Biology subjects

Arab, I.

Publications and source records attributed to Arab, I..

5 recordsLinked to original sources

bioRxiv2025

Improved open modification searching via unified spectral search with predicted libraries and enhanced vector representations in ANN-SoLo

The primary computational challenge in mass spectrometry-based proteomics is determining the peptide sequence responsible for generating each measured tandem mass spectrum. This task is traditionally addressed through sequence database searching, as well as alternative approaches such as spectral library searching. ANN-SoLo is a powerful spectral library search engine optimized for open modification searching, enabling the detection of peptides carrying any post-translational modification. Here, we present an enhanced version of ANN-SoLo that combines strengths of both spectral library searching and sequence database searching, by integrating with Prosit to generate predicted spectral libraries from protein sequence databases. Additionally, it provides functionality to generate decoys at both the spectrum and the peptide level, introduces an optimized internal file structure for large-scale analytics, and improves search accuracy by incorporating neutral loss information into spectrum vector representations. These advancements collectively address challenges associated with missing spectral libraries and enhance peptide identification in large-scale and complex proteomics workflows.

bioinformatics↗

bioRxiv2024

Semi-Supervised Learning to Boost Cardiotoxicity Prediction by Mining a Large Unlabeled Small Molecule Dataset

Predicting drug toxicity is a critical aspect of ensuring patient safety during the drug design process. Although conventional machine learning techniques have shown some success in this field, the scarcity of annotated toxicity data poses a significant challenge in enhancing models performance. In this study, we explore the potential of leveraging large unlabeled datasets using semi-supervised learning to improve predictive performance for cardiotoxicity across three targets: the voltage-gated potassium channel (hERG), the voltage-gated calcium channel (Cav1.2), and the voltage-gated sodium channel (Nav1.5). We extensively mined the ChEMBL database, comprising approximately 2 million small molecules, then employed semi-supervised learning to construct robust classification models for this purpose. We achieved a performance boost on highly diverse (i.e. structurally dissimilar) test datasets across all three targets. Using our built models, we screened the whole ChEMBL database and a large set of FDA-approved drugs, identifying several compounds with potential cardiac channel activity. To ensure broad accessibility and usability for both technical and non-technical users, we developed a cross-platform graphical user interface that allows users to make predictions and gain insights into the cardiotoxicity of drugs and other small molecules. The software is made available as open source under the permissive MIT license at https://github.com/issararab/CToxPred2.

pharmacology and toxicology↗

bioRxiv2023

Benchmarking of Small Molecule Feature Representations for hERG, Nav1.5, and Cav1.2 Cardiotoxicity Prediction

In the field of drug discovery, there is a substantial challenge in seeking out chemical structures that possess desirable pharmacological, toxicological, and pharmacokinetic properties. Complications arise when drugs interfere with the functioning of cardiac ion channels, leading to serious cardiovascular consequences. The discontinuation and removal of numerous approved drugs from the market or at late development stages in the pipeline due to such inhibitory effects further highlight the urgency of addressing this issue. Consequently, the early prediction of potential blockers targeting cardiac ion channels during the drug discovery process is of paramount importance. This study introduces a deep learning framework that computationally determines the cardiotoxicity associated with the voltagegated potassium channel (hERG), the voltage-gated calcium channel (Cav1.2), and the voltage-gated sodium channel (Nav1.5) for drug candidates. The predictive capabilities of three feature representations--molecular fingerprints, descriptors, and graph-based numerical representations-- are rigorously benchmarked. Additionally, a novel training and evaluation dataset framework is presented, enabling predictive model training of drug off-target cardiotoxicity using a comprehensive and large curated dataset covering these three cardiac ion channels. To facilitate these predictions, a robust and comprehensive small molecule cardiotoxicity prediction tool named CToxPred has been developed. It is made available as open source under the permissive MIT license at https://github.com/issararab/CToxPred.

pharmacology and toxicology↗

bioRxiv2022

Semi-supervised machine learning for sensitive open modification spectral library searching

A key analysis task in mass spectrometry proteomics is matching the acquired tandem mass spectra to their originating peptides by sequence database searching or spectral library searching. Machine learning is an increasingly popular post-processing approach to maximize the number of confident spectrum identifications that can be obtained at a given false discovery rate threshold. Here, we have integrated semi-supervised machine learning in the ANN-SoLo tool, an efficient spectral library search engine that is optimized for open modification searching to identify peptides with any type of post-translational modification. We show that machine learning rescoring boosts the number of spectra that can be identified for both standard searching and open searching, and we provide insights into relevant spectrum characteristics harnessed by the machine learning model. The semi-supervised machine learning functionality has now been fully integrated into ANN-SoLo, which is available as open source under the permissive Apache 2.0 license on GitHub at https://github.com/bittremieux/ANN-SoLo.

bioinformatics↗

bioRxiv2022

IsarPipeline: Combining MMseqs2 and PSI-BLAST to Quickly Generate Extensive Protein Sequence Alignment Profiles

Many of the machine learning (ML) models used in the field of bioinformatics and computational biology to predict either function or structure of proteins rely on the evolutionary information as summarized in multiple-sequence alignments (MSAs) or the resulting position-specific scoring matrices (PSSMs), as generated by PSI-BLAST. The current procedure used in protein structure and function prediction is computationally exhaustive and time-consuming. The main issue relies on the PSI-BLAST software being forced to load the current database of sequences (about 220 GB) in batches and search for similar sequence alignments to a query sequence. This leads to an average runtime of about 40-60 min for a medium-sized (450 Amino Acids) query protein. This average runtime is strictly dependent on the hardware used to run the software. The issue is becoming more problematic since the bio-sequence data pools are increasing in size exponentially over time, hence raising PSI-BLAST runtime as well. A prominent solution claims to speed up the current process by 100 folds. The MMseqs2 method, given enough memory, will load the whole database in memory and apply certain heuristics to retrieve the relevant set of aligned sequences. However, this solution cannot be used directly to generate the final output in the desired PSI-BLAST alignment and PSSM profile data format. In this research project, we analyzed the runtime performance of each tool separately. Furthermore, we built a pipeline that combines both MMseqs2 and PSI-BLAST to obtain a robust, optimized and very fast hybrid alignment tool, faster than PSI-BLAST by two orders of magnitude. It is implemented in C++ and is freely available under the MIT license at https://github.com/issararab/IsarPipeline. The output of our pipeline was evaluated on two previously built predictive models.

bioinformatics↗