INHIBITORS OF THE ANDROGEN RECEPTOR DNA-BINDING DOMAIN GOVERNMENT SUPPORT CLAUSE This invention was made with government support under W81XWH-18-1-0584 awarded by the Medical Research and Development Command. The government has certain rights in the invention. CROSS REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Provisional Patent Application Serial No. 63/408,933 filed 22 September 2022 titled “NOVEL INHIBITORS OF ANDROGEN RECEPTOR’S DNA-BINDING DOMAIN”. TECHNICAL FIELD The present invention relates to therapeutic compounds and compositions, and meth- ods for their use in the treatment of various cancers. In particular, this invention re- lates to inhibitors of androgen receptor (AR) activity that target the DNA-bindng do- main (DBD) and their use in the treatment of diseases associated with or mediated by AR. BACKGROUND The androgen receptor (AR) is the main driver of prostate cancer (PCa), which is the most common malignancy in men, since AR activates the transcription of a variety of on- cogenes and stimulates cancer cell growth ^1-6 . The inhibition of AR with small mole- cules that compete with natural androgens is one of the primary strategies in PC ther- apy along with androgen synthesis ablation through castration ⁷ . However, PCa often relapses as a more aggressive castration-resistant PCa (CRPC) after it gains various mu- tations that confer resistance to common antiandrogen treatments ^8-10 . The mecha- nisms underlying such resistance include gain-of-function point mutations in the andro- gen-binding site (ABS) that prevent antagonistic action of the drugs as well as complete splicing of the ligand-binding domain (LBD) ^10-13 . For example, a well-characterized splice variant of AR V7 lacking the LBD was shown to activate gene expression of vari- ous oncogenes and drive the progression of PCa in an androgen-independent man- ner ^14,15 . Therefore, the development of new therapeutics that target AR signaling through other functionalities than LBS is crucial to alleviate the issue of drug-resistance through LBD mutations. We have previously reported the development of small molecules that target N-termi- nus domain (NTD) and DNA-binding domain (DBD) of AR ^16-21 . In particular, two dis- tinct mechanisms of DBD targeting have been utilized – a direct inhibition of the pro- tein-DNA interaction site (P-box) and disruption of AR DBD dimerization (D-box). The compounds binding at P-box and D-box successfully halted AR transcriptional activ- ity of both full-length and V7 splice variants, reduced the expression of prostate-specific antigen (PSA), a key biomarker of PCa, and reduced the viability in AR-expressing cells. Importantly, our previous compound VPC-14449 targeting the P-box was shown to in- hibit AR activity in cell lines resistant to conventional antiandrogen drugs such as en- zalutamide ²² . VPC-14449 was later used as a starting point for a SAR-guided develop- ment of a potent thiazole-based compound as well as a proteolysis-targeting chimera (PROTAC) ^23,24 . Collectively, these studies serve as proof of principle for LBD-inde- pendent AR inhibition. Despite the potent activity in vitro, the aforementioned compounds suffered from sub- optimal pharmacokinetic characteristics such as low microsomal stability that pre- vented them from entering animal studies. The attempts to optimize for these param- eters through subtle substitutions were challenging and often resulted in a loss of activ- ity, thus, proving that alternative chemotypes may be useful. SUMMARY This invention is based in part on the fortuitous discovery that compounds described herein od Formulas I-VI modulate androgen receptor (AR) activity. Specifically, compounds identified herein, show inhibition of Androgen Receptor the AR-DNA interface site (P-box) or the AR DBD dimerization site (D-box). In accordance with a first aspect, there is provided a method of inhibiting AR activity, the method including administering a compound may have the structure of Formula I: , wherein, A ¹ may be selected from N, CH and CCH ₃ ; A ² and A ³ may join G ² may be selected from F, Cl, and Br; D ¹ may be selected from CH ₃ , and H; D ² may be selected from C(=O)NH ₂ , CH ₃ , and H; D ³ may be selected from C(=O)NH ₂ , Cl, F, Br, CH ₃ , and H; alternatively, when A ¹ is N, A ¹ and D ¹ may form a five membered ring having the structure ; alternatively, D ² and D ³ may form a six membered ring having the structure and E may be selected from CN, C(=O)OCH ₃ , H, F, Cl, Br, and CH ₃ . Alternatively, D ² may be selected from C(=O)NH ₂ , and H. Alternatively, D ³ may be selected from Cl, F, CH ₃ , and H. Alternatively, E may be selected from CN, C(=O)OCH ₃ , H, F, Cl, and Br. Alternatively, E may be selected from CN, C(=O)OCH ₃ , H, and F. Alternatively, A ² and A ³ may join to form a 5 or 6 membered ring, wherein may

, In accordance with a further aspect, there is provided a method of inhibiting AR activity, the method including administering a compound may have the structure of Formula II: II, wherein, Q ¹ may be selected from H and CH ₃ ; Q ² may be selected from

F, Cl, and Br; G ⁴ may be selected from F, Cl, and Br; G ⁵ may be selected from F, Cl, and Br; G ⁶ may be selected from F, Cl, and Br; G ⁷ may be selected from F, Cl, and Br; G ⁸ may be selected from F, Cl, and Br; G ⁹ may be selected from F, Cl, and Br; G ¹⁰ may be selected from F, Cl, and Br; G ¹¹ may be selected from F, Cl, and Br; G ¹² may be selected from F, Cl, and Br; G ¹³ may be selected from F, Cl, and Br; and G ¹⁴ may be selected from F, Cl, and Br. In accordance with a further aspect, there is provided a method of inhibiting AR activity, the method including administering a compound may have the structure of one of Formulas III-VI: wherein, Q ³ may be selected from H and CH ₃ ; Q ⁴ may be selected from H and CH ₃ ; Q ⁵ may be selected from H and CH ₃ ; Q ⁸ may be selected from H and CH ₃ ; Q ⁶ and Q ⁷ may form a substituted six membered ring having the structure and Q ¹⁰ may form a substituted six membered ring having the structure selected from may be selected from , , may be selected from F, Cl, and Br; G ¹⁶ may be selected from F, Cl, and Br; G ¹⁷ may be selected from F, Cl, and Br; G ¹⁸ may be selected from F, Cl, and Br; G ¹⁹ may be selected from F, Cl, and Br; G ²⁰ may be selected from F, Cl, and Br; G ²¹ may be selected from F, Cl, and Br; G ²² may be selected from F, Cl, and Br; G ²³ may be selected from F, Cl, and Br; G ²⁴ may be selected from F, Cl, and Br; G ²⁵ may be selected from F, Cl, and Br; G ²⁶ may be selected from F, Cl, and Br; G ²⁷ may be selected from F, Cl, and Br; and G ²⁸ may be selected from F, Cl, and Br.

Alternatively, Z ⁸ may be selected from D ³ may be selected from Cl, F, CH ₃ , and H. E may be selected from CN, C(=O)OCH ₃ , H, and F. G ¹ may be F. G ² may be F. G ³ may be Cl. G ⁴ may be F. G ⁵ may be Cl. G ⁶ may be Cl. G ⁷ may be F. G ⁸ may be Cl. G ⁹ may be Br. G ¹⁰ may be Cl. G ¹¹ may be F. G ¹² may be F. G ¹³ may be F. G ¹⁴ may be Cl. G ¹⁵ may be Cl. G ¹⁶ may be Cl. G ¹⁷ may be Cl. G ¹⁸ may be Br. G ¹⁹ may be Br. G ²⁰ may be Cl. G ²¹ may be Cl. G ²² may be Cl. G ²³ may be Cl. G ²⁴ may be Cl. G ²⁵ may be F. G ²⁶ may be Cl. G ²⁷ may be Br. G ²⁸ may be F. The compound of Formula II wherein at least one of Q ¹ and Q ² is H. The inhibition of the androgen receptor may be for the treatment of cancer. The inhibition of the androgen receptor may be for the treatment of one or more of the following: cervical cancer; small-cell lung cancer; testicular cancer; carcinoma; neuroblastoma; osteosarcoma; glioblastoma; melanoma; lymphoma; leukemia; esophageal cancer; stomach cancer; colon cancer; breast cancer; ovarian cancer; endometrial cancer; chondrosarcomas; central nervous system cancer; liver cancer; prostate cancer, hair loss, acne, hirsutism, ovarian cysts, polycystic ovary disease, precocious puberty, Kennedy’s disease, and age-related macular degeneration. The prostate cancer may be selected from: Neuroendocrine Prostate Cancer (NEPC); Prostate Adenocarcinoma; castration resistant prostate cancer (CRPC); androgen receptor pathway inhibitor (ARPI) resistant prostate cancer; enzalutamide (ENZ)- resistant (ENZ ^R ); and Abiraterone (Abi)-resistant (ABI _R ).

The compound may be selected from one or more of the following: The compound may be selected from and . In accordance with a further aspect, there is provided a pharmaceutical composition including compound of Formulas I-VI and a pharmaceutically acceptable carrier, for the treatment of one or more of the following: cervical cancer; small-cell lung cancer; testicular cancer; carcinoma; neuroblastoma; osteosarcoma; glioblastoma; melanoma; lymphoma; leukemia; esophageal cancer; stomach cancer; colon cancer; breast cancer; ovarian cancer; endometrial cancer; chondrosarcomas; central nervous system cancer; liver cancer; prostate cancer, hair loss, acne, hirsutism, ovarian cysts, polycystic ovary disease, precocious puberty, Kennedy’s disease, and age-related macular degeneration. In accordance with a further aspect, there is provided a pharmaceutical composition including compound of Formulas I-VI and a pharmaceutically acceptable carrier, for the treatment of prostate cancer which may be selected from: Neuroendocrine Prostate Cancer (NEPC); Prostate Adenocarcinoma; castration resistant prostate cancer (CRPC); androgen receptor pathway inhibitor (ARPI) resistant prostate cancer; enzalutamide (ENZ)-resistant (ENZ ^R ); and Abiraterone (Abi)-resistant (ABIR). In accordance with a further aspect, there is provided a use of a compound of Formulas I-VI for the treatment of one or more of the following: cervical cancer; small-cell lung cancer; testicular cancer; carcinoma; neuroblastoma; osteosarcoma; glioblastoma; melanoma; lymphoma; leukemia; esophageal cancer; stomach cancer; colon cancer; breast cancer; ovarian cancer; endometrial cancer; chondrosarcomas; central nervous system cancer; liver cancer; prostate cancer, hair loss, acne, hirsutism, ovarian cysts, polycystic ovary disease, precocious puberty, Kennedy’s disease, and age-related macular degeneration. In accordance with a further aspect, there is provided a use of a compound of Formulas I-VI in the manufacture of a medicament for treating one or more of the following: cervical cancer; small-cell lung cancer; testicular cancer; carcinoma; neuroblastoma; osteosarcoma; glioblastoma; melanoma; lymphoma; leukemia; esophageal cancer; stomach cancer; colon cancer; breast cancer; ovarian cancer; endometrial cancer; chondrosarcomas; central nervous system cancer; liver cancer; prostate cancer, hair loss, acne, hirsutism, ovarian cysts, polycystic ovary disease, precocious puberty, Kennedy’s disease, and age-related macular degeneration. In accordance with a further aspect, there is provided a commercial package comprising (a) a compound of any one of Formulas I-VI and a pharmaceutically acceptable carrier; and (b) instructions for the use thereof for treating one or more of the following: cervical cancer; small-cell lung cancer; testicular cancer; carcinoma; neuroblastoma; osteosarcoma; glioblastoma; melanoma; lymphoma; leukemia; esophageal cancer; stomach cancer; colon cancer; breast cancer; ovarian cancer; endometrial cancer; chondrosarcomas; central nervous system cancer; liver cancer; prostate cancer, hair loss, acne, hirsutism, ovarian cysts, polycystic ovary disease, precocious puberty, Kennedy’s disease, and age-related macular degeneration. In accordance with a further aspect, there is provided a commercial package comprising (a) a pharmaceutical composition comprising a compound of any one of Formulas I-VI and a pharmaceutically acceptable carrier; and (b) instructions for the use thereof for treating prostate cancer. In accordance with a further aspect, there is provided a use of a compound having the structure of Formulas I-VI as described herein for inhibiting AR activity. In accordance with a further aspect, there is provided a use of a compound having the structure of Formulas I-VI as described herein for the manufacture of a medicament for inhibiting AR activity. The compound may be for use in the treatment of at least one indication selected from the group including: prostate cancer, breast cancer, ovarian cancer, endometrial cancer, hair loss, acne, hirsutism, ovarian cysts, polycystic ovary disease, precocious puberty, Kennedy’s disease, and age-related macular degeneration. The inhibiting AR activity may be for the treatment of at least one indication selected from the group including: prostate cancer, breast cancer, ovarian cancer, endometrial cancer, hair loss, acne, hirsutism, ovarian cysts, polycystic ovary disease, precocious puberty, Kennedy’s disease, and age-related macular degeneration. BRIEF DESCRIPTION OF THE DRAWINGS FIGURE 1 shows in silico screening against P-box and D-box on the surface of the Androgen Receptor (AR) DNA Binding Domain (DBD), where A shows tha AR DBD dimer with P-box with VPC-14449 docked and D-box with VPC-17005 docked shaded and DNA ribbon interacting with the P-box; B shows a schematic of the in silico screening pipeline workflow, indicating the number of D-box and P-box compounds after each step in the workflow pipeline; C shows the pharmacophore model built to select compounds for the D-box and was based on the common features of VPC-17005, VPC-17160, VPC-17121, and VPC-17281; and D shows the pharmacophore model built to select compounds for the P-box and was based on the common features of VPC- 14449. FIGURE 2 shows two compounds identifed through the in silico screening, VPC-14668 and VPC-17493, that were further tested for inhibiting the transcriptional activity of AR full length and AR-V7. A Left: structure of VPC-14668; Right: structure of VPC-17493. B shows the inhibition of AR full-length transcriptional activity in reporter eGFP assay in LNCaP cells. C shows the inhibition of AR V7 transcriptional activity in reporter eGFP assay in PC3 cells. D shows the direct effects on Nanoluciferase expression in a PC3 cell line transfected with Nanoluciferase and lacking AR. E shows the inhibition of AR-regulated PSA expression in LNCaP cells. Data points represent a pool of triplicate for each concentration. FIGURE 3 shows ligand-protein interactions of VPC-14668 (left) and VPC-17493 (right), with hydrophobic residues Pro 613, Ala 587 and Phe 583 in A and Ala 597, Pro 613, and Leu 595 in B, with polar residues Gln 592, Tyr 594, Arg 586, Arg 609, Ser 579Arg 616, and Lys 610 in A, and Arg 608, Asn 611, Thr 603, Cys 602 Ser 598 and Cys 612 in B, while the shading respresents solvent exposed areas. DETAILED DESCRIPTION The following detailed description will be better understood when read in conjunction with the appended figures. For the purpose of illustrating the invention, the figures demonstrate embodiments of the present invention. However, the invention is not limited to the precise arrangements, examples, and instrumentalities shown. We launched a computer-aided drug design (CADD)-based screening against the two sites on the surface of DBD: the AR-DNA interface site (P-box) and the AR DBD dimeri- zation site (D-box). Importantly, while previous studies derived the hits from rela- tively small virtual screenings of up to 3 million compounds, in this study, we imple- mented an ultra-large screening using our in-house developed AI-facilitated docking ap- proach, called DeepDocking ²⁵ . The use of ultra-large libraries has been proven to aid the discovery of new chemotypes ^26,27 . Herein, we present two chemical scaffolds, VPC-14668 and VPC-17493, that emerged as hit compounds from an AI-facilitated vir- tual screening of over 1 billion chemicals. These molecules were designed to bind P- and D-boxes, respectively, and represent unexplored chemical scaffolds that are not found in conventional ‘in-stock’ libraries. Both compounds were further shown to suppress the transcriptional activity of AR and AR V7 splice variants. It will be understood by a person of skill that COOH and NR2 may include the corre- sponding ions, for example carboxylate ions and ammonium ions, respectively. Alter- natively, where the ions are shown, a person of skill in the art will appreciate that the counter ion may also be present. Those skilled in the art will appreciate that the point of covalent attachment of the moi- ety to the compounds as described herein may be, for example, and without limitation, cleaved under specified conditions. Specified conditions may include, for example, and without limitation, in vivo enzymatic or non-enzymatic means. Cleavage of the moiety may occur, for example, and without limitation, spontaneously, or it may be cat- alyzed, induced by another agent, or a change in a physical parameter or environmental parameter, for example, an enzyme, light, acid, temperature or pH. The moiety may be, for example, and without limitation, a protecting group that acts to mask a functional group, a group that acts as a substrate for one or more active or passive transport mech- anisms, or a group that acts to impart or enhance a property of the compound, for exam- ple, solubility, bioavailability or localization. In some embodiments, compounds of Formulas I-VI, as described herein, may be used for systemic treatment of at least one indication selected from the group consisting of: cervical cancer; small-cell lung cancer; testicular cancer; carcinoma; neuroblastoma; os- teosarcoma; glioblastoma; melanoma; lymphoma; leukemia; esophageal cancer; stom- ach cancer; colon cancer; breast cancer; ovarian cancer; endometrial cancer; chondro- sarcomas; central nervous system cancer; liver cancer; and prostate cancer. Alterna- tively, the compounds of Formulas II and III may be used for systemic treatment of at least one indication selected from the group consisting of:prostate cancer; breast can- cer; colon cancer; cervical cancer; small-cell lung carcinoma; neuroblastomas; osteosar- coma; glioblastoma; melanoma; and myeloid leukaemia. In some embodiments com- pounds of Formulas II and III may be used in the preparation of a medicament or a com- position for systemic treatment of an indication described herein. In some embodi- ments, methods of systemically treating any of the indications described herein are also provided. Compounds as described herein may be in the free form or in the form of a salt thereof. In some embodiment, compounds as described herein may be in the form of a pharma- ceutically acceptable salt, which are known in the art (Berge S. M. et al., J. Pharm. Sci. (1977) 66(1):1-19). Pharmaceutically acceptable salt as used herein includes, for ex- ample, salts that have the desired pharmacological activity of the parent compound (salts which retain the biological effectiveness and/or properties of the parent com- pound and which are not biologically and/or otherwise undesirable). Compounds as described herein having one or more functional groups capable of forming a salt may be, for example, formed as a pharmaceutically acceptable salt. Compounds containing one or more basic functional groups may be capable of forming a pharmaceutically ac- ceptable salt with, for example, a pharmaceutically acceptable organic or inorganic acid. Pharmaceutically acceptable salts may be derived from, for example, and without limita- tion, acetic acid, adipic acid, alginic acid, aspartic acid, ascorbic acid, benzoic acid, ben- zenesulfonic acid, butyric acid, cinnamic acid, citric acid, camphoric acid, camphorsul- fonic acid, cyclopentanepropionic acid, diethylacetic acid, digluconic acid, dodecyl- sulfonic acid, ethanesulfonic acid, formic acid, fumaric acid, glucoheptanoic acid, glu- conic acid, glycerophosphoric acid, glycolic acid, hemisulfonic acid, heptanoic acid, hexa- noic acid, hydrochloric acid, hydrobromic acid, hydriodic acid, 2-hydroxyethanesulfonic acid, isonicotinic acid, lactic acid, malic acid, maleic acid, malonic acid, mandelic acid, methanesulfonic acid, 2-napthalenesulfonic acid, naphthalenedisulphonic acid, p-tol- uenesulfonic acid, nicotinic acid, nitric acid, oxalic acid, pamoic acid, pectinic acid, 3- phenylpropionic acid, phosphoric acid, picric acid, pimelic acid, pivalic acid, propionic acid, pyruvic acid, salicylic acid, succinic acid, sulfuric acid, sulfamic acid, tartaric acid, thiocyanic acid or undecanoic acid. Compounds containing one or more acidic func- tional groups may be capable of forming pharmaceutically acceptable salts with a phar- maceutically acceptable base, for example, and without limitation, inorganic bases based on alkaline metals or alkaline earth metals or organic bases such as primary amine compounds, secondary amine compounds, tertiary amine compounds, quater- nary amine compounds, substituted amines, naturally occurring substituted amines, cy- clic amines or basic ion-exchange resins. Pharmaceutically acceptable salts may be derived from, for example, and without limitation, a hydroxide, carbonate, or bicar- bonate of a pharmaceutically acceptable metal cation such as ammonium, sodium, po- tassium, lithium, calcium, magnesium, iron, zinc, copper, manganese or aluminum, am- monia, benzathine, meglumine, methylamine, dimethylamine, trimethylamine, ethyla- mine, diethylamine, triethylamine, isopropylamine, tripropylamine, tributylamine, etha- nolamine, diethanolamine, 2-dimethylaminoethanol, 2-diethylaminoethanol, dicyclo- hexylamine, lysine, arginine, histidine, caffeine, hydrabamine, choline, betaine, ethylene- diamine, glucosamine, glucamine, methylglucamine, theobromine, purines, piperazine, piperidine, procaine, N-ethylpiperidine, theobromine, tetramethylammonium com- pounds, tetraethylammonium compounds, pyridine, N,N-dimethylaniline, N-methylpi- peridine, morpholine, N-methylmorpholine, N-ethylmorpholine, dicyclohexylamine, dibenzylamine, N,N-dibenzylphenethylamine, 1-ephenamine, N,N'-dibenzylethylenedia- mine or polyamine resins. In some embodiments, compounds as described herein may contain both acidic and basic groups and may be in the form of inner salts or zwit- terions, for example, and without limitation, betaines. Salts as described herein may be prepared by conventional processes known to a person skilled in the art, for exam- ple, and without limitation, by reacting the free form with an organic acid or inorganic acid or base, or by anion exchange or cation exchange from other salts. Those skilled in the art will appreciate that preparation of salts may occur in situ during isolation and purification of the compounds or preparation of salts may occur by separately reacting an isolated and purified compound. In some embodiments, compounds and all different forms thereof (e.g. free forms, salts, polymorphs, isomeric forms) as described herein may be in the solvent addition form, for example, solvates. Solvates contain either stoichiometric or non-stoichiometric amounts of a solvent in physical association the compound or salt thereof. The sol- vent may be, for example, and without limitation, a pharmaceutically acceptable solvent. For example, hydrates are formed when the solvent is water or alcoholates are formed when the solvent is an alcohol. In some embodiments, compounds and all different forms thereof (e.g. free forms, salts, solvates, isomeric forms) as described herein may include crystalline and amorphous forms, for example, polymorphs, pseudopolymorphs, conformational polymorphs, amorphous forms, or a combination thereof. Polymorphs include different crystal packing arrangements of the same elemental composition of a compound. Poly- morphs usually have different X-ray diffraction patterns, infrared spectra, melting points, density, hardness, crystal shape, optical and electrical properties, stability and/or solubility. Those skilled in the art will appreciate that various factors includ- ing recrystallization solvent, rate of crystallization and storage temperature may cause a single crystal form to dominate. In some embodiments, compounds and all different forms thereof (e.g. free forms, salts, solvates, polymorphs) as described herein include isomers such as geometrical isomers, optical isomers based on asymmetric carbon, stereoisomers, tautomers, individual en- antiomers, individual diastereomers, racemates, diastereomeric mixtures and combina- tions thereof, and are not limited by the description of the formulas illustrated for the sake of convenience. In some embodiments, pharmaceutical compositions as described herein may comprise a salt of such a compound, preferably a pharmaceutically or physiologically acceptable salt. Pharmaceutical preparations will typically comprise one or more carriers, excipi- ents or diluents acceptable for the mode of administration of the preparation, be it by injection, inhalation, topical administration, lavage, or other modes suitable for the se- lected treatment. Suitable carriers, excipients or diluents (used interchangeably herein) are those known in the art for use in such modes of administration. Suitable pharmaceutical compositions may be formulated by means known in the art and their mode of administration and dose determined by the skilled practitioner. For parenteral administration, a compound may be dissolved in sterile water or saline or a pharmaceutically acceptable vehicle used for administration of non-water soluble com- pounds such as those used for vitamin K. For enteral administration, the compound may be administered in a tablet, capsule or dissolved in liquid form. The tablet or cap- sule may be enteric coated, or in a formulation for sustained release. Many suitable formulations are known, including, polymeric or protein microparticles encapsulating a compound to be released, ointments, pastes, gels, hydrogels, or solutions which can be used topically or locally to administer a compound. A sustained release patch or im- plant may be employed to provide release over a prolonged period of time. Many techniques known to one of skill in the art are described in Remington: the Science & Practice of Pharmacy by Alfonso Gennaro, 20th ed., Lippencott Williams & Wilkins, (2000). Formulations for parenteral administration may, for example, contain excipi- ents, polyalkylene glycols such as polyethylene glycol, oils of vegetable origin, or hydro- genated naphthalenes. Biocompatible, biodegradable lactide polymer, lactide/gly- colide copolymer, or polyoxyethylene polyoxypropylene copolymers may be used to control the release of the compounds. Other potentially useful parenteral delivery systems for modulatory compounds include ethylene vinyl acetate copolymer particles, osmotic pumps, implantable infusion systems, and liposomes. Formulations for inha- lation may contain excipients, for example, lactose, or may be aqueous solutions con- taining, for example, polyoxyethylene 9 lauryl ether, glycocholate and deoxycholate, or may be oily solutions for administration in the form of nasal drops, or as a gel. Compounds or pharmaceutical compositions as described herein or for use as described herein may be administered by means of a medical device or appliance such as an im- plant, graft, prosthesis, stent, etc. Also, implants may be devised which are intended to contain and release such compounds or compositions. An example would be an im- plant made of a polymeric material adapted to release the compound over a period of time. An “effective amount” of a pharmaceutical composition as described herein includes a therapeutically effective amount or a prophylactically effective amount. A “therapeu- tically effective amount” refers to an amount effective, at dosages and for periods of time necessary, to achieve the desired therapeutic result, such as reduced tumor size, increased life span or increased life expectancy. A therapeutically effective amount of a compound may vary according to factors such as the disease state, age, sex, and weight of the subject, and the ability of the compound to elicit a desired response in the subject. Dosage regimens may be adjusted to provide the optimum therapeutic re- sponse. A therapeutically effective amount is also one in which any toxic or detri- mental effects of the compound are outweighed by the therapeutically beneficial effects. A “prophylactically effective amount” refers to an amount effective, at dosages and for periods of time necessary, to achieve the desired prophylactic result, such as smaller tu- mors, increased life span, increased life expectancy or prevention of the progression of prostate cancer to an androgen independent form. Typically, a prophylactic dose is used in subjects prior to or at an earlier stage of disease, so that a prophylactically effec- tive amount may be less than a therapeutically effective amount. It is to be noted that dosage values may vary with the severity of the condition to be al- leviated. For any particular subject, specific dosage regimens may be adjusted over time according to the individual need and the professional judgment of the person ad- ministering or supervising the administration of the compositions. Dosage ranges set forth herein are exemplary only and do not limit the dosage ranges that may be selected by medical practitioners. The amount of active compound(s) in the composition may vary according to factors such as the disease state, age, sex, and weight of the subject. Dosage regimens may be adjusted to provide the optimum therapeutic response. For example, a single bolus may be administered, several divided doses may be adminis- tered over time or the dose may be proportionally reduced or increased as indicated by the exigencies of the therapeutic situation. It may be advantageous to formulate par- enteral compositions in dosage unit form for ease of administration and uniformity of dosage. In some embodiments, compounds and all different forms thereof as described herein may be used, for example, and without limitation, in combination with other treatment methods for at least one indication selected from the group consisting of: cervical can- cer; small-cell lung cancer; testicular cancer; carcinoma; neuroblastoma; osteosarcoma; glioblastoma; melanoma; lymphoma; leukemia; esophageal cancer; stomach cancer; co- lon cancer; breast cancer; ovarian cancer; endometrial cancer; chondrosarcomas; cen- tral nervous system cancer; liver cancer; and prostate cancer. Alternatively, the com- pounds described herein may be useful for the treatment of one or more of the follow- ing: cervical cancer, small-cell lung cancer, testicular cancer, lymphoma, leukemia, esophageal cancer, stomach cancer, colon cancer, breast cancer, ovarian cancer, endo- metrial cancer, chondrosarcomas, central nervous system cancer, liver cancer and pros- tate cancer. For example, compounds and all their different forms as described herein may be used as neo-adjuvant (prior), adjunctive (during), and/or adjuvant (after) ther- apy with surgery, radiation (brachytherapy or external beam), or other therapies (for example, HIFU). Furthermore, the compounds described herein may be administered with or combined with known chemotherapeutic treatments. For example, a com- pound of any one of Formulas I-VI may be administered in combination with taxols and Topoisomerase poisons, as well as in combination with androgen receptor (AR) thera- pies (for example, ADT, ARPIs, etc.) for prostate cancer (PCa). In general, compounds as described herein should be used without causing substantial toxicity. Toxicity of the compounds as described herein can be determined using standard techniques, for example, by testing in cell cultures or experimental animals and determining the therapeutic index, i.e., the ratio between the LD50 (the dose lethal to 50% of the population) and the LD100 (the dose lethal to 100% of the population). In some circumstances however, such as in severe disease conditions, it may be appro- priate to administer substantial excesses of the compositions. Some compounds as described herein may be toxic at some concentrations. Titration studies may be used to determine toxic and non-toxic concentrations. Toxicity may be evaluated by exam- ining a particular compound’s or composition’s specificity across cell lines using PC3 cells as a negative control that do not express AR. Animal studies may be used to pro- vide an indication if the compound has any effects on other tissues. Systemic therapy that targets the AR will not likely cause major problems to other tissues since anti-an- drogens and androgen insensitivity syndrome are not fatal. Compounds as described herein may be administered to a subject. As used herein, a “subject” may be a human, non-human primate, rat, mouse, cow, horse, pig, sheep, goat, dog, cat, etc. The subject may be suspected of having or at risk for having a cancer, such as cervical cancer; small-cell lung cancer; testicular cancer; carcinoma; neuroblas- toma; osteosarcoma; glioblastoma; melanoma; lymphoma; leukemia; esophageal can- cer; stomach cancer; colon cancer; breast cancer; ovarian cancer; endometrial cancer; chondrosarcomas; central nervous system cancer; liver cancer; and prostate cancer. Diagnostic methods for various cancers, such as cervical cancer, small-cell lung cancer, testicular cancer, lymphoma, leukemia, esophageal cancer, stomach cancer, colon can- cer, breast cancer, ovarian cancer, endometrial cancer, chondrosarcomas, central nerv- ous system cancer, liver cancer and prostate cancer, are known to those of ordinary skill in the art. All compounds specifically described herein are commercially available. Further- more, modifications to those compounds would be possible based on the knowledge of a person of skill in the art. Various alternative embodiments and examples are described herein. These embodi- ments and examples are illustrative and should not be construed as limiting the scope of the invention. MATERIALS AND METHODS Virtual Screening For structure-based virtual screening, we used the crystal structure of rat AR DBD bound to DR3 oligonucleotide (PDB:1R4I) ²⁸ . The structure was prepared using Pro- tein Preparation Wizard™ from Schrödinger™ ^29,30 . In detail, hydrogen atoms were added, the energy of the system was minimized, bond orders were assigned and missing side chains were added with the Prime module. Small molecule library was downloaded from ZINC20™ ³¹ database and prepared with OpenEye Omega™ software ³² . In particular, the preparation process involved proto- nation, partial charge assignment and energy minimization. The docking with GlideSP™ (Schrodinger) was performed using standard settings. The docking with ICM was performed using a thoroughness of 5. DeepDocking™ was set to run for 5 iterations with other steps as outlined in the protocol publication ³³ . Pharmacophore model development and screening were also performed using MOE software ³⁴ . Molecular dynamics™ (MD) were performed using Desmond package from Schrodinger™ ³⁵ . The structure as solvated using System Builder™ package from Schrodinger™ using simple point charge (SPC) water model ³⁶ and neutralized by add- ing Na+ ions. The system was build using the OPLS3e force field ³⁷ . The simulations were carried out with 2-femtosecond time step using constant-pressure (NPT) ensem- ble at 300K and pressure of 1.03 bar. Each simulation recorded 1000 frames that were then analyzed using Simulation Interactions Diagram™ module (Schrodinger™). Compounds All compounds identified through virtual screening were purchased from Enamine™ (https://enamine.net/). Plasmids and constructructs Full-length human AR (hARWT) was encoded on pcDNA3.1 expression plasmid. Lentivi- rus plasmid pLIX402-ARV7 (ARV7 cDNA, doxycycline inducible promoter, puromycin selection), was a gift from Dr. N. Lack. pLIX402-Na4.2. PCa cell lines LNCaP (ATCC, CRL-1740) and PC-3 (ATCC, CRL-1435) cells were obtained in 2013 and authenticated by IDEXX Laboratories™ every 6 months. The cell lines are tested for mycoplasma contamination every two weeks. Reporter assays and cell viability experiments LNCaP cells incorporating an AR2PB-eGFP reporter construct (2 x probasin) are previ- ously described ³⁸ . eGFP and secreted PSA assays were performed as described ^18,38 . PC3_iV7 + 3TKNLuc cell line generation is previously described ²¹ . Nanoluciferase™ reporter assays were performed by treating the cells with 200ng/mL Doxycycline and compounds overnight, and cell lysis with Nano-Glo Luciferase™ reagent (Promega™). Luminescence detection was carried out on a TECAN m200pro™ luminometer. EXAMPLES Example 1: In Silico Screening To identify novel chemotypes that target AR DBD, we employed in-house computer- aided drug design (CADD) pipeline that relies on Deep Docking™ ¹⁷ . For both of the targets on the surface of AR DBD, P- and D-box sites, separate in silico screenings were initiated (FIGURE 1A, B). First, to assess the performance of molecular docking software, we collected a set of ac- tive compounds identified in our previous studies ^16,18,21 . For P-box, we selected 11 compounds that suppress AR full length and AR V7 transcriptional activity. For D-box, we selected 17 compounds that were active in AR full-length assay and showed antidi- merization effects. For each subset, we then generated 50 decoys per active molecule using the Database of Useful Decoys: Enhanced (DUD-E™) ³⁹ . We then docked the ac- tive compounds and corresponding decoys using four docking software available in our laboratory: Glide™ ³⁵ , ICM™, OpenEye FRED™ ⁴⁰ and AutoDock™ ⁴¹ . We then calculated AUC scores with the output docking scores to estimate how well each software sepa- rates actives from decoys. For both sites, Glide™ performed the best with 0.62 and 0.82 ROC AUC scores (P-box and D-box, respectively) followed by ICM™ (AUC of 0.59 and 0.76), Autodock™ and FRED™. The performance of FRED™ and Autodock™ on both sites was close to random with AUC scores around 0.5. Thus, these docking pro- grams were not considered for further use. Next, we screened an ultra-large library comprising 1.4 billion molecules from ZINC20™ database ³¹ . The initial screening was performed using our in-house developed AI- based tool that accelerates docking called DeepDocking™ ²⁵ . Briefly, a random sample from the ZINC20™ database was first docked with GlideSP™ and used to train a neural network that predicts docking scores for the site of interest. The docking scores of the remaining molecules were then predicted and the best-predicted molecules were used to train another neural network. This process is repeated reducing the number of molecules left after each iteration and enriching an average docking score. Thus, from 1.4 billion compounds passed through five iterations of DeepDocking™, we ended up with 15 million and 17 million compounds (see FIGURE 1B) with predicted low docking scores for P-box and D-box, respectively. These molecules were then docked with GlideSP™ and compounds that exhibited scores better than those of our previously iden- tified inhibitors (-4.7 for VPC-14449 targeting P-box; -7.5 for VPC-17005 targeting D- box) were selected. We then performed consensus scoring as it was shown to be an effective strategy to improve docking results and enrich the selection set ^42,43 . In- formed from the decoy experiment that Glide™ and ICM™ perform the best on both sites, we docked the remaining compounds with ICM™ software and computed dis- tances between Glide™-predicted and ICM™predicted poses. The compounds with predicted poses differing by more than 2 Angstrom were removed criteria were based on the properties of active compounds from previous screening campaigns ^18,21 . Fi- nally, we eliminated compounds with poor predicted ADMET profiles. To perform the final selection, we constructed pharmacophore models using the knowledge about our previously identified hit compounds ^18,19,21 . For P-box, we learned through mutagenesis studies (with VPC-14449) that interaction with Tyr594 is important for binding. Thus, hydrogen bonding with Tyr594 was set as a necessary pharmacophore feature and compounds with a docking pose lacking this interaction were filtered out (FIGURE 1C). For D-box, we examined the binding poses of previ- ously published inhibitors (i.e. VPC-17005, VPC-17160, VPC-17121, and VPC-17281) and derived a pharmacophore model containing two aromatic features and one hydro- gen bond acceptor (FIGURE 1D). Importantly, we ran a 50ns molecular dynamics simulation with VPC-17005 in the D-box site to determine the relative importance of the interactions. We observed that a hydrogen bond formed with a zinc atom bound to a cystine was maintained throughout 100% of the simulation. Thus, the presence of a hydrogen acceptor at the junction between two aromatic groups was considered an im- portant feature and was used to filter down the D-box selection set. Finally, we ap- plied pKi scoring implemented in Molecular Operating Environment™ ³⁴ for both sets. The compounds that passed all stages of filtering were then ranked by glide score, glide ligand efficiency score, ICM™ score and pKi score. The top 20-40 molecules from each ranking were selected. The ranking by different metrics allows diversifying the selec- tion set as scorings have implicit biases. The final sets purchased for experimental validation contained 160 and 270 compounds for P-box and D-box, respectively. Example 2: Selected Compounds Reduce AR Full Length and AR V7 Transcrip- tional Activity The purchased compounds were first tested for inhibition of full-length AR transcrip- tional activity. The AR-enhanced green fluorescent protein (eGFP) assay was per- formed in LNCaP cells, where an androgen-inducible probation-derived promoter con- trols the expression of eGFP ³⁸ . From P-box selection, 23 compounds showed more than 50% inhibition at 10µM concentration while from D-box, 54 compounds passed the threshold. Thus, given that we tested 160 and 270 compounds from each selec- tion, respectively, hit rates from the initial screening were roughly equal to 14% and 20%. Then, we performed dose-dependent titration against a full-length AR eGFP as- say. The IC ₅₀ s for 18 compounds that produced a smooth downward curve ranged from 0.28 to 26.8 µM. Hit compounds VPC-17493 and VPC-14668 exhibited an IC50 of 0.28 and 0.9, respectively (FIGURE 2A, B). To prove that the designed compounds inhibit AR transcriptional activity through bind- ing to DBD, we performed a nanoluciferase assay on the AR V7 splice variant with two of the AR inhibitory compounds. The assay was performed in PC3 cells transfected with AR-V7 cDNA and the ARR3tk-nanoLuciferase reporter construct. Whereby the activation of nanoluciferase was an indication AR-V7 transcriptional activity. Two compounds, VPC-17493 and VPC-14668, exhibited complete inhibition of AR V7 tran- scriptional activity at 10 µM. To deduce the dose-dependent effects of these com- pounds, the cells were treated with increasing concentrations of the compounds and doxycycline. The IC50s for compounds VPC-17493 and VPC-14668 in AR V7 are equal to ~10 and 12 µM, respectively (FIGURE 2C). To rule out the possibility that the observed inhibition could be due to direct effects on the NanoLuciferase™ reporter, we performed the nanoluciferase assay in PC3 cells ex- pressing Dox-inducible nanoluciferase without AR. Both VPC-17493 and VPC-14668 were inactive in this assay proving the absence of assay interference activity (FIGURE 2D). Additionally, we tested the toxicity effects on PC3 cells PrestoBlue™ assay. Both of the selected compounds showed less than 10% toxicity at 10 µM. Finally, we tested the expression of AR-regulated prostate-specific antigen (PSA), which is a well-established biomarker of PC ⁴⁴ , in response to treatment with the selected hit compounds. We observed a dose-dependent reduction in PSA production with IC ⁵⁰ s of 0.3 and 0.9 for VPC-14668 and VPC-17493, respectively (FIGURE 2E). AR plays a significant role in the development and progression of PC. Conventional AR blockers (anti-androgens) bind to the ABS site on LBD, which is susceptible to muta- tions that confer resistance to chemotherapy. In our previous studies, we showed that inhibiting AR at DBD is an effective strategy to block AR transcriptional activity. Herein, we demonstrate how the use of an AI-accelerated CADD campaign helps to iden- tify novel AR inhibitors. The hit compounds, VPC-14668 and VPC-17493, were discov- ered through screening campaigns that targeted the DNA-binding interface site, namely the P-box, and dimerization site, namely D-box, respectively. Both of the compounds effectively block the transcriptional activity of AR full length as well as splice variant AR V7. Importantly, PC cells that acquire AR V7 become resistant to widely used anti-an- drogens such as enzalutamide and drive the development of highly metastatic forms of PCa ^13,45 . Thus, the development of candidate drugs that target AR V7 represents an attractive alternative therapeutic strategy. Furthermore, VPC-14668 and VPC-17493 reduced the levels of PSA, a PCa biomarker, in a PCa cell line. As AR tightly regulates the production of PSA, the reduction in PSA levels indicates successful inhibition of AR signaling. The use of CADD techniques enables finding novel chemotypes with desired bioactivi- ties and further adds to the growing body of research advocating for ultra-large screen- ings in drug discovery ^26,27,46,47 . Both of the identified hits, VPC-14668 and VPC-17493, represent unexplored chemical scaffolds that are not present in the standard ‘in-stock’ libraries of the ZINC20 database ³¹ . These compounds are stored in the ‘make-on-de- mand’ libraries that grow each year and are projected to exceed 100 billion soon ⁴⁸ . Thus, the identification of those compounds would be unlikely with conventional molec- ular docking techniques that allow the screening of up to a few million compounds with a generous amount of computational resources. Therefore, as the available chemical space grows each year, the use of tools that accelerate virtual screening, such as DeepDocking™, is useful to effectively screen for new potent drug candidates. The analysis of docking poses of the hit compounds revealed shared binding features with our previously identified hits. In particular, the P-box targeting compound VPC- 14668 forms a strong hydrogen bond with Tyr594 (-2.1 kcal/mol) through oxygen atom in a similar manner to VPC-14449’s morpholine ring ¹⁸ . Importantly, this bond was conserved throughout 70% of a 50ns molecular dynamics simulation illustrating the im- portance of the bond. This observation is in agreement with the previously identified loss of activity of compounds VPC-14449 in mutant Tyr594Asp AR DBD ¹⁸ . Therefore, we conclude that hydrogen bonding with Tyr594 is an important binding feature for AR DBD inhibition at P-box. Interestingly, residue Tyr594 is likely to be a so-called ‘hot- spot’ residue (i.e. residue with a strong contribution to protein-DNA binding affinity) ac- cording to predictions with PreHots™ web server ⁴⁹ . Thus, it is plausible that disrup- tion of DNA interaction with Tyr594 is required to suppress AR transcriptional activity. These findings support our previous claim that the structure-based design of molecules that bind to hot spot residues represents a viable strategy to disrupt protein-DNA inter- actions ⁵⁰ . Similarly, VPC-17493 resembles binding modes of published inhibitors including VPC- 17005, VPC-17160 and VP-17281 ^19,21 . The hit compound also contains an amide group that forms critical hydrogen bonding with the zinc atom and neighbouring cys- tines. Importantly, molecular dynamics analysis showed that this interaction was also stably maintained. Additionally, strong hydrogen bonding with Ala597 and Asn611 were observed throughout the simulation. Therefore, VPC-17493 further proves our binding hypothesis for disruption of AR dimerization where an amide group bound to the zinc atom is an important binding feature. Although various embodiments of the invention are disclosed herein, many adaptations and modifications may be made within the scope of the invention in accordance with the common general knowledge of those skilled in this art. Such modifications include the substitution of known equivalents for any aspect of the invention in order to achieve the same result in substantially the same way. Numeric ranges are inclusive of the numbers defining the range. The word “comprising” is used herein as an open-ended term, substantially equivalent to the phrase “including, but not limited to”, and the word “comprises” has a corresponding meaning. As used herein, the singular forms “a”, “an” and “the” include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to “a thing” includes more than one such thing. Citation of ref- erences herein is not an admission that such references are prior art to an embodiment of the present invention. The invention includes all embodiments and variations sub- stantially as hereinbefore described and with reference to the examples and drawings.

REFERENCES 1 Siegel, R. L., Miller, K. D. & Jemal, A. Cancer statistics, 2020. CA: a cancer journal for clinicians 70, 7-30 (2020). 2 Huggins, C. & Hodges, C. V. Studies on prostatic cancer: I. The effect of castration, of estrogen and of androgen injection on serum phosphatases in metastatic carcinoma of the prostate. CA: a cancer journal for clinicians 22, 232-240 (1972). 3 La Vignera, S., Condorelli, R., Russo, G., Morgia, G. & Calogero, A. Endocrine control of benign prostatic hyperplasia. Andrology 4, 404-411 (2016). 4 Decker, K. F. et al. Persistent androgen receptor-mediated transcription in castration-resistant prostate cancer under androgen-deprived conditions. Nucleic acids research 40, 10765-10779 (2012). 5 Green, S. M., Mostaghel, E. A. & Nelson, P. S. Androgen action and metabolism in prostate cancer. Molecular and cellular endocrinology 360, 3-13 (2012). 6 Eder, I. E. et al. Molecular biology of the androgen receptor: from molecular understanding to the clinic. European urology 40, 241-251 (2001). 7 Litwin, M. S. & Tan, H.-J. The diagnosis and treatment of prostate cancer: a review. Jama 317, 2532-2542 (2017). 8 Kirby, M., Hirst, C. & Crawford, E. Characterising the castration-resistant prostate cancer population: a systematic review. International journal of clinical practice 65, 1180-1192 (2011). 9 Lorente, D. et al. Switching and withdrawing hormonal agents for castration- resistant prostate cancer. Nature Reviews Urology 12, 37 (2015). 10 Snow, O. et al. Androgen receptor plasticity and its implications for prostate cancer therapy. Cancer Treatment Reviews 81, 101871 (2019). 11 Rice, M. A., Malhotra, S. V. & Stoyanova, T. I. Second-generation antiandrogens in castration resistant prostate cancer. Frontiers in oncology 9, 801 (2019). 12 Korpal, M. et al. An F876L mutation in androgen receptor confers genetic and phenotypic resistance to MDV3100 (enzalutamide). Cancer discovery 3, 1030-1043 (2013). 13 Antonarakis, E. S. et al. AR-V7 and resistance to enzalutamide and abiraterone in prostate cancer. New England Journal of Medicine 371, 1028-1038 (2014). 14 Sun, S. et al. Castration resistance in human prostate cancer is conferred by a frequently occurring androgen receptor splice variant. The Journal of clinical investigation 120, 2715-2730 (2010). 15 Guo, Z. et al. A novel androgen receptor splice variant is up-regulated during prostate cancer progression and promotes androgen depletion–resistant growth. Cancer research 69, 2305-2313 (2009). 16 Dalal, K. et al. Selectively targeting the DNA-binding domain of the androgen receptor as a prospective therapy for prostate cancer. The Journal of biological chemistry 289, 26417-26429, doi:10.1074/jbc.M114.553818 (2014). 17 Ban, F. et al. Best Practices of Computer-Aided Drug Discovery: Lessons Learned from the Development of a Preclinical Candidate for Prostate Cancer with a New Mechanism of Action. Journal of Chemical Information and Modeling 57, 1018-1028, doi:10.1021/acs.jcim.7b00137 (2017). 18 Li, H. et al. Discovery of small-molecule inhibitors selectively targeting the DNA- binding domain of the human androgen receptor. Journal of medicinal chemistry 57, 6458-6467 (2014). 19 Radaeva, M. et al. Development of novel inhibitors targeting the d-box of the dna binding domain of androgen receptor. International journal of molecular sciences 22, 2493 (2021). 20 Ban, F. et al. Development of an androgen receptor inhibitor targeting the N- Terminal domain of androgen receptor for treatment of castration resistant prostate cancer. Cancers 13, 3488 (2021). 21 Dalal, K. et al. Selectively targeting the dimerization interface of human androgen receptor with small-molecules to treat castration-resistant prostate cancer. Cancer Letters 437, 35-43 (2018). 22 Dalal, K. et al. Bypassing Drug Resistance Mechanisms of Prostate Cancer with Small Molecules that Target Androgen Receptor–Chromatin Interactions. Molecular cancer therapeutics 16, 2281-2291 (2017). 23 Lee, G. T. et al. Effects of MTX-23, a Novel PROTAC of Androgen Receptor Splice Variant-7 and Androgen Receptor, on CRPC resistant to Second-Line Antiandrogen Therapy. Molecular cancer therapeutics 20, 490-499 (2021). 24 Xu, R. et al. Synthesis and evaluation of novel thiazole-based derivatives as selective inhibitors of DNA-binding domain of the androgen receptor. Chem Biol Drug Des 91, 172-180, doi:10.1111/cbdd.13068 (2018). 25 Gentile, F. et al. Deep docking: a deep learning platform for augmentation of structure based drug discovery. ACS central science 6, 939-949 (2020). 26 Lyu, J. et al. Ultra-large library docking for discovering new chemotypes. Nature 566, 224-229 (2019). 27 Ton, A. T., Gentile, F., Hsing, M., Ban, F. & Cherkasov, A. Rapid identification of potential inhibitors of SARS-CoV-2 main protease by deep docking of 1.3 billion compounds. Molecular informatics 39, 2000028 (2020). 28 Shaffer, P. L., Jivan, A., Dollins, D. E., Claessens, F. & Gewirth, D. T. Structural basis of androgen receptor binding to selective androgen response elements. Proceedings of the National Academy of Sciences 101, 4758-4763 (2004). 29 Sastry, G. M., Adzhigirey, M., Day, T., Annabhimoju, R. & Sherman, W. Protein and ligand preparation: parameters, protocols, and influence on virtual screening enrichments. Journal of computer-aided molecular design 27, 221-234 (2013). 30 Berman, H. M. et al. The protein data bank. Nucleic acids research 28, 235-242 (2000). 31 Irwin, J. J. et al. ZINC20—a free ultralarge-scale chemical database for ligand discovery. Journal of chemical information and modeling 60, 6065-6073 (2020). 32 Hawkins, P. C., Skillman, A. G., Warren, G. L., Ellingson, B. A. & Stahl, M. T. Conformer generation with OMEGA: algorithm and validation using high quality structures from the Protein Databank and Cambridge Structural Database. Journal of chemical information and modeling 50, 572-584 (2010). 33 Gentile, F. et al. Artificial intelligence–enabled virtual screening of ultra-large chemical libraries with deep docking. Nature Protocols 17, 672-697 (2022). 34 Molecular Operating Environment (MOE) (Chemical Computing Group (ULC), 2019). 35 Schrödinger Release 2020-4: Glide, Schrödinger, LLC, New York, NY, 2020. 36 Berendsen, H. J., Postma, J. P., van Gunsteren, W. F. & Hermans, J. in Intermolecular forces 331-342 (Springer,1981). 37 Roos, K. et al. OPLS3e: Extending force field coverage for drug-like small molecules. Journal of chemical theory and computation 15, 1863-1874 (2019). 38 Tavassoli, P., Snoek, R., Ray, M., Rao, L. G. & Rennie, P. S. Rapid, non-destructive, cell-based screening assays for agents that modulate growth, death, and androgen receptor activation in prostate cancer cells. The Prostate 67, 416-426 (2007). 39 Mysinger, M. M., Carchia, M., Irwin, J. J. & Shoichet, B. K. Directory of useful decoys, enhanced (DUD-E): better ligands and decoys for better benchmarking. Journal of medicinal chemistry 55, 6582-6594 (2012). 40 McGann, M. FRED pose prediction and virtual screening accuracy. Journal of chemical information and modeling 51, 578-596 (2011). 41 Morris, G. M. et al. AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibility. Journal of computational chemistry 30, 2785-2791 (2009). 42 Palacio-Rodríguez, K., Lans, I., Cavasotto, C. N. & Cossio, P. Exponential consensus ranking improves the outcome in docking and receptor ensemble docking. Scientific reports 9, 1-14 (2019). 43 Houston, D. R. & Walkinshaw, M. D. Consensus docking: improving the reliability of docking in a virtual screening context. Journal of chemical information and modeling 53, 384-390 (2013).44 Dhanasekaran, S. M. et al. Delineation of prognostic biomarkers in prostate cancer. Nature 412, 822-826 (2001). 45 Sobhani, N. et al. AR-V7 in Metastatic Prostate Cancer: A Strategy beyond Redemption. International Journal of Molecular Sciences 22, 5515 (2021). 46 Luttens, A. et al. Ultralarge virtual screening identifies SARS-CoV-2 main protease inhibitors with broad-spectrum activity against coronaviruses. Journal of the American Chemical Society 144, 2905-2920 (2022). 47 Gloriam, D. E. (Nature Publishing Group, 2019). 48 Grebner, C. et al. Virtual screening in the cloud: how big is big enough? Journal of Chemical Information and Modeling 60, 4274-4282 (2019). 49 Pan, Y., Zhou, S. & Guan, J. Computationally identifying hot spots in protein-DNA binding interfaces using an ensemble approach. BMC bioinformatics 21, 1-16 (2020). 50 Radaeva, M., Ton, A.-T., Hsing, M., Ban, F. & Cherkasov, A. Drugging the ‘undruggable’. Therapeutic targeting of protein–DNA interactions with the use of computer-aided drug discovery methods. Drug Discovery Today 26, 2660-2679 (2021).