README.md

The following steps for installing sortem can be done through conda or pip. The easiest way is to install the requirements through conda as the gpu libraries and other requirements are downloaded with the python packages. If you install the packages through pip the nvidia modules will not be installed with it. In addition installing it into a conda environment avoids breaking paths. 



**1) Create conda enviroment**:  conda create -n sortem python=3.7

**2) activate the environment**: conda activate sortem

**3) download the repository**:  git clone https://gitlab.au.dk/au482896/sortem.git 

**4) go into directory**: cd sortem

**5) install the requirements**: conda install --file requirements.txt

**6) install the GUI**: pip install appjar



The algorithm is works the following way:
1) The algorithm computes transformation invariant keypoints represented as a binary vector of [-1,1] , meaning the feature vector contains the same information for all projections  from the same molecule(https://ieeexplore.ieee.org/abstract/document/9169844).

2) The vector expresses key characteristics of the protein, each pixel of the computed 16 x 16 image is weighed by a value between [0,max]. 4 areas of the protein are is extracted used for training of the neural network, improving the classification. ()

3) Each protein component is represented as a binarized vector which is concatenated with the other part , partial and full image vectors, improving the overall accuracy(https://arxiv.org/pdf/1902.09941.pdf).


Running SortEM
    
    --num_gpus how many gpus to use( only tested on single gpu, can run on multi gpu)
    --gpu_list list of strings of specific gpus to use if not using slurm queue ,write: gpu:0 gpu:1 gpu:2 (does not work for multi gpu yet)
    --num_cpus integer, how many CPUs to use to preprocess the images optained from the mrc files.
    --float16 , write True to use half precision, works well on volta series and higher, increases training speed up to 2.5 times.
    --star  list of star files, can contain wild cards
    --ab The batch size to train with on a single gpu.
    --o The output director (defaults ./results)
    --mp The max particles to use pr training epoch.
    --epochs The number of epochs, such that the total number of training imabes are epochs*mp
    --tr Use pretrained model, this will skip step 1 and 2, and the optimization procedure in step 3 so everything is just        predicted. This can   predict image dater within 10 min for a huge dataset.
    --log If the star file contains classes you can track the training with actual human classification, from Relion / cryosparc (to test to see if its worth it)
    --num_classes How many parts of the protein to rfine you want when you want to compare pretraining (step 1) with the number of classes in star file. 


    - Finalize multi gpu support 
    - Finalize transfer learning support
    
Example of typical run , the star file is required, the --ab argument is the batch size. If the batch size is to big 

 python3 main.py --star /u/misser11/Sortinator/p28/*.star --ab 64