Apply suggestions from code review

Co-Authored-By: j3xugit <[email protected]>

content/04.study.md

@@ -326,7 +326,7 @@ Contact prediction is much more challenging than secondary structure prediction,
 Contact maps can broadly speaking be seen as distance maps with a specific distance cutoff applied.
 In recent years, the accuracy of contact prediction has greatly improved [@doi:10.1371/journal.pcbi.1005324; @doi:10.1093/bioinformatics/btu791; @doi:10.1073/pnas.0805923106; @doi:10.1371/journal.pone.0028766].
 
-Protein contact prediction and contact-assisted folding (i.e. folding proteins using predicted contacts as restraints) represents a promising new direction for *ab initio* folding of proteins without good templates in PDB.
+Protein contact prediction and contact-assisted folding (i.e. folding proteins using predicted contacts as restraints) has proven to be a successful direction for *ab initio* folding of proteins without good templates in PDB.
 Co-evolution analysis is effective for proteins with a very large number (>1000) of sequence homologs [@doi:10.1371/journal.pone.0028766], but fares poorly for proteins without many sequence homologs.
 By combining co-evolution information with a few other protein features, shallow neural network methods such as MetaPSICOV [@doi:10.1093/bioinformatics/btu791] and CoinDCA-NN [@doi:10.1093/bioinformatics/btv472] have shown some advantage over pure co-evolution analysis for proteins with few sequence homologs, but their accuracy is still far from satisfactory.
 In recent years, deeper architectures have been explored for contact prediction, such as CMAPpro [@doi:10.1093/bioinformatics/bts475], DNCON [@doi:10.1093/bioinformatics/bts598] and PConsC [@doi:10.1371/journal.pcbi.1003889].
@@ -335,10 +335,10 @@ However, blindly tested in the well-known CASP competitions, these methods did n
 RaptorX-Contact [@doi:10.1371/journal.pcbi.1005324] significantly improved contact prediction over MetaPSICOV and pure co-evolution methods, especially for proteins without many sequence homologs.
 It employed a network architecture formed by one 1D residual neural network and one 2D residual neural network. Blindly tested in the latest Critical Assesment of Structure Prediction (CASP) competition (i.e. CASP12 [@url:http://www.predictioncenter.org/casp12/rrc_avrg_results.cgi]), RaptorX-Contact ranked first in F₁ score on free-modeling targets as well as the whole set of targets. In CAMEO (which can be interpreted as a fully-automated CASP) [@url:https://www.cameo3d.org], its predicted contacts were also able to fold proteins with a novel fold and only 65--330 sequence homologs.
 This technique also worked well on membrane proteins even when trained on non-membrane proteins [@arxiv:1704.07207].
-RaptorX-Contact performed better mainly due to introduction of residual neural networks and exploitation of contact occurrence patterns by simultaneously predicting all the contacts in a single protein.
+RaptorX-Contact performed better mainly due to introduction of very deep convolutional residual neural networks and exploitation of contact occurrence patterns by simultaneously predicting all the contacts in a single protein.
 
 Most methods until late 2018 relied on just one distance threshold, simply defined by the ideal contact distance, to produce contact maps for 3D structure prediction.
-Recent seminal work presented at the 13th edition of CASP combined multiple distance cutoffs together with torsion prediction and a new folding pipeline to achieve state of the art results [@doi:10.1038/s41586-019-1923-7].
+Recent seminal work presented at the 13th edition of CASP combined multiple distance cutoffs together with torsion prediction and a new folding pipeline to achieve state of the art results [@doi:10.1073/pnas.1821309116; @doi:10.1038/s41586-019-1923-7].
 
 Taken together, *ab initio* folding is becoming much easier with the advent of direct evolutionary coupling analysis and deep learning techniques.