Commit 84cd3f86 authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

removing old scripts

parent 81ae1551
Loading
Loading
Loading
Loading

SUPPORTERS.md

deleted100644 → 0
+0 −14
Original line number Diff line number Diff line
## Corporate Supporters
DeepChem is supported by a number of corporate partners who use DeepChem to solve interesting problems.

### Schrödinger
[![Schödinger](https://github.com/deepchem/deepchem/blob/master/docs/source/_static/schrodinger_logo.png)](https://www.schrodinger.com/)

> DeepChem has transformed how we think about building QSAR and QSPR models when very large data sets are available; and we are actively using DeepChem to investigate how to best combine the power of deep learning with next generation physics-based scoring methods.

### DeepCrystal
<img src="https://github.com/deepchem/deepchem/blob/master/docs/source/_static/deep_crystal_logo.png" alt="DeepCrystal Logo" height=150px/>

> DeepCrystal was an early adopter of DeepChem, which we now rely on to abstract away some of the hardest pieces of deep learning in drug discovery. By open sourcing these efficient implementations of chemically / biologically aware deep-learning systems, DeepChem puts the latest research into the hands of the scientists that need it, materially pushing forward the field of in-silico drug discovery in the process.

scripts/__init__.py

deleted100644 → 0
+0 −0

Empty file deleted.

scripts/controller.sh

deleted100644 → 0
+0 −15
Original line number Diff line number Diff line
#!/bin/bash
#SBATCH --job-name=controller
#SBATCH --output=controller_%A_%a.out
#SBATCH --error=controller_%A_%a.err
#SBATCH --time=12:00:00
##SBATCH --partition=normal
#SBATCH --partition=bigmem
#SBATCH --qos=bigmem
#SBATCH -n 4
ipcontroller --ip='*' --log-to-file=False &
for i in {0..90}; do
    echo $i;
    sbatch engine.sh
done
sleep 48h

scripts/data_process.py

deleted100644 → 0
+0 −59
Original line number Diff line number Diff line
"""
Manipulate CSV data files.
"""
from __future__ import print_function
from __future__ import division
from __future__ import absolute_import

import pandas as pd
import csv
import argparse

def parse_args(input_args=None):
  parser = argparse.ArgumentParser()
  parser.add_argument(
    "--descriptor", required=1,
    help="Name of input descriptor CSV file.")
  parser.add_argument(
    "--activities", required=1,
    help="Name of input activities CSV file.")
  parser.add_argument(
    "--output", required=1,
    help="Name of output CSV file.")
  return parser.parse_args(input_args)


def remove_trailing_comma(infile, outfile):
  with open(infile, 'r') as infile, open(outfile, 'w') as outfile:
    csv_writer = csv.writer(outfile)
    for row in csv.reader(infile):
      csv_writer.writerow(row[:-1])  # removes the last comma in each row


# TODO (Bowen): make this function less memory intensive
def combine_descriptor_activities(descriptor_file, activities_file, outfile):
  # set 1st column as the column index of dataframe
  descriptor_df = pd.read_csv(descriptor_file,
                              index_col=0)
  activities_df = pd.read_csv(activities_file, index_col=0)

  # merge descriptor and activities dataframe into output dataframe based on
  # the molecule name, which is the index for both dataframes (but named
  # differently). Default merge is inner merge
  combined_df = pd.merge(descriptor_df, activities_df,
                         left_index=True, right_index=True)
  # need to manually set dataframe indexname after merge based on index
  combined_df.index.name = "Molecule"
  combined_df.to_csv(outfile)


def main():
  args = parse_args()
  descriptor_file = args.descriptor
  activities_file = args.activities
  outfile = args.output
  combine_descriptor_activities(descriptor_file, activities_file, outfile)


if __name__ == '__main__':
  main()

scripts/detect_devices.py

deleted100644 → 0
+0 −9
Original line number Diff line number Diff line
from tensorflow.python.client import device_lib


def get_available_gpus():
  local_device_protos = device_lib.list_local_devices()
  return [x.name for x in local_device_protos if x.device_type == 'GPU']


print(get_available_gpus())
Loading