DeepMASS2 is a cross-platform GUI software tool, which enables deep-learning based metabolite annotation via semantic similarity analysis of mass spectral language. This approach enables the prediction of structurally related metabolites for the unknown compounds. By considering the chemical space, these structurally related metabolites provide valuable information about the potential location of the unknown metabolites and assist in ranking candidates obtained from molecular structure databases.
video_DeepMASS-GUI.mov
Please follow the following installation steps:
-
Create a new conda environment and activate:
conda create -n deepmass python=3.8.13 conda activate deepmass -
Download the lastest released version of source codes, unzip, enter:
# download and unzip, then, cd DeepMASS2_GUI -
Install dependency (note, for MacOS some dependency may install with conda manually):
pip install -r requirements.txt -
Download the dependent data.
-
put the following files into data folder:
DeepMassStructureDB-v1.0.csv references_index_negative_spec2vec.bin references_index_positive_spec2vec.bin references_spectrums_negative.pickle references_spectrums_positive.pickle -
put the following files into model folder:
Ms2Vec_allGNPSnegative.hdf5 Ms2Vec_allGNPSnegative.hdf5.syn1neg.npy Ms2Vec_allGNPSnegative.hdf5.wv.vectors.npy Ms2Vec_allGNPSpositive.hdf5 Ms2Vec_allGNPSpositive.hdf5.syn1neg.npy Ms2Vec_allGNPSpositive.hdf5.wv.vectors.npy
-
-
Run DeepMASS
python DeepMASS2.py
For the details on how to use DeepMASS, please check Ducomentation.
In preparation
Ji Hongchao
E-mail: ji.hongchao@foxmail.com
https://orcid.org/0000-0002-7364-0741WeChat public account: Chemocoder
