Skip to content
Other

DPP-4 pIC50 DNN-MLP

прогноз активности по SMILES

1 min read

Это MLP-регрессия от Delower, которая предсказывает pIC50 — логарифмическую меру ингибирования DPP-4 — по SMILES. На вход подаётся 4 608-мерный фингерпринт (Morgan/ECFP4 и CDK-Extended), архитектура — 4608-768-384-192-1. Модель обучена на 10 085 отобранных соединениях из ChEMBL; загруженные веса переобучены на 100% очищенных данных.

Ключевые особенности

  • 4 608-мерный фингерпринт: Morgan/ECFP4-1024, CDK-Extended-1024, ECFP4-512 и ECFP4-2048.
  • MLP 4608-768-384-192-1; в комплекте model.pt, конфиг и infer.py.
  • Лучшая из 10 моделей по held-out RMSE: 0.5712 против 0.5750 у lgbm и 0.5822 у xgb.
  • Обучение на 10 085 соединениях, split 80/10/10 по canonical SMILES, стратификация по pIC50, seed 42; FDA-12 исключены.
  • Только фингерпринт: без 3D-структуры и метаданных assay; не клинический инструмент.

Пример

pip install -r requirements.txt
python infer.py "CC(C)Cc1ccccc1"
ПодробнееМетрики split-run на held-out (n = 1 014): RMSE 0.5712, MAE 0.3105, R2 0.8019.
FDA RMSE 0.7269 — только tie-break, не независимый holdout.
Ошибки выше для слабо активных соединений (pIC50 < 5.5).
Загруженные веса переобучены на 100% данных; метрики относятся к split-run. Research use only.
Discuss Telegram 0 27

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.0 GB · ready files0.5 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # Delower/dpp4-pic50-dnn_mlp
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download Delower/dpp4-pic50-dnn_mlp --local-dir ~/models/dpp4-pic50-dnn_mlp
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to dpp4-pic50-dnn_mlp
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of dpp4-pic50-dnn_mlp (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

Delower/dpp4-pic50-dnn_mlp
Author
Delower
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

270

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments