Hypothesis-Driven Artificial Intelligence Approaches for Complex Systems Biology

Dear Colleagues,

Artificial Intelligence (AI) was born in 1956 with the aim of conferring computers the ability to perform complex tasks involving cognitive processes that were previously the prerogative of humans.

Over the years, as the power and number of its techniques expanded, so did its spectrum of application: from computers that play chess to biological software capable of predicting the structure of proteins from their amino acid sequences, i.e., AlphaFold.

In recent years, scientific research has seen an unprecedented surge of publications that exploit data-driven AI approaches, leading some authors to proclaim that we are living “in the era where data dominates theory” (Pigliucci, 2009; Huang, 2018).

Complex systems biology (CSB) is no exception, and the literature on this topic reflects this trend, with data slowly replacing mathematical and biological models; for example, recent work features AI models —mainly deep neural networks — trained on large multidimensional and multi-omics data for biomarker research and the prediction of clinical outcomes.

On the other hand, hypothesis-driven research has only benefited from AI techniques to a limited extent, leaving ample territory for exploration of the intersection of AI and complex systems biology. This is especially true in scenarios where biology knowledge is extracted using AI techniques.

This Special Issue aims at gathering investigations dealing with approaches that attempt to recapitulate information extracted from data with AI tools into general frameworks that advance biological knowledge according to a hypothesis-driven methodology with the goal of overcoming mere statistical correlations.

To this end, the theoretical frameworks and modelling paradigms of non-linear systems theory, complex systems science and dynamical systems theory, with their rich repertoire of tools, concepts and methods, can be a valuable source of inspiration.

From the point of view of AI, all AI techniques and subfields—e.g. Large Language Models (LLMs), optimisation, logic and learning—are welcome as long as they are included in works that recapitulate the results in theory-based or model-based approaches.

The non-exhaustive lists of potential contributions we are interested in will focus on approaches that integrate AI techniques with the following:

• Applications of dynamical systems theory to biological processes;
• Modelling approaches that exploit biological principles to reproduce observed data patterns;
• Parameters tuning and optimisation of mathematical models for biological and biochemical systems, e.g., through the use of evolutionary algorithms and other optimisation techniques;
• Computational systems biology methodologies, such as multi-scale modelling, network analysis and pathway simulation;
• Machine learning tools for pattern identification in large biological datasets, drug response prediction, and similar applications.

REFERENCES

Huang, S. The tension between big data and theory in the" omics" era of biomedical research. Perspectives in biology and medicine 2018, 61, 472–488.

Pigliucci, M.  The end of theory in science?. EMBO reports 2009, 10, 534–534.

Dr. Michele Braccini
Dr. Andrea Roli
Dr. Pasquale Stano
Guest Editors

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 250 words) can be sent to the Editorial Office for assessment.

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. Systems is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). 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.