A5038675407- Constraint Satisfaction and Optimization
- Logic, Reasoning, and Knowledge
- Machine Learning in Bioinformatics
- Protein Structure and Dynamics
- Data Management and Algorithms
- Semantic Web and Ontologies
- Multi-Agent Systems and Negotiation
- Advanced Database Systems and Queries
- AI-based Problem Solving and Planning
- RNA and protein synthesis mechanisms
- Computational Drug Discovery Methods
- Logic, programming, and type systems
- Metaheuristic Optimization Algorithms Research
- Bayesian Modeling and Causal Inference
- Formal Methods in Verification
- Enzyme Structure and Function
- Optimization and Search Problems
- Scheduling and Optimization Algorithms
- Algorithms and Data Compression
- Optimization and Packing Problems
- Advanced Manufacturing and Logistics Optimization
- Face recognition and analysis
- Vehicle Routing Optimization Methods
- Genomics and Phylogenetic Studies
- Face and Expression Recognition
Mehran University of Engineering and Technology
2020-2025
Sindh Agriculture University
2025
Lahore Garrison University
2025
Majmaah University
2025
Griffith University
2015-2024
University of the Punjab
2024
Invictus Medical (United States)
2024
Allama Iqbal Medical College
2024
Khwaja Fareed University of Engineering and Information Technology
2024
Sukkur IBA University
2020-2023
Abstract Direct prediction of protein structure from sequence is a challenging problem. An effective approach to break it up into independent sub-problems. These sub-problems such as secondary can then be solved independently. In previous study, we found that an iterative use predicted and backbone torsion angles further improve angle prediction. this expand the features include solvent accessible surface area dihedrals based on Cα atoms. By using deep learning neural network in three...
Because a nearly constant distance between two neighbouring Cα atoms, local backbone structure of proteins can be represented accurately by the angle i−1 Cα i i+1 (θ) and dihedral rotated about bond (τ). θ τ angles, as representative structural properties three to four amino‐acid residues, offer description conformations that is complementary φ ψ angles (single residue) secondary structures (>3 residues). Here, we report first machine‐learning technique for sequence‐based prediction...
The Minimum Vertex Cover (MVC) problem is a prominent NP-hard combinatorial optimization of great importance in both theory and application. Local search has proved successful for this problem. However, there are two main drawbacks state-of-the-art MVC local algorithms. First, they select pair vertices to exchange simultaneously, which time-consuming. Secondly, although using edge weighting techniques diversify the search, these algorithms lack mechanisms decreasing weights. To address...
Abstract Motivation: Solvent exposure of amino acid residues proteins plays an important role in understanding and predicting protein structure, function interactions. can be characterized by several measures including solvent accessible surface area (ASA), residue depth (RD) contact numbers (CN). More recently, orientation-dependent number called half-sphere (HSE) was introduced separating the contacts within upper down half spheres defined according to Cα-Cβ (HSEβ) vector or neighboring...
Background: The natural history of scar maturation in humans has never been formally described from either a clinical or histologic standpoint. Methods: incisional scars was observed 58 healthy male volunteers who each had 2 × 1-cm wounds created on the inner aspect both upper arms. resulting were photographed digitally at monthly intervals for 12 months and excised analysis specific time points. All specimens stained using Masson's trichrome reviewed together with corresponding digital...
Small RNA molecules play important roles in many biological processes and their dysregulation or dysfunction can cause disease. The current method of choice for genome-wide sRNA expression profiling is deep sequencing. Here we present Oasis 2, which a new main release the web application detection, differential expression, classification small RNAs sequencing data. Compared to its predecessor Oasis, 2 features novel speed-optimized detection module that supports identification any organism...
Prediction of the structural classes proteins can provide important information about their functionalities as well major tertiary structures. It is also considered an step towards protein structure prediction problem. Despite all efforts have been made so far, finding a fast and accurate computational approach to solve class problem still remains challenging in bioinformatics biology. In this study we propose segmented distribution auto covariance feature extraction methods capture local...
Post-translational modification refers to the biological mechanism involved in enzymatic of proteins after being translated ribosome. This comprises a wide range structural modifications, which bring dramatic variations function proteins. One recently discovered modifications is succinylation. Although succinylation can be detected through mass spectrometry, its current experimental detection turns out timely process unable meet exponential growth sequenced Therefore, implementation fast and...
Toxicity prediction of chemical compounds is a grand challenge. Lately, it achieved significant progress in accuracy but using huge set features, implementing complex blackbox technique such as deep neural network, and exploiting enormous computational resources. In this paper, we strongly argue for the models methods that are simple machine learning characteristics, efficient computing resource usage, powerful to achieve very high levels. To demonstrate this, develop single task-based...
Ether-a-go-go-related gene (hERG) channel blockade by small molecules is a big concern during drug development in the pharmaceutical industry. Blockade of hERG channels may cause prolonged QT intervals that potentially could lead to cardiotoxicity. Various in-silico techniques including deep learning models are widely used screen out with potential related toxicity. Most published methods utilize single type features which might restrict their performance. Methods based on more than one such...
A paperless computer applications course, which is driven by an online syllabus described. Students demo their work on the rather than hand in paper assignments. Several advanced topics are included to challenge students and downloads provided minimize amount of student busywork. The use weekly lecture assignment allow instructors teach sections with twenty-five no graduate or clerical support.