Computational and Structural Biotechnology Journal

The data set contains Python scripts, raw and processed data to benchmark hit detection in high-content screening. The raw data contains the extracted numerical features from high content images of 641 validated, highly selective pharmaceutically relevant inhibitors for over 123 targets. There were 979 features extracted using Perkin Elmer software Columbus (2.9.1532). In addition, two further raw data sets are available that were used to validate the machine learning models. These contain staurosporines in different concentrations or compounds that effect the cell cycle. The processed data were cleaned using an outlier test and Z-score transformed. The processing of the data is also available as a Python script and can be followed there. The other Python scripts contain the benchmarking of AI workflows for hit detection. Various machine learning models were tested, ranging from classic classifiers from the Scikit-Learn library over a partial least square regression to simple neural networks. To deal with unknown patterns in the hit detection, novelty detection was also tested. In addition, the used packages or environments with which the benchmarking was carried out are included.

This data set is provided as supplementary information to the manuscript "Investigating metabolic interactions in a microbial co-culture through integrated modelling and experiments". This folder also contains all the codes necessary to generate the results reported in the manuscript.

The simulation results from the kinetic Monte-Carlo Method

Supplimentary files

This data set contains all integral membrane protein subunits analyzed in the associated manuscript. We annotated the oligomeric state of each membrane protein complex and whether the complex is obligate based on experimental findings in the literature. The data set has a total of 14245 data points (amino acid residues). For each residue, we also calculated the rate of evolution of the corresponding sequence position, its weighted contact numbers and relative solvent accessibilities based on protomer structure and oligomer structure.

This compressed file contains raw data used to generate results reported in the manuscript. A detailed description of the data is provided in the README, which can be obtained after decompressing the file.

Supplementary material 1. The name and molecular descriptor of inhibitors and non-inhibitors in the training and test set Supplementary material 2. The value of experimental pIC50 and predicted pIC50 for all the training set and independent test set molecules Supplementary material 3.The Total Score (TS) and C Score (CS) of the NAIs Supplementary material 4. The name and 2D-SAR results of designed compounds Supplementary material 5. The CoMFA Contour map of Compound M13

The file "Precision_CASP12_22FM.pdf" lists the detailed contact prediction results for 22 CASP12 free modeling targets using our algorithm DeepConPred2, including the precision values at various top-scored pairs for each individual protein target. The file "RMSD_comparison_CONFOLD_results.pdf" lists the structure prediction results for the 22 CASP12 free modeling targets, using the top 2L predicted contacts (by DeepConPred2, DNCON2, RaptorX-Contact and SPOT-Contact) as constraints.