Merge pull request #82 from LukaszSztukiewicz/style/last-touches

Style/last touches

Author: LukaszSztukiewicz

Project.toml

@@ -1,7 +1,7 @@
 name = "MolecularFingerprints"
 uuid = "6289f4a8-86f2-4df5-b427-d4de5bbdeb05"
 authors = ["Lukasz Sztukiewicz <lukasz.sztukiewicz@campus.tu-berlin.de>"]
-version = "1.0.0-DEV"
+version = "1.3.0"
 
 [deps]
 Graphs = "86223c79-3864-5bf0-83f7-82e725a168b6"

README.md

@@ -26,7 +26,7 @@ Pkg.add(url="https://github.com/LukaszSztukiewicz/MolecularFingerprints.jl")
 using MolecularFingerprints
 ```
 
-## Usage
+## Minimalistic Usage
 Once you have installed the MolecularFingerprints.jl package, you can start using it to calculate molecular fingerprints. Here is a simple example:
 
 ```julia
@@ -41,6 +41,42 @@ println(fingerprint_vector)
 findall(fingerprint_vector)  # Indices of bits set to 1
 ```
 
+## Usage of all Fingerprint Types
+The MolecularFingerprints.jl package supports several types of molecular fingerprints. Here is an example of how to use all available fingerprint types:
+
+```julia
+smiles = "C1=CC=CC=C1"
+
+# 2. This package implements 4 types of fingerprints. 
+# All of them could be customized with parameters, but here we use default settings.
+ecfp_calc = ECFP() # Extended Connectivity Fingerprints
+mhfp_calc = MHFP() # MinHash Fingerprints
+torsion_calc = TopologicalTorsion() # Topological Torsion Fingerprints
+maccs_calc = MACCS() # MACCS Keys
+
+# 3. Execution: Compute the fingerprint for each type
+ecfp_vector = fingerprint(smiles, ecfp_calc)
+mhfp_vector = fingerprint(smiles, mhfp_calc)
+torsion_vector = fingerprint(smiles, torsion_calc)
+maccs_vector = fingerprint(smiles, maccs_calc)
+
+# 4. Analysis: Find indices of active features
+
+# ECFP returns BitVector to see active bits, we can use findall
+println("ECFP active bits: ", findall(ecfp_vector))
+
+# MACCS returns BitVector to see active bits, we can use findall
+println("MACCS active bits: ", findall(maccs_vector))
+
+# MHFP returns Vector{Int64} with each non-zero entry, so all bits are active
+# You will see that are of the 2048 bits are being listed
+println("MHFP active bits: ", findall(mhfp_vector .!= 0))
+
+# TopologicalTorsion returns SparseArrays.SparseVector{Int32, Int64} so it is easy to find non-zero entries
+using SparseArrays
+println("Topological Torsion active bits: ", SparseArrays.findnz(torsion_vector)[1])
+```
+
 
 # Documentation
 

src/interface.jl

@@ -1,3 +1,5 @@
+# ACKNOWLEDGEMENT: docstings were partly written with the support of Microsoft Copilot AI (completion mode, not chat mode) 
+
 # --- Abstract Interfaces for Fingerprint Calculators ---
 
 """

test/Manifest.toml

@@ -1,12 +1,13 @@
 using Test
 using MolecularGraph
-using MolecularGraph: smilestomol, MolGraph
 using MolecularFingerprints
+
 using Random: seed!, randstring
-using SparseArrays
 using Graphs: nv, all_simple_paths, degree, vertices
 using PythonCall: Py, pyimport, pyconvert
 using Distances: cosine_dist
+using MolecularGraph: smilestomol, MolGraph, add_hydrogens!
+using SparseArrays: SparseVector, sparsevec, spzeros, findnz
 
 # Set seed for reproducibility across all tests
 seed!(42)

test/runtests.jl

@@ -1,3 +1,5 @@
+# ACKNOWLEDGEMENT: this code was partly written with the support of Microsoft Copilot AI (completion mode, not chat mode) 
+
 using MolecularFingerprints
 using Test