From 1c52157b530951d07c817dd8c95cb012617d10e9 Mon Sep 17 00:00:00 2001 From: Christopher Yeh Date: Tue, 16 Nov 2021 16:31:40 -0800 Subject: [PATCH] Minor formatting updates to README --- README.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 2643c67..dd946bd 100644 --- a/README.md +++ b/README.md @@ -284,10 +284,10 @@ MLDE predictions are made using the execute_mlde.py script. This script should b ### Inputs for execute_mlde.py | Argument | Type | Description | |:---------|-----------|-------------| -| training_data | Required Argument | A csv file containing the sequence-function information for sampled combinations. More information on this file can be found [below](#trainingdata.csv). | +| training_data | Required Argument | A csv file containing the sequence-function information for sampled combinations. More information on this file can be found [below](#trainingdatacsv). | | encoding_data | Required Argument | A numpy array containing the embedding information for the full combinatorial space. Encoding arrays generated by generate_encoding.py can be passed directly in here. Custom encodings can be passed in here too, the details of which are discussed [below](#custom-encodings). | | combo_to_ind_dict | Required Argument | A pickle file containing a dictionary that links a combination to its index. The ComboToIndex.pkl file output by generate_encoding.py can be passed in directly here. | -| model_params | Optional Argument | A csv file dictating which inbuilt MLDE models to use as well as how many rounds of hyperparameter optimization to perform. The makeup of this file is discussed [below](#mldeparameters.csv). | +| model_params | Optional Argument | A csv file dictating which inbuilt MLDE models to use as well as how many rounds of hyperparameter optimization to perform. The makeup of this file is discussed [below](#mldeparameterscsv). | | output | Optional Argument | The location to save the results. Default is the current working directory. | | n_averaged | Optional Argument | The number of top-performing models to average to get final prediction results. Default is 3. | | n_cv | Optional Argument | The number of rounds of cross validation to perform during training. Default is 5. | @@ -435,7 +435,6 @@ MLDE requires the dependencies given below. Instructions on the [tape-neurips](h - torchaudio - cudatoolkit - transformers - - evcouplings Any specific versions listed were those used during the development of MLDE. There should be some leeway if users use different versions, though if running in a new environment, it is strongly recommended to perform the [pytest validation](#Installation-Validation) first.