Biology subjects

Torrisi, M.

Publications and source records attributed to Torrisi, M..

4 recordsLinked to original sources

bioRxiv2023

Do chemical language models provide a better compound representation?

In recent years, several chemical language models have been developed, inspired by the success of protein language models and advancements in natural language processing. In this study, we explore whether pre-training a chemical language model on billion-scale compound datasets, such as Enamine and ZINC20, can lead to improved compound representation in the drug space. We compare the learned representations of these models with the de facto standard compound representation, and evaluate their potential application in drug discovery and development by benchmarking them on biophysics, physiology, and physical chemistry datasets. Our findings suggest that the conventional masked language modeling approach on these extensive pre-training datasets is insufficient in enhancing compound representations. This highlights the need for additional physicochemical inductive bias in the modeling beyond scaling the dataset size.

bioinformatics↗

bioRxiv2022

Improving the assessment of deep learning models in the context of drug-target interaction prediction

AO_SCPLOWBSTRACTC_SCPLOWMachine Learning techniques have been widely adopted to predict drug-target interactions, a central area of research in early drug discovery. These techniques have shown promising results on various benchmarks although they tend to suffer from poor generalization. This is typically related to very sparse and nonuniform datasets available, which limits the applicability domain of machine learning techniques. Moreover, widespread approaches to split datasets (into training and test sets) treat a drug-target interaction as an independent entities, when in reality the drug and target involved may take part in other interactions, breaking apart the assumption of independence. We observe that this leads to overly optimistic test results and poor generalization of out-of-distribution samples for various state-of-the-art sequence-based machine learning models for drug-target prediction. We show that previous approaches to reduce bias in binding datasets focus on drug or target information only and, thus, lead to similar pitfalls. Finally, we propose a minimum viable solution to evaluate the generalization capability of a machine learning model based on the systematic separation of test samples with respect to drugs and targets in the training set, thus discerning the three out-of-distribution scenarios seen at test time: (1) drug or (2) target present in the training set, or (3) neither.

bioinformatics↗

bioRxiv2020

Protein Profiles: Biases and Protocols

The use of evolutionary profiles to predict protein secondary structure, as well as other protein structural features, has been standard practice since the 1990s. Using profiles in the input of such predictors, in place or in addition to the sequence itself, leads to significantly more accurate predictors. While profiles can enhance structural signals, their role remains somewhat surprising as proteins do not use profiles when folding in vivo. Furthermore, the same sequence-based redundancy reduction protocols initially derived to train and evaluate sequence-based predictors, have been applied to train and evaluate profile-based predictors. This can lead to unfair comparisons since profile may facilitate the bleeding of information between training and test sets. Here we use the extensively studied problem of secondary structure prediction to better evaluate the role of profiles and show that: (1) high levels of profile similarity between training and test proteins are observed when using standard sequence-based redundancy protocols; (2) the gain in accuracy for profile-based predictors, over sequence-based predictors, strongly relies on these high levels of profile similarity between training and test proteins; and (3) the overall accuracy of a profile-based predictor on a given protein dataset provides a biased measure when trying to estimate the actual accuracy of the predictor, or when comparing it to other predictors. We show, however, that this bias can be avoided by implementing a new protocol (EVALpro) which evaluates the accuracy of profile-based predictors as a function of the profile similarity between training and test proteins. Such a protocol not only allows for a fair comparison of the predictors on equally hard or easy examples, but also completely removes the need for selecting arbitrary similarity cutoffs when selecting test proteins. The EVALpro program is available for download from the SCRATCH suite (http://scratch.proteomics.ics.uci.edu).

bioinformatics↗

bioRxiv2018

Porter 5: state-of-the-art ab initio prediction of protein secondary structure in 3 and 8 classes

MotivationAlthough Secondary Structure Predictors have been developed for more than 60 years, current ab initio methods have still some way to go to reach their theoretical limits. Moreover, the continuous effort towards harnessing ever increasing data sets and more sophisticated, deeper Machine Learning techniques, has not come to an end.\n\nResultsHere we present Porter 5, the last release of one of the best performing ab initio secondary structure predictor. Version 5 achieves 84% accuracy (84% SOV) when tested on 3 classes, and 73% accuracy (82% SOV) on 8 classes, on a large independent set, significantly outperforming all the most recent ab initio predictors we have tested.\n\nAvailabilityThe web and standalone versions of Porter5 are available at http://distilldeep.ucd.ie/porter.\n\nContactname@bio.com\n\nSupplementary informationSupplementary data are available at Bioinformatics online.

bioinformatics↗