=======================

Scoring-Assisted Generative Exploration for Proteins (SAGE-Prot) is an effective framework for generating high-scoring proteins with deep neural networks, genetic algorithms, retrieval-augmented generation, and various QSAR/QSPR scoring models for desired objectives.

All source codes will be uploaded.

This is additional supplementary data in "Scoring-Assisted Generative Exploration for Proteins (SAGE-Prot): A Framework for Multi-Objective Protein Optimization via Iterative Sequence Generation and Evaluation"

• LINUX/UNIX Cluster Machines (Ubuntu 20.04)
• Python 3.9
• conda package: openbabel, hmmer
• pip package: numpy, scipy, scikit-learn, xgboost, nltk, networkx, pyyaml, nbformat, lightgbm, optuna, pandas, PyTDC, mordred, gensim, PubChemPy, torch, matplotlib, seaborn, jupyter, neptune-client, tqdm, rdkit-pypi tensorflow, deepchem, meeko, autograd, tensorflow_addons, tensorflow_probability, holoviews, Flask, Jinja2, bokeh, panel, guacamol, requests, transformers, sentencepiece, catboost, omegaconf, mlxtend, huggingface-hub, portalocker, ftfy, datasets, biotite, biopython, py3Dmol, torchensemble, ema-pytorch, einops, accelerate, x-transformers, aiohttp, attrs, jsonschema, charset_normalizer, swagger-spec-validator, torch-geometric, torch-scatter, torch-sparse, torch-cluster, torch-spline-conv, torchvision, ESM, protobuf, tape_proteins, torchtext

• Dr. Hocheol Lim (ihc0213@yonsei.ac.kr)

The research was supported by the Ministry of Trade, Industry, and Energy (MOTIE), the Republic of Korea, under the project “Industrial Technology Infrastructure Program” (Project No. RS-2024-00466693).

Lim, Hocheol. "Scoring-Assisted Generative Exploration for Proteins (SAGE-Prot): A Framework for Multi-Objective Protein Optimization via Iterative Sequence Generation and Evaluation"