Moayad Alnammi

Moayad Alnammi

Auto-generated profile, based on publicly available information

Moayad Alnammi

Department of Information and Computer Science, Interdisciplinary Research Center for Intelligent Secure Systems, King Fahd University of Petroleum and Minerals, Dhahran, Saudi Arabia

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 November 2018 in Journal of Chemical Information and Modeling
Verified
Journal Article
Open access
SLShengchao Liu
Shengchao Liu
MAMoayad Alnammi
Moayad Alnammi
SESpencer Snyder Ericksen
Spencer Snyder Ericksen
AVAndrew F. Voter
Andrew F. Voter
GAGene E. Ananiev
Gene E. Ananiev
AGAnthony Gitter
Anthony Gitter
Virtual (computational) high-throughput screening provides a strategy for prioritizing compounds for experimental screens, but the choice of virtual screening algorithm depends on the dataset and evaluation strategy. We consider a wide range of ligand-based machine learning and docking-based approaches for virtual screening on two protein-protein interactions, PriA-SSB and RMI-FANCM, and present a strategy for choosing which algorithm is best for prospective compound prioritization. Our workflow identifies a random forest as the best algorithm for these targets over more sophisticated neural network-based models. The top 250 predictions from our selected random forest recover 37 of the 54 active compounds from a library of 22,434 new molecules assayed on PriA-SSB. We show that virtual screening methods that perform well on public datasets and synthetic benchmarks, like multi-task neural networks, may not always translate to prospective screening performance on a specific assay of interest.

4 June 2018 in bioRxiv
Verified
Preprint
Open access
PDF file
SLShengchao Liu
Shengchao Liu
MAMoayad Alnammi
Moayad Alnammi
SESpencer Snyder Ericksen
Spencer Snyder Ericksen
AVAndrew F. Voter
Andrew F. Voter
GAGene E. Ananiev
Gene E. Ananiev
AGAnthony Gitter
Anthony Gitter
Virtual (computational) high-throughput screening provides a strategy for prioritizing compounds for experimental screens, but the choice of virtual screening algorithm depends on the dataset and evaluation strategy. We consider a wide range of ligand-based machine learning and docking-based approaches for virtual screening on two protein-protein interactions, PriA-SSB and RMI-FANCM, and present a strategy for choosing which algorithm is best for prospective compound prioritization. Our workflow identifies a random forest as the best algorithm for these targets over more sophisticated neural network-based models. The top 250 predictions from our selected random forest recover 37 of the 54 active compounds from a library of 22,434 new molecules assayed on PriA-SSB. We show that virtual screening methods that perform well in public datasets and synthetic benchmarks, like multi-task neural networks, may not always translate to prospective screening performance on a specific assay of interest.

20 June 2023 in ChemRxiv
Verified
Preprint
Open access
PDF file
MAMoayad Alnammi
Moayad Alnammi
SLShengchao Liu
Shengchao Liu
SESpencer Snyder Ericksen
Spencer Snyder Ericksen
GAGene E Ananiev
Gene E Ananiev
AVAndrew F Voter
Andrew F Voter
AGAnthony Gitter
Anthony Gitter
Traditional small molecule drug discovery is a time consuming and costly endeavor. High-throughput chemical screening can only assess a tiny fraction of drug-like chemical space. The strong predictive power of modern machine learning methods for virtual chemical screening enables training models on known active and inactive compounds and extrapolating to much larger chemical libraries. However, there has been limited experimental validation of these methods in practical applications on large commercially-available or synthesize-on-demand chemical libraries. Through a prospective evaluation with the bacterial protein-protein interaction PriA-SSB, we demonstrate that ligand-based virtual screening can identify many active compounds in large commercial libraries. We use cross validation to compare different types of supervised learning models and select a random forest classifier as the best model for this target. When predicting the activity of more than 8 million compounds from Aldrich Market Select, the random forest substantially outperforms a naïve baseline based on chemical structure similarity. 48% of the random forest's 701 selected compounds are active. The random forest model easily scales to score one billion compounds from the synthesize-on-demand Enamine REAL database. We tested 68 chemically-diverse top predictions from Enamine REAL and observed 31 hits (46%), including one with an IC50 value of 1.3µM.

19 May 2026 in IEEE Access
Verified
Journal Article
Open access
SSShirin Shahsavary
Shirin Shahsavary
MAMoayad Alnammi
Moayad Alnammi
JNJavad Navaei
Javad Navaei
AAAhmed Azab
Ahmed Azab
In today’s interconnected and volatile global economy, distributed manufacturing has become not only feasible but imperative. Traditional facility location models, typically static and deterministic, fail to capture the dynamic risks posed by geopolitical instability and socioeconomic volatility. To address this, a bi-objective Integer Linear Programming (ILP) model is developed that simultaneously minimizes cost and risk in supply chain facility decisions. The model permits flexible reallocation of existing capacities and explores new potential sites under various shift-based capacity expansion patterns. A core contribution of this work is the integration of a robust Machine Learning (ML) framework to estimate location-specific risk based on political, economic, and social factors. Using an extensive dataset covering 161 countries from 2006 to 2019, we construct a multiclass risk prediction pipeline that incorporates coordinates, political, economic, and social indicators. A comprehensive model selection exercise, spanning 23 feature-set configurations and 42 model hyperparameter combinations, is performed using a stratified ten-fold cross-validation approach. Random Forests (RF) ensemble emerges as the top-performing classifier, followed closely by XGBoost (XGB), significantly outperforming neural networks in both accuracy and robustness. The RF model achieves a ten-fold cross-validated accuracy of over 96% and a macro F1-score of over 95%, indicating strong performance even on minority classes. These risk predictions are then embedded into the ILP formulation using a lexicographic preemptive optimization approach to resolve the trade-off between cost and risk, given the predictions made by RF for the years 2020-2024. A case study from the North American automotive sector is used to validate the proposed methodology. Results demonstrate that incorporating ML-based fragility forecasts into facility location planning enables risk-aware, cost-effective decision-making via an integrated decision-support framework for organizations navigating uncertain global supply chains.

27 May 2025 in TechRxiv
Verified
Preprint
Open access
AAAhmed Azab
Ahmed Azab
MAMoayad Alnammi
Moayad Alnammi
HOHany Osman
Hany Osman
FBFazle Baki
Fazle Baki
In this article, a Large Multimodal Model (LMM) is developed for the macro-CAPP for Hybrid Manufacturing (HM), which leverages the flexibility of metal-based additive manufacturing and metal cutting. A Generative Pretrained Transformer (GPT) architecture is developed to address the problem at hand. CAPP-GPT uses an architecture with an encoder-decoder layout, where a Part Encoder processes part data and a Plan Decoder generates the plan sequence. The LMM's Part Encoder handles CAD data, converting it into token embeddings with positional information. It then performs geometric feature recognition followed by mapping each geometric feature into its processing steps or features. Using the geometric and processing features as supportive encoder input, the Plan Decoder autoregressively predicts the sequence of operations on processing features, starting with a special token and iterating until the sequence is complete. The developed architecture allows for robust and systematic process planning for hybrid manufacturing. A framework employing a hybrid approach combining Operations Research and Machine Learning (ML) to generate the corpus for the pretraining of GPT has been developed. It can independently create process plans without commercial datasets, using a hybridized heuristic that considers additive and subtractive manufacturing's unique requirements. Constrained clustering, interpretable ML Logical Analysis of Data (LAD), and mathematical programming are integrated to iteratively develop process plans by identifying promising patterns through LAD in an autoregressive manner by rule mining.

7 September 2026
Verified
Journal Article
Open access
PDF file
FAFahad Ali Atwi
Fahad Ali Atwi
MAMoayad Ahmed Alnammi
Moayad Ahmed Alnammi
MAMohammed Fahad Al-Khater
Mohammed Fahad Al-Khater
The acid dissociation constant (pKa) is a fundamental physicochemical property that governs molecular ionization, solubility, and bioavailability, rendering its accurate prediction essential in drug design and environmental toxicology. This study entailed a systematic comparison of molecular descriptor representations for pKa prediction using eXtreme Gradient Boosting (XGBoost) regression. Four descriptor categories were evaluated: Morgan circular fingerprints, known as extended-connectivity fingerprints (ECFP), with varying radii (one to four) and bit lengths (12–16,384), Molecular ACCess System (MACCS) structural keys, physicochemical descriptors (molecular weight, logP, rotatable bond count, and fragment counts), and combined representations. A comprehensive grid search optimized the XGBoost hyperparameters across all configurations using five-fold cross-validation on a curated dataset of 7,912 compounds with experimental pKa values obtained from DataWarrior. Morgan fingerprints with radius two and 16,384 bits achieved the highest standalone performance (test R2 = 0.795, root mean squared error, RMSE = 1.539), whereas combining Morgan fingerprints (radius one, 2,048 bits) with MACCS keys and physicochemical descriptors yielded the optimal overall result (test R2 = 0.817; RMSE = 1.455). An extended analysis employing 1,135 Mordred and RDKit cheminformatic descriptors with XGBoost feature selection further improved the prediction accuracy (test R2 = 0.829; RMSE = 1.404). Moreover, feature importance analysis identified the number of acidic groups, spectral descriptors, and aromatic amine fragments as the most influential predictors. These results demonstrate that multisource descriptor fusion consistently outperforms individual representations and that XGBoost provides a computationally efficient and interpretable framework for pKa modeling.