PyTorch-lightning...

Positive Semi-definite Procrustes (PSDP) Problem

Procrustes (a part of Theochem by QC-Devs) is a library for finding the optimal transformation that makes two matrices as close as possible to each...

D-MPNN Model Implementation for DeepChem

The DeepChem project aims to create high-quality, open-source tools to democratize the use of deep learning in drug discovery, materials science,...

The Porting of Normalizing Flow model from TensorFlow to PyTorch

TensorFlow, Keras, and PyTorch are the most prominent libraries used for building DL and ML models. The use of PyTorch, as the primary backend for...

Implement multi-step calculation protocols

CalcUS aims to democratize access to computational chemistry by providing a user-friendly web interface to simplify running and analyzing quantum...

Democratizing deep learning models for genomic data

The project I am proposing would expand DeepChem’s tools for working with genomic datasets for drug discovery thus strengthening DeepChem’s new...

Implementing Ferminet, an Ab initio solution to many-electron systems using DNNs

Implementation of Ferminet with PyTorch. Ferminet is a neural-network-based Variational Monte-Carlo technique that aims to minimize the local energy...

Porting xyz2mol to the RdKit core

This project aims to construct a C++ implementation of the Python package xyz2mol from Prof. Jan H. Jensen’s research group...

2021

7 projects

Official year page

Large Scale Protein Modeling in DeepChem

DeepChem has enabled powerful and practical applications for machine learning in many disciplines of the natural sciences. While its name recognizes...

Tools for visualization and efficient editing

Data visualization is a key aspect to understand complex models. In biology they work with complex structures composed of atoms, a common structure...

DeepChem Retrosynthesis

Synthesis is at the heart of organic chemistry. It is the process of constructing a molecule through a series of reactions. Efficient molecular...

3Dmol UI Design and Improved Controls

3Dmol has most of the necessary features that make it a good visualization plugin for application and web. But this tool becomes difficult for the...

Make Deepchem More Robust: Implement Cutting-Edge Models and Other Features

Deepchem is one of the premier open-source deep learning libraries for chemistry. It is used by people worldwide, thus there is a need to develop and...

Extended Interoperability of ChemTools and Quantum Chemistry Software

ChemTools is an open-source Python library for interpreting quantum chemistry calculations. It is currently the only library capable of interpreting...

JaxModel: A high level API for building purely functional models suitable for Molecular Predictions & Simulations

In this proposed project we build JaxModel, which provides a high-level API for training and deploying Machine Learning Models using JAX framework....

2020

5 projects

Official year page

Implementation of Modern Quantum Chemical Analysis in cclib

The usual approach taken in computational chemistry is to first run a simulation, which can often be long, on a target molecule and then to analyze...

Integrating Trained Neural Networks with RDKit

RDKit is a collection of cheminformatics and machine learning tools written in C++ and Python. Which is more important, it allows you to work with...

Creating a Chemically Intelligent MongoDB Integration for RDKit

Chemical databases involve great heterogeneity. They are often variably indexed and represent chemical structures using custom data structures. This...

Implement a generalized file reader

The goal is to implement a flexible generic interface for reading molecular file formats (for example .smi, .sdf, and the compressed versions...

JAX Chem : JAX-based Deep Learning Library for complex and versatile chemical modelings

In recent years, deep learning has made remarkable progress in the area of NLP and CV with big data. In the area of chemistry, Graph Convolutional...

2019

6 projects

Official year page

CNN Scoring for Flexible Docking

Molecular docking—the prediction of binding modes and binding affinity of a molecule to a target of known structure—is a great computational tool for...

Volumetric rendering for 3Dmol.js

Volumetric viewing of scientific phenomena is an important feature in modern scientific visualizing tools because it can express specific phenomena...

More Improved Coordinate Generation for Open Babel: Combining Fragment-based Method and Distance Geometry

Open Babel is a widely used open source toolkit for cheminformatics. One of its important functions is 3D structure prediction of input molecules....

Project: neo4j integration

The project will be focused on development of extension for neo4j graph database for querying knowledge graphs storing molecular and chemical...

Transfer Learning Framework

Even though chemistry has become a more data driven discipline in the recent years, the amount of data available for training deep learning models is...

Active Learning Environment In 3Dmol.js

The 3D structures of protein and organic molecules are tough to understand since not all can visualize their structures in the mind. The project aims...

2018

7 projects

Official year page

Implementing new parsers

In this project I aim to implement new parsers for MOLCAS and TURBOMOLE. They will be a part of the cclib.parser module and will be implemented along...

Imaging Tools

DeepChem has been great library for the application of deep learning for drug/chemical discovery. As of now there is no imaging models implemented in...

Create a generalized fingerprinting API

Chemical fingerprints are very important for both querying chemical data (using similarity in fingerprint space) and the use of molecular entities in...

Avogadro 2: Molecular Dynamics

This project aims to implement support for Molecular Dynamics in Avogadro. Molecular dynamics (MD) is a computer simulation method for studying the...

RDKit-MolVS Integration Project - GSoC 2018

MolVS (https://molvs.readthedocs.io/en/latest/) provides very useful functionality for molecular validation and standardization. MolVS is built using...

MS/MS identification module for MZmine.

The goal is to implement a wrapper (common interface) for the identification algorithms’ logic in MSDK (that will allow to invoke tools like SIRIUS...

Fast, Efficient Fragment-Based Coordinate Generation

Chemical information is provided in various formats. Open Babel is a tool to convert file formats. When we translate a format which does not include...

2017

6 projects

Official year page

RDKIt - 3Dmol.js integration

Although RDKit is a widely used extremely versatile chemoinformatics software package, it still lacks efficient 3D molecule visualization capability....

Computational Chemistry Web repository

This project aims at creating a framework consisting of following modules : Script to setup MongoDB based database storing parsed results from...

cclib Project: Implement New Writers

The project aims to bridge the AIMALL and Molden programs with cclib by adding support for writing wfx/wfn files and Molden format files. Molden...

Intelligent LC/MS Feature Detection

This project aims at developing efficient algorithm to analyze complex 3D data obtained from the Liquid Chromatography Mass Spectrometry (LCMS). The...

Visualization of MD trajectory files using Google cardboard

Virtual reality has become a rage with Oculus Rift VR headsets and Google Daydream View headsets hitting the markets. More importantly, with the...

MSDK-IO library

There are many file formats in use for mass spectrometry data. For interoperability of algorithms in Java-based processing workflows, there is an...

2016

2 projects

Official year page

Materials Science Advances in Avogadro 2

As a Ph. D. student in a computational chemistry research group involving crystallography, I’m very familiar with many of the features and functions...

Avogadro-2: Integration of cclib data parser using Chemical JSON

This project proposes to integrate the cclib data parsing library with Avogadro-2 using the Chemical JSON format. Chemical JSON is a standard JSON...