We lifted 9 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| airi-institute/ffreed | canonical | 8 of 9 |
| Function | Status | Where it lives |
|---|---|---|
| HSF | Ran | airi-institute/ffreed/ffreed/env/reward.py code served (permissive licence) · get_code("9955da56a485cdfd") |
| ReLU | Ran | airi-institute/ffreed/ffreed/env/reward.py code served (permissive licence) · get_code("4542b8f7b6c43580") |
| brics_compatible | Ran | airi-institute/ffreed/ffreed/env/utils.py code served (permissive licence) · get_code("ba5df7ab771cb02c") |
| identity | Ran | airi-institute/ffreed/ffreed/env/reward.py code served (permissive licence) · get_code("9910e2fc297f8665") |
| lmap | Ran | airi-institute/ffreed/ffreed/utils.py code served (permissive licence) · get_code("a18ae998f817f851") |
| log_time | Ran | airi-institute/ffreed/ffreed/train/utils.py code served (permissive licence) · get_code("7d0881a0d7a421a8") |
| read_json | Ran | airi-institute/ffreed/ffreed/utils.py code served (permissive licence) · get_code("b0cf9a70a462ead4") |
| str2strs | Ran | airi-institute/ffreed/ffreed/args.py code served (permissive licence) · get_code("f93a33caebf99076") |
| read_mols | Not yet run | airi-institute/ffreed/ffreed/utils.py code served (permissive licence) · get_code("a0e4ddb131be1778") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
A rational design of new therapeutic drugs aims to find a molecular structure with desired biological functionality, e.g., an ability to activate or suppress a specific protein via binding to it. Molecular docking is a common technique for evaluating protein-molecule interactions. Recently, Reinforcement Learning (RL) has emerged as a promising approach to generating molecules with the docking score (DS) as a reward. In this work, we reproduce, scrutinize and improve the recent RL model for molecule generation called FREED (arXiv:2110.01219). Extensive evaluation of the proposed method reveals several limitations and challenges despite the outstanding results reported for three target proteins. Our contributions include fixing numerous implementation bugs and simplifying the model while increasing its quality, significantly extending experiments, and conducting an accurate comparison with current state-of-the-art methods for protein-conditioned molecule generation. We show that the resulting fixed model is capable of producing molecules with superior docking scores compared to alternative approaches.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2401.09840")
get_code_for_paper("2401.09840")
have("2401.09840")
Connect an agent — have() is free.