Merge pull request #3 from amorehead/develop

Develop to Master Checkpoint

Author: amorehead

.gitignore

@@ -131,4 +131,10 @@ project/datasets/DB5/final/final_raw_db5.tar.gz*
 project/datasets/EVCoupling/raw/**
 project/datasets/EVCoupling/interim/**
 project/datasets/EVCoupling/final/raw/**
-project/datasets/EVCoupling/final/processed/**
+project/datasets/EVCoupling/final/processed/**
+
+# CASP-CAPRI
+project/datasets/CASP-CAPRI/raw/**
+project/datasets/CASP-CAPRI/interim/**
+project/datasets/CASP-CAPRI/final/raw/**
+project/datasets/CASP-CAPRI/final/processed/**

README.md

@@ -203,7 +203,6 @@ tar -xzf project/datasets/DB5.tar.gz --directory project/datasets/
 
 # Remove (now) redundant DB5 archive and other miscellaneous files:
 rm project/datasets/DB5.tar.gz project/datasets/DB5/.README.swp
-rm project/datasets/DB5.tar.gz project/datasets/DB5/.README.swp
 rm -rf project/datasets/DB5/interim project/datasets/DB5/processed
 
 # Create relevant interim and final data directories:

project/datasets/DB5/README

@@ -1,25 +1,24 @@
 Cleaned up version of Docking Benchmark 5 (https://zlab.umassmed.edu/benchmark/). 
 
-Originally released with "End-to-End Learning on 3D Protein Structure for Interface Prediction."
+Released with "End-to-End Learning on 3D Protein Structure for Interface Prediction."
 by Raphael J.L. Townshend, Rishi Bedi, Patricia Suriana, Ron O. Dror
 https://arxiv.org/abs/1807.01297
 
 Specifically, bound chains and residue indexes were aligned across unbound and bound complexes.
 
 A total of 230 binary protein complexes are included.
 
-Processing code to regenerate and use the original provided tfrecords is located at
+Processing code to regenerate and use the provided tfrecords is located at
 https://github.com/drorlab/DIPS
 
-final/
-    raw/            - List of all postprocessed (i.e. feature-enriched) pairs.
+MANIFEST
 
+raw/            - All pre-aligned and cleaned DB5 structures, organized into directories 
+                  with individual files for ligand-unbound, ligand-bound, receptor-unbound, 
+                  receptor-bound.
 interim/
-    complexes/      - List of all possible pairs in parsed.
-    external_feats/ - List of all residue-level features generated using external software packages.
-    pairs/          - Dill files of individual pairs listed in complexes.
-    parsed/         - All DB5 structures processed to pickled dataframes.
-
-raw/                - All pre-aligned and cleaned DB5 structures, organized into directories
-                    with individual files for ligand-unbound, ligand-bound, receptor-unbound,
-                    receptor-bound.
+    parsed/     - All DB5 structures processed to pickled dataframes.
+    complexes/  - List of all possible pairs in parsed.
+    pairs/      - Dill files of indivudal pairs listed in complexes.
+processed/
+    tfrecords/  - pairs converted to tfrecords.