tape
asap
tape | asap | |
---|---|---|
1 | 1 | |
620 | 25 | |
0.0% | - | |
0.0 | 0.0 | |
over 1 year ago | almost 4 years ago | |
Python | Python | |
BSD 3-clause "New" or "Revised" License | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tape
-
ProteinBERT: A universal deep-learning model of protein sequence and function
We evaluated based on downstream tasks (multiple supervised benchmarks, including 4 from TAPE), not the LM performance.
asap
-
ProteinBERT: A universal deep-learning model of protein sequence and function
That should be trivial for it, attention models are good for "feature X exists somewhere in the text"/ That said, if your feature is just the presence of some short motif, why not just use n-gram/k-mer features? Those are invariant to location, and super fast/simple. I did some packages in the past for that, specially for proteins (PROFET, ASAP(for residue level)).
What are some alternatives?
protein-bert-pytorch - Implementation of ProteinBERT in Pytorch
protein_bert
fashion-mnist - A MNIST-like fashion product database. Benchmark :point_down:
beir - A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
evodiff - Generation of protein sequences and evolutionary alignments via discrete diffusion models
ProFET - ProFET: Protein Feature Engineering Toolkit for Machine Learning
text - Models, data loaders and abstractions for language processing, powered by PyTorch
pypdb - A Python API for the RCSB Protein Data Bank (PDB)
openfold - Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
ronin - RoNIN: Robust Neural Inertial Navigation in the Wild