1 January 2022 in Bioinformatics Advances
Motivation: Protein–protein interactions (PPIs) play an essential role in a great variety of cellular processes and are therefore of significant interest for the design of new therapeutic compounds as well as the identification of side effects due to unexpected binding. Here, we present ProteinPrompt, a webserver that uses machine learning algorithms to calculate specific, currently unknown PPIs. Our tool is designed to quickly and reliably predict contact propensities based on an input sequence in order to scan large sequence libraries for potential binding partners, with the goal to accelerate and assure the quality of the laborious process of drug target identification. Results: We collected and thoroughly filtered a comprehensive database of known binders from several sources, which is available as download. ProteinPrompt provides two complementary search methods of similar accuracy for comparison and consensus building. The default method is a random forest (RF) algorithm that uses the auto-correlations of seven amino acid scales. Alternatively, a graph neural network (GNN) implementation can be selected. Additionally, a consensus prediction is available. For each query sequence, potential binding partners are identified from a protein sequence database. The proteom of several organisms are available and can be searched for binders. To evaluate the predictive power of the algorithms, we prepared a test dataset that was rigorously filtered for redundancy. No sequence pairs similar to the ones used for training were included in this dataset. With this challenging dataset, the RF method achieved an accuracy rate of 0.88 and an area under the curve of 0.95. The GNN achieved an accuracy rate of 0.86 using the same dataset. Since the underlying learning approaches are unrelated, comparing the results of RF and GNNs reduces the likelihood of errors. The consensus reached an accuracy of 0.89. Availability and implementation: ProteinPrompt is available online at: http://proteinformatics.org/ProteinPrompt, where training and test data used to optimize the methods are also available. The server makes it possible to scan the human proteome for potential binding partners of an input sequence within minutes. For local offline usage, we furthermore created a ProteinPrompt Docker image which allows for batch submission: https://gitlab.hzdr.de/proteinprompt/ProteinPrompt. In conclusion, we offer a fast, accurate, easy-to-use online service for predicting binding partners from an input sequence.
1 October 2021 in Biophysical Chemistry
Many newly developed drugs suffer from poor water solubility and low bioavailability and hence, need special formulation vehicles like vesicular or micellar drug delivery systems. The knowledge of their membrane-water partition coefficient K becomes critical as is governs drug loading and release from the vehicle, as well as absorption into the body. The dilemma is that measuring K is particularly challenging for these very compounds. Here we establish a strategy to resolve this problem. We added DMSO to shift K and solubility into a convenient range and extrapolated these results back to zero-DMSO. Isothermal titration calorimetry revealed that logK of the kinase inhibitor Lapatinib decreased proportionally to DMSO content (2.5 - 20v%) with a slope of -1/20v% (m value = 28 kJ/mol). This implies a K of 84 mM-1 in DMSO-free buffer. This strategy should be transferable to other poorly soluble drugs and further detection methods.
3 August 2022 in Computational Biology and Chemistry
1 December 2020 in Biochemistry and Biophysics Reports
Ruxolitinib is a small-molecule protein kinase inhibitor, which is used as a therapeutic agent against several diseases. Due to its anti-inflammatory impact, ruxolitinib has also been considered recently for usage in the treatment of Covid-19. While the specific effects of ruxolitinib on Janus kinases (JAK) is comparatively well investigated, its (unspecific) impact on membranes has not been studied in detail so far. Therefore, we characterized the interaction of this drug with lipid membranes employing different biophysical approaches. Ruxolitinib incorporates into the glycerol region of lipid membranes causing an increase in disorder of the lipid chains. This binding, however, has only marginal influence on the structure and integrity of membranes as found by leakage and permeation assays.
1 September 1998 in Endoscopy