Biomedical and Health Sciences

The ability to estimate the probability of a drug to receive approval in clinical trials provides natural advantages to optimizing pharmaceutical research workflows. Success rates of a clinical trials have deep implications to costs, duration of development, and under pressure due to stringent regulatory approval processes. We propose a machine learning approach that can predict the outcome of trial with reliable accuracies, using biological activities, physico-chemical properties of the compounds, target related features and NLP-based compound representation.

Categories:
428 Views

The Open Big Healthy Brains (OpenBHB) dataset is a large (N>5000) multi-site 3D brain MRI dataset gathering 10 public datasets (IXI, ABIDE 1, ABIDE 2, CoRR, GSP, Localizer, MPI-Leipzig, NAR, NPC, RBP) of T1 images acquired across 93 different centers, spread worldwide (North America, Europe and China). Only healthy controls have been included in OpenBHB with age ranging from 6 to 88 years old, balanced between males and females.

Categories:
2429 Views

Walking disorders are common in post-stroke. Body weight support (BWS) systems have been proposed and proven to enhance gait training systems for recovering in individuals with hemiplegia. However, the fixed weight support and walking speed increase the risk of falling and decrease the active participation of the subjects. This paper proposes a strategy to enhance the efficiency of BWS treadmill training.

Categories:
145 Views

This dataset includes 70 sets of 3D confocal high-resolution images. All images were imaged using an LSM800 Zeiss microscope with a Plan-apochromat 1.40-NA, 63× objective, and Zeiss ZEN Blue 2.6 software was used to acquire the images. Three channels were used to acquire transmitted light (TL), SYBR GoldTM- (Thermo Fisher Scientific, Inc.) labeled (nuclear and mitochondrial DNA), and TMRM-labeled (mitochondria) images. Each confocal image consists of 32 slices with an interval of 0.15 µm and a YX resolution of 917 × 917 pixels.

Categories:
146 Views

This is a comprehensive dataset of human arm motion during Activities of Daily Living (ADL). The Cartesian locations of the head, torso, and arm segments were recorded using a motion capture system (Vicon) from 12 participants (ages 18-72, 6 male, 6 female) performing 24 unique tasks. These include both standing and sitting tasks, as well as repetitions, selected based on what would be most useful for prosthesis users, resulting in 72 recorded trials per subject.

Categories:
413 Views

This is the protein PDB dataset for the article "Novel Algorithm for Improved Protein Classification Using Graph Similarity".  This dataset consists of 9 classes of proteins.

Categories:
287 Views

<p>All life on Earth is related, so that some molecular interactions are common across almost all living cells, with the number of common interactions increasing as we look at more closely related species. In particular, we expect the {\it protein-protein interaction} (PPI) networks of closely-related species to share high levels of similarity. This similarity may facilitate the transfer of functional knowledge between model species and human. {\it Multiple Network Alignment} is the process of uncovering the connection similarity between 3 or more networks simultaneously.

Categories:
55 Views

All life on Earth is related, so that some molecular interactions are common across almost all living cells, with the number of common interactions increasing as we look at more closely related species. In particular, we expect the {\it protein-protein interaction} (PPI) networks of closely-related species to share high levels of similarity. This similarity may facilitate the transfer of functional knowledge between model species and human. {\it Multiple Network Alignment} is the process of uncovering the connection similarity between 3 or more networks simultaneously.

Categories:
41 Views

These simulated live cell microscopy sequences were generated by the CytoPacq web service https://cbia.fi.muni.cz/simulator [R1]. The dataset is composed of 51 2D sequences and 41 3D sequences. The 2D sequences are divided into distinct 44 training and 7 test sets. The 3D sequences are divided into distinct 34 training and 7 test sets. Each sequence contains up to 200 frames.

Categories:
213 Views

The dataset represents the negative interaction dataset of the Drugbank that has been generated from our proposed machine learning method based on drug similarity, which achieved an average accuracy of 95% compared to the randomly generated negative datasets in the literature. Drugbank was used as the drug target interaction dataset from https://go.drugbank.com/.

Categories:
441 Views

Pages