Alfredo Ferro is an Emeritus Professor in Computer Science at the Department of Clinical and Experimental Medicine of the University of Catania, Italy and Salvatore Alaimo is an Associate Professor at the same Department. Alfredo is also the Founder and Director of the Lipari International Summer School for Scientific Research (liparischool.it). The Lipari School promotes scientific interactions in a unique mediterranean island setting. It was started in 1989 and has hosted many well-known scientists and international advanced students in computational disciplines applied to different research fields.
Dear Alfredo and Salvatore,
What could be achieved if there was a public or nonprofit AI effort with the same scale and level of funding as the current large private efforts? What would be the benefits for society?
We have developed several software tools for the modeling and simulation of biological processes. Among these are:
MITHRIL (1) a method that takes as input the expression values of genes and/or microRNAs and returns a list of pathways sorted according to the degree of their deregulation;
PHENSIM (2) a computational tool using a systems biology approach to simulate how cell phenotypes are affected by the activation/inhibition of one or multiple biomolecules;
and
NetMe (3), which is a web-based platform for extracting and modeling knowledge from biomedical literature as a labeled graph.
When we developed MITHRIL and PHENSIM we started by using known databases containing biological data, like KEGG and Reactome, but we soon realized that key genes important for some applications were missing. Initially we updated the data manually, but this was too time consuming, and we started developing NetMe to allow the automated extraction of information from the scientific literature. At the moment, NetMe can analyze up to 500 papers but with more computational resources it could be scaled up. We are also investigating the use of LLMs to query the model and receive responses in natural language and more in general to extract information from the literature. Another challenging problem is extending the simulations from simple models to entire organism and to clinical conditions.
We are encouraging researchers at different career stages to share ideas about complex science problems that could benefit from a large-scale AI effort. We found that motivation and recognition could be provided if you and other well-known scientists were willing to talk to people that suggest the best ideas. You would be the judge and decide if any idea is for you deserving of attention. Any scientist selected might receive advice but could also be a potential collaborator. Many ideas will be produced, and society will take notice. Would you be willing to talk to any of these scientists?
We would be very happy to do so. Many of our past activities have promoted open scientific discussions. For example, we have been part of RxCovea ( rxcovea.org ) , an initiative promoting collaboration and open exchange of information among an interdisciplinary group of scientists that originated as a response to the COVID-19 pandemic. Another example is the open-source software movement in computer science.
We should consider that if scientists contribute significantly to a public platform that solves an important scientific problem, their academic career should have advantages. Basing career advancement only on publications slows down progress towards addressing urgent medical needs.
REFERENCES
1- https://doi.org/10.18632%2Foncotarget.9788
2- https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1009069
3- https://academic.oup.com/bioinformatics/article/40/5/btae194/7643510