Hosein Fooladi

Hosein Fooladi

Machine Learning Researcher

Posts by Collection

portfolio

publications

Optimum Design, Manufacturing and Experiment of a Passive Walking Biped: Effects of Structural Parameters on Efficiency, Stability and Robustness on Uneven Trains

Published in Applied Mechanics and Materials, 2013

In this research, a deployed model of biped that can be built has been considered, and then its walking performance sensitivity such as efficiency, stability and robustness on uneven trains due to variation of structural parameters and their optimum limits have been investigated.

Recommended citation: Hadi, Sadati et al. (2013). "Optimum Design, Manufacturing and Experiment of a Passive Walking Biped: Effects of Structural Parameters on Efficiency, Stability and Robustness on Uneven Trains." Applied Mechanics and Materials. https://www.scientific.net/AMM.307.107

Enhanced Waddington Landscape Model with Cell-Cell Communication Can Explain Molecular Mechanisms of Self-Organization

Published in Bioinformatics, 2019

Here, we propose a multicellular mathematical model for pattern formation during in vitro gastrulation of human ESCs. This model enhances the basic principles of Waddington epigenetic landscape with cell-cell communication, in order to enable pattern and tissue formation.

Recommended citation: Hosein, Fooladi. (2019). "Enhanced Waddington Landscape Model with Cell-Cell Communication Can Explain Molecular Mechanisms of Self-Organization." Bioinformatics 1. 1(3). https://academic.oup.com/bioinformatics/advance-article-abstract/doi/10.1093/bioinformatics/btz201/5418791?redirectedFrom=fulltext

Recognizing Arrow Of Time In The Short Stories

Published in ACL, 2019

Recognizing arrow of time in short stories is a challenging task. i.e., given only two paragraphs, determining which comes first and which comes next is a difficult task even for humans. In this paper, we have collected and curated a novel dataset for tackling this challenging task. We have shown that a pre-trained BERT architecture achieves reasonable accuracy on the task, and outperforms RNN-based architectures.

Recommended citation: Hosseini, Fahimeh, Hosein Fooladi, and Mohammad Reza Samsami. "Recognizing Arrow Of Time In The Short Stories." arXiv preprint arXiv:1903.10548 (2019). https://www.aclweb.org/anthology/W19-3606/

Bayesian optimization for ternary complex prediction (BOTCP)

Published in Artificial Intelligence in the Life Sciences, 2023

Proximity-inducing compounds (PICs) are an emergent drug technology through which a protein of interest (POI), often a drug target, is brought into the vicinity of a second protein which modifies the POI’s function, abundance or localisation, giving rise to a therapeutic effect. One of the best-known examples for such compounds are heterobifunctional molecules known as proteolysis targeting chimeras (PROTACs). PROTACs reduce the abundance of the target protein by establishing proximity to an E3 ligase which labels the protein for degradation via the ubiquitin-proteasomal pathway. Design of PROTACs in silico requires the computational prediction of the ternary complex consisting of POI, PROTAC molecule, and the E3 ligase.

Recommended citation: Rao, Arjun, et al. "Bayesian optimization for ternary complex prediction (BOTCP)." Artificial Intelligence in the Life Sciences 3 (2023): 100072. https://www.sciencedirect.com/science/article/pii/S2667318523000168

Encoding Protein-Ligand Interactions: Binding Affinity Prediction with Multigraph-based Modeling and Graph Convolutional Network

Published in ChemRxiv, 2023

Machine learning models are employed to enhance the speed and provide novel insights in drug discovery due to their demonstrated effectiveness in predicting properties of small molecules like pKa, solubility, and binding affinity. These approaches accelerate drug discovery by helping researchers efficiently identify, prioritize, and optimize compounds.

Recommended citation: Mekni, Nedra, et al. "Encoding Protein-Ligand Interactions: Binding Affinity Prediction with Multigraph-based Modeling and Graph Convolutional Network" ChemRxiv (2023) https://chemrxiv.org/engage/chemrxiv/article-details/657c870b66c13817294342d9

Quantifying the hardness of bioactivity prediction tasks for transfer learning

Published in Journal of Chemical Information and Modeling, 2024

Today, machine learning methods are widely employed in drug discovery. However, the chronic lack of data continues to hamper their further development, validation, and application. Several modern strategies aim to mitigate the challenges associated with data scarcity by learning from data on related tasks.

Recommended citation: Fooladi, Hosein, et al. "Quantifying the hardness of bioactivity prediction tasks for transfer learning" Journal of Chemical Information and Modeling (2024) https://doi.org/10.1021/acs.jcim.4c00160

talks

System biology and waddington landscape

Published:

In this talk, I presented our work on pattern formation during human embryonic stem cell development. We proposed a multicellular mathematical model for pattern formation during the in-vitro gastrulation of human ESCs. This model enhances the basic principles of the Waddington epigenetic landscape with cell-cell communication, which enables us to describe how the pattern and tissue formation occurs in the course of development.

Causal learning and inference

Published:

Causal learning and discovery have received significant attention in the machine learning community. Causal learning allows us to answer the question about intervention (i.e., tinkering in the world) and imagination. This framework can mitigate the problem of robustness, adaptation, and explanation that is present in current machine learning practice.

teaching

Advanced bioinformatics

graduate course, Sharif University of Technology, Computer Engineering, 2017

I worked as the teaching assistant of “Advanced bioinformatics course”. This is a graduate level course which covers topics such as: Microaarray and RNA-Seq data analysis, sequence alignment and assembly from genomics data and so on.

Machine learning workshop

Workshop, Shenakht Pajouh, 2019

I am running a machine learning workshop, which I present diverse topics; from knowledge distillation and compression to causal inference and invariance.

Active learning in drug discovery

Workshop, Online, 2022

Active learning and Bayesian optimization have become important/prevalent tools in drug discovery and design. They provide a systematic way to select samples with a high amount of information. This property has made them an ideal choice in early-stage drug discovery, e.g., in hit identification through virtual screening and also lead optimization. Also, they can be used to search through usually very large drug combination space to find drug pairs with the highest synergy score. In this workshop, first, we read and review the theoretical aspects of active learning and bayesian optimization.