# kexinhuang12345/DeepPurpose

A Deep Learning Toolkit for DTI, Drug Property, PPI, DDI, Protein Function Prediction (Bioinformatics)

Repository: https://github.com/kexinhuang12345/DeepPurpose
Canonical: https://ross.abutalabs.com/products/deeppurpose
Homepage: https://doi.org/10.1093/bioinformatics/btaa1005
Language: Jupyter Notebook
License: BSD-3-Clause
License Family: permissive
Topics: drug-repurposing, deep-learning, drug-target-interactions, toolkit, covid19, virtual-screening, drug-discovery, ppi, ddi, dti-prediction, drug-property-prediction, protein-function-prediction, repurposing-drugs, qsar, side-effects, drug-drug-interaction, protein-protein-interaction, drug-target-interaction, bioinformatics
Last push: 2024-06-10T00:41:46+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2359, "days_push": 815, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1184, forks 305 (observed 2026-08-28T04:03:54.582141+00:00)

## What it is
DeepPurpose is a PyTorch-based deep learning library for molecular modeling, supporting drug-target interaction (DTI), drug property, drug-drug interaction, protein-protein interaction, and protein function prediction. It enables drug repurposing, virtual screening, and QSAR workflows with just a few lines of code.

## Use cases
- predict drug-target interactions with deep learning
- run virtual screening for drug repurposing
- predict drug-drug interactions and side effects
- build QSAR models for compound property prediction
- predict protein-protein interactions
- screen compounds against SARS-CoV-2 targets

## When to choose
- you need pretrained models for DTI or drug property prediction
- you want a simple, few-lines-of-code API for molecular ML tasks
- you are doing drug repurposing or virtual screening research
- you want graph neural network encodings for compounds

## When to avoid
- you need a production clinical decision system rather than research tooling
- you need non-PyTorch frameworks or custom training loops beyond its abstractions
- you need actively developed features - development has slowed

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning, nlp, data-science
- domain: bioinformatics, healthcare, machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: drug-discovery, drug-target-interaction, virtual-screening, drug-repurposing, qsar, ddi, ppi, pytorch, molecular-modeling

## Member repositories
- kexinhuang12345/DeepPurpose (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:54.582141+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:24:19.440092+00:00, confidence not recorded.
  - readme: https://github.com/kexinhuang12345/DeepPurpose (fetched 2026-08-28T04:03:54.582141+00:00, sha a0d5095c8ddf)
  - registry_pypi: https://pypi.org/pypi/deeppurpose/json (fetched 2026-08-29T12:31:33.481467+00:00, sha f9f567a0aeed)
- Data as of 2026-08-30T08:39:29.467469+00:00.