The promises of large language models for protein design and modeling.

The recent breakthroughs of Large Language Models (LLMs) in the context of natural language processing have opened the way to significant advances in protein research. Indeed, the relationships between human natural language and the "language of proteins" invite the application and adaptation of LLMs to protein modelling and design. Considering the impressive results of GPT-4 and other recently developed LLMs in processing, generating and translating human languages, we anticipate analogous results with the language of proteins. Indeed, protein language models have been already trained to accurately predict protein properties, generate novel functionally characterized proteins, achieving state-of-the-art results. In this paper we discuss the promises and the open challenges raised by this novel and exciting research area, and we propose our perspective on how LLMs will affect protein modeling and design.

A pilot study for investigating the feasibility of supervised machine learning approaches for the classification of pedestrians struck by vehicles.

This research focuses on the application of Artificial Intelligence (AI) methodologies to the problem of classifying vehicles involved in lethal pedestrian collisions. Specifically, the vehicle type is predicted on the basis of traumatic injury suffered by casualties, exploiting machine learning algorithms. In the present study, AI-assisted diagnosis was shown to have correct prediction about 70% of the time. In pedestrians struck by trucks, more severe injuries were appreciated in the facial skeleton, lungs, major airways, liver, and spleen as well as in the sternum/clavicle/rib complex, whereas the lower extremities were more affected by fractures in pedestrians struck by cars. Although the distinction of the striking vehicle should develop beyond autopsy evidence alone, the presented approach which is novel in the realm of forensic science, is shown to be effective in building automated decision support systems. Outcomes from this system can provide valuable information after the execution of autoptic examinations supporting the forensic investigation. Preliminary results from the application of machine learning algorithms with real-world datasets seem to highlight the efficacy of the proposed approach, which could be used for further studies concerning this topic.

Factors affecting the urinary aldosterone-to-creatinine ratio in healthy dogs and dogs with naturally occurring myxomatous mitral valve disease.

BACKGROUND: Chronic renin-angiotensin-aldosterone system (RAAS) activation in course of heart diseases contributes to cardiac remodeling and heart failure. Myxomatous mitral valve disease (MMVD) is characterized by different stages of severity and trend of RAAS activity during the course of the disease is still uncertain. The urinary aldosterone-to-creatinine ratio (UAldo:C) has been proven to reflect RAAS activation in dogs and might be a useful marker in monitoring therapy and disease progression, but data about this parameter need to be expanded. The objective of this study was to evaluate the UAldo:C in healthy dogs and dogs with naturally occurring MMVD, and to investigate the relationships between this parameter and clinical, echocardiographic and laboratory variables. RESULTS: The study population consisted of 149 dogs: 49 healthy and 100 MMVD dogs (45 stage B1, 13 stage B2 and 42 stage C). Urinary aldosterone-to-creatinine ratio was not significantly different among healthy and MMVD dogs of any stages. Breed, sex and age showed a significant impact on UAldo:C. In particular, Chihuahua and Cavalier King Charles spaniel showed significantly higher UAldo:C than other breeds, as well as intact females than other genders. In stage C dogs, UAldo:C appeared to be increased by spironolactone and was positively associated with furosemide dose (P = 0.024). Aldosterone breakthrough (ABT) appeared to occur in 36% (8/22) of stage C dogs not receiving spironolactone. A significant positive association between UAldo:C and left atrium-to-aortic root ratio (LA/Ao) was found. CONCLUSIONS: Individual factors such as breed, sex and age appeared to influence UAldo:C, and therapy seemed to add further variability. In the light of these results, comparing the UAldo:C of a single patient with a population-based reference value might lead to wrong interpretations and an individual monitoring should be considered. The prevalence of ABT in the present study (36%) was in line with those previously reported. However, due to the high individual variability of UAldo:C found in the study, even this result should be re-evaluated in the setting of an individual longitudinal approach. The positive association between UAldo:C and LA/Ao supports the mutual relationship between RAAS and cardiac remodeling.

Explainable Machine Learning for Early Assessment of COVID-19 Risk Prediction in Emergency Departments.

Between January and October of 2020, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus has infected more than 34 million persons in a worldwide pandemic leading to over one million deaths worldwide (data from the Johns Hopkins University). Since the virus begun to spread, emergency departments were busy with COVID-19 patients for whom a quick decision regarding in- or outpatient care was required. The virus can cause characteristic abnormalities in chest radiographs (CXR), but, due to the low sensitivity of CXR, additional variables and criteria are needed to accurately predict risk. Here, we describe a computerized system primarily aimed at extracting the most relevant radiological, clinical, and laboratory variables for improving patient risk prediction, and secondarily at presenting an explainable machine learning system, which may provide simple decision criteria to be used by clinicians as a support for assessing patient risk. To achieve robust and reliable variable selection, Boruta and Random Forest (RF) are combined in a 10-fold cross-validation scheme to produce a variable importance estimate not biased by the presence of surrogates. The most important variables are then selected to train a RF classifier, whose rules may be extracted, simplified, and pruned to finally build an associative tree, particularly appealing for its simplicity. Results show that the radiological score automatically computed through a neural network is highly correlated with the score computed by radiologists, and that laboratory variables, together with the number of comorbidities, aid risk prediction. The prediction performance of our approach was compared to that that of generalized linear models and shown to be effective and robust. The proposed machine learning-based computational system can be easily deployed and used in emergency departments for rapid and accurate risk prediction in COVID-19 patients.

Correction to: Evaluating the impact of topological protein features on the negative examples selection.

After publication of the original article [1], it was noticed that the dagger symbol indicating equal contribution wasn't added next to the names of all authors.

Evaluating the impact of topological protein features on the negative examples selection.

BACKGROUND: Supervised machine learning methods when applied to the problem of automated protein-function prediction (AFP) require the availability of both positive examples (i.e., proteins which are known to possess a given protein function) and negative examples (corresponding to proteins not associated with that function). Unfortunately, publicly available proteome and genome data sources such as the Gene Ontology rarely store the functions not possessed by a protein. Thus the negative selection, consisting in identifying informative negative examples, is currently a central and challenging problem in AFP. Several heuristics have been proposed through the years to solve this problem; nevertheless, despite their effectiveness, to the best of our knowledge no previous existing work studied which protein features are more relevant to this task, that is, which protein features help more in discriminating reliable and unreliable negatives. RESULTS: The present work analyses the impact of several features on the selection of negative proteins for the Gene Ontology (GO) terms. The analysis is network-based: it exploits the fact that proteins can be naturally structured in a network, considering the pairwise relationships coming from several sources of data, such as protein-protein and genetic interactions. Overall, the proposed protein features, including local and global graph centrality measures and protein multifunctionality, can be term-aware (i.e., depending on the GO term) and term-unaware (i.e., invariant across the GO terms). We validated the informativeness of each feature utilizing a temporal holdout in three different experiments on yeast, mouse and human proteomes: (i) feature selection to detect which protein features are more helpful for the negative selection; (ii) protein function prediction to verify whether the features considered are also useful to predict GO terms; (iii) negative selection by applying two different negative selection algorithms on proteins represented through the proposed features. CONCLUSIONS: Term-aware features (with some exceptions) resulted more informative for problem (i), together with node betweenness, which is the most relevant among term-unaware features. The node positive neighborhood instead is the most predictive feature for the AFP problem, while experiment (iii) showed that the proposed features allow negative selection algorithms to select effectively negative instances in the temporal holdout setting, with better results when nonlinear combinations of features are also exploited.

A general framework for learning rules from data.

With the aim of getting understandable symbolic rules to explain a given phenomenon, we split the task of learning these rules from sensory data in two phases: a multilayer perceptron maps features into propositional variables and a set of subsequent layers operated by a PAC-like algorithm learns Boolean expressions on these variables. The special features of this procedure are that: i) the neural network is trained to produce a Boolean output having the principal task of discriminating between classes of inputs; ii) the symbolic part is directed to compute rules within a family that is not known a priori; iii) the welding point between the two learning systems is represented by a feedback based on a suitability evaluation of the computed rules. The procedure we propose is based on a computational learning paradigm set up recently in some papers in the fields of theoretical computer science, artificial intelligence and cognitive systems. The present article focuses on information management aspects of the procedure. We deal with the lack of prior information about the rules through learning strategies that affect both the meaning of the variables and the description length of the rules into which they combine. The paper uses the task of learning to formally discriminate among several emotional states as both a working example and a test bench for a comparison with previous symbolic and subsymbolic methods in the field.