Table 7.
Deep learning packages and resources
| Resource Name | Category | Application | Date created | Link | Free/paid |
|---|---|---|---|---|---|
| Libraries | |||||
| Janggua | Python package | facilitates deep learning in the context of genomics | 2020 | https://github.com/BIMSBbioinfo/janggu | Free |
| ExPectoa | Python-based repository | Contains code for predicting expression effects of human genome variants ab initio from sequence | 2018 | https://github.com/FunctionLab/ExPecto | Free |
| Selenea | PyTorch-based Library | A library for biological sequence data training and model architecture development | 2019 | https://selene.flatironinstitute.org/ | Free |
| Pysstera | TensorFlow-based Library | Used for learning sequence and structure motifs In biological sequences using convolutional neural networks | 2018 | https://github.com/budach/pysster | Free |
| Kipoia | Python package | Kipoi is an API and a repository of ready-to-use trained models for genomics | 2019 | Free | |
| Compute platform | |||||
| Google Colaboratory (Colab) | PnP GPUs | Colab allows anybody to write and execute arbitrary python code through the browser, and is especially well suited to machine learning, data analysis and education | 2017 | https://colab.research.google.com/ | Free |
| IBM Cloud | Cloud service | Cloud computing platform; Design complex neural networks, then experiment at scale to deploy optimised learning models within IBM Watson Studio | 2011 | https://www.ibm.com/cloud | Free tier Cost tier |
| Google CloudML | PnP GPUs | For extreme scalability in the long run | 2008 | https://cloud.google.com/ai-platform | Paid |
| Vertex AI | AI platform | Google Cloud’s new unified ML platform | 2021 | https://cloud.google.com/vertex-ai | |
| Amazon EC2 | Cloud service | A website facility which delivers secure, scalable compute power in the cloud | 2006 | https://aws.amazon.com/ec2/ | Free Paid |
aThese deep learning libraries/packages are specific to Genomic application