Spaces:
Sleeping
Sleeping
File size: 5,284 Bytes
bbcd4a0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 |
# The Selector library provides a set of tools for selecting a
# subset of the dataset and computing diversity.
#
# Copyright (C) 2023 The QC-Devs Community
#
# This file is part of Selector.
#
# Selector is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# as published by the Free Software Foundation; either version 3
# of the License, or (at your option) any later version.
#
# Selector is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, see <http://www.gnu.org/licenses/>
#
# --
import streamlit as st
import sys
import os
from selector.methods.distance import DISE
# Add the streamlit_app directory to the Python path
current_dir = os.path.dirname(os.path.abspath(__file__))
parent_dir = os.path.join(current_dir, "..")
sys.path.append(parent_dir)
from utils import *
# Set page configuration
st.set_page_config(
page_title = "DISE",
page_icon = os.path.join(parent_dir, "assets" , "QC-Devs.png"),
)
st.title("Directed Sphere Exclusion (DISE)")
description = """
In a nutshell, this algorithm iteratively excludes any sample within a given radius from
any already selected sample. The radius of the exclusion sphere is an adjustable parameter.
Compared to Sphere Exclusion algorithm, the Directed Sphere Exclusion algorithm achieves a
more evenly distributed subset selection by abandoning the random selection approach and
instead imposing a directed selection.
Reference sample is chosen based on the `ref_index`, which is excluded from the selected
subset. All samples are sorted (ascending order) based on their Minkowski p-norm distance
from the reference sample. Looping through sorted samples, the sample is selected if it is
not already excluded. If selected, all its neighboring samples within a sphere of radius r
(i.e., exclusion sphere) are excluded from being selected. When the selected number of points
is greater than specified subset `size`, the selection process terminates. The `r0` is used
as the initial radius of exclusion sphere, however, it is optimized to select the desired
number of samples.
"""
references = "Gobbi, A., and Lee, M.-L. (2002). DISE: directed sphere exclusion."\
"Journal of Chemical Information and Computer Sciences,"\
"43(1), 317–323. https://doi.org/10.1021/ci025554v"
display_sidebar_info("Directed Sphere Exclusion (DISE)", description, references)
# File uploader for feature matrix or distance matrix (required)
matrix_file = st.file_uploader("Upload a feature matrix or distance matrix (required)",
type=["csv", "xlsx", "npz", "npy"], key="matrix_file", on_change=clear_results)
# Clear selected indices if a new matrix file is uploaded
if matrix_file is None:
clear_results()
# Load data from matrix file
else:
matrix = load_matrix(matrix_file)
num_points = st.number_input("Number of points to select", min_value = 1, step = 1,
key = "num_points", on_change=clear_results)
label_file = st.file_uploader("Upload a cluster label list (optional)", type = ["csv", "xlsx"],
key = "label_file", on_change=clear_results)
labels = load_labels(label_file) if label_file else None
# Parameters for Directed Sphere Exclusion
st.info("The parameters below are optional. If not specified, default values will be used.")
r0 = st.number_input("Initial guess for radius of exclusion sphere (r0)", value=None, step=0.1,
on_change=clear_results)
ref_index = st.number_input("Reference index (ref_index)", value=0, step=1, on_change=clear_results)
tol = st.number_input("Percentage tolerance of sample size error (tol)", value=0.05, step=0.05,
on_change=clear_results)
n_iter = st.number_input("Number of iterations for optimizing the radius of exclusion sphere (n_iter)",
value=10, step=10, on_change=clear_results)
p = st.number_input("Minkowski p-norm distance (p)", value=2.0, step=1.0, on_change=clear_results)
eps = st.number_input("Approximate nearest neighbor search parameter (eps)", value=0.0, step=0.1,
on_change=clear_results)
if st.button("Run DISE Algorithm"):
selector = DISE(r0=r0, ref_index=ref_index, tol=tol, n_iter=n_iter, p=p, eps=eps)
selected_ids = run_algorithm(selector, matrix, num_points, labels)
st.session_state['selector'] = selector
st.session_state['selected_ids'] = selected_ids
# Check if the selected indices are stored in the session state
if 'selected_ids' in st.session_state and matrix_file is not None:
selected_ids = st.session_state['selected_ids']
st.write("Selected indices:", selected_ids)
if 'selector' in st.session_state:
st.write("Radius of the exclusion sphere:", st.session_state['selector'].r)
export_results(selected_ids)
|