29 skills found
digital-chemistry-laboratory / MorfeusA Python package for calculating molecular features
zhenglz / OnionnetA multiple-layer inter-molecular contact features based deep neural network for protein-ligand binding affinity prediction
patonlab / DBSTEPDBSTEP: DFT-based Steric Parameters - python-based tool to extract molecular shape and steric descriptors from essentially any structure format
gmum / Graph RepresentationsComparing graph representations for molecular features prediction
EnriqueSPR / Drug Discovery ProjectA computational drug discovery project, in which bioinformatic and machine learning tools are used to identify possible molecular targets and drug chemical features to treat prostate cancer
BeckResearchLab / PyMolSARA Python toolkit to compute molecular features and predict activities and properties of small molecules
ait5 / CNAppCNApp represents the first web tool to perform a comprehensive and integrative analysis of copy number alterations (CNAs) in a user-friendly interface. The software uses segmented data from either aCGH, SNP-array, whole-exome sequencing or whole-genome sequencing to assess sample profiles and CNA levels, establishing associations with molecular and clinical features. CNApp has three main sections: Re-Seg & Score, Region profile and Classifier model
rinikerlab / RestraintmakerRestraintmaker is a tool intended to build Position or Distance restraints for Molecular Dynamics simulations (or any other simulation technique with coordinate-based particles). It can be used on a script layer or as an interactive plugin for PyMol. Features are different selection modes and Optimizers to distribute restraints.
MahdiDavari / FPTEThe FPTE package is a collection of tools for finite pressure temperature elastic constants calculation. Features include, but are not limited to stress-strain method for getting second order elastic tensors using DFT package VASP as well as, ab initio molecular dynamic method for temperature dependent elastic constatns. The package is free and open-source, available on Github.
LanceKnight / MolKGNNMolKGNN is a deep learning model for predicting biological activity or molecular properties. It features in 1. SE(3)-invariance 2. conformation-invariance 3. interpretability. MolKGNN uses a novel molecular convolution to leverage the similarity of molecular neighborhood and kernels. It shows superior results in realistic drug discovery datasets.
digital-chemistry-laboratory / LibconeangleLibrary for calculating exact ligand cone angles
maclandrol / Molfeat HypeCan ChatGPT generate molecular features ?
Sylvie / SambadaSamβada is an integrated software for landscape genomic analysis of large datasets. The key features are the study of local adaptation in relationship with environment and the measure of spatial autocorrelation in environmental and molecular datasets.
zilanjiuwan / Single Cell Imaging Analysis Of HCC DataCurrent molecular classification is often based on cancer cell-intrinsic genomic features, which disregards contribution of the tumor microenvironment and lacks spatial context. Here, we develop an imaging-based tumor classification system by integrating both sources of information. We first trained a multi-task deep learning neural network for automated single-cell segmentation and classification, and applied to whole-slide hematoxylin and eosin-stained tissue section images of 304 hepatocellular carcinoma. Given the single-cell map, we calculated 246 quantitative image features to characterize individual nuclei as well as spatial distribution and interaction between tumor cells and lymphocytes. Unsupervised consensus clustering revealed three reproducible imaging subtypes associated with distinct genetic and molecular features. Further, these imaging subtypes complement established molecular classification and demonstrate independent prognostic value beyond conventional clinicopathologic risk factors.
paukstelis / MolPrintBlender tools addon with features to enhance 3D printing of molecular models
mldlproject / 2020 DILI CNN MFESource code and data of the paper entitled "Predicting Drug-Induced Liver Injury Using Convolutional Neural Network and Molecular Fingerprint-Embedded Features"
hariomgupta70427 / Medical AI PlatformMediAI Discovery Platform is a web-based tool for AI-powered drug discovery and molecular optimization. It offers features like molecular visualization, predictive analysis, and API integrations with PubChem, IBM RXN, and RDKit, all within an interactive, research-friendly interface built using Next.js and optional Python services.
rlaplaza / LibarvoLibrary to compute molecular surfaces and volumes.
RowleyGroup / Charmm ConformationA set of scripts to perform a conformation search using replica-exchange MD features of the CHARMM molecular modeling code.
mhlee216 / Solubility Prediction GCNCode for "Novel Solubility Prediction Models: Molecular Fingerprints and Physicochemical Features vs Graph Convolutional Neural Networks" (https://doi.org/10.1021/acsomega.2c00697)
