Tools

Links to external tools & services

Machine Learning Tools

NVIDIA

The RAPIDS suite of open source software libraries and APIs gives you the ability to execute end-to-end data science and analytics pipelines entirely on GPUs. RAPIDS is meant to help make data science easier to program and execute on CUDA-capable GPUs by allowing developers to interface through through user-friendly Python interfaces.

RAPIDS also focuses on common data preparation tasks for analytics and data science. This includes a familiar dataframe API that integrates with a variety of machine learning algorithms for end-to-end pipeline accelerations without paying typical serialization costs. RAPIDS also includes support for multi-node, multi-GPU deployments, enabling vastly accelerated processing and training on much larger dataset sizes.

Types: machine learning productivity

API: Link

MIT has created a website which hosts a number of computational tools to assist in synthetic planning and other aspects of organic chemistry. Resources include: One-step Retrosynthesis, Synthesis Plan Tree Builder, Context Recommendations, Forward Prediction, Reaction Evaluation, SCSore Evaluator, Buyable Look-Up, and Drawing

Types: machine learning

UC Berkeley -- Teresa Head-Gordon

A Multi-Resolution 3D-DenseNet for Chemical Shift Prediction in NMR Crystallography and for molecular solids

Types: machine learning

eToxPred is a machine learning tool to reliably estimate the toxicity and synthetic accessibility of small organic compounds. Has links to pre-trained data and instructions for how to train your own data sets. Driven by Python and Theano for easy use and accessibility.

Types: machine learning

IBM

IBM has established a free AI web service for predicting chemical reactions. This can be helpful for planning complex synthesis routes for drug molecules and potential treatments. Allows uploading and testing molecules through SMILES, API, or in-browser drawn molecules.

Types: machine learning

API: Link

Molecule.one

Molecule.one is a computational chemistry platform that helps bring theoretical substances to life. This is a desktop application which can predict the synthetic feasibility/complexity of a drug candidate.

Types: machine learning

UC Berkeley -- Teresa Head-Gordon

UCBShift is a program for predicting chemical shifts for backbone atoms and β-carbon of a protein in solution. It utilizes a machine learning module that makes predictions from features extracted from the 3D structures of the proteins.

Types: machine learning

Analysis Tools

BioExcel

Platform designed to provide web-access to atomistic-MD trajectories for macromolecules involved in the COVID-19 disease. The project is part of the open access initiatives promoted by the world-wide scientific community to share information about COVID-19 research. BioExcel-CV19 web server interface presents the resulting trajectories, with a set of quality control analyses and system information. All data produced by the project is available to download from an associated programmatic access API.

Types: analysis

Input Dataset: structure trajectory

Output: visualization analytics structure trajectory

Indian Institute of Technology

Lipinski rule of 5 helps in distinguishing between drug like and non drug like molecules. It predicts high probability of success or failure due to drug likeness for molecules complying with 2 or more of the following rules.

Types: analysis

Input Dataset: structure

Output: analytics

Swiss Institute of Bioinformatics

This website allows you to compute physicochemical descriptors as well as to predict ADME parameters, pharmacokinetic properties, druglike nature and medicinal chemistry friendliness of one or multiple small molecules to support drug discovery.

Types: analysis

Input Dataset: structure

Output: analytics

Workflows Tools

EOSC-Life and collaborators

The COVID-19 Workflow Hub is a workflow system agnostic repository of workflows in native and standardised form. It provides standardised workflow identifiers and metadata descriptions needed for workflow discovery, reuse, preservation, interoperability and monitoring and metadata harvesting using standard protocols.

This COVID-19 research centric one provides workflow snapshot preservation, publishing, citation and monitoring, credit claiming, and workflows part of the scholarly communication landscape.

Types: workflows

API: Link

Productivity Tools

NVIDIA

The RAPIDS suite of open source software libraries and APIs gives you the ability to execute end-to-end data science and analytics pipelines entirely on GPUs. RAPIDS is meant to help make data science easier to program and execute on CUDA-capable GPUs by allowing developers to interface through through user-friendly Python interfaces.

RAPIDS also focuses on common data preparation tasks for analytics and data science. This includes a familiar dataframe API that integrates with a variety of machine learning algorithms for end-to-end pipeline accelerations without paying typical serialization costs. RAPIDS also includes support for multi-node, multi-GPU deployments, enabling vastly accelerated processing and training on much larger dataset sizes.

Types: machine learning productivity

API: Link