HeapMS: An Automatic Peak-Picking Pipeline for Targeted Proteomic Data Powered by 2D Heatmap Transformation and Convolutional Neural Networks.

The process of peak picking and quality assessment for multiple reaction monitoring (MRM) data demands significant human effort, especially for signals with low abundance and high interference. Although multiple peak-picking software packages are available, they often fail to detect peaks with low quality and do not report cases with low confidence. Furthermore, visual examination of all chromatograms is still necessary to identify uncertain or erroneous cases. This study introduces HeapMS, a web service that uses artificial intelligence to assist with peak picking and the quality assessment of MRM chromatograms. HeapMS applies a rule-based filter to remove chromatograms with low interference and high-confidence peak boundaries detected by Skyline. Additionally, it transforms two histograms (representing light and heavy peptides) into a single encoded heatmap and performs a two-step evaluation (quality detection and peak picking) using image convolutional neural networks. HeapMS offers three categories of peak picking: uncertain peak picking that requires manual inspection, deletion peak picking that requires removal or manual re-examination, and automatic peak picking. HeapMS acquires the chromatogram and peak-picking boundaries directly from Skyline output. The output results are imported back into Skyline for further manual inspection, facilitating integration with Skyline. HeapMS offers the benefit of detecting chromatograms that should be deleted or require human inspection. Based on defined categories, it can significantly reduce human workload and provide consistent results. Furthermore, by using heatmaps instead of histograms, HeapMS can adapt to future updates in image recognition models. The HeapMS is available at: https://github.com/ccllabe/HeapMS.

Easy and Rapid Approach to Obtaining the Binding Affinity of Biomolecular Interactions Based on the Deep Learning Boost.

Recently, the deep learning (DL) dimension of artificial intelligence has received much attention from biochemical researchers and thus has gradually become the key approach adopted in the area of biosensing applications. Studies have shown that the use of DL techniques for sensing can not only shorten the time of data analysis but also significantly increase the accuracy of data analysis and prediction, resulting in the performance improvement of biosensing systems in comparison to conventional methods. However, obtaining reliable equilibrium and rate constants of biomolecular interactions during the detection process remains difficult and time-consuming to date. In this study, we propose a transformed model based on the deep transfer learning and sequence-to-sequence autoencoder that can successfully transfer the SPR sensorgram to the protein-binding constants, that is, the association rate constant (ka) and dissociation rate constant (kd), which provide crucial information to understand the mechanisms of drug action and the functional structures of biomolecules. Experimentally, we first trained and tested the pre-trained model using the Langmuir model which generated ideal SPR sensorgrams and then we fine-tuned the pre-trained model through the augmented SPR sensorgrams which were synthesized by using the synthesized minority oversampling technique (SMOTE) through the moderate-scale experiment. Next, the fine-tuned model was inputted with a short experimental SPR sensorgram that only needs 110 s, and the sensorgram was directly transformed into a reconstructed ideal sensorgram. Finally, the binding kinetic constants, that is, ka and kd, as outputs, were obtained through fitting the reconstructed ideal sensorgram. The results showed that the prediction errors of ka and kd obtained by our model were less than 12 and 24%, respectively. Based on the convenience, accuracy, and reliability of the proposed DL approach, we believe our strategy significantly boosts the feasibility to monitor the binding affinity of antibodies online during production.

Pathogenic Protist Transmembranome database (PPTdb): a web-based platform for searching and analysis of protist transmembrane proteins.

BACKGROUND: Pathogenic protist membrane transporter proteins play important roles not only in exchanging molecules into and out of cells but also in acquiring nutrients and biosynthetic compounds from their hosts. Currently, there is no centralized protist membrane transporter database published, which makes system-wide comparisons and studies of host-pathogen membranomes difficult to achieve. RESULTS: We analyzed over one million protein sequences from 139 protists with full or partial genome sequences. Putative transmembrane proteins were annotated by primary sequence alignments, conserved secondary structural elements, and functional domains. We have constructed the PPTdb (Pathogenic Protist Transmembranome database), a comprehensive membrane transporter protein portal for pathogenic protists and their human hosts. The PPTdb is a web-based database with a user-friendly searching and data querying interface, including hierarchical transporter classification (TC) numbers, protein sequences, functional annotations, conserved functional domains, batch sequence retrieving and downloads. The PPTdb also serves as an analytical platform to provide useful comparison/mining tools, including transmembrane ability evaluation, annotation of unknown proteins, informative visualization charts, and iterative functional mining of host-pathogen transporter proteins. CONCLUSIONS: The PPTdb collected putative protist transporter proteins and offers a user-friendly data retrieving interface. Moreover, a pairwise functional comparison ability can provide useful information for identifying functional uniqueness of each protist. Finally, the host and non-host protein similarity search can fulfill the needs of comprehensive studies of protists and their hosts. The PPTdb is freely accessible at http://pptdb.cgu.edu.tw .