Advances in Computational Intelligence for Protein Design
A special issue of International Journal of Molecular Sciences (ISSN 1422-0067). This special issue belongs to the section "Molecular Informatics".
Deadline for manuscript submissions: closed (15 June 2023) | Viewed by 2335
Special Issue Editor
Special Issue Information
Dear Colleagues,
Protein Design is a fast growing area of theoretically-inspired research undertaken to develop groundbreaking life science applications. Emerging technologies of Machine Learning (ML) have undoubtedly demonstrated their impactful roles in human genomics and bioinformatics during the last decade.
Natural Language Processing (NLP) technologies were recently shown to be extremely efficient in Protein Design and Prediction Molecular Structures. An exciting example of such a technology is AlphaFold by DeepMind.
The NLP technologies are especially attractive when solutions to complex problems are designed by using transferable learning and pretrained explanatory models. NLP technologies allow Users to find efficient solutions despite differences in molecular structures and attributions.
In practice, molecular sequences being carefully scanned have yet uncertain components which affect the accuracy and reliability of experimental results. Computational Intelligence technologies are expected to bring quantitative and feasible evaluations of the uncertainties in order to inform Users about possible losses, using e.g. Markov chain Monte Carlo.
Because of the complex nature, the interactions between combinations of enzymes and RNA molecules are represented within a probabilistic framework interpretable by Users. Finding a concise set of enzymes which maximes binding of RNA molecules within the probabilistic framework is another challenge expected to be resolved in order to reduce the cost of experiments.
Finding new insights in imbalanced and/or under-determined molecular data is a specific area of discovering Structure-Activity Relationships. Efficient solutions to this problem were provided by using hierarchical feature representation, using e.g. a Deep Learning paradigm such as Group Method of Data Handling (GMDH). Using GMDH, Active Learning can efficiently discover explanatory models from the under-determined data, supported with User’s feedback.
Obviously, a key challenge of the above study cases is the reproducibility of results obtained on experimental data, using e.g. Python Machine Learning libraries.
This special issue is leading by Dr. Vitaly Schetinin and assisting by our Topical Advisory Panel Member Dr. Livija Jakaite (Protein Design and Machine Learning Department, Zenith AI). Authors are invited to contribute research articles to a Special Issue on Advances in Computational Intelligence for Protein Design. State-of-art review papers are also considered for publication. The main focus of this issue is on new theoretical results and applications, which demonstrate the advantages of using Computational Intelligence for designing cost-efficient solutions to the related problems.
Topics of interest include but are not limited to the following:
- New ML approaches proven for delivering efficient solutions to Protein Design and Prediction of Molecular Structure
- ML for discovering new insights in molecular data, e.g. which are capable of explaining interactions between enzymes and RNA molecules
- Design of reliable solutions on imbalanced and/or under-determined sequential data
- Reliable estimation of uncertainties existing in molecular data as well as in explanatory models
Dr. Vitaly Schetinin
Guest Editor
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. International Journal of Molecular Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. There is an Article Processing Charge (APC) for publication in this open access journal. For details about the APC please see here. Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- deep learning
- computational intelligence
- protein design
- molecular structure prediction
- sequence alignment