Abdulk084

50_layer_Resnet

50 Layer Resnet to predict the regression values of Tetrahymena pyriformis IGC50 from 2d molecular images only

ALALI

Automated Loading assuming Atomic Level Interactions (ALALI): A python tool to map atoms to qubits, including IBM Q topologies. GPL-3.0-or-later.

CardioTox

Chemception

CNN model based on Google Inception model to predict regression values of regression values of Tetrahymena pyriformis IGC50 from 2D images of molcules

HPE

Heterogeneous Predictors Ensembling for Quantitative Toxicity Prediction

HybridTox2D

In recent times, toxicological classification of chemical compounds is considered to be a grand challenge for pharma-ceutical and environment regulators. Advancement in machine learning techniques enabled efficient toxicity predic-tion pipelines. Random forests (RF), support vector machines (SVM) and deep neural networks (DNN) are often ap-plied to model the toxic effects of chemical compounds. However, complexity-accuracy tradeoff still needs to be ac-counted in order to improve the efficiency and commercial deployment of these methods. In this study, we implement a hybrid framework consists of a shallow neural network and a decision classifier for toxicity prediction of chemicals that interrupt nuclear receptor (NR) and stress response (SR) signaling pathways. A model based on proposed hybrid framework is trained on Tox21 data using 2D chemical descriptors that are less multifarious in nature and easy to calcu-late. Our method achieved the highest accuracy of 0.847 AUC (area under the curve) using a shallow neural network with only one hidden layer consisted of 10 neurons. Furthermore, our hybrid model enabled us to elucidate the inter-pretation of most important descriptors responsible for NR and SR toxicity.

Intent_classification

My demo code and a report for Intent classification

New_molecules_generation

Character level RNN to generate new molecules

QuantitativeTox

Smiles2vec

Proof of the concept implementation of smiles2vec paper

Abdulk084/Smiles2vec

Proof of the concept implementation of smiles2vec paper

Abdulk084/HybridTox2D

In recent times, toxicological classification of chemical compounds is considered to be a grand challenge for pharma-ceutical and environment regulators. Advancement in machine learning techniques enabled efficient toxicity predic-tion pipelines. Random forests (RF), support vector machines (SVM) and deep neural networks (DNN) are often ap-plied to model the toxic effects of chemical compounds. However, complexity-accuracy tradeoff still needs to be ac-counted in order to improve the efficiency and commercial deployment of these methods. In this study, we implement a hybrid framework consists of a shallow neural network and a decision classifier for toxicity prediction of chemicals that interrupt nuclear receptor (NR) and stress response (SR) signaling pathways. A model based on proposed hybrid framework is trained on Tox21 data using 2D chemical descriptors that are less multifarious in nature and easy to calcu-late. Our method achieved the highest accuracy of 0.847 AUC (area under the curve) using a shallow neural network with only one hidden layer consisted of 10 neurons. Furthermore, our hybrid model enabled us to elucidate the inter-pretation of most important descriptors responsible for NR and SR toxicity.

Abdulk084/HPE

Heterogeneous Predictors Ensembling for Quantitative Toxicity Prediction

Abdulk084/ALALI

Automated Loading assuming Atomic Level Interactions (ALALI): A python tool to map atoms to qubits, including IBM Q topologies. GPL-3.0-or-later.

Abdulk084/Name-Entity-Recognition

Recognize named entities on Twitter with LSTMs

Abdulk084/Tag_Prediction_Multiclassification

Multi-classifier for Stack-overflow tag prediction using logistic regression

Abdulk084/AI_Clinician

Reinforcement learning for medical decisions

Abdulk084/aitextgen

A robust Python tool for text-based AI training and generation using GPT-2.

Abdulk084/bayeslabs.github.io

Blog that explains our research work.

Abdulk084/biopython.github.io

Source of biopython.org website, migrated from MediaWiki

Abdulk084/Deep-Reinforcement-Learning-DQN

Deep Reinforcement Learning with DQN, Double DQN, Dueling DQN, Noisy Net (Noisy DQN), and DQN with Prioritized Experience Replay

Abdulk084/Deep-Reinforcement-Learning-Hands-On

Hands-on Deep Reinforcement Learning, published by Packt

Abdulk084/deepchem

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

Abdulk084/DeepLearningLifeSciences

Example code from the book "Deep Learning for the Life Sciences"

Abdulk084/deepsmiles

DeepSMILES - A variant of SMILES for use in machine-learning

Abdulk084/flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

Abdulk084/FP2VEC

Abdulk084/GENTRL

Generative Tensorial Reinforcement Learning (GENTRL) model

Abdulk084/gpt-3

GPT-3: Language Models are Few-Shot Learners

Abdulk084/GraphINVENT

Graph neural networks for molecular design.

Abdulk084/lime

Lime: Explaining the predictions of any machine learning classifier

Abdulk084/MEDIUM_NoteBook

Repository containing notebooks of my posts on Medium

Abdulk084/mimic-code

MIMIC Code Repository: Code shared by the research community for the MIMIC-III database

Abdulk084/mordred

a molecular descriptor calculator

Abdulk084/pytorch-unsupervised-segmentation

Abdulk084/reinvent-gdb13

A Recurrent Neural Network implementation that uses SMILES strings to generate molecules from GDB-13

Abdulk084/reinvent-randomized

Recurrent Neural Network using randomized SMILES strings to generate molecules

Abdulk084/reinvent-scaffold-decorator

A SMILES-based encoder-decoder architecture for molecular scaffold decoration

Abdulk084/spektral

Graph Neural Networks with Keras and Tensorflow 2.

Abdulk084/stackoverflow

Data for stackoverflow questions