Literature search – Exploring in silico protein toxicity prediction methods to support the food and feed risk assessment

Palazzolo, Luca; Gianazza, Elisabetta; Eberini, Ivano

doi:10.2903/sp.efsa.2020.en-1875

Cited by 4 publications

(1 citation statement)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In line with its constant commitment to incorporate the latest scientific developments in the risk assessment process, EFSA is investigating further on new developments and tools for enhancing protein safety assessment (see Palazzolo et al, 2020) including exploring in silico predicting tools when appropriate. Finally, EFSA remarks that most of the papers cited by Testbiotech refer to the possible effects of Bt proteins (and their combinations) on insects and are therefore considered of no relevance for the assessment of the safety of food and feed.…”

Section: Toxicity Of the Bt Toxinsmentioning

confidence: 99%

Scientific assistance on the internal review under Regulation (EC) No 1367/2006 of the Commission Implementing Decisions on genetically modified soybean MON 87751 x MON 87701 × MON 87708 x MON 89788, maize MON 87427 × MON 87460 × MON 89034 × MIR162 × NK603 and subcombinations and maize MON 87427 × MON 89034 × MIR162 × MON 87411 and subcombinations

Neri¹,

Afonso²,

Sanctis³

et al. 2021

EFS3

View full text Add to dashboard Cite

Following a request of the European Commission, the European Food Safety Authority (EFSA) reviewed the scientific arguments raised by the non-governmental organisation Testbiotech requesting the review of Commission Implementing Decisions (EU) No 2021/66, 2021/61 and 2021/65 , authorising the placing on the market of products containing, consisting of or produced from the four-event stack soybean MON 87751 × MON 87701 × MON 87708 × MON 89788 (application EFSA-GMO-NL-2016-128), the five-event stack maize MON 87427 × MON 87460 × MON 89034 × MIR162 × NK603 and its subcombinations (application EFSA-GMO-NL-2016-134) and the four-event stack maize MON 87427 × MON 89034 × MIR162 × MON 87411 and its subcombinations (application EFSA- GMO-NL-2017-144). In relation to the four-event stack soybean and the five-event stack maize, Testbiotech argued that the risk assessment performed by the EFSA Scientific Panel on Genetically Modified Organisms (EFSA GMO Panel) is insufficient as regards molecular characterisation, comparative analyses, toxicological and allergenicity assessment and environmental assessment. For the four-event stack maize, Testbiotech claims that the risk assessment performed by the EFSA GMO Panel is inadequate considering the general knowledge gaps in the assessment of RNAi-based GM plants. EFSA's assessment focuses on scientific elements and does not cover legal aspects, as they are not in EFSA's remit and not in the frame of the mandate received from the EC. The assessment of the scientific arguments provided in the technical background of the three requests does not give enough justification to support the re-examination of the EFSA GMO Panel risk assessment conclusions and risk management recommendations.

show abstract

Section: Toxicity Of the Bt Toxinsmentioning

confidence: 99%

Scientific assistance on the internal review under Regulation (EC) No 1367/2006 of the Commission Implementing Decisions on genetically modified soybean MON 87751 x MON 87701 × MON 87708 x MON 89788, maize MON 87427 × MON 87460 × MON 89034 × MIR162 × NK603 and subcombinations and maize MON 87427 × MON 89034 × MIR162 × MON 87411 and subcombinations

Neri¹,

Afonso²,

Sanctis³

et al. 2021

EFS3

View full text Add to dashboard Cite

show abstract

Implementing New Approach Methodologies (NAMs) in food safety assessments: Strategic objectives and actions taken by the European Food Safety Authority

Cattaneo¹,

Astuto²,

Binaglia³

et al. 2023

Trends in Food Science & Technology

View full text Add to dashboard Cite

Development of in silico methodologies to predict the toxicity of novel proteins in the context of food and feed risk assessment

Palazzolo,

Laurenzi,

Mariem

et al. 2024

EFS3

View full text Add to dashboard Cite

This report is the outcome of an EFSA procurement (OC/EFSA/GMO/2021/02 – LOT1) aiming at developing an in silico strategy to predict the toxicity of (novel) proteins. Up‐to‐date, commercially available tools predicting protein toxicity based on primary structures were evaluated for their accuracy and usability, using a curated dataset of annotated toxins and non‐toxins from UniProt. ToxinPred2 and Toxify emerged as the top performers, showing both high accuracy and suitability for integration into an automated pipeline. Additional bioinformatics methods were explored, which provide sequence similarity‐based information rather than direct predictions (BLAST, InterPro HMM profiles). By converting their outputs into features for machine learning models, a high prediction accuracy was achieved, though there is potential for improvement to reduce overfitting risks. An Artificial Intelligence (AI)‐based consensus pipeline, integrating results from ToxinPred2, Toxify, and our machine learning models was developed. This consensus model reached a 95% accuracy rate in distinguishing toxins from non‐toxins. Noteworthy, our BLAST‐based machine learning model ‐ although performance‐wise comparable to BLAST ‐ offers higher sensitivity and specificity across diverse queries than BLAST; it relies on database‐based evolutionary relationships, which may significantly limit its applicability to novel or mutated toxins. Structure‐based prediction methods are deemed impractical due to their resource intensity and reliance on accurate structural data; AI‐driven structure prediction methods ‐ like Rosetta and AlphaFold ‐ are promising, however they are still under development and may not be suitable for the regulatory context yet. Recommendations are provided, including enhancement of the proposed consensus pipeline to create an independent open‐source, user‐friendly tool for evaluating the safety of (novel) proteins in food and feed; regular updates of the proposed databases and models; incorporation of 3D structures and in general validation of AI and machine learning models for regulatory uses.

show abstract

Literature search – Exploring in silico protein toxicity prediction methods to support the food and feed risk assessment

Cited by 4 publications

References 49 publications

Implementing New Approach Methodologies (NAMs) in food safety assessments: Strategic objectives and actions taken by the European Food Safety Authority

Development of in silico methodologies to predict the toxicity of novel proteins in the context of food and feed risk assessment

Contact Info

Product

Resources

About