Period Changer

Donated on 5/4/2022

The dataset includes 90 non-toxic molecules designed for functional domain of a core clock protein, CRY1, of which 27 molecules significantly lengthen the period of circadian rhythm and the rest, 63 molecules, are no changers.

Dataset Characteristics

Tabular

Subject Area

Biology

Associated Tasks

Classification

Feature Type

-

# Instances

90

# Features

1177

Dataset Information

What do the instances in this dataset represent?

Small molecules

Was there any data preprocessing performed?

The data consists of a complete set of 1177 molecular descriptors and needs feature selection before classification since some of the features are redundant. We used Recursive Feature Elimination together with Extreme Gradient Boosting Classifier (XGBC) to get the best set of molecular descriptors for XGBC. Subsetted data with 10 features is included as supplementary file.

Has Missing Values?

No

Introductory Paper

Structure-based design and classifications of small molecules regulating the circadian rhythm period

By Seref Gul, F. Rahim, Safak Isin, Fatma Yilmaz, Nuri Ozturk, M. Turkay, I. Kavakli. 2021

Published in Scientific reports

Variables Table

Variable NameRoleTypeDescriptionUnitsMissing Values
MATS3vFeatureContinuousno
nHBint10FeatureIntegerno
MATS3sFeatureContinuousno
MATS3pFeatureContinuousno
nHBDon_LipinskiFeatureIntegerno
minHBint8FeatureContinuousno
MATS3eFeatureContinuousno
MATS3cFeatureContinuousno
minHBint2FeatureContinuousno
MATS3mFeatureContinuousno

0 to 10 of 1178

Reviews

There are no reviews for this dataset yet.

Login to Write a Review
Download
1 citations
4166 views

Keywords

Small MoleculeCircadian Clock

Creators

Şeref Gül

serefgul@ku.edu.tr

Koç University

FATIH RAHIM

frahim@ku.edu.tr

License

By using the UCI Machine Learning Repository, you acknowledge and accept the cookies and privacy practices used by the UCI Machine Learning Repository.

Read Policy