amirmohan / epistatic-net
Epistatic Net is an algorithm which allows for spectral regularization of deep neural networks to predict biological fitness functions (e.g., protein functions).
☆18Updated 3 years ago
Alternatives and similar repositories for epistatic-net:
Users that are interested in epistatic-net are comparing it to the libraries listed below
- Learning with uncertainty for biological discovery and design☆34Updated 2 years ago
- ☆30Updated 4 years ago
- Code associated with "Biophysical prediction of protein-peptide interactions and signaling networks using machine learning."☆71Updated 11 months ago
- Open source code for AlphaFold to extract protein embeddings☆26Updated 3 years ago
- Learning Protein Constitutive Motifs from Sequence Data: RBM toolbox☆20Updated 6 years ago
- ☆108Updated 3 years ago
- ☆56Updated 2 years ago
- ☆25Updated 5 years ago
- Code and data to reproduce analyses in Biswas et al. (2020) "Low-N protein engineering with data-efficient deep learning".☆57Updated 3 years ago
- LoRA for protein language models☆36Updated last year
- PyTorch implementation for our paper "Proximal Exploration for Model-guided Protein Sequence Design"☆35Updated last year
- Fork of matteofigliuzzi/bmDCA repository for Boltzmann-machine Direct Coupling Analysis (bmDCA).☆34Updated 4 years ago
- A structure-based, alignment-free embedding approach for proteins. Can be used as input to machine learning algorithms.☆37Updated last year
- Code for ICML 2023 paper "Reprogramming Pretrained Language Models for Antibody Sequence Infilling"☆23Updated last year
- Protein design and variant prediction using autoregressive generative models☆97Updated last year
- DistilProtBert implementation, a distilled version of ProtBert model.☆15Updated 2 years ago
- Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functions☆24Updated last year
- ☆36Updated 2 months ago
- Predict the structure of immune receptor proteins☆48Updated 4 months ago
- An unofficial re-implementation of AntiBERTy, an antibody-specific protein language model, in PyTorch.☆24Updated last year
- GeneDisco is a benchmark suite for evaluating active learning algorithms for experimental design in drug discovery.☆37Updated last year
- PDNET: A fully open-source framework for deep learning protein real-valued distances☆35Updated 3 years ago
- PDBench is a dataset and software package for evaluating fixed-backbone sequence design algorithms.☆28Updated 2 years ago
- ☆21Updated 2 months ago
- Autoregressive networks for protein☆36Updated last month
- De novo protein structure prediction using iteratively predicted structural constraints☆57Updated 3 years ago
- PyTorch implementation of Parapred (Liberis et al., 2018) with Paratyping (Richardson et al., 2021)☆19Updated last year
- Source code for fitting thermodynamic models (MoCHI), downstream analyses and to reproduce all figures in the following publication: Mapp…☆19Updated last year
- Protein design and variant prediction using autoregressive generative models☆23Updated 2 years ago
- Fast deep learning methods for large-scale protein-protein interaction screening☆36Updated 5 months ago